Net0is in the Air Pollution Management Tech Industry

Net0

net0

Map of the Internet I recently expanded on my Internet map visualization that showed all of the undersea internet cables that run along the bottom of the oceans and seas. This time, I also added dots that represent the locations of all of the advertised internet exchanges in the world. The brighter/greener/bigger the dot, the more bandwidth the internet exchange supports. What’s an internet exchange? Internet Exchange: An Internet exchange, often referred to as an Internet Exchange Point (IXP), is a physical infrastructure or facility where Internet Service Providers (ISPs) and other network operators connect their networks together to exchange Internet traffic. The primary purpose of an internet exchange is to improve the efficiency of data exchange between different networks by allowing direct peering between them. Instead of sending data through multiple third-party networks, which can lead to increased latency and costs, ISPs can directly exchange traffic at an internet exchange, resulting in faster and more cost-effective data transmission. Internet exchanges play a crucial role in the functioning of the global internet. By facilitating direct peering, they help reduce the reliance on expensive long-distance links and enhance the overall performance and resilience of the internet. They also promote competition among ISPs and encourage the growth of internet infrastructure in specific regions. Traceroute Command: The command is a network diagnostic tool used to trace the route that data packets take from one computer to another across a network, typically the Internet. It helps identify the network path taken by the data, showing the sequence of intermediate devices (routers) that the packets pass through before reaching the destination. traceroute $ sudo mtr apple.com
                            My traceroute  [v0.95]
kevins-mbp-m1.local (192.168.88.31) -> apple.com (17.22023-08-02T13:19:54+0200
Keys:  Help   Display mode   Restart statistics   Order of fields   quit
                                      Packets               Pings
 Host                               Loss%   Snt   Last   Avg  Best  Wrst StDev
 1. router.lan                       0.0%     5    5.2   4.8   4.3   5.2   0.4
 2. 10.24.0.1                        0.0%     4    4.7   4.6   4.3   5.0   0.3
 3. soeborg2.net.gigabit.dk          0.0%     4    5.6   6.6   5.5   9.7   2.1
 4. apple-1.equinix-am1.nl-ix.net    0.0%     4   15.6  15.5  14.1  16.6   1.0
 5. apple.com.sg                     0.0%     4   15.2  15.0  14.5  15.6   0.5 In the provided example output: is the name of the source host or the computer from which the is initiated. That’s my laptop, so I know that it is located in Copenhagen, Denmark. kevins-mbp-m1.local traceroute is the destination host or the target server to which the is being performed. apple.com traceroute The columns in the output represent the following information: : The intermediate routers or nodes in the network path. Host : The percentage of packet loss experienced while reaching each router. Loss% : The number of packets sent to each router. Snt : The last round-trip time taken to reach the router. Last : The average round-trip time to reach the router. Avg : The best (minimum) round-trip time to reach the router. Best : The worst (maximum) round-trip time to reach the router. Wrst : The standard deviation of round-trip times to the router. StDev Identifying Exchange Location using Reverse IP Lookup: In the output, you can sometimes infer the location of an internet exchange based on the names of the intermediate routers. Many internet exchanges are named explicitly to indicate their location. For example, in the provided , the router with the name suggests that it is associated with Equinix Amsterdam (AM1), which is a prominent internet exchange in Amsterdam, Netherlands. traceroute traceroute apple-1.equinix-am1.nl-ix.net However, it’s important to note that not all routers or nodes in a traceroute will have such descriptive names. Some routers might be labeled with IP addresses or generic names that do not reveal their location. In such cases, it becomes more challenging to pinpoint the exact location of an internet exchange solely based on the traceroute output. Additionally, the reverse IP lookup method depends on the accuracy and up-to-date information in the IP address registries, and some routers might not be accurately represented. Because of all of this, we can see the path that is taken when connecting to a server, which I think is really cool. With my example, I can know that it takes around 15.5 milliseconds for my network traffic to reach the Netherlands, and I can tell that Apple is peering directly in this facility. You can verify this fact by looking at . Essentially, if you want to load faster for your users who are near(ish) to Amsterdam, you may want to run some fiber optic cable to this internet exchange. Put another way, the closer you are to the dots, the closer you are to the internet. PeeringDB apple.com How it’s made First, this is where I got the data from: - PeeringDB is a user-driven database that offers information about network interconnection facilities and peering arrangements, supporting network administrators in optimizing Internet connectivity. PeeringDB - I used this dataset to geolocate all internet exchanges in PeeringDB using the city and country fields. Simple Maps - TeleGeography maintains a database of all major submarine fiber optic cables and their status. Submarine Cable Map Next, these are the different tools/languages that I used: Javascript (nodejs) - D3.js is a powerful JavaScript library for data visualization that allows developers to create interactive and dynamic charts, graphs, and other visual representations on the web using HTML, SVG, and CSS. D3 - library that helps with running d3 inside of a nodejs environment d3-node - library that handles translating coordinates for different map projections. I know it’s controversial now, but the earth isn’t flat. So to make a flat image you have to pick how you are going to translate the globe coordinates onto a map. Despite its flaws, I used the because it is by far the most popular map projection. d3-geo mercator projection - This is my current working language, so it’s what I used to integrate with the PeeringDB API and do some data processing/validation. The Go Programming Language - A library for talking to the PeeringDB API. PeeringDB The pipeline looks like this: Mapping of Cities to lat/long GPS coordinates I had so many data validation issues when doing this project. I should have expected this more since PeeringDB is user-managed, and there’s no validation of the City field. I had a lot of random issues mapping internet exchanges with their GPS coordinates. First, the geolocation database I was using was not complete. It only has around 43 thousand cities, but there are many, many more towns and cities. The way I handled that was to manually map to the closest city that I do have geo coordinates for. Additionally, the city field would be misspelled or formatted in a way differently than my database, or the name of the city may have changed. This happens a lot because there are usually multiple ways to convert many languages into Latin characters. And sometimes cities just change their names. All-in-all, I have 95 internet exchanges that I have had to manually map. I can’t guarantee that they are all correct… but it is definitely good enough. You can see all of the places that I manually mapped . on github Here are my favorites: There was an Internet Exchange named “BGP.Exchange - Los Angles.” Either they were talking about Los Angeles, or they just really like angles. - entry on PeeringDB (note: I believe they fixed the city entry but haven’t yet fixed the name of the IX) There is an exchange named “Example IX” which is obviously just used as an example: entry on PeeringDB The accepted Western name for the capital city of Ukraine changed from Kiev to Kyiv due to the efforts of a campaign called . There are several internet exchanges still using the old spelling in its address. KyivNotKiev Observations from the map Now here’s the pretty part. Here are close-ups of different parts of the map with some general observations. North America The internet exchanges in North America look how I’d imagine them. There are more and higher bandwidth internet exchanges on the eastern side of the US and a good amount along the west coast. However, there are some very important internet exchanges in Colorado. It likely serves as a good halfway point between East and West to transition traffic to different backbone providers. Europe After seeing the map from North America, it’s rather surprising to see how dense European internet exchanges are. There’s almost too much to comment on here, but I will say that it’s interesting how important Amsterdam, Frankfurt, and London are. Asia-Pacific The area around Asia looks rather crazy, but it’s important to note that fiber links can visit islands along the way in order to give them internet access. Those islands will have networking gear that ‘drops’ and ‘adds’ certain channels of the signal. The network device is typically a ROADM (reconfigurable optical add-drop multiplexer). I bet you can guess why they made that an acronym. Also, I think open peering in China is not really a thing, as I believe most traffic goes through so-called backbone providers instead of through internet exchanges. This is likely related to the . On the map, you only see a good number of internet exchanges in Hong Kong. great firewall of China Africa Africa has many optical cables that travel along coasts. I suspect the terrestrial optical networks aren’t as well developed in most parts of Africa. There are exceptions, though. There is a lot of bandwidth capacity in internet exchanges in Capetown and Pretoria. Also, it’s crazy to see how many optical cables lie at the bottom of the Suez canal. South America In South America, we have Fortaleza and Sao Paula have a lot of landings and internet exchanges. Svalbard Svalbard is a set of islands owned by Norway that is waaay far north. It’s one of those places that gets six months of day followed by six months of night. And it’s always super cold. It’s interesting to see two undersea cables to a place like this. Svalbard is where lives, with seeds from all over the world. If you want to use these two cables, you can check out . the global seed vault some webcams that are set up in Svalbard Maldives Maldives is another interesting place where fiber optic cables live. You might notice that the fiber optic cables cross each other. It appears that it was done in order to connect islands that the first cable didn’t service before. The cables were commissioned around five years apart. It must have been a hard five years if you lived on one of the islands that didn’t get high-speed internet in the first round. Thanks for reading So far, I’m pretty happy with the results of this little project. If I were to work more on this, I would want there to be an actual heatmap instead of just drawing dots. I have attempted to do this, but it was taking too long to figure out how to properly do it, specifically with the node-d3 library. Also, there’s probably a lot of data validation that I could do… but I do feel like it’s not my job to fix this database, so I’m probably not going to do that for the sake of a small side project. The part that is still missing is the terrestrial fiber links. There’s not good public data on those for a number of reasons, but you can be assured that there are significant backbone fiber optic cables buried nearby almost every major highway and rail line in the US. So imagine lines that nearly mimic the US road system, and you’ll have an idea of what that map would look like. That may actually be the next step for this map since it’s a bit hard to understand that we only have undersea cables. References: Github: https://github.com/sudorandom/submarine-cable-map PeeringDB: https://www.peeringdb.com/ Simple Maps (Geolocation Database): https://simplemaps.com/data/world-cities Submarine Cable Map: https://submarinecablemap.com Also published . here

Mapping the Internet: A Visualization of the Web

With the birth of the blockchain movement it seems new companies are popping up everyday in almost every sector of the digital world. Companies have an idea, draft a white paper, and spring into action with their initial coin offerings. But the question arises that too few people ask; is this a creation of necessity? Or am I being sold vaporware? There are 4 types of ICO’s in the market today: A group of individuals create a pseudo company (or no company at all), scrape together a whitepaper (or copy another) and go straight into a token sale launch with a basic idea. The issue is they either don’t have the knowledge to pull it off, don’t need blockchain to build their product, or have no intention of ever delivering a live product. Turn and Burn: A legitimate company goes into a token sale built upon a popular blockchain (i.e. Ethereum) with the full intention of switching to another blockchain after the token sale. This allows them to ride the wave of popularity around the distribution of a specific token (higher token sale result) while knowing full well that it will never go into production use. Riding the Wave: While this group does have a chance at succeeding, they have rushed into a token sale to chase the money. They have placed thought into their idea and their white paper, but it’s based on hopes and dreams with nothing built out. There is full intention of bringing a product to market, but conceptualizing it into reality is beyond their current motives. Young & Dumb: This group has the best chance of succeeding. They have either started to build or have built out their blockchain-based application, they are organized, and have a full plan on how to take their product to market. The Realist: The problem is that no one has a giant sticker on their forehead. On the website of these ICOs you won’t find statements that say “We are Riding the Wave!” Unfortunately, nothing is black and white and you have to read between the lines. THE LINES: There is much discussion at the moment around which blockchain is going to rule them all in the future. Some say Bitcoin, other’s say Ethereum. Without understanding the fundamentals of a blockchain, I can easily see how someone can take a side purely based upon popularity or name recognition. However, blockchain is a type of protocol in which a computer does actions based upon pre-defined rules. Similarly, you can compare this to a programming language in which a programmer writes a set of instructions (code) and a computer performs actions based upon the pre-defined instructions. When we begin to switch gears away from popularity and focus our attention on functionality, reading between the lines becomes clear. Today, developers around the world use a plethora of different programming languages to build highly scalable applications. There is not and never will never be one blockchain to rule them all. Blockchains themselves become tools for us to utilize in which each has its own distinct utility. Ethereum is great for building within applications, but is horrendously costly and slow for volume transactions. Stellar is great for payments — transactions are super fast and super cheap. However, it lacks the functionality that would be required within an application setting such as smart contract’s. Many ICO’s will fail because they don’t have the basic understanding of the reason for the use of blockchain. If you don’t know the reason as to why your application is utilizing blockchain and how to choose the appropriate framework for the task, you will fail every time. Reading between the lines is seeing what technology is being used. Why and how it’s being used? Was it chosen appropriately or did this company hurriedly go for popularity over functionality? At Ternio, we know the advertising industry well and know the problems that the industry faces. After months of back and forth and trial and error, Ternio’s blockchain system was born. By understanding both the functionality and utility of blockchain Ternio is the first solution to support programmatic advertising and be able to manage the high volume of transactional impressions that are required. By seeing blockchain as a protocol, we accomplish this with a chain of multiple different blockchains communicating together in tandem. Like the dawn of the internet and the dot-com online business era, we are just now learning the power, utility, and feasibility behind blockchain itself. We are in a moment right now that generations after us will look back to as a time in history. A key point in which the internet around the world changed forever. Ternio is at the forefront and leading the charge in this digital revolution by introducing blockchain to mainstream advertising. It will affect everyone in the supply chain from advertiser all the way down to the publisher. Ternio will offer a number of services for advertisers, publishers, and ad tech companies such as Net0 payments, supply chain transparency, transparent auditing, invoiceless payment processing, free ad fraud detection, and more. Through a simple integration, Ternio resolves many of the problems plaguing mainstream digital advertising without requiring anyone within the supply chain to make dramatic changes to their code or infrastructure. Learn more about Ternio here: https://ternio.io As always, be careful when trading, do your due-diligence research, know what your risks are, and take everything with a grain salt. There are those who are growing a business, and those who are growing their wallets. ’Til next time, happy trading!

