Yehya Belhadad
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yehya Belhadad has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
Okba Saidani
2 shared publications- Rasidul Islam
Department of Electrical and Electronic Engineering Jamalpur Science & Technology University Jamalpur Bangladesh
2 shared publications Abdelhalim Brahimi
1 shared publicationAbderrahim Yousfi
1 shared publication- Abderrahim Yousfi
ETA Laboratory , Department of Electronics , IET Institute , University Mohamed El Bachir El Ibrahimi , Algeria
1 shared publication - Allaoua Refoufi
Department of Computer Science, University of Ferhat Abbas Stif-1, Stif, Algeria
1 shared publication
Latest Publications
- Top Cited Papers
- 8 January 2026
- Published by Elsevier in Chinese Journal of Physics
- Vol. 103, 759-785
Synergistic first-principles and SCAPS-1D study of halide-site engineered Sr₃BiX₃ (X = I, Br, and Cl) perovskites for optoelectronic applications
- 8 January 2026
- Published by Elsevier in Chinese Journal of Physics
- Vol. 103, 759-785
Top Cited PapersSynergistic first-principles and SCAPS-1D study of halide-site engineered Sr₃BiX₃ (X = I, Br, and Cl) perovskites for optoelectronic applications
- Open Access
- 1 January 2026
- Published by Wiley in International Journal of Energy Research
- Vol. 2026 (1) , 4459483
Machine Learning‐Assisted Optimization of K 2 InSbBr 6 ‐Based Perovskite Solar Cells: A Hybrid Approach to High‐Efficiency Device Design Using ANN and SCAPS‐1D Simulations
In this paper, a methodology dedicated to improving the design of perovskite solar cells (PSCs), particularly those utilizing K 2 InSbBr 6 as the absorbing material, is presented. The methodology combines artificial intelligence’s potential and modern physics‐driven simulators’ capabilities. A detailed dataset created using the SCAPS‐1D simulator investigated the effect of various factors, such as the choice of electron transport‐layer (ETL) and hole transport‐layer (HTL) materials, absorber thickness, and material defects, on the solar cells’ efficiency. Based on this dataset, an artificial neural network (ANN) model was trained. This dataset was then exploited to predict the power conversion efficiency (PCE) of various solar cell configurations by training an ANN. The ANN model’s predictive results strongly correlate with the simulation results (Pearson coefficient = 0.801). Considering this ANN model’s interesting prediction capabilities, a solar cell is designed and optimized using such a model. This cell is characterized by a WS 2 (1 µm) as the ETL, K 2 InSbBr 6 (700 nm) as the absorber, and NiO (100 nm) as the HTL, and its simulation PCE is about 32.11%.
- 1 January 2026
- Published by Wiley in International Journal of Energy Research
- Vol. 2026 (1) , 4459483
Open AccessMachine Learning‐Assisted Optimization of K 2 InSbBr 6 ‐Based Perovskite Solar Cells: A Hybrid Approach to High‐Efficiency Device Design Using ANN and SCAPS‐1D Simulations
In this paper, a methodology dedicated to improving the design of perovskite solar cells (PSCs), particularly those utilizing K 2 InSbBr 6 as the absorbing material, is presented. The methodology combines artificial intelligence’s potential and modern physics‐driven simulators’ capabilities. A detailed dataset created using the SCAPS‐1D simulator investigated the effect of various factors, such as the choice of electron transport‐layer (ETL) and hole transport‐layer (HTL) materials, absorber thickness, and material defects, on the solar cells’ efficiency. Based on this dataset, an artificial neural network (ANN) model was trained. This dataset was then exploited to predict the power conversion efficiency (PCE) of various solar cell configurations by training an ANN. The ANN model’s predictive results strongly correlate with the simulation results (Pearson coefficient = 0.801). Considering this ANN model’s interesting prediction capabilities, a solar cell is designed and optimized using such a model. This cell is characterized by a WS 2 (1 µm) as the ETL, K 2 InSbBr 6 (700 nm) as the absorber, and NiO (100 nm) as the HTL, and its simulation PCE is about 32.11%.
- 25 May 2018
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 77 (23) , 30437-30474
Spatial reasoning about multimedia document for a profile based adaptation
- 25 May 2018
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 77 (23) , 30437-30474
Spatial reasoning about multimedia document for a profile based adaptation