Project number:
RESML SASPRO2
Title of the project:
Advancing Guidelines for RESponsible Machine Learning (RESML)
Grant scheme:
SASPRO2
Project type:
European Projects
Project duration (start):
01.02.2022
Project duration (end):
31.01.2025
Principal investigator for FCFT:
Michal Kvasnica

RESponsible Machine Learning (RESML) proposes a unique synergy between the social sciences and information sciences for shaping the future of machine learning modelling techniques. RESML, through an innovative interdisciplinary approach bridges the discipline gap and integrates nonquantifiable data into models for the advancement of the accountable, responsible, interpretable, and bias-free machine learning models. Principal guidelines for ethical machine learning modelling are proposed and implemented for the first time. RESML contributes to developing new EU regulations toward customer policies and privacy in accessing responsible artificial intelligence, and further supports handling the societal challenges of Horizon 2020, the EU Green Deal, and the European Flagship Initiative by effectively regulating ethical machine learning.

Publications

2022

  1. S. Ardabili – L. Abdolalizadeh – C. Mako – B. Torok – A. Mosavi: Systematic Review of Deep Learning and Machine Learning for Building Energy. Frontiers in Energy Research, vol. 10, 2022.   arXiv
  2. M. Dehghan Manshadi – N. Alafchi – A. Tat – M. Mousavi – A. Mosavi: Comparative Analysis of Machine Learning and Numerical Modeling for Combined Heat Transfer in Polymethylmethacrylate. Polymers, 2022.
  3. F. Hejazi – H. Karim – H. Kazemi – S. Shahbazpanahi – A. Mosavi: Fracture mechanics modeling of reinforced concrete joints strengthened by CFRP sheets. Case Studies in Construction Materials, no. 11, vol. 6, 2022.
  4. M. Mousavi – M. Dehghan Manshadi – M. Soltani – F. M. Kashkooli – A. Rahmim – A. MosaviM. Kvasnica – P. M. Atkinson – L. Kovács – A. Koltay – N. Kiss – H. Adeli: Modeling the efficacy of different anti-angiogenic drugs on treatment of solid tumors using 3D computational modeling and machine learning. Computers in Biology and Medicine, vol. 146, 2022.
  5. S. S. Band – S. Ardabili – M. SOOKHAK – A. T. CHRONOPOULOS – S. ELNAFFAR – M. MOSLEHPOUR – M. CSABA – B. TOROK – H. PAI – A. Mosavi: When Smart Cities Get Smarter via Machine Learning: An In-Depth Literature Review. IEEE ACCESS, 2022.
  6. G. Shahgholi – S. Ardabili – A. Shayei – I. Felde – A. Mosavi: Computational Analysis of the Effect of Balancer on the Vibration Performance of the Engine: Experimental and Simulation. Acta Polytechnica Hungarica, no. 4, vol. 19, 2022.
  7. M. Yaseliani – A. Zeinal Hamadani – A. Ijadi Maghsoodi – A. Mosavi: Pneumonia Detection Proposing a Hybrid Deep Convolutional Neural Network Based on Two Parallel Visual Geometry Group Architectures and Machine Learning Classifiers. IEEE ACCESS, no. 8, vol. 11, 2022.

Investigators


Responsibility for content: prof. Ing. Michal Kvasnica, PhD.
Last update: 07.02.2022 11:15
Facebook / Youtube

Facebook / Youtube

RSS