Why Most Blockchain ICO’s Will Fail

**LONDON, United Kingdom, June 25th, 2024/Chainwire/--**Minutes Network is pleased to announce a ground-breaking collaboration that is set to bring 1.2 billion users to Minutes Network over the next 24 months. In a strategic move that leverages Minutes Network`s rapid scaling technology with SEW´s AI-driven customer and workforce experience platforms, the extensive SEW base of over 1.2 billion consumers is now in the reachable userbase of Minutes Network. Josh Watkins, Minutes Network CEO said "This is a huge moment for Minutes Network and leverages off the success and strength of World Mobile’s existing relationship with SEW. The integration of the Minutes Network SDK into SEW’s ecosystem and marketplace transforms our scale, reach and the revenue potential. We could not wish for a more supportive scaling partner and our internal technical work now has a singular objective to bring the entire user base online. Our first milestone will have 20million users live within the coming months.” "Watkins added, "This is our first scale integration, and it will be the first of many. We now have a growing slate of applications that have agreed to join Minutes Network and as we are ready to onboard them, we will make further announcements. This new collaboration has been secured due to the outstanding existing relationship between SEW and the World Mobile team." About SEW Founded in 2012 and based in Irvine, California SEW is a technology company that provides digital customer experience and workforce engagement solutions for electric, water, and gas providers. SEW operates in 45 countries and has over 1.2 billion integrated mobile application users.  With its innovative and industry-leading cloud platforms, currently delivers the best Digital Customer Experiences (CX) and Workforce Experiences (WX), powered by AI, ML, and IoT Analytics to the global energy, water, and gas providers. Expanding the platform into the telecom sector is a natural progression to realize the vision to Engage, Empower, and Educate billions of people to save on their utilities services and prepare for the future. Contact CEO Josh Watkins Minutes Network Ltd josh@minutesnetwork.io This story was distributed as a release by Chainwire under HackerNoon’s Business Blogging Program. Learn more about the program here. **LONDON, United Kingdom, June 25th, 2024/Chainwire/--**Minutes Network is pleased to announce a ground-breaking collaboration that is set to bring 1.2 billion users to Minutes Network over the next 24 months. In a strategic move that leverages Minutes Network`s rapid scaling technology with SEW´s AI-driven customer and workforce experience platforms, the extensive SEW base of over 1.2 billion consumers is now in the reachable userbase of Minutes Network. Josh Watkins, Minutes Network CEO said "This is a huge moment for Minutes Network and leverages off the success and strength of World Mobile’s existing relationship with SEW. The integration of the Minutes Network SDK into SEW’s ecosystem and marketplace transforms our scale, reach and the revenue potential. We could not wish for a more supportive scaling partner and our internal technical work now has a singular objective to bring the entire user base online. Our first milestone will have 20million users live within the coming months.” Josh Watkins, Minutes Network CEO said "This is a huge moment for Minutes Network and leverages off the success and strength of World Mobile’s existing relationship with SEW. The integration of the Minutes Network SDK into SEW’s ecosystem and marketplace transforms our scale, reach and the revenue potential. We could not wish for a more supportive scaling partner and our internal technical work now has a singular objective to bring the entire user base online. Our first milestone will have 20million users live within the coming months.” "Watkins added, "This is our first scale integration, and it will be the first of many. We now have a growing slate of applications that have agreed to join Minutes Network and as we are ready to onboard them, we will make further announcements. This new collaboration has been secured due to the outstanding existing relationship between SEW and the World Mobile team." "Watkins added, "This is our first scale integration, and it will be the first of many. We now have a growing slate of applications that have agreed to join Minutes Network and as we are ready to onboard them, we will make further announcements. This new collaboration has been secured due to the outstanding existing relationship between SEW and the World Mobile team." About SEW Founded in 2012 and based in Irvine, California SEW is a technology company that provides digital customer experience and workforce engagement solutions for electric, water, and gas providers. SEW operates in 45 countries and has over 1.2 billion integrated mobile application users.  With its innovative and industry-leading cloud platforms, currently delivers the best Digital Customer Experiences (CX) and Workforce Experiences (WX), powered by AI, ML, and IoT Analytics to the global energy, water, and gas providers. Expanding the platform into the telecom sector is a natural progression to realize the vision to Engage, Empower, and Educate billions of people to save on their utilities services and prepare for the future. Contact CEO Josh Watkins Minutes Network Ltd josh@minutesnetwork.io This story was distributed as a release by Chainwire under HackerNoon’s Business Blogging Program. Learn more about the program here. This story was distributed as a release by Chainwire under HackerNoon’s Business Blogging Program. Learn more about the program here . here here

Minutes Network Closes In On Its First 1.2 billion Users With Smart Energy Water

How to Generate Large Datasets in .NET for Excel With OpenXML

কিভাবে OpenXML এর সাথে Excel এর জন্য .NET-এ বড় ডেটাসেট তৈরি করবেন

So generieren Sie mit OpenXML große Datensätze in .NET für Excel

Cómo generar grandes conjuntos de datos en .NET para Excel con OpenXML

Comment générer de grands ensembles de données dans .NET pour Excel avec OpenXML

OpenXML के साथ Excel के लिए .NET में बड़े डेटासेट कैसे उत्पन्न करें

OpenXML を使用して .NET で Excel 用の大規模なデータセットを生成する方法

OpenXML을 사용하여 Excel용 .NET에서 대규모 데이터 세트를 생성하는 방법

Como gerar grandes conjuntos de dados em .NET para Excel com OpenXML

Как генерировать большие наборы данных в .NET для Excel с помощью OpenXML

OpenXML ile Excel için .NET'te Büyük Veri Kümeleri Nasıl Oluşturulur

Cách tạo bộ dữ liệu lớn trong .NET cho Excel bằng OpenXML

如何使用 OpenXML 在 .NET 中为 Excel 生成大型数据集

Exaion, a subsidiary of EDF, Europe's largest electricity group, has announced its partnership with Cronos, a prominent blockchain ecosystem. Exaion will be joining Cronos as a validator node, contributing to the stability and security of the network. This collaboration brings together Exaion's expertise in providing responsible digital services and Cronos' innovative blockchain technology. Validator nodes play a crucial role in the decentralized validation of transactions on a blockchain network. They are responsible for producing or confirming new blocks at regular intervals, ensuring the smooth operation of the network. In the case of Cronos, validators produce or confirm new blocks every five to six seconds on average. By joining Cronos as a validator, Exaion will actively participate in the governance of the blockchain and the approval of network updates. The addition of Exaion as a validator aligns with Cronos' strategy of partnering with open-source contributors and validators known for their robust technical expertise. Cronos has already collaborated with notable contributors such as Crypto.com, Blockdaemon, Allnodes, and several top-tier validators. This approach ensures that the Cronos ecosystem benefits from a diverse range of expertise and strengthens its position in the blockchain industry. Ken Timsit, Managing Director of Cronos Labs, highlighted the significance of the partnership with Exaion. He emphasized that the collaboration will enhance Cronos' brand recognition, attract new talent and expertise to the ecosystem, and strengthen Cronos' participation in the French blockchain community. This partnership demonstrates Cronos' commitment to fostering a vibrant and diverse ecosystem that brings together crypto-native developers, mainstream users, and established enterprises. Fatih Balyeli, CEO of Exaion, expressed his admiration for the technical depth of Cronos developers and the enthusiasm of the Cronos user community. He acknowledged Cronos' focus on decentralized finance, NFTs, and Web3 gaming, recognizing the ecosystem's potential. Exaion's decision to support Cronos as a validator, alongside other prominent blockchain protocols such as Avalanche, Bitcoin, Ethereum, EWF, Starknet, Tezos, Polkadot, Moonbeam, and Polygon, demonstrates its confidence in Cronos' capabilities and future prospects. The partnership between Exaion and Cronos represents a significant milestone for both entities. Exaion's expertise in providing responsible digital services, coupled with its association with EDF, Europe's largest electricity group, brings credibility and resources to the Cronos ecosystem. This collaboration can potentially attract more enterprises and mainstream users to explore the benefits of blockchain technology through Cronos. Exaion's involvement as a validator node strengthens the decentralization and security of the Cronos network. With a diverse set of validators, including reputable companies like Exaion, Cronos ensures that its network remains resilient and resistant to potential attacks or centralization risks. The partnership also highlights the growing interest and adoption of blockchain technology by established companies. Exaion's decision to support Cronos as a validator, alongside other prominent blockchain protocols, indicates a recognition of the potential and maturity of the blockchain industry. This validation from a subsidiary of a major electricity group can inspire confidence among other enterprises considering blockchain adoption. Final Thoughts The collaboration between Exaion and Cronos represents a significant step forward for the blockchain industry. It demonstrates the increasing convergence of traditional industries with blockchain technology, as established companies like EDF, through its subsidiary Exaion, actively participate in blockchain networks as validators. This partnership not only strengthens the Cronos ecosystem but also sets an example for other enterprises to explore the benefits of blockchain technology. By joining forces with reputable companies like Exaion, Cronos is positioning itself as a leading blockchain ecosystem that can attract mainstream users and enterprises. As the blockchain industry continues to evolve, collaborations like this will play a crucial role in driving adoption, enhancing security, and unlocking the full potential of decentralized technologies. The Exaion-Cronos partnership is a testament to the growing maturity and recognition of blockchain technology, and it will be exciting to see how this collaboration contributes to the future development of the Cronos ecosystem and the wider blockchain industry. Don’t forget to like and share the story! Vested Interest Disclosure: This author is an independent contributor publishing via our business blogging program. HackerNoon has reviewed the report for quality, but the claims herein belong to the author. #DYOR. Exaion , a subsidiary of EDF, Europe's largest electricity group, has announced its partnership with Cronos, a prominent blockchain ecosystem. Exaion will be joining Cronos as a validator node, contributing to the stability and security of the network. This collaboration brings together Exaion's expertise in providing responsible digital services and Cronos' innovative blockchain technology. Exaion blockchain Validator nodes play a crucial role in the decentralized validation of transactions on a blockchain network. They are responsible for producing or confirming new blocks at regular intervals, ensuring the smooth operation of the network. In the case of Cronos, validators produce or confirm new blocks every five to six seconds on average. By joining Cronos as a validator, Exaion will actively participate in the governance of the blockchain and the approval of network updates. The addition of Exaion as a validator aligns with Cronos' strategy of partnering with open-source contributors and validators known for their robust technical expertise. Cronos has already collaborated with notable contributors such as Crypto.com, Blockdaemon, Allnodes, and several top-tier validators. This approach ensures that the Cronos ecosystem benefits from a diverse range of expertise and strengthens its position in the blockchain industry. Ken Timsit, Managing Director of Cronos Labs , highlighted the significance of the partnership with Exaion. He emphasized that the collaboration will enhance Cronos' brand recognition, attract new talent and expertise to the ecosystem, and strengthen Cronos' participation in the French blockchain community. This partnership demonstrates Cronos' commitment to fostering a vibrant and diverse ecosystem that brings together crypto-native developers, mainstream users, and established enterprises. Cronos Labs Fatih Balyeli, CEO of Exaion, expressed his admiration for the technical depth of Cronos developers and the enthusiasm of the Cronos user community. He acknowledged Cronos' focus on decentralized finance, NFTs, and Web3 gaming, recognizing the ecosystem's potential. Exaion's decision to support Cronos as a validator, alongside other prominent blockchain protocols such as Avalanche, Bitcoin, Ethereum, EWF, Starknet, Tezos, Polkadot, Moonbeam, and Polygon, demonstrates its confidence in Cronos' capabilities and future prospects. The partnership between Exaion and Cronos represents a significant milestone for both entities. Exaion's expertise in providing responsible digital services, coupled with its association with EDF, Europe's largest electricity group, brings credibility and resources to the Cronos ecosystem. This collaboration can potentially attract more enterprises and mainstream users to explore the benefits of blockchain technology through Cronos. Exaion's involvement as a validator node strengthens the decentralization and security of the Cronos network. With a diverse set of validators, including reputable companies like Exaion, Cronos ensures that its network remains resilient and resistant to potential attacks or centralization risks. The partnership also highlights the growing interest and adoption of blockchain technology by established companies. Exaion's decision to support Cronos as a validator, alongside other prominent blockchain protocols, indicates a recognition of the potential and maturity of the blockchain industry. This validation from a subsidiary of a major electricity group can inspire confidence among other enterprises considering blockchain adoption. Final Thoughts The collaboration between Exaion and Cronos represents a significant step forward for the blockchain industry. It demonstrates the increasing convergence of traditional industries with blockchain technology, as established companies like EDF, through its subsidiary Exaion, actively participate in blockchain networks as validators. This partnership not only strengthens the Cronos ecosystem but also sets an example for other enterprises to explore the benefits of blockchain technology. By joining forces with reputable companies like Exaion, Cronos is positioning itself as a leading blockchain ecosystem that can attract mainstream users and enterprises. As the blockchain industry continues to evolve, collaborations like this will play a crucial role in driving adoption, enhancing security, and unlocking the full potential of decentralized technologies. The Exaion-Cronos partnership is a testament to the growing maturity and recognition of blockchain technology, and it will be exciting to see how this collaboration contributes to the future development of the Cronos ecosystem and the wider blockchain industry. Don’t forget to like and share the story! Vested Interest Disclosure: This author is an independent contributor publishing via our business blogging program. HackerNoon has reviewed the report for quality, but the claims herein belong to the author. #DYOR. Vested Interest Disclosure: This author is an independent contributor publishing via our business blogging program . HackerNoon has reviewed the report for quality, but the claims herein belong to the author. #DYOR. Vested Interest Disclosure: business blogging program business blogging program

