COVID-19 health crisis highlights the fragility of European industrial strategies and leads us to develop more agile, distributed, and resilient production models at a territorial level. There are two major challenges in this regard: one is to find solutions to secure supplies and/or industrial value chains, and the other is to identify companies that have the potential to transform their production quickly to cope with an emergency situation. We extended the Word2Vec vector space with products and economic activities allowing us to calculate proximities. We present a methodology based on semantic proximity and productive complexities to assess the ability of an A-company to produce a product B and to anticipate customer/supplier-type collaboration according to industrial quality standards. We consider recommendation topics by intertwining machine learning techniques with semantic approaches, referring to area ontologies incorporating territorial dimensionality.
CCS CONCEPTS• Natural language processing; • Recommender systems; • Supply chain management;
Artificial Intelligence (AI) is used to create more sustainable production methods and model climate change, making it a valuable tool in the fight against environmental degradation. This paper describes the paradox of an energy-consuming technology serving the ecological challenges of tomorrow. The study provides an overview of the sectors that use AI-based solutions for environmental protection. It draws on numerous examples from AI for Green players to present use cases and concrete examples. In the second part of the study, the negative impacts of AI on the environment and the emerging technological solutions to support Green AI are examined. It is also shown that the research on less energy-consuming AI is motivated more by cost and energy autonomy constraints than by environmental considerations. This leads to a rebound effect that favors an increase in the complexity of models. Finally, the need to integrate environmental indicators into algorithms is discussed. The environmental dimension is part of the broader ethical problem of AI, and addressing it is crucial for ensuring the sustainability of AI in the long term.
Cyber-attacks are becoming more common and their consequences more and more disastrous. Machine learning is revolutionizing cyber security by analyzing massive amounts of data automatically. In this paper, we test the unsupervised learning method of k-means to detect the intrusion of Sodinokibi ransomware in logs. The k-means highlighted a small cluster of anomalous logs that are revealed to be the entry points of the cyberattack. This positive result allows us to consider automating of k-means, as a solution to monitor logs in real time and report abnormal behavior.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.