Link
Abstract and 1. Introduction
2 related work and 2.1 technology relevant approach
2.2 Technology Relating Measures
2.3 Technology Models
3 data
4 methods and 4.1 proximity indices
4.2 interpolation and fitting data
4.3 Clustering
4.4 Forecasting
5 results and discussions and 5.1 general results
5.2 Case Study
5.3 Limitations and future works
6 conclusions and references
Appendix
2.3 Technology Models
This section will explore graphic and forecasts models used to distinguish and predict clusters of converting technologies from other common technologies.
2.3.1 Graph based models
Graph -based techniques provide an alternative, allowing for a technological scene evaluation from a macro perspective, rather than relying solely on separate pairing analysis [8, 11, 20–23]. Cluster and Hypergraphs evaluate to facilitate this process, which contributes to the identity and prediction of technology converting clusters [8, 11, 20, 22, 23]. This method is recognized that technological scene usually occurs within groups, featuring the limits of study pairs in a field characterized by interrelated networks [22, 24]. However, the broader perspective of graph-based techniques can diminish mild contact with micro-levels, which potentially over-expression of complex relationships and lead to loss of information or bias interpretation.
2.3.2 Forecasting models
Forecasting models for technological scenes use a diverse set of algorithms and techniques. These models include graph-based clustering algorithms such as spectral louvain modularity (SLM) and the Louvain method, Matrix structure design (DSM), random forests, and topological clustering to study connections between technological evolution and emergences [8, 12, 23, 25–27]. In addition, unpredictable models use autoregressive integrated average transition (Arima), neural networks, and expansion approaches to rely on technological trends [12, 25, 26, 28].
Those with -set:
.[email protected]);
.
.
.