Exaion, Subsidiary of Europe's Largest Electricity Group, Joins Cronos Network as Validator 

Authors:
(1) J. Quetzalcóatl Toledo-Marín, University of British Columbia, BC Children’s Hospital Research Institute Vancouver BC, Canada (Email: j.toledo.mx@gmail.com);
(2) James A. Glazier, Biocomplexity Institute and Department of Intelligent Systems Engineering, Indiana University, Bloomington, IN 47408, USA (Email: jaglazier@gmail.com);
(3) Geoffrey Fox, University of Virginia, Computer Science and Biocomplexity Institute, 994 Research Park Blvd, Charlottesville, Virginia, 22911, USA (Email: gcfexchange@gmail.com). Table of Links Abstract and Introduction Methods Results Discussion Conclusions and References 4 Discussion Deep diffusion surrogates can aid in obtaining the steady-state solution for multiscale modeling. In this paper we looked at 20 sources randomly placed in 2D lattice. It’s still far less complex than the real problem, e.g., simulation of a vascular system. Nevertheless, this is a step forward in that direction. We have shown that increasing the number of sources already pose a number of challenges in different aspects. We showed how the network architecture, the training set structure and size, the loss function, the hyperparameters for training algorithms and defining metrics to evaluate the task-specific performance of the trained network (which may differ from the loss function used in training) are all aspects that affect the final product. In the case of the NN architecture we argued that the encoder-decoder CNN architecture performs well not due to data compression, as believed by many, rather to data transformation akin to Fourier transform. However a more rigorous proof is, both required and desired. That’s not to say that other architecture should not be able to perform well in predicting the steady-state solution. In fact, in prior work [17] we combined an ED-CNN and a CNN for a similar task and found that the CNN improved the performance by reinforcing the sources in the prediction. The results shown in this paper highlight that the largest absolute error occurs at and near the sources. Therefore, we reckon the architecture such as a UNet [27] as a good candidate for this task and we leave it for future work. We considered different loss functions and compared the different performances due to the different loss functions. The wide numeric range for input and output of neural networks makes the analysis very sensitive to choices in the loss function. Our results suggest that the loss function can have a significant effect on the model’s performance. However, we showed that the data set size has a greater effect in the model’s performance and, furthermore, the performance associated to the loss function depends on the data set size. We also showed how a large enough data set reduces the performance fluctuations in the test set. In a real problem the landscape of possibilities is unknown, which implies that the model fluctuations are, at least, unknown. This hints the difficulty in bounding the performance error for any unseen configuration. The naive solution is to increase the training data set. Increasing the training set arbitrarily will lead to an increase in training time. So care must be taken in such approach. One needs to take the best of both worlds, i.e., models trained on sufficiently large data sets to reduce fluctuations but small enough in order be able to train in a fashionable time. A better curated data set where configuration redundancy is kept at a minimum can lead to better performance. Another approach that seem promising is active learning [28] whereby data is ranked by the magnitude of the performance error and data with the largest error is then fed into the training. Defining the right metrics in deep learning is highly challenging. Partly because quantifying the degree of success can be difficult, whereas it is fairly easy agreeing in the ideal success. In other words, quantifying good enough is not straightforward and requires bench-marking different approaches for comparison. A thorough discussion on benchmark suite can be found in [29]. This paper is available on arxiv under CC 4.0 license. Authors: (1) J. Quetzalcóatl Toledo-Marín, University of British Columbia, BC Children’s Hospital Research Institute Vancouver BC, Canada (Email: j.toledo.mx@gmail.com); (2) James A. Glazier, Biocomplexity Institute and Department of Intelligent Systems Engineering, Indiana University, Bloomington, IN 47408, USA (Email: jaglazier@gmail.com); (3) Geoffrey Fox, University of Virginia, Computer Science and Biocomplexity Institute, 994 Research Park Blvd, Charlottesville, Virginia, 22911, USA (Email: gcfexchange@gmail.com). Authors: Authors: (1) J. Quetzalcóatl Toledo-Marín, University of British Columbia, BC Children’s Hospital Research Institute Vancouver BC, Canada (Email: j.toledo.mx@gmail.com); (2) James A. Glazier, Biocomplexity Institute and Department of Intelligent Systems Engineering, Indiana University, Bloomington, IN 47408, USA (Email: jaglazier@gmail.com); (3) Geoffrey Fox, University of Virginia, Computer Science and Biocomplexity Institute, 994 Research Park Blvd, Charlottesville, Virginia, 22911, USA (Email: gcfexchange@gmail.com). Table of Links Abstract and Introduction Abstract and Introduction Methods Methods Results Results Discussion Discussion Conclusions and References Conclusions and References 4 Discussion Deep diffusion surrogates can aid in obtaining the steady-state solution for multiscale modeling. In this paper we looked at 20 sources randomly placed in 2D lattice. It’s still far less complex than the real problem, e.g., simulation of a vascular system. Nevertheless, this is a step forward in that direction. We have shown that increasing the number of sources already pose a number of challenges in different aspects. We showed how the network architecture, the training set structure and size, the loss function, the hyperparameters for training algorithms and defining metrics to evaluate the task-specific performance of the trained network (which may differ from the loss function used in training) are all aspects that affect the final product. In the case of the NN architecture we argued that the encoder-decoder CNN architecture performs well not due to data compression, as believed by many, rather to data transformation akin to Fourier transform. However a more rigorous proof is, both required and desired. That’s not to say that other architecture should not be able to perform well in predicting the steady-state solution. In fact, in prior work [17] we combined an ED-CNN and a CNN for a similar task and found that the CNN improved the performance by reinforcing the sources in the prediction. The results shown in this paper highlight that the largest absolute error occurs at and near the sources. Therefore, we reckon the architecture such as a UNet [27] as a good candidate for this task and we leave it for future work. We considered different loss functions and compared the different performances due to the different loss functions. The wide numeric range for input and output of neural networks makes the analysis very sensitive to choices in the loss function. Our results suggest that the loss function can have a significant effect on the model’s performance. However, we showed that the data set size has a greater effect in the model’s performance and, furthermore, the performance associated to the loss function depends on the data set size. We also showed how a large enough data set reduces the performance fluctuations in the test set. In a real problem the landscape of possibilities is unknown, which implies that the model fluctuations are, at least, unknown. This hints the difficulty in bounding the performance error for any unseen configuration. The naive solution is to increase the training data set. Increasing the training set arbitrarily will lead to an increase in training time. So care must be taken in such approach. One needs to take the best of both worlds, i.e., models trained on sufficiently large data sets to reduce fluctuations but small enough in order be able to train in a fashionable time. A better curated data set where configuration redundancy is kept at a minimum can lead to better performance. Another approach that seem promising is active learning [28] whereby data is ranked by the magnitude of the performance error and data with the largest error is then fed into the training. Defining the right metrics in deep learning is highly challenging. Partly because quantifying the degree of success can be difficult, whereas it is fairly easy agreeing in the ideal success. In other words, quantifying good enough is not straightforward and requires bench-marking different approaches for comparison. A thorough discussion on benchmark suite can be found in [29]. This paper is available on arxiv under CC 4.0 license. This paper is available on arxiv under CC 4.0 license. available on arxiv

Optimizing Data Set Size and Loss Functions for Enhanced Neural Network Performance

Understanding Factors Affecting Neural Network Performance in Diffusion Prediction

