New achievements in Artificial Intelligence (AI) and Machine Learning (ML) are reported almost daily by the big companies. While those achievements are accomplished by fast and massive data processing techniques, the potential of embedded machine learning, where intelligent algorithms run in resource-constrained devices rather than in the cloud, is still not understood well by the majority of the industrial players and Small and Medium Enterprises (SMEs). Nevertheless, the potential embedded machine learning for processing high-performance algorithms without relying on expensive cloud solutions is perceived as very high. This potential has led to a broad demand by industry and SMEs for a practical and application-oriented feasibility study, which helps them to understand the potential benefits, but also the limitations of embedded AI. To address these needs, this paper presents the approach of the AITIA project, a consortium of four Universities which aims at developing and demonstrating best practices for embedded AI by means of four industrial case studies of high-relevance to the European industry and SMEs: sensors, security, automotive and industry 4.0.
Brandalero, M, Ali, M, Le Jeune, L, Muñoz Hernandez, HG, Veleski, M , da Silva, B , Lemeire, J , Van Beeck, K , Touhafi, A , Goedeme, T, Mentens, N, Göhringer, D & Hubner, M 2020, AITIA: Embedded AI Techniques for Embedded Industrial Applications . in AITIA: Embedded AI Techniques for Embedded Industrial Applications. pp. 1-7, 2020 International Conference on Omni-layer Intelligent Systems (COINS), Barcelona, Spain, 31/08/20 .
Brandalero, M., Ali, M., Le Jeune, L., Muñoz Hernandez, H. G., Veleski, M. , da Silva, B. , Lemeire, J. , Van Beeck, K. , Touhafi, A. , Goedeme, T., Mentens, N., Göhringer, D., & Hubner, M. (2020). AITIA: Embedded AI Techniques for Embedded Industrial Applications . In AITIA: Embedded AI Techniques for Embedded Industrial Applications (pp. 1-7)
@inproceedings{73a27ea04e764dcab7acd494671d1df2,
title = " AITIA: Embedded AI Techniques for Embedded Industrial Applications " ,
abstract = " New achievements in Artificial Intelligence (AI) and Machine Learning (ML) are reported almost daily by the big companies. While those achievements are accomplished by fast and massive data processing techniques, the potential of embedded machine learning, where intelligent algorithms run in resource-constrained devices rather than in the cloud, is still not understood well by the majority of the industrial players and Small and Medium Enterprises (SMEs). Nevertheless, the potential embedded machine learning for processing high-performance algorithms without relying on expensive cloud solutions is perceived as very high. This potential has led to a broad demand by industry and SMEs for a practical and application-oriented feasibility study, which helps them to understand the potential benefits, but also the limitations of embedded AI. To address these needs, this paper presents the approach of the AITIA project, a consortium of four Universities which aims at developing and demonstrating best practices for embedded AI by means of four industrial case studies of high-relevance to the European industry and SMEs: sensors, security, automotive and industry 4.0. " ,
author = " Marcelo Brandalero and Muhammad Ali and {Le Jeune}, Laurens and {Mu{~n}oz Hernandez}, {Hector Gerardo} and Mitko Veleski and {da Silva}, Bruno and Jan Lemeire and {Van Beeck}, Kristof and Abdellah Touhafi and Toon Goedeme and Nele Mentens and Diana G{ " o}hringer and Michael Hubner " ,
year = " 2020 " ,
month = aug,
day = " 31 " ,
doi = " 10.1109/COINS49042.2020.9191672 " ,
language = " English " ,
isbn = " 978-1-7281-6372-7 " ,
pages = " 17 " ,
booktitle = " AITIA: Embedded AI Techniques for Embedded Industrial Applications " ,
note = " 2020 International Conference on Omni-layer Intelligent Systems (COINS), COINS Conference date: 31-08-2020 Through 02-09-2020 " ,
url = " https://ieeexplore.ieee.org/xpl/conhome/9186550/proceeding " ,
}