126 reads

Models for Identifying Technology Convergence: Graph-Based and Forecasting

by textmining...April 28th, 2025
Read on Terminal Reader
Read this story w/o Javascript
tldt arrow

Too Long; Didn't Read

Explore graph-based (cluster analysis, hypergraphs) and forecasting (SLM, ARIMA, neural networks) models used to identify and predict technological convergence.
featured image - Models for Identifying Technology Convergence: Graph-Based and Forecasting
Text Mining HackerNoon profile picture
0-item

Abstract and 1. Introduction

2 Related Work and 2.1 Technology Convergence Approaches

2.2 Technology Convergence Measurements

2.3 Technology Convergence Models

3 Data

4 Method and 4.1 Proximity Indices

4.2 Interpolation and Fitting Data

4.3 Clustering

4.4 Forecasting

5 Results and Discussion and 5.1 Overall Results

5.2 Case Study

5.3 Limitations and Future Works

6 Conclusion and References

Appendix

2.3 Technology Convergence Models

This section explores graph-based and forecasting models used to identify and predict clusters of converging technologies from among other common technologies.


2.3.1 Graph-based Models


Graph-based strategies provide an alternative, allowing for an examination of technological convergence from a macro perspective, rather than relying solely on isolated pairwise analysis [8, 11, 20–23]. Cluster analyses and hypergraphs facilitate this process, aiding in the identification and prediction of converging technology clusters [8, 11, 20, 22, 23]. This approach recognizes that technological convergence generally occurs within groups, highlighting the limitations of pairwise analyses in a field characterized by interconnected networks [22, 24]. However, the broader perspective of graph-based methods may obscure subtle interactions at the micro-level, potentially oversimplifying or misrepresenting complex relationships and leading to information loss or biased interpretations.


2.3.2 Forecasting Models


Forecasting models for technological convergence leverage a diverse range of algorithms and methodologies. These models incorporate graph-based clustering algorithms such as Spectral Louvain Modularity (SLM) and the Louvain method, Design Structure Matrix (DSM) tools, random forests, and topological clustering to analyze the connections between technological evolutions and emergences [8, 12, 23, 25–27]. In addition, predictive models utilize AutoRegressive Integrated Moving Average (ARIMA), neural networks, and exponential smoothing techniques to anticipate technological trends [12, 25, 26, 28].


This paper is available on arxiv under CC BY 4.0 DEED license.

Authors:

(1) Alessandro Tavazz, Cyber-Defence Campus, armasuisse Science and Technology, Building I, EPFL Innovation Park, 1015, Lausanne, Switzerland, Institute of Mathematics, EPFL, 1015, Lausanne, Switzerland and a Corresponding author ([email protected]);

(2) Dimitri Percia David, Cyber-Defence Campus, armasuisse Science and Technology, Building I, EPFL Innovation Park, 1015, Lausanne, Switzerland and Institute of Entrepreneurship & Management, University of Applied Sciences of Western Switzerland (HES-SO Valais-Wallis), Techno-Pole 1, Le Foyer, 3960, Sierre, Switzerland;

(3) Julian Jang-Jaccard, Cyber-Defence Campus, armasuisse Science and Technology, Building I, EPFL Innovation Park, 1015, Lausanne, Switzerland;

(4) Alain Mermoud, Cyber-Defence Campus, armasuisse Science and Technology, Building I, EPFL Innovation Park, 1015, Lausanne, Switzerland.


Trending Topics

blockchaincryptocurrencyhackernoon-top-storyprogrammingsoftware-developmenttechnologystartuphackernoon-booksBitcoinbooks