Authors:
(1) J. Quetzalcóatl Toledo-Marín, University of British Columbia, BC Children’s Hospital Research Institute Vancouver BC, Canada (Email: j.toledo.mx@gmail.com);
(2) James A. Glazier, Biocomplexity Institute and Department of Intelligent Systems Engineering, Indiana University, Bloomington, IN 47408, USA (Email: jaglazier@gmail.com);
(3) Geoffrey Fox, University of Virginia, Computer Science and Biocomplexity Institute, 994 Research Park Blvd, Charlottesville, Virginia, 22911, USA (Email: gcfexchange@gmail.com). Table of Links Abstract and Introduction Methods Results Discussion Conclusions and References 2 Methods The steady state of the diffusion equation is precisely the convolution of the equation’s associated Green’s function and the initial state. Hence a naive approach would consider a deep convolutional NN (CNN) where the height and width in each layer is kept fixed and equal to the input. CNNs are good at detecting edges and as the number of convolution layers increases, the CNN can detect more sophisticated elements. So can a CNN predict the stationary solution? We argue that it would require a large number of convolution layers such that each convolution would be proportional to a timestep. Adding many convolutions would lead to a rather harder and slower training, as it would increase the chances of under or overflow in the gradient. Furthermore, the number of convolution layers would need to be variable is some form or fashion in order to mimic the timesteps required to reach the stationary solution given an initial condition. There are ways to address each of the previous setbacks but there’s also a trade-off for every decision (e.g., increasing the number of convolutional layers increases the model’s instability which can be addressed by adding more regularization layers which makes the model larger and requires more time to train). Experience tells us that deep convolutional NNs where the height and width in each layer is kept fixed and equal to the input are not good for our task [17]. We designed and built an encoder-decoder CNN (ED-CNN) as our architecture. Fig. 2 provides a sketch of our NN architecture. We denote by |x〉 and |yˆ〉 the input and output images, that is the initial condition layout of the source cells and the predicted stationary solution of the diffusion equation, respectively. The input |x〉 goes through convolutional blocks depicted in Fig. 2 and generates the prediction |yˆ〉 which we then compare with the ground truth |y〉. The core feature of an encoder-decoder is the cone-like structure whereby the information is being compressed when it reaches the bottle neck and then it’s decompressed. Consider the following: A CNN can be seen as a set of operators {Oi} acting on the input, i.e., where the i tags the convolutional layer. Notice that in the particular case where {Oi} are unitary linear operators and all the same O = 1− Ad t, Eq. (1) becomes Notice that the previous Eq. is akin to a ResNet architecture [19]. By defining d t = t/n, where t is time, and taking the limit n → ∞ leads to |yˆ〉 = exp(At)|x〉. Hence, when |yˆ〉 equals the ground truth |y〉, the CNN has learnt the operator exp(At). Notice that taking the derivative with respect to time leads to the diffusion equation: Typically, numerical methods for searching for the stationary solution of a diffusion equation operate by comparing the solution at time t with the solution at time t +∆t, and halting the process when the difference between |y(t)〉 and |y(t+∆t)〉is smaller in magnitude than some pre-determined error value. However, the time t at which the stationary solution is reached depends on the initial conditions and the inhomogeneity term in the diffusion equation. This analogy suggests that, similar to traditional numerical methods, CNNs also require a flexible number of layers to reach the stationary solution, rather than an infinite number of layers. There have been recent developments in addressing the issue of a variable number of layers. For example, in reference [20], the authors propose a method in which the dropout parameters are trained in conjunction with the model parameters. In the context of ED-CNNs, it is a widely held belief that the cone-like architecture leads to improved performance due to the compression in the bottleneck. However, we argue that this is not the sole, if any, contributing factor. It is important to note that the ED-CNN architecture involves summing over the lattice and introducing a new variable, the depth. Additionally, past the bottleneck, the ED-CNN projects back to the original space. In this sense, we say the ED-CNN learns a propagator in a reciprocal space similar to methods such as Laplace and Fourier transform. In Table 1 we specify the neural network by specifying the type of operation and output shape through the sequence of blocks in the NN. Notice that the bottleneck block is 2048∗16∗16 which is twice the size of the input. We built and trained the NN in PyTorch. We used ADAM as the optimizer [25]. Deciding on a loss function is a critical choice in the creation of the surrogate. The loss function determines the types of error the surrogate’s approximation will make compared to the direct calculation and the acceptability of these errors will depend on the specific application. The mean squared error (MSE) error is a standard choice. However, it is more sensitive to larger absolute errors and therefore tolerates large relative errors at pixels with small values. In most biological contexts we want to have a small absolute error for small values and a small relative error for large values. We explored the NN’s performance when trained using a set of different loss functions with different hyperparameters. The set of different loss functions we used were MAE, MSE, Huber loss [26] and inverse Huber loss defined as: where α is 1 or 2 for MAE or MSE, respectively and β tags the tuple in the data set (input and target). Here 〈|〉 denotes the inner product and |i〉 is a unitary vector with the same size as |yβ〉 with all components equal to zero except the element in position i which is equal to one. |1〉 is a vector with all components equal to 1 and with size equal to that of |yβ〉. Then 〈i|yβ〉 is a scalar corresponding to the pixel value at the ith position in |yβ〉, whereas 〈i|1〉 = 1 for all i. Notice that high and low pixel values will have an exponential weight ≈ 1 and ≈ exp(−1/w), respectively. This implies that the error associated to high pixels will have a larger value than that for low pixels. Another prefactor we considered was a step-wise function, viz. This paper is available on arxiv under CC 4.0 license. Authors: (1) J. Quetzalcóatl Toledo-Marín, University of British Columbia, BC Children’s Hospital Research Institute Vancouver BC, Canada (Email: j.toledo.mx@gmail.com); (2) James A. Glazier, Biocomplexity Institute and Department of Intelligent Systems Engineering, Indiana University, Bloomington, IN 47408, USA (Email: jaglazier@gmail.com); (3) Geoffrey Fox, University of Virginia, Computer Science and Biocomplexity Institute, 994 Research Park Blvd, Charlottesville, Virginia, 22911, USA (Email: gcfexchange@gmail.com). Authors: Authors: (1) J. Quetzalcóatl Toledo-Marín, University of British Columbia, BC Children’s Hospital Research Institute Vancouver BC, Canada (Email: j.toledo.mx@gmail.com); (2) James A. Glazier, Biocomplexity Institute and Department of Intelligent Systems Engineering, Indiana University, Bloomington, IN 47408, USA (Email: jaglazier@gmail.com); (3) Geoffrey Fox, University of Virginia, Computer Science and Biocomplexity Institute, 994 Research Park Blvd, Charlottesville, Virginia, 22911, USA (Email: gcfexchange@gmail.com). Table of Links Abstract and Introduction Abstract and Introduction Methods Methods Results Results Discussion Discussion Conclusions and References Conclusions and References 2 Methods The steady state of the diffusion equation is precisely the convolution of the equation’s associated Green’s function and the initial state. Hence a naive approach would consider a deep convolutional NN (CNN) where the height and width in each layer is kept fixed and equal to the input. CNNs are good at detecting edges and as the number of convolution layers increases, the CNN can detect more sophisticated elements. So can a CNN predict the stationary solution? We argue that it would require a large number of convolution layers such that each convolution would be proportional to a timestep. Adding many convolutions would lead to a rather harder and slower training, as it would increase the chances of under or overflow in the gradient. Furthermore, the number of convolution layers would need to be variable is some form or fashion in order to mimic the timesteps required to reach the stationary solution given an initial condition. There are ways to address each of the previous setbacks but there’s also a trade-off for every decision (e.g., increasing the number of convolutional layers increases the model’s instability which can be addressed by adding more regularization layers which makes the model larger and requires more time to train). Experience tells us that deep convolutional NNs where the height and width in each layer is kept fixed and equal to the input are not good for our task [17]. We designed and built an encoder-decoder CNN (ED-CNN) as our architecture. Fig. 2 provides a sketch of our NN architecture. We denote by |x〉 and |yˆ〉 the input and output images, that is the initial condition layout of the source cells and the predicted stationary solution of the diffusion equation, respectively. The input |x〉 goes through convolutional blocks depicted in Fig. 2 and generates the prediction |yˆ〉 which we then compare with the ground truth |y〉. The core feature of an encoder-decoder is the cone-like structure whereby the information is being compressed when it reaches the bottle neck and then it’s decompressed. Consider the following: A CNN can be seen as a set of operators {Oi} acting on the input, i.e., where the i tags the convolutional layer. Notice that in the particular case where {Oi} are unitary linear operators and all the same O = 1− Ad t, Eq. (1) becomes Notice that the previous Eq. is akin to a ResNet architecture [19]. By defining d t = t/n, where t is time, and taking the limit n → ∞ leads to |yˆ〉 = exp(At)|x〉. Hence, when |yˆ〉 equals the ground truth |y〉, the CNN has learnt the operator exp(At). Notice that taking the derivative with respect to time leads to the diffusion equation: Typically, numerical methods for searching for the stationary solution of a diffusion equation operate by comparing the solution at time t with the solution at time t +∆t, and halting the process when the difference between |y(t)〉 and |y(t+∆t)〉is smaller in magnitude than some pre-determined error value. However, the time t at which the stationary solution is reached depends on the initial conditions and the inhomogeneity term in the diffusion equation. This analogy suggests that, similar to traditional numerical methods, CNNs also require a flexible number of layers to reach the stationary solution, rather than an infinite number of layers. There have been recent developments in addressing the issue of a variable number of layers. For example, in reference [20], the authors propose a method in which the dropout parameters are trained in conjunction with the model parameters. In the context of ED-CNNs, it is a widely held belief that the cone-like architecture leads to improved performance due to the compression in the bottleneck. However, we argue that this is not the sole, if any, contributing factor. It is important to note that the ED-CNN architecture involves summing over the lattice and introducing a new variable, the depth. Additionally, past the bottleneck, the ED-CNN projects back to the original space. In this sense, we say the ED-CNN learns a propagator in a reciprocal space similar to methods such as Laplace and Fourier transform. In Table 1 we specify the neural network by specifying the type of operation and output shape through the sequence of blocks in the NN. Notice that the bottleneck block is 2048∗16∗16 which is twice the size of the input. We built and trained the NN in PyTorch. We used ADAM as the optimizer [25]. Deciding on a loss function is a critical choice in the creation of the surrogate. The loss function determines the types of error the surrogate’s approximation will make compared to the direct calculation and the acceptability of these errors will depend on the specific application. The mean squared error (MSE) error is a standard choice. However, it is more sensitive to larger absolute errors and therefore tolerates large relative errors at pixels with small values. In most biological contexts we want to have a small absolute error for small values and a small relative error for large values. We explored the NN’s performance when trained using a set of different loss functions with different hyperparameters. The set of different loss functions we used were MAE, MSE, Huber loss [26] and inverse Huber loss defined as: where α is 1 or 2 for MAE or MSE, respectively and β tags the tuple in the data set (input and target). Here 〈|〉 denotes the inner product and |i〉 is a unitary vector with the same size as |yβ〉 with all components equal to zero except the element in position i which is equal to one. |1〉 is a vector with all components equal to 1 and with size equal to that of |yβ〉. Then 〈i|yβ〉 is a scalar corresponding to the pixel value at the ith position in |yβ〉, whereas 〈i|1〉 = 1 for all i. Notice that high and low pixel values will have an exponential weight ≈ 1 and ≈ exp(−1/w), respectively. This implies that the error associated to high pixels will have a larger value than that for low pixels. Another prefactor we considered was a step-wise function, viz. This paper is available on arxiv under CC 4.0 license. This paper is available on arxiv under CC 4.0 license. available on arxiv

Architecting Neural Networks for Diffusion Prediction: A Study on Encoder-Decoder CNNs

Analyzing the Performance of Deep Encoder-Decoder Networks as Surrogates for a Diffusion Equation

