Slide
Centre Interdisciplinaire
de Recherche et d’Innovation
en Cybersécurité et Société
de Recherche et d’Innovation
en Cybersécurité et Société
1.
Bouafia, Y.; Allili, M. S.; Hebbache, L.; Guezouli, L.
SES-ReNet: Lightweight deep learning model for human detection in hazy weather conditions Article de journal
Dans: Signal Processing: Image Communication, vol. 130, 2025, ISSN: 09235965 (ISSN), (Publisher: Elsevier B.V.).
Résumé | Liens | BibTeX | Étiquettes: Condition, Deep learning, face recognition, Hazy weather, Human detection, Knowledge distillation, Learning models, Lightweight Retinanet, Outdoor scenes, Personal safety, Personal security, Safety and securities
@article{bouafia_ses-renet_2025,
title = {SES-ReNet: Lightweight deep learning model for human detection in hazy weather conditions},
author = {Y. Bouafia and M. S. Allili and L. Hebbache and L. Guezouli},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85208562795&doi=10.1016%2fj.image.2024.117223&partnerID=40&md5=322b79f8d78045395efcabcbf86c6e1c},
doi = {10.1016/j.image.2024.117223},
issn = {09235965 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {Signal Processing: Image Communication},
volume = {130},
abstract = {Accurate detection of people in outdoor scenes plays an essential role in improving personal safety and security. However, existing human detection algorithms face significant challenges when visibility is reduced and human appearance is degraded, particularly in hazy weather conditions. To address this problem, we present a novel lightweight model based on the RetinaNet detection architecture. The model incorporates a lightweight backbone feature extractor, a dehazing functionality based on knowledge distillation (KD), and a multi-scale attention mechanism based on the Squeeze and Excitation (SE) principle. KD is achieved from a larger network trained on unhazed clear images, whereas attention is incorporated at low-level and high-level features of the network. Experimental results have shown remarkable performance, outperforming state-of-the-art methods while running at 22 FPS. The combination of high accuracy and real-time capabilities makes our approach a promising solution for effective human detection in challenging weather conditions and suitable for real-time applications. © 2024},
note = {Publisher: Elsevier B.V.},
keywords = {Condition, Deep learning, face recognition, Hazy weather, Human detection, Knowledge distillation, Learning models, Lightweight Retinanet, Outdoor scenes, Personal safety, Personal security, Safety and securities},
pubstate = {published},
tppubtype = {article}
}
Accurate detection of people in outdoor scenes plays an essential role in improving personal safety and security. However, existing human detection algorithms face significant challenges when visibility is reduced and human appearance is degraded, particularly in hazy weather conditions. To address this problem, we present a novel lightweight model based on the RetinaNet detection architecture. The model incorporates a lightweight backbone feature extractor, a dehazing functionality based on knowledge distillation (KD), and a multi-scale attention mechanism based on the Squeeze and Excitation (SE) principle. KD is achieved from a larger network trained on unhazed clear images, whereas attention is incorporated at low-level and high-level features of the network. Experimental results have shown remarkable performance, outperforming state-of-the-art methods while running at 22 FPS. The combination of high accuracy and real-time capabilities makes our approach a promising solution for effective human detection in challenging weather conditions and suitable for real-time applications. © 2024
2.
Khosrojerdi, F.; Gagnon, S.; Valverde, R.
Leveraging AI for Sustainable Energy Development in Solar Power Plants Operating Under Shading Conditions Article de journal
Dans: Energies, vol. 18, no 11, 2025, ISSN: 19961073 (ISSN), (Publisher: Multidisciplinary Digital Publishing Institute (MDPI)).
