Explainable AI Within the Digital Transformation and Cyber Physical Systems

Moamar Sayed-Mouchaweh received his Master degree from the University of Technology of Compiegne-France in 1999, PhD degree from the University of Reims-France in December 2002, and the Habilitation to Direct Researches (HDR) in Computer science, Control and Signal processing in December 2008. Since September 2011, he is working as a Full Professor in the High National Engineering School of Mines-Telecom Lille-Douai in France. He edited and wrote several Springer books, served as member of Editorial Board, IPC, conference, workshop and tutorial chair for different international conferences, an invited speaker, a guest editor of several special issues of international journals targeting the use of advanced artificial intelligence techniques and tools for digital transformation (energy transition and industry 4.0). He served and is serving as an expert for the evaluation of industrial and research projects in the domain of digital transformation. He is leading an inter-disciplinary and industry based research theme around the use of advanced Artificial Intelligence techniques in order to address the challenges of energy transition and Industry 4.0.

Introduction.- Part 1 Methods used to generate explainable models.- Explainable Artificial Intelligence (XAI).- intrinsic explainable models.- model-agnostic methods.- Part 2 Evaluation layout and meaningful criteria.- expressive power.- portability evaluation layout.- accuracy evaluation layout.- algorithmic complexity.- fidelity evaluation.- stability evaluation.- representativeness evaluation layout.- local/global explanation.- Part 3 XAI applications within the context of digital transformation and cyber-physical systems.- applications of XAI in decision support tools.- smart energy management.- finance.- telemedicine and healthcare.- critical systems.- e-government.- Conclusion.