Fuse Network, a decentralized finance (DeFi) platform, has recently announced the launch of its second airdrop campaign, following the successful completion of Season 1. The new campaign, which began on June 17, 2024, aims to distribute 2.5 million $FUSE tokens to participants who engage in various tasks and quests within the Fuse ecosystem. The points-based reward system will rank participants on a leaderboard, with each completed task and quest earning them corresponding points. This approach encourages users to actively explore and interact with the various features and partners of the Fuse Network, fostering a more vibrant and engaged community. Fuse Network's decision to launch a second airdrop campaign demonstrates its commitment to incentivizing user participation and growth within its ecosystem. By partnering with Layer 3, a blockchain-based platform focused on enhancing user engagement and rewards, Fuse Network is leveraging innovative solutions to create a more attractive and rewarding environment for its users. The inclusion of new partners, such as Meridian, LogX, Mirakle, Lynx Finance, GoodDollar, and Demented Games, expands the range of opportunities available to participants and showcases Fuse Network's efforts to collaborate with diverse projects in the DeFi space. These partnerships not only provide additional avenues for users to earn rewards but also expose them to a wider array of DeFi applications and services. Furthermore, the introduction of new enhanced quests, made possible through the collaboration with Layer 3, indicates Fuse Network's desire to promote exploration and discovery within its ecosystem. By encouraging users to interact with various features and services, such as lending on Meridian, staking $FUSE via the Volt App, and providing liquidity on LogX and Lynx, Fuse Network is fostering a more knowledgeable and engaged user base. The reset of the leaderboard from Season 1 ensures that new participants have an equal opportunity to earn rewards, while still acknowledging the contributions of previous participants who continue to earn points automatically for their past activities. This approach strikes a balance between attracting new users and retaining existing ones, promoting a sense of fairness and inclusivity within the community. Final Thoughts Fuse Network's Season 2 airdrop campaign represents a significant step forward in its mission to create a thriving and engaging DeFi ecosystem. By incentivizing user participation, collaborating with diverse partners, and introducing new enhanced quests, Fuse Network is demonstrating its commitment to innovation and growth. As the DeFi space continues to evolve and mature, initiatives like Fuse Network's airdrop campaign will play an increasingly important role in attracting and retaining users. By providing tangible rewards for engagement and exploration, Fuse Network is not only encouraging the adoption of its own platform but also contributing to the overall growth and development of the DeFi sector. As Season 2 progresses, it will be interesting to observe how users respond to the new opportunities and how Fuse Network continues to adapt and innovate to meet the changing needs and expectations of its community. With its focus on collaboration, engagement, and rewards, Fuse Network is well-positioned to make a significant impact in the DeFi space and beyond. Don’t forget to like and share the story! Vested Interest Disclosure: This author is an independent contributor publishing via our business blogging program. HackerNoon has reviewed the report for quality, but the claims herein belong to the author. #DYOR. Fuse Network , a decentralized finance ( DeFi ) platform, has recently announced the launch of its second airdrop campaign, following the successful completion of Season 1. The new campaign, which began on June 17, 2024, aims to distribute 2.5 million $FUSE tokens to participants who engage in various tasks and quests within the Fuse ecosystem. Fuse Network DeFi The points-based reward system will rank participants on a leaderboard, with each completed task and quest earning them corresponding points. This approach encourages users to actively explore and interact with the various features and partners of the Fuse Network, fostering a more vibrant and engaged community. Fuse Network's decision to launch a second airdrop campaign demonstrates its commitment to incentivizing user participation and growth within its ecosystem. By partnering with Layer 3, a blockchain-based platform focused on enhancing user engagement and rewards, Fuse Network is leveraging innovative solutions to create a more attractive and rewarding environment for its users. The inclusion of new partners, such as Meridian, LogX, Mirakle, Lynx Finance, GoodDollar, and Demented Games, expands the range of opportunities available to participants and showcases Fuse Network's efforts to collaborate with diverse projects in the DeFi space. These partnerships not only provide additional avenues for users to earn rewards but also expose them to a wider array of DeFi applications and services. Furthermore, the introduction of new enhanced quests, made possible through the collaboration with Layer 3, indicates Fuse Network's desire to promote exploration and discovery within its ecosystem. By encouraging users to interact with various features and services, such as lending on Meridian, staking $FUSE via the Volt App, and providing liquidity on LogX and Lynx, Fuse Network is fostering a more knowledgeable and engaged user base. The reset of the leaderboard from Season 1 ensures that new participants have an equal opportunity to earn rewards, while still acknowledging the contributions of previous participants who continue to earn points automatically for their past activities. This approach strikes a balance between attracting new users and retaining existing ones, promoting a sense of fairness and inclusivity within the community. Final Thoughts Fuse Network's Season 2 airdrop campaign represents a significant step forward in its mission to create a thriving and engaging DeFi ecosystem. By incentivizing user participation, collaborating with diverse partners, and introducing new enhanced quests, Fuse Network is demonstrating its commitment to innovation and growth. As the DeFi space continues to evolve and mature, initiatives like Fuse Network's airdrop campaign will play an increasingly important role in attracting and retaining users. By providing tangible rewards for engagement and exploration, Fuse Network is not only encouraging the adoption of its own platform but also contributing to the overall growth and development of the DeFi sector. As Season 2 progresses, it will be interesting to observe how users respond to the new opportunities and how Fuse Network continues to adapt and innovate to meet the changing needs and expectations of its community. With its focus on collaboration, engagement, and rewards, Fuse Network is well-positioned to make a significant impact in the DeFi space and beyond. Don’t forget to like and share the story! Vested Interest Disclosure: This author is an independent contributor publishing via our business blogging program. HackerNoon has reviewed the report for quality, but the claims herein belong to the author. #DYOR. Vested Interest Disclosure: This author is an independent contributor publishing via our business blogging program . HackerNoon has reviewed the report for quality, but the claims herein belong to the author. #DYOR. Vested Interest Disclosure: business blogging program business blogging program

Fuse Network Launches Season 2 Airdrop: 2.5 Million $FUSE Tokens Up for Grabs

Autonomys Network: ex-Jumio Executive Appointed CEO For New deAI Vision Ahead Of Mainnet Launch

অটোনমিস নেটওয়ার্ক: মেইননেট লঞ্চের আগে নতুন ডিএআই ভিশনের জন্য প্রাক্তন জুমিও এক্সিকিউটিভ সিইও নিযুক্ত হয়েছেন

Autonomys Network: ehemaliger Jumio-Manager vor Mainnet-Start zum CEO für neue deAI-Vision ernannt

Autonomys Network: ex ejecutivo de Jumio nombrado director ejecutivo para la nueva visión deAI antes del lanzamiento de Mainnet

Autonomys Network : un ancien cadre de Jumio est nommé PDG de la nouvelle vision deAI avant le lancement du réseau principal

ऑटोनोमिस नेटवर्क: पूर्व-जुमियो कार्यकारी को मेननेट लॉन्च से पहले नए डीएआई विजन के लिए सीईओ नियुक्त किया गया

Autonomys Network: メインネットの立ち上げに先立ち、元Jumio幹部が新たなdeAIビジョンのCEOに任命される

Autonomys Network: 전 Jumio 임원이 메인넷 출시를 앞두고 새로운 deAI 비전을 위해 CEO로 임명됨

Rede Autonomys: ex-executivo da Jumio nomeado CEO para nova visão deAI antes do lançamento da Mainnet

Сеть Autonomys: бывший исполнительный директор Jumio назначен генеральным директором новой концепции deAI в преддверии запуска основной сети

Autonomys Network: Eski Jumio Yöneticisi, Mainnet Lansmanı Öncesinde Yeni deAI Vizyonu İçin CEO Olarak Atandı

Autonomys Network: Cựu Giám đốc điều hành Jumio được bổ nhiệm làm Giám đốc điều hành cho Tầm nhìn deAI mới trước khi ra mắt Mainnet

Autonomys Network：前 Jumio 高管被任命为新 deAI 愿景的首席执行官，主网发布前夕

Bitcoin Runes: How Do the New Tokens on the Bitcoin Network Differ From BRC-20?

Author:
(1) Yigit Ege Bayiz, Electrical and Computer Engineering The University of Texas at Austin Austin, Texas, USA (Email: egebayiz@utexas.edu);
(2) Ufuk Topcu, Aerospace Engineering and Engineering Mechanics The University of Texas at Austin Austin, Texas, USA (Email: utopcu@utexas.edu). Table of Links Abstract and Introduction Related Works Preliminaries Optimal Prebunking Problem Deterministic Baseline Policies Temporally Equidistant Prebunking Numerical Results Conclusion and References IV. OPTIMAL PREBUNKING PROBLEM To guard user c against misinformation, we employ prebunking. Prebunking relies on inoculating the users in the network by providing the users with correct information before they encounter a misinformation that contradicts the correct information. The idea of prebunking is similar to that of vaccination, where an early intervention to misinformation can immunize some users against it, reducing misinformation spread in the population. Fig. 1 shows the effect of prebunking in a small network of users. Lastly, we note that it is impossible to guard the center user c against a cascading misinformation k if the misinformation starts from c. As there is no way of estimating when a new misinformation cascade will start, there is no way to preemptively provide a prebunk to the central user c if a misinformation cascade starts on it. Thus, for theoretical analysis it is often necessary to assume that a misinformation cascade never starts at c. We rephrase this assumption as follows: This paper is available on arxiv under CC 4.0 license. Author: (1) Yigit Ege Bayiz, Electrical and Computer Engineering The University of Texas at Austin Austin, Texas, USA (Email: egebayiz@utexas.edu); (2) Ufuk Topcu, Aerospace Engineering and Engineering Mechanics The University of Texas at Austin Austin, Texas, USA (Email: utopcu@utexas.edu). Author: Author: (1) Yigit Ege Bayiz, Electrical and Computer Engineering The University of Texas at Austin Austin, Texas, USA (Email: egebayiz@utexas.edu); (2) Ufuk Topcu, Aerospace Engineering and Engineering Mechanics The University of Texas at Austin Austin, Texas, USA (Email: utopcu@utexas.edu). Table of Links Abstract and Introduction Abstract and Introduction Related Works Related Works Preliminaries Preliminaries Optimal Prebunking Problem Optimal Prebunking Problem Deterministic Baseline Policies Deterministic Baseline Policies Temporally Equidistant Prebunking Temporally Equidistant Prebunking Numerical Results Numerical Results Conclusion and References Conclusion and References IV. OPTIMAL PREBUNKING PROBLEM To guard user c against misinformation, we employ prebunking. Prebunking relies on inoculating the users in the network by providing the users with correct information before they encounter a misinformation that contradicts the correct information. The idea of prebunking is similar to that of vaccination, where an early intervention to misinformation can immunize some users against it, reducing misinformation spread in the population. Fig. 1 shows the effect of prebunking in a small network of users. Lastly, we note that it is impossible to guard the center user c against a cascading misinformation k if the misinformation starts from c. As there is no way of estimating when a new misinformation cascade will start, there is no way to preemptively provide a prebunk to the central user c if a misinformation cascade starts on it. Thus, for theoretical analysis it is often necessary to assume that a misinformation cascade never starts at c. We rephrase this assumption as follows: This paper is available on arxiv under CC 4.0 license. This paper is available on arxiv under CC 4.0 license. available on arxiv

