Ehsan Adibnia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ehsan Adibnia has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Mohammad Soroosh
Department of Electrical Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran
6 shared publications - Abdullah S. Karar
College of Engineering and Technology, American University of the Middle East, Egaila 54200, Kuwait
5 shared publications - Behnam Jafari
University of Tabriz
5 shared publications Faouzi Bahloul
University of Carthage
3 shared publications- Faouzi Bahloul
SERCOM Laboratory, Tunisia Polytechnic School (EPT), University of Carthage, Tunis 2078, Tunisia
3 shared publications - Haraprasad Mondal
Electronics and Communication Engineering, Dibrugarh University, Dibrugarh, India
3 shared publications
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 37 (10) , 1-9
Deep Reinforcement Learning-Based Optimization of Identical-Dual-Band Filters
Designing identical dual-band optical filters remains a complex optimization challenge in photonics and optical communication systems. Conventional methods, which rely on iterative electromagnetic simulations or analytical approximations, often suffer from limited generalizability and high computational costs. In this work, we propose a deep reinforcement learning (RL) framework for the autonomous optimization of identical dual-band fiber Bragg grating (FBG) filters. A policy network based on a three-layer fully connected neural architecture is trained using a proximal policy optimization algorithm to minimize the full width at half maximum (FWHM) of both transmission bands while maintaining spectral symmetry and identical channel characteristics. The deep RL-based design achieves a 43% reduction in FWHM and a 49% reduction in grating length compared to baseline designs, without sacrificing reflectivity or channel uniformity. This study demonstrates the feasibility and effectiveness of deep RL as a powerful optimization tool for complex photonic systems, providing a scalable and data-efficient pathway toward next-generation optical device design.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 37 (10) , 1-9
Deep Reinforcement Learning-Based Optimization of Identical-Dual-Band Filters
Designing identical dual-band optical filters remains a complex optimization challenge in photonics and optical communication systems. Conventional methods, which rely on iterative electromagnetic simulations or analytical approximations, often suffer from limited generalizability and high computational costs. In this work, we propose a deep reinforcement learning (RL) framework for the autonomous optimization of identical dual-band fiber Bragg grating (FBG) filters. A policy network based on a three-layer fully connected neural architecture is trained using a proximal policy optimization algorithm to minimize the full width at half maximum (FWHM) of both transmission bands while maintaining spectral symmetry and identical channel characteristics. The deep RL-based design achieves a 43% reduction in FWHM and a 49% reduction in grating length compared to baseline designs, without sacrificing reflectivity or channel uniformity. This study demonstrates the feasibility and effectiveness of deep RL as a powerful optimization tool for complex photonic systems, providing a scalable and data-efficient pathway toward next-generation optical device design.
- Open Access
- 23 December 2025
- Published by Elsevier in Results in Optics
- Vol. 22
Algorithmic optimization of figure-of-9 fiber lasers via particle swarm methods
- 23 December 2025
- Published by Elsevier in Results in Optics
- Vol. 22
Open AccessAlgorithmic optimization of figure-of-9 fiber lasers via particle swarm methods
- Open Access
- 9 December 2025
- Published by Elsevier in Results in Optics
- Vol. 22
Development of a high-performance 16-to-4 electro-optical encoder using photonic crystal resonant cavities
- 9 December 2025
- Published by Elsevier in Results in Optics
- Vol. 22
Open AccessDevelopment of a high-performance 16-to-4 electro-optical encoder using photonic crystal resonant cavities
- 17 October 2025
- Published by Optica Publishing Group in Journal of the Optical Society of America B
- Vol. 42 (11) , 2526
Compact and efficient NAND logic gate based on photonic crystal cavities
We propose a compact NAND logic gate implemented in a photonic crystal platform featuring a novel, to our knowledge, architecture with four optimized cavity resonators. The device achieves high-performance metrics, including a contrast ratio of 44.52 dB, a fast response time of 0.18 ps, and a theoretical maximum bit rate of 5.55 Tbit/s. Finite-difference time-domain simulations confirm robust operation across a wide temperature range with negligible performance degradation. The design occupies a footprint of only 84.84µm 2 , marking a substantial reduction in device dimensions compared to existing implementations while maintaining CMOS compatibility. Our comprehensive benchmarking against reported architectures establishes the superior performance of this design in terms of switching speed, signal integrity, and power consumption. These results demonstrate a viable pathway toward practical, large-scale optical computing systems and next-generation optical communication networks.
- 17 October 2025
- Published by Optica Publishing Group in Journal of the Optical Society of America B
- Vol. 42 (11) , 2526
Compact and efficient NAND logic gate based on photonic crystal cavities
We propose a compact NAND logic gate implemented in a photonic crystal platform featuring a novel, to our knowledge, architecture with four optimized cavity resonators. The device achieves high-performance metrics, including a contrast ratio of 44.52 dB, a fast response time of 0.18 ps, and a theoretical maximum bit rate of 5.55 Tbit/s. Finite-difference time-domain simulations confirm robust operation across a wide temperature range with negligible performance degradation. The design occupies a footprint of only 84.84µm 2 , marking a substantial reduction in device dimensions compared to existing implementations while maintaining CMOS compatibility. Our comprehensive benchmarking against reported architectures establishes the superior performance of this design in terms of switching speed, signal integrity, and power consumption. These results demonstrate a viable pathway toward practical, large-scale optical computing systems and next-generation optical communication networks.
- 23 June 2025
- Published by Springer Nature in Plasmonics
- Vol. 20 (11) , 10313-10320
Analysis of Dual Layer Plasmonic Switch Utilizing ITO and Graphene for Photonic Integrated Circuits
- 23 June 2025
- Published by Springer Nature in Plasmonics
- Vol. 20 (11) , 10313-10320
Analysis of Dual Layer Plasmonic Switch Utilizing ITO and Graphene for Photonic Integrated Circuits
- Open Access
- 15 June 2025
- Published by Elsevier in Optical Fiber Technology
- Vol. 94
Inverse design of figure eight fiber laser by artificial neural network
- 15 June 2025
- Published by Elsevier in Optical Fiber Technology
- Vol. 94
Open AccessInverse design of figure eight fiber laser by artificial neural network
- Open Access
- 10 April 2025
- Published by Elsevier in Results in Optics
- Vol. 21
High-performance and compact photonic crystal channel drop filter using P-shaped ring resonator
- 10 April 2025
- Published by Elsevier in Results in Optics
- Vol. 21
Open AccessHigh-performance and compact photonic crystal channel drop filter using P-shaped ring resonator
- 22 March 2025
- Published by Springer Nature in Optical and Quantum Electronics
- Vol. 57 (4) , 1-19
Design of a photonic crystal 4 × 2 encoder based on all-optical NOT and XOR logic gates
- 22 March 2025
- Published by Springer Nature in Optical and Quantum Electronics
- Vol. 57 (4) , 1-19
Design of a photonic crystal 4 × 2 encoder based on all-optical NOT and XOR logic gates
- Open Access
- 12 March 2025
- Published by Elsevier in Results in Physics
- Vol. 71
Inverse design of octagonal plasmonic structure for switching using deep learning
- 12 March 2025
- Published by Elsevier in Results in Physics
- Vol. 71
Open AccessInverse design of octagonal plasmonic structure for switching using deep learning