Unveiling Latent Relations in the Photonics Techno-Economic Complex System

Abstract

The aim of this study is to capture a technology's pathway by identifying emerging subdomains in a complex system of economic processes. The objective is to uncover indirect latent relations among agents interacting in a specific techno-economic segment (TES). A methodology, including an "Extract-Transform-Load" (ETL) process preceding the two steps aimed for analysis, is developed to analyse a TES regarding R&D economic processes of the photonics technology. In the first step, economic relevant R&D activities (EU funded projects and patents) are analysed through a multilayer network (MLN) of agents, considering their interactions in three dimensions, which represent occurred and latent relationships: co-participations in economic activities, common geographical location provenance, common use of technological terms. Then communities are detected (Infomap Algorithm for MLN), and their ongoing within and between connections are studied, as potential factors that affect the entire structured technological ecosystem. In the second step, technological subdomains associated with method-oriented and application-oriented activities are identified through topic modelling. Using the MLN structure, the textual information of the corpus of documents describing the aforementioned economic R&D activities is associated to agents, and the topic model (Latent Dirichlet Allocation) uncovers additional potential semantic connections among them. Subsequently, the results of the MLN community detection and of the topic modelling based on the descriptions of economic activities are considered. Hence, the latent relations of agents are mapped.

Artificial intelligence in nursing and midwifery: A systematic review

“…Hence, computer scientists have strived to develop ways to address this through Artificial Intelligence (AI), which has been defined as "software (and possibly also hardware) systems designed by humans that, given a complex goal, act in the physical or digital dimension by perceiving their environment through data acquisition, interpreting the collected structured or unstructured data, reasoning on the knowledge, or processing the information, derived from this data and deciding the best action(s) to take to achieve the given goal. AI systems can either use symbolic rules or learn a numeric model, and they can also adapt their behaviour by analysing how the environment is affected by their previous actions" (Samoili et al, 2020). AI strives to mimic human cognitive abilities such as abstract reasoning, knowledge representation, learning, autonomous decision-making, communicating in natural languages, as well as sensing and interacting with the natural world.…”

Toward Sustainable Water Infrastructure: The State‐Of‐The‐Art for Modeling the Failure Probability of Water Pipes

“…In the past few decades, ML-based models have emerged as the way forward in modeling water pipe failure due to their robust predictive capacity. ML models are developed by simulating human intelligence on computer systems (Samoili et al, 2020). In this section, models relating to fuzzy and ML algorithms are reviewed and presented in Table 7.…”

Artificial Intelligence Applications in the Diagnosis of Neuromuscular Diseases: A Narrative Review

“…The European Commission AI High-Level Expert Group (AI HLEG) pointed out that AI refers to systems designed by humans, which given an objective can interact with the physical or digital world, by interpreting structured or unstructured data, and to reason based on the knowledge obtained from this data. In this way, its final objective is to present the best actions to take according to predefined parameters to achieve the initially proposed objective [ 5 ]. As a scientific discipline, AI is subdivided into domains and subdomains (Table 1 ) [ 5 ].…”

“…In this way, its final objective is to present the best actions to take according to predefined parameters to achieve the initially proposed objective [ 5 ]. As a scientific discipline, AI is subdivided into domains and subdomains (Table 1 ) [ 5 ].…”