Enhancing User Protection with Optimal Prebunking in Social Networks

Authors:
(1) Yigit Ege Bayiz, Electrical and Computer Engineering The University of Texas at Austin Austin, Texas, USA (Email: egebayiz@utexas.edu);
(2) Ufuk Topcu, Aerospace Engineering and Engineering Mechanics The University of Texas at Austin Austin, Texas, USA (Email: utopcu@utexas.edu). Table of Links Abstract and Introduction Related Works Preliminaries Optimal Prebunking Problem Deterministic Baseline Policies Temporally Equidistant Prebunking Numerical Results Conclusion and References Abstract—The growing reliance on social media for news consumption necessitates effective countermeasures to mitigate the rapid spread of misinformation. Prebunking, a proactive method that arms users with accurate information before they come across false content, has garnered support from journalism and psychology experts. We formalize the problem of optimal prebunking as optimizing the timing of delivering accurate information, ensuring users encounter it before receiving misinformation while minimizing the disruption to user experience. Utilizing a susceptible-infected epidemiological process to model the propagation of misinformation, we frame optimal prebunking as a policy synthesis problem with safety constraints. We then propose a policy that approximates the optimal solution to a relaxed problem. The experiments show that this policy cuts the user experience cost of repeated information delivery in half, compared to delivering accurate information immediately after identifying a misinformation propagation. I. INTRODUCTION Social media have become an integral part of modern communication, with more than 70% of adults in the U.S. using at least one social media service [1]. At least 60% of these users use social networking platforms, a type of social media platform in which users build social networks and communicate with other users who share similar interests, opinions, or backgrounds. These platforms allow their users to easily share information and their opinions. However, the ease of information sharing on social networking platforms has also led to the rise of misinformation and fake news. Misinformation can spread faster and more broadly than accurate information, causing significant harm to public discourse. The consequences of misinformation can range from confusion to substantial damage to public health [2], or political manipulation [3]. The widespread adoption of social networking platforms and the growing reliance on social networking services as sources of news consumption exacerbates this issue, often resulting in significant portions of the population believing in unsubstantiated or provably incorrect claims, making it difficult to correct these false beliefs later through debunking. Prebunking has emerged as a promising solution for mitigating the spread of misinformation. Unlike debunking, which aims to correct false information after its spread, prebunking exposes people to factual information before they encounter false claims. The idea is to inoculate the public against misinformation, akin to a vaccine [4]. Studies indicate that this preemptive approach has the potential to reduce the spread of misinformation [5], without relying on media censorship. The effectiveness of prebunking depends on the timing of delivery of the factual information. It is clear that for prebunking to work as intended the user has to see the factual information before seeing the related misinformation. Furthermore, the effectiveness of prebunking depends on the time gap between the delivery of the factual information and the arrival of the misinformation. Research in characterizing this relation has been sparse, leaving a significant gap in understanding the optimal timing for successful prebunking interventions [6]. Another consideration is the effect of prebunking on the userexperience. Too frequent delivery of factual information can push users to other social networking platforms that do not utilize prebunking, rendering prebunking ineffective. We formalize optimal prebunking as a mathematical optimization problem over the timing of factual information delivery. The primary objective is to ensure that users encounter the factual information before being exposed to corresponding misinformation while minimizing any disruptions to the userexperience. We model the effect of factual information on user-experience by adopting a leaky bucket cost, that is an exponentially decaying cumulative count over the number of prebunking related factual informations the user receives. Minimizing this cost discourages repeated and frequent delivery of factual information, minimizing the impact of prebunking on user-experience. We use the susceptible-infected (SI) epidemiological model to characterize misinformation propagation and frame optimal prebunking as a policy synthesis problem with constraints to ensure the user receives the factual information before the corresponding misinformation. Building on this framework, we propose a locally optimal policy that attempts to minimize the leaky bucket cost, while ensuring that the user receives factual information prior to misinformation that is propagating over the social network. Contributions • We present the problem of optimally delivering pregenerated factual information for the purpose of prebunking as a policy synthesis problem. • We analyze two baseline methods that provide guaranteed delivery of factual information before its corresponding misinformation. • We provide a third method that approximates the optimal solution to a relaxed problem and provides the same guarantees as the previously mentioned methods with less cost. This paper is available on arxiv under CC 4.0 license. Authors: (1) Yigit Ege Bayiz, Electrical and Computer Engineering The University of Texas at Austin Austin, Texas, USA (Email: egebayiz@utexas.edu); (2) Ufuk Topcu, Aerospace Engineering and Engineering Mechanics The University of Texas at Austin Austin, Texas, USA (Email: utopcu@utexas.edu). Authors: Authors: (1) Yigit Ege Bayiz, Electrical and Computer Engineering The University of Texas at Austin Austin, Texas, USA (Email: egebayiz@utexas.edu); (2) Ufuk Topcu, Aerospace Engineering and Engineering Mechanics The University of Texas at Austin Austin, Texas, USA (Email: utopcu@utexas.edu). Table of Links Abstract and Introduction Abstract and Introduction Related Works Related Works Preliminaries Preliminaries Optimal Prebunking Problem Optimal Prebunking Problem Deterministic Baseline Policies Deterministic Baseline Policies Temporally Equidistant Prebunking Temporally Equidistant Prebunking Numerical Results Numerical Results Conclusion and References Conclusion and References Abstract—The growing reliance on social media for news consumption necessitates effective countermeasures to mitigate the rapid spread of misinformation. Prebunking, a proactive method that arms users with accurate information before they come across false content, has garnered support from journalism and psychology experts. We formalize the problem of optimal prebunking as optimizing the timing of delivering accurate information, ensuring users encounter it before receiving misinformation while minimizing the disruption to user experience. Utilizing a susceptible-infected epidemiological process to model the propagation of misinformation, we frame optimal prebunking as a policy synthesis problem with safety constraints. We then propose a policy that approximates the optimal solution to a relaxed problem. The experiments show that this policy cuts the user experience cost of repeated information delivery in half, compared to delivering accurate information immediately after identifying a misinformation propagation. Abstract —The growing reliance on social media for news consumption necessitates effective countermeasures to mitigate the rapid spread of misinformation. Prebunking, a proactive method that arms users with accurate information before they come across false content, has garnered support from journalism and psychology experts. We formalize the problem of optimal prebunking as optimizing the timing of delivering accurate information, ensuring users encounter it before receiving misinformation while minimizing the disruption to user experience. Utilizing a susceptible-infected epidemiological process to model the propagation of misinformation, we frame optimal prebunking as a policy synthesis problem with safety constraints. We then propose a policy that approximates the optimal solution to a relaxed problem. The experiments show that this policy cuts the user experience cost of repeated information delivery in half, compared to delivering accurate information immediately after identifying a misinformation propagation. Abstract I. INTRODUCTION Social media have become an integral part of modern communication, with more than 70% of adults in the U.S. using at least one social media service [1]. At least 60% of these users use social networking platforms, a type of social media platform in which users build social networks and communicate with other users who share similar interests, opinions, or backgrounds. These platforms allow their users to easily share information and their opinions. However, the ease of information sharing on social networking platforms has also led to the rise of misinformation and fake news. Misinformation can spread faster and more broadly than accurate information, causing significant harm to public discourse. The consequences of misinformation can range from confusion to substantial damage to public health [2], or political manipulation [3]. The widespread adoption of social networking platforms and the growing reliance on social networking services as sources of news consumption exacerbates this issue, often resulting in significant portions of the population believing in unsubstantiated or provably incorrect claims, making it difficult to correct these false beliefs later through debunking. Prebunking has emerged as a promising solution for mitigating the spread of misinformation. Unlike debunking, which aims to correct false information after its spread, prebunking exposes people to factual information before they encounter false claims. The idea is to inoculate the public against misinformation, akin to a vaccine [4]. Studies indicate that this preemptive approach has the potential to reduce the spread of misinformation [5], without relying on media censorship. The effectiveness of prebunking depends on the timing of delivery of the factual information. It is clear that for prebunking to work as intended the user has to see the factual information before seeing the related misinformation. Furthermore, the effectiveness of prebunking depends on the time gap between the delivery of the factual information and the arrival of the misinformation. Research in characterizing this relation has been sparse, leaving a significant gap in understanding the optimal timing for successful prebunking interventions [6]. Another consideration is the effect of prebunking on the userexperience. Too frequent delivery of factual information can push users to other social networking platforms that do not utilize prebunking, rendering prebunking ineffective. We formalize optimal prebunking as a mathematical optimization problem over the timing of factual information delivery. The primary objective is to ensure that users encounter the factual information before being exposed to corresponding misinformation while minimizing any disruptions to the userexperience. We model the effect of factual information on user-experience by adopting a leaky bucket cost, that is an exponentially decaying cumulative count over the number of prebunking related factual informations the user receives. Minimizing this cost discourages repeated and frequent delivery of factual information, minimizing the impact of prebunking on user-experience. We use the susceptible-infected (SI) epidemiological model to characterize misinformation propagation and frame optimal prebunking as a policy synthesis problem with constraints to ensure the user receives the factual information before the corresponding misinformation. Building on this framework, we propose a locally optimal policy that attempts to minimize the leaky bucket cost, while ensuring that the user receives factual information prior to misinformation that is propagating over the social network. Contributions • We present the problem of optimally delivering pregenerated factual information for the purpose of prebunking as a policy synthesis problem. • We analyze two baseline methods that provide guaranteed delivery of factual information before its corresponding misinformation. • We provide a third method that approximates the optimal solution to a relaxed problem and provides the same guarantees as the previously mentioned methods with less cost. This paper is available on arxiv under CC 4.0 license. This paper is available on arxiv under CC 4.0 license. available on arxiv

Prebunking Design as a Defense Mechanism Against Misinformation Propagation on Social Networks

The cryptocurrency market has taken a significant step towards standardization and accessibility with the launch of the GMCI 30 Index (GM 30) on the Pyth Network. This integration brings real-time pricing data for the 30 largest digital assets by market capitalization to developers across more than 60 blockchain ecosystems. The GM 30, created by index provider GMCI, offers a comprehensive snapshot of the cryptocurrency market, including major players like Bitcoin and Ethereum, as well as long-standing industry leaders. By tracking the performance of these top digital assets, the index provides valuable insights into the stability, sentiment, and growth trends of the overall market. The Pyth Network, known for its decentralized financial data oracle, has made the GM 30 feed accessible to developers in a permissionless manner. This means that DeFi applications can now base their operations on real-time pricing data for the index, opening up new possibilities for financial products and services in the cryptocurrency space. The integration of the GM 30 into the Pyth Network is a testament to the growing importance of reliable and transparent financial data in the world of decentralized finance. As more traditional investors and financial institutions enter the cryptocurrency market, the need for standardized benchmarks and indices becomes increasingly apparent. Several DeFi protocols across multiple blockchain ecosystems have already begun integrating the Pyth GMCI 30 feed into their operations. These include decentralized exchanges like Bluefin on Sui, D8X Exchange on Arbitrum and Polygon zkEVM, Pingu Exchange on Arbitrum, and Vela Exchange on Arbitrum and Base. Additionally, Horizon Protocol, a derivatives trading and liquidity protocol, is also leveraging the GM 30 feed to provide users with exposure to the broader cryptocurrency market. The collaboration between GMCI and the Pyth Network represents a significant milestone in the evolution of the cryptocurrency market. By combining GMCI's expertise in creating unique indices with Pyth's cutting-edge Oracle technology, this integration provides developers and users with a reliable and accurate source of market data. As more DeFi protocols and applications adopt the GM 30 feed, we can expect to see increased transparency, efficiency, and innovation in the cryptocurrency space. Final Thoughts The launch of the GMCI 30 Index on the Pyth Network is just the beginning. As the cryptocurrency market continues to mature and evolve, the demand for sophisticated financial products and services will only grow. With the foundation laid by this integration, developers and entrepreneurs have a powerful tool at their disposal to create the next generation of DeFi applications that can revolutionize the way we interact with digital assets. Don’t forget to like and share the story! Vested Interest Disclosure: This author is an independent contributor publishing via our business blogging program. HackerNoon has reviewed the report for quality, but the claims herein belong to the author. #DYOR. The cryptocurrency market has taken a significant step towards standardization and accessibility with the launch of the GMCI 30 Index (GM 30) on the Pyth Network . This integration brings real-time pricing data for the 30 largest digital assets by market capitalization to developers across more than 60 blockchain ecosystems. GMCI 30 Index Pyth Network The GM 30, created by index provider GMCI , offers a comprehensive snapshot of the cryptocurrency market, including major players like Bitcoin and Ethereum, as well as long-standing industry leaders. By tracking the performance of these top digital assets, the index provides valuable insights into the stability, sentiment, and growth trends of the overall market. The Pyth Network, known for its decentralized financial data oracle, has made the GM 30 feed accessible to developers in a permissionless manner. This means that DeFi applications can now base their operations on real-time pricing data for the index, opening up new possibilities for financial products and services in the cryptocurrency space. GMCI The integration of the GM 30 into the Pyth Network is a testament to the growing importance of reliable and transparent financial data in the world of decentralized finance. As more traditional investors and financial institutions enter the cryptocurrency market, the need for standardized benchmarks and indices becomes increasingly apparent. Several DeFi protocols across multiple blockchain ecosystems have already begun integrating the Pyth GMCI 30 feed into their operations. These include decentralized exchanges like Bluefin on Sui, D8X Exchange on Arbitrum and Polygon zkEVM, Pingu Exchange on Arbitrum, and Vela Exchange on Arbitrum and Base. Additionally, Horizon Protocol, a derivatives trading and liquidity protocol, is also leveraging the GM 30 feed to provide users with exposure to the broader cryptocurrency market. The collaboration between GMCI and the Pyth Network represents a significant milestone in the evolution of the cryptocurrency market. By combining GMCI's expertise in creating unique indices with Pyth's cutting-edge Oracle technology, this integration provides developers and users with a reliable and accurate source of market data. As more DeFi protocols and applications adopt the GM 30 feed, we can expect to see increased transparency, efficiency, and innovation in the cryptocurrency space. Final Thoughts The launch of the GMCI 30 Index on the Pyth Network is just the beginning. As the cryptocurrency market continues to mature and evolve, the demand for sophisticated financial products and services will only grow. With the foundation laid by this integration, developers and entrepreneurs have a powerful tool at their disposal to create the next generation of DeFi applications that can revolutionize the way we interact with digital assets. Don’t forget to like and share the story! Vested Interest Disclosure: This author is an independent contributor publishing via our business blogging program. HackerNoon has reviewed the report for quality, but the claims herein belong to the author. #DYOR. Vested Interest Disclosure: This author is an independent contributor publishing via our business blogging program . HackerNoon has reviewed the report for quality, but the claims herein belong to the author. #DYOR. Vested Interest Disclosure: business blogging program business blogging program

GMCI 30 Index Launches on Pyth Network, Expanding Access to Cryptocurrency Market Data

GMCI 30 Index Pyth নেটওয়ার্কে চালু হয়েছে, ক্রিপ্টোকারেন্সি মার্কেট ডেটাতে অ্যাক্সেস প্রসারিত করছে

GMCI 30 Index wird im Pyth Network eingeführt und erweitert den Zugang zu Marktdaten für Kryptowährungen

El índice GMCI 30 se lanza en Pyth Network, ampliando el acceso a los datos del mercado de criptomonedas

L'indice GMCI 30 est lancé sur le réseau Pyth, élargissant l'accès aux données du marché des crypto-monnaies

GMCI 30 इंडेक्स पाइथ नेटवर्क पर लॉन्च हुआ, जिससे क्रिप्टोकरेंसी मार्केट डेटा तक पहुंच का विस्तार हुआ

GMCI 30指数がPythネットワークで開始、暗号通貨市場データへのアクセスを拡大

GMCI 30 지수가 Pyth Network에서 출시되어 암호화폐 시장 데이터에 대한 액세스가 확대되었습니다.

Índice GMCI 30 é lançado na Pyth Network, expandindo o acesso aos dados do mercado de criptomoedas

Индекс GMCI 30 запускается в сети Pyth, расширяя доступ к данным рынка криптовалют

GMCI 30 Endeksi Pyth Ağında Başlatılarak Kripto Para Piyasası Verilerine Erişimi Genişletiyor

Chỉ số GMCI 30 ra mắt trên mạng Pyth, mở rộng quyền truy cập vào dữ liệu thị trường tiền điện tử

GMCI 30 指数在 Pyth 网络上推出，扩大了加密货币市场数据的访问权限

Deep Neural Networks to Detect and Quantify Lymphoma Lesions: Results

ডিপ নিউরাল নেটওয়ার্ক লিম্ফোমা ক্ষত সনাক্ত এবং পরিমাপ করতে: ফলাফল

Tiefe neuronale Netzwerke zur Erkennung und Quantifizierung von Lymphomläsionen: Ergebnisse

Redes neuronales profundas para detectar y cuantificar lesiones de linfoma: resultados

Réseaux de neurones profonds pour détecter et quantifier les lésions de lymphome : résultats

लिम्फोमा घावों का पता लगाने और मात्रा निर्धारित करने के लिए डीप न्यूरल नेटवर्क: परिणाम

リンパ腫病変を検出し定量化するディープニューラルネットワーク：結果

림프종 병변을 탐지하고 정량화하기 위한 심층 신경망: 결과

Redes Neurais Profundas para Detectar e Quantificar Lesões de Linfoma: Resultados

Глубокие нейронные сети для обнаружения и количественной оценки поражений лимфомой: результаты

Lenfoma Lezyonlarını Tespit Etmek ve Ölçmek İçin Derin Sinir Ağları: Sonuçlar

Mạng lưới thần kinh sâu để phát hiện và định lượng tổn thương ung thư hạch: Kết quả

深度神经网络检测和量化淋巴瘤病变：结果

Deep Neural Networks to Detect and Quantify Lymphoma Lesions: Materials and Methods

ডিপ নিউরাল নেটওয়ার্ক লিম্ফোমা ক্ষত সনাক্ত এবং পরিমাপ করার জন্য: উপাদান এবং পদ্ধতি

Tiefe neuronale Netzwerke zur Erkennung und Quantifizierung von Lymphomläsionen: Materialien und Methoden

Redes neuronales profundas para detectar y cuantificar lesiones de linfoma: materiales y métodos

Réseaux de neurones profonds pour détecter et quantifier les lésions de lymphome : matériels et méthodes

लिम्फोमा घावों का पता लगाने और मात्रा निर्धारित करने के लिए डीप न्यूरल नेटवर्क: सामग्री और विधियाँ

リンパ腫病変を検出し定量化するディープニューラルネットワーク：材料と方法

림프종 병변을 검출하고 정량화하기 위한 심층 신경망: 재료 및 방법

Redes Neurais Profundas para Detectar e Quantificar Lesões de Linfoma: Materiais e Métodos

Глубокие нейронные сети для обнаружения и количественной оценки поражений лимфомой: материалы и методы

Lenfoma Lezyonlarını Tespit Etmek ve Ölçmek İçin Derin Sinir Ağları: Malzemeler ve Yöntemler

Mạng lưới thần kinh sâu để phát hiện và định lượng tổn thương ung thư hạch: Vật liệu và phương pháp

深度神经网络检测和量化淋巴瘤病变：材料和方法

Authors:
(1) Shadab Ahamed, University of British Columbia, Vancouver, BC, Canada, BC Cancer Research Institute, Vancouver, BC, Canada. He was also a Mitacs Accelerate Fellow (May 2022 - April 2023) with Microsoft AI for Good Lab, Redmond, WA, USA (e-mail: shadabahamed1996@gmail.com);
(2) Yixi Xu, Microsoft AI for Good Lab, Redmond, WA, USA;
(3) Claire Gowdy, BC Children’s Hospital, Vancouver, BC, Canada;
(4) Joo H. O, St. Mary’s Hospital, Seoul, Republic of Korea;
(5) Ingrid Bloise, BC Cancer, Vancouver, BC, Canada;
(6) Don Wilson, BC Cancer, Vancouver, BC, Canada;
(7) Patrick Martineau, BC Cancer, Vancouver, BC, Canada;
(8) Franc¸ois Benard, BC Cancer, Vancouver, BC, Canada;
(9) Fereshteh Yousefirizi, BC Cancer Research Institute, Vancouver, BC, Canada;
(10) Rahul Dodhia, Microsoft AI for Good Lab, Redmond, WA, USA;
(11) Juan M. Lavista, Microsoft AI for Good Lab, Redmond, WA, USA;
(12) William B. Weeks, Microsoft AI for Good Lab, Redmond, WA, USA;
(13) Carlos F. Uribe, BC Cancer Research Institute, Vancouver, BC, Canada, and University of British Columbia, Vancouver, BC, Canada;
(14) Arman Rahmim, BC Cancer Research Institute, Vancouver, BC, Canada, and University of British Columbia, Vancouver, BC, Canada. Table of Links Abstract and Intro
Related Work
Materials and Methods
Results
Discussion
Conclusion and References VI. CONCLUSION In this study, we assessed various neural network architectures for automating lymphoma lesion segmentation in PET/CT images across multiple datasets. We examined the reproducibility of lesion measures, revealing differences among networks, highlighting their suitability for specific clinical uses. Additionally, we introduced three lesion detection criteria to assess network performance at a per-lesion level, emphasizing their clinical relevance. Lastly, we discussed challenges related to ground truth consistency and stressed the importance of having well-defined protocol for segmentation. This work provides valuable insights into deep learning’s potentials and limitations in lymphoma lesion segmentation and emphasizes the need for standardized annotation practices to enhance research validity and clinical applications. REFERENCES [1] S. F. Barrington et al. “FDG PET for therapy monitoring in Hodgkin and non-Hodgkin lymphomas”. In: European Journal of Nuclear Medicine and Molecular Imaging 44.1 (Aug. 2017), pp. 97–110. ISSN: 1619- 7089. [2] K. Okuyucu et al. “Prognosis estimation under the light of metabolic tumor parameters on initial FDG-PET/CT in patients with primary extranodal lymphoma”. en. In: Radiol. Oncol. 50.4 (Dec. 2016), pp. 360–369. [3] N. Wu et al. “Deep Neural Networks Improve Radiologists’ Performance in Breast Cancer Screening”. In: IEEE Transactions on Medical Imaging 39.4 (2020), pp. 1184–1194. [4] C. Yuan et al. “Diffuse large B-cell lymphoma segmentation in PET-CT images via hybrid learning for feature fusion”. In: Medical Physics 48.7 (2021), pp. 3665– 3678. [5] H. Hu et al. “Lymphoma Segmentation in PET Images Based on Multi-view and Conv3D Fusion Strategy”. In: 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI). 2020, pp. 1197–1200. [6] H. Li et al. “DenseX-Net: An End-to-End Model for Lymphoma Segmentation in Whole-Body PET/CT Images”. In: IEEE Access 8 (2020), pp. 8004–8018. [7] L. Liu et al. “Improved Multi-modal Patch Based Lymphoma Segmentation with Negative Sample Augmentation and Label Guidance on PET/CT Scans”. In: Multiscale Multimodal Medical Imaging. Ed. by X. Li et al. Cham: Springer Nature Switzerland, 2022, pp. 121–129. ISBN: 978-3-031-18814-5. [8] C. S. Constantino et al. “Evaluation of Semiautomatic and Deep Learning–Based Fully Automatic Segmentation Methods on [18F]FDG PET/CT Images from Patients with Lymphoma: Influence on Tumor Characterization”. In: Journal of Digital Imaging 36.4 (Aug. 2023), pp. 1864–1876. ISSN: 1618-727X. [9] A. J. Weisman et al. “Comparison of 11 automated PET segmentation methods in lymphoma”. English. In: Physics in medicine & biology 65.23 (2020), pp. 235019–235019. [10] A. J. Weisman et al. “Convolutional Neural Networks for Automated PET/CT Detection of Diseased Lymph Node Burden in Patients with Lymphoma”. In: Radiology: Artificial Intelligence 2.5 (2020), e200016. [11] C. Jiang et al. “Deep learning–based tumour segmentation and total metabolic tumour volume prediction in the prognosis of diffuse large B-cell lymphoma patients in 3D FDG-PET images”. In: European Radiology 32.7 (July 2022), pp. 4801–4812. ISSN: 1432-1084. [12] P. Blanc-Durand et al. “Fully automatic segmentation of diffuse large B cell lymphoma lesions on 3D FDGPET/CT for total metabolic tumour volume prediction using a convolutional neural network.” In: European Journal of Nuclear Medicine and Molecular Imaging 48.5 (May 2021), pp. 1362–1370. ISSN: 1619-7089. [13] S. Ahamed et al. “A U-Net Convolutional Neural Network with Multiclass Dice Loss for Automated Segmentation of Tumors and Lymph Nodes from Head and Neck Cancer PET/CT Images”. In: Head and Neck Tumor Segmentation and Outcome Prediction. Ed. by V. Andrearczyk et al. Cham: Springer Nature Switzerland, 2023, pp. 94–106. ISBN: 978-3-031-27420-6. [14] S. Gatidis et al. “A whole-body FDG-PET/CT Dataset with manually annotated Tumor Lesions”. In: Scientific Data 9.1 (Oct. 2022), p. 601. ISSN: 2052-4463. [15] M. Pop et al. “Left-Ventricle Quantification Using Residual U-Net”. English. In: vol. 11395. Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges. Switzerland: Springer International Publishing AG, 2019, pp. 371–380. ISBN: 0302-9743. [16] A. Myronenko. “3D MRI Brain Tumor Segmentation Using Autoencoder Regularization”. English. In: Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. Cham: Springer International Publishing, 2019, pp. 311–320. ISBN: 0302-9743. [17] F. Isensee et al. “nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation”. In: Nature Methods 18.2 (Dec. 2020), pp. 203–211. [18] A. Hatamizadeh et al. “Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images”. English. In: (2022). [19] M. J. Cardoso et al. MONAI: An open-source framework for deep learning in healthcare. 2022. arXiv: 2211. 02701 [cs.LG]. [20] S. Ahamed et al. “Towards enhanced lesion segmentation using a 3D neural network trained on multiresolution cropped patches of lymphoma PET images”. In: Journal of Nuclear Medicine 64.supplement 1 (2023), P1360–P1360. ISSN: 0161-5505. [21] J. L. Fleiss. “Measuring nominal scale agreement among many raters”. English. In: Psychological bulletin 76.5 (1971), pp. 378–382. [22] A. K. Jha et al. “Nuclear Medicine and artificial intelligence: Best practices for evaluation (the RELAINCE guidelines)”. en. In: J. Nucl. Med. 63.9 (Sept. 2022), pp. 1288–1299. [23] N. Hasani et al. “Artificial Intelligence in Lymphoma PET Imaging: A Scoping Review (Current Trends and Future Directions)”. In: PET clinics 17.1 (Jan. 1), pp. 145–174. ISSN: 1556-8598. [24] S. K. Warfield et al. “Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation”. en. In: IEEE Trans. Med. Imaging 23.7 (July 2004), pp. 903–921. This paper is available on arxiv under CC 4.0 license. Authors: (1) Shadab Ahamed, University of British Columbia, Vancouver, BC, Canada, BC Cancer Research Institute, Vancouver, BC, Canada. He was also a Mitacs Accelerate Fellow (May 2022 - April 2023) with Microsoft AI for Good Lab, Redmond, WA, USA (e-mail: shadabahamed1996@gmail.com); (2) Yixi Xu, Microsoft AI for Good Lab, Redmond, WA, USA; (3) Claire Gowdy, BC Children’s Hospital, Vancouver, BC, Canada; (4) Joo H. O, St. Mary’s Hospital, Seoul, Republic of Korea; (5) Ingrid Bloise, BC Cancer, Vancouver, BC, Canada; (6) Don Wilson, BC Cancer, Vancouver, BC, Canada; (7) Patrick Martineau, BC Cancer, Vancouver, BC, Canada; (8) Franc¸ois Benard, BC Cancer, Vancouver, BC, Canada; (9) Fereshteh Yousefirizi, BC Cancer Research Institute, Vancouver, BC, Canada; (10) Rahul Dodhia, Microsoft AI for Good Lab, Redmond, WA, USA; (11) Juan M. Lavista, Microsoft AI for Good Lab, Redmond, WA, USA; (12) William B. Weeks, Microsoft AI for Good Lab, Redmond, WA, USA; (13) Carlos F. Uribe, BC Cancer Research Institute, Vancouver, BC, Canada, and University of British Columbia, Vancouver, BC, Canada; (14) Arman Rahmim, BC Cancer Research Institute, Vancouver, BC, Canada, and University of British Columbia, Vancouver, BC, Canada. Authors: Authors: (1) Shadab Ahamed, University of British Columbia, Vancouver, BC, Canada, BC Cancer Research Institute, Vancouver, BC, Canada. He was also a Mitacs Accelerate Fellow (May 2022 - April 2023) with Microsoft AI for Good Lab, Redmond, WA, USA (e-mail: shadabahamed1996@gmail.com); (2) Yixi Xu, Microsoft AI for Good Lab, Redmond, WA, USA; (3) Claire Gowdy, BC Children’s Hospital, Vancouver, BC, Canada; (4) Joo H. O, St. Mary’s Hospital, Seoul, Republic of Korea; (5) Ingrid Bloise, BC Cancer, Vancouver, BC, Canada; (6) Don Wilson, BC Cancer, Vancouver, BC, Canada; (7) Patrick Martineau, BC Cancer, Vancouver, BC, Canada; (8) Franc¸ois Benard, BC Cancer, Vancouver, BC, Canada; (9) Fereshteh Yousefirizi, BC Cancer Research Institute, Vancouver, BC, Canada; (10) Rahul Dodhia, Microsoft AI for Good Lab, Redmond, WA, USA; (11) Juan M. Lavista, Microsoft AI for Good Lab, Redmond, WA, USA; (12) William B. Weeks, Microsoft AI for Good Lab, Redmond, WA, USA; (13) Carlos F. Uribe, BC Cancer Research Institute, Vancouver, BC, Canada, and University of British Columbia, Vancouver, BC, Canada; (14) Arman Rahmim, BC Cancer Research Institute, Vancouver, BC, Canada, and University of British Columbia, Vancouver, BC, Canada. Table of Links Abstract and Intro Related Work Materials and Methods Results Discussion Conclusion and References Abstract and Intro Abstract and Intro Related Work Related Work Materials and Methods Materials and Methods Results Results Discussion Discussion Conclusion and References Conclusion and References VI. CONCLUSION In this study, we assessed various neural network architectures for automating lymphoma lesion segmentation in PET/CT images across multiple datasets. We examined the reproducibility of lesion measures, revealing differences among networks, highlighting their suitability for specific clinical uses. Additionally, we introduced three lesion detection criteria to assess network performance at a per-lesion level, emphasizing their clinical relevance. Lastly, we discussed challenges related to ground truth consistency and stressed the importance of having well-defined protocol for segmentation. This work provides valuable insights into deep learning’s potentials and limitations in lymphoma lesion segmentation and emphasizes the need for standardized annotation practices to enhance research validity and clinical applications. REFERENCES [1] S. F. Barrington et al. “FDG PET for therapy monitoring in Hodgkin and non-Hodgkin lymphomas”. In: European Journal of Nuclear Medicine and Molecular Imaging 44.1 (Aug. 2017), pp. 97–110. ISSN: 1619- 7089. [2] K. Okuyucu et al. “Prognosis estimation under the light of metabolic tumor parameters on initial FDG-PET/CT in patients with primary extranodal lymphoma”. en. In: Radiol. Oncol. 50.4 (Dec. 2016), pp. 360–369. [3] N. Wu et al. “Deep Neural Networks Improve Radiologists’ Performance in Breast Cancer Screening”. In: IEEE Transactions on Medical Imaging 39.4 (2020), pp. 1184–1194. [4] C. Yuan et al. “Diffuse large B-cell lymphoma segmentation in PET-CT images via hybrid learning for feature fusion”. In: Medical Physics 48.7 (2021), pp. 3665– 3678. [5] H. Hu et al. “Lymphoma Segmentation in PET Images Based on Multi-view and Conv3D Fusion Strategy”. In: 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI). 2020, pp. 1197–1200. [6] H. Li et al. “DenseX-Net: An End-to-End Model for Lymphoma Segmentation in Whole-Body PET/CT Images”. In: IEEE Access 8 (2020), pp. 8004–8018. [7] L. Liu et al. “Improved Multi-modal Patch Based Lymphoma Segmentation with Negative Sample Augmentation and Label Guidance on PET/CT Scans”. In: Multiscale Multimodal Medical Imaging. Ed. by X. Li et al. Cham: Springer Nature Switzerland, 2022, pp. 121–129. ISBN: 978-3-031-18814-5. [8] C. S. Constantino et al. “Evaluation of Semiautomatic and Deep Learning–Based Fully Automatic Segmentation Methods on [18F]FDG PET/CT Images from Patients with Lymphoma: Influence on Tumor Characterization”. In: Journal of Digital Imaging 36.4 (Aug. 2023), pp. 1864–1876. ISSN: 1618-727X. [9] A. J. Weisman et al. “Comparison of 11 automated PET segmentation methods in lymphoma”. English. In: Physics in medicine & biology 65.23 (2020), pp. 235019–235019. [10] A. J. Weisman et al. “Convolutional Neural Networks for Automated PET/CT Detection of Diseased Lymph Node Burden in Patients with Lymphoma”. In: Radiology: Artificial Intelligence 2.5 (2020), e200016. [11] C. Jiang et al. “Deep learning–based tumour segmentation and total metabolic tumour volume prediction in the prognosis of diffuse large B-cell lymphoma patients in 3D FDG-PET images”. In: European Radiology 32.7 (July 2022), pp. 4801–4812. ISSN: 1432-1084. [12] P. Blanc-Durand et al. “Fully automatic segmentation of diffuse large B cell lymphoma lesions on 3D FDGPET/CT for total metabolic tumour volume prediction using a convolutional neural network.” In: European Journal of Nuclear Medicine and Molecular Imaging 48.5 (May 2021), pp. 1362–1370. ISSN: 1619-7089. [13] S. Ahamed et al. “A U-Net Convolutional Neural Network with Multiclass Dice Loss for Automated Segmentation of Tumors and Lymph Nodes from Head and Neck Cancer PET/CT Images”. In: Head and Neck Tumor Segmentation and Outcome Prediction. Ed. by V. Andrearczyk et al. Cham: Springer Nature Switzerland, 2023, pp. 94–106. ISBN: 978-3-031-27420-6. [14] S. Gatidis et al. “A whole-body FDG-PET/CT Dataset with manually annotated Tumor Lesions”. In: Scientific Data 9.1 (Oct. 2022), p. 601. ISSN: 2052-4463. [15] M. Pop et al. “Left-Ventricle Quantification Using Residual U-Net”. English. In: vol. 11395. Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges. Switzerland: Springer International Publishing AG, 2019, pp. 371–380. ISBN: 0302-9743. [16] A. Myronenko. “3D MRI Brain Tumor Segmentation Using Autoencoder Regularization”. English. In: Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. Cham: Springer International Publishing, 2019, pp. 311–320. ISBN: 0302-9743. [17] F. Isensee et al. “nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation”. In: Nature Methods 18.2 (Dec. 2020), pp. 203–211. [18] A. Hatamizadeh et al. “Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images”. English. In: (2022). [19] M. J. Cardoso et al. MONAI: An open-source framework for deep learning in healthcare. 2022. arXiv: 2211. 02701 [cs.LG]. [20] S. Ahamed et al. “Towards enhanced lesion segmentation using a 3D neural network trained on multiresolution cropped patches of lymphoma PET images”. In: Journal of Nuclear Medicine 64.supplement 1 (2023), P1360–P1360. ISSN: 0161-5505. [21] J. L. Fleiss. “Measuring nominal scale agreement among many raters”. English. In: Psychological bulletin 76.5 (1971), pp. 378–382. [22] A. K. Jha et al. “Nuclear Medicine and artificial intelligence: Best practices for evaluation (the RELAINCE guidelines)”. en. In: J. Nucl. Med. 63.9 (Sept. 2022), pp. 1288–1299. [23] N. Hasani et al. “Artificial Intelligence in Lymphoma PET Imaging: A Scoping Review (Current Trends and Future Directions)”. In: PET clinics 17.1 (Jan. 1), pp. 145–174. ISSN: 1556-8598. [24] S. K. Warfield et al. “Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation”. en. In: IEEE Trans. Med. Imaging 23.7 (July 2004), pp. 903–921. This paper is available on arxiv under CC 4.0 license. This paper is available on arxiv under CC 4.0 license. available on arxiv available on arxiv

Deep Neural Networks to Detect and Quantify Lymphoma Lesions: Conclusion and References

ডিপ নিউরাল নেটওয়ার্ক লিম্ফোমা ক্ষত সনাক্ত এবং পরিমাপ করার জন্য: উপসংহার এবং রেফারেন্স

Tiefe neuronale Netzwerke zur Erkennung und Quantifizierung von Lymphomläsionen: Schlussfolgerung und Referenzen

Redes neuronales profundas para detectar y cuantificar lesiones de linfoma: conclusiones y referencias

Réseaux de neurones profonds pour détecter et quantifier les lésions de lymphome : conclusion et références

लिम्फोमा घावों का पता लगाने और मात्रा निर्धारित करने के लिए डीप न्यूरल नेटवर्क: निष्कर्ष और संदर्भ

リンパ腫病変の検出と定量化のためのディープニューラルネットワーク：結論と参考文献

림프종 병변을 검출하고 정량화하기 위한 심층 신경망: 결론 및 참고 문헌

Redes Neurais Profundas para Detectar e Quantificar Lesões de Linfoma: Conclusão e Referências

Глубокие нейронные сети для обнаружения и количественной оценки поражений лимфомой: заключение и ссылки

Lenfoma Lezyonlarını Tespit Etmek ve Ölçmek İçin Derin Sinir Ağları: Sonuç ve Referanslar

Mạng lưới thần kinh sâu để phát hiện và định lượng tổn thương ung thư hạch: Kết luận và tài liệu tham khảo

深度神经网络检测和量化淋巴瘤病变：结论和参考文献

Stories, News & Mentions about NET0

Net0’s Stories on HackerNoon