Résumé | Liens | BibTeX | Étiquettes: Computer control systems, Condition, Electric power system control, Energy, Energy forecasting, Energy output, Maximum Power Point Tracking, MPPT, Photovoltaic arrays, Photovoltaic systems, Power, PSC, SDGs, Solar energy, Solar fuels, Solar heating, sustainable development, Sustainable energy development
@article{khosrojerdi_leveraging_2025,
title = {Leveraging AI for Sustainable Energy Development in Solar Power Plants Operating Under Shading Conditions},
author = {F. Khosrojerdi and S. Gagnon and R. Valverde},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105007798431&doi=10.3390%2fen18112960&partnerID=40&md5=2a1c721151c469168b124841a0edd4d7},
doi = {10.3390/en18112960},
issn = {19961073 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {Energies},
volume = {18},
number = {11},
abstract = {In a photovoltaic (PV) system, shading caused by weather and environmental factors can significantly impact electricity production. For over a decade, artificial intelligence (AI) techniques have been applied to enhance energy production efficiency in the solar energy sector. This paper demonstrates how AI-based control systems can improve energy output in a solar power plant under shading conditions. The findings highlight that AI contributes to the sustainable development of the solar power sector. Specifically, maximum power point tracking (MPPT) control systems, utilizing metaheuristic and computer-based algorithms, enable PV arrays to mitigate the impacts of shading effectively. The effect of shading on a PV module is also simulated using MATLAB R2018b. Using actual PV data from a solar power plant, power outputs are compared in two scenarios: (I) PV systems without a control system and (II) PV arrays equipped with MPPT boards. The System Advisor Model (SAM) is employed to calculate the monthly energy output of the case study. The results confirm that PV systems using MPPT technology generate significantly more monthly energy compared to those without MPPTs. © 2025 by the authors.},
note = {Publisher: Multidisciplinary Digital Publishing Institute (MDPI)},
keywords = {Computer control systems, Condition, Electric power system control, Energy, Energy forecasting, Energy output, Maximum Power Point Tracking, MPPT, Photovoltaic arrays, Photovoltaic systems, Power, PSC, SDGs, Solar energy, Solar fuels, Solar heating, sustainable development, Sustainable energy development},
pubstate = {published},
tppubtype = {article}
}
In a photovoltaic (PV) system, shading caused by weather and environmental factors can significantly impact electricity production. For over a decade, artificial intelligence (AI) techniques have been applied to enhance energy production efficiency in the solar energy sector. This paper demonstrates how AI-based control systems can improve energy output in a solar power plant under shading conditions. The findings highlight that AI contributes to the sustainable development of the solar power sector. Specifically, maximum power point tracking (MPPT) control systems, utilizing metaheuristic and computer-based algorithms, enable PV arrays to mitigate the impacts of shading effectively. The effect of shading on a PV module is also simulated using MATLAB R2018b. Using actual PV data from a solar power plant, power outputs are compared in two scenarios: (I) PV systems without a control system and (II) PV arrays equipped with MPPT boards. The System Advisor Model (SAM) is employed to calculate the monthly energy output of the case study. The results confirm that PV systems using MPPT technology generate significantly more monthly energy compared to those without MPPTs. © 2025 by the authors.
3.
Khosrojerdi, F.; Gagnon, S.; Valverde, R.
Identifying Influential Factors Affecting the Shading of a Solar Panel Article d'actes
Dans: 2021 IEEE Electrical Power and Energy Conference, EPEC 2021, p. 255–260, Institute of Electrical and Electronics Engineers Inc., 2021, ISBN: 978-1-66542-928-3.
Résumé | Liens | BibTeX | Étiquettes: Condition, Energy forecasting, Forecasting, Influential factors, Knowledge based systems, Partial shading, Photovoltaic planning, Photovoltaic power plant, Photovoltaics, Solar energy, Solar energy forecasting, Solar panels, Uniformly shading
@inproceedings{khosrojerdi_identifying_2021,
title = {Identifying Influential Factors Affecting the Shading of a Solar Panel},
author = {F. Khosrojerdi and S. Gagnon and R. Valverde},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85123618954&doi=10.1109%2fEPEC52095.2021.9621688&partnerID=40&md5=089defe4cb4ff62c6d3a367d1c6260d1},
doi = {10.1109/EPEC52095.2021.9621688},
isbn = {978-1-66542-928-3},
year = {2021},
date = {2021-01-01},
booktitle = {2021 IEEE Electrical Power and Energy Conference, EPEC 2021},
pages = {255–260},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Photovoltaic (PV) systems produce less energy when operating under shadings. PV planners need to identify important factors affecting the shadings to forecast power generations in various ambient conditions. Using a case study, we show that overlooking the impact of an environmental factor, herein snowfalls, will result in overestimations in the power forecasting. In this paper, we study the context of the shading from different perspectives and introduce parameters that can affect the duration and severity of shading conditions. To identify key notions of the shading and important factors involved, we implement a literature review and include experts' knowledge by exploring PV planning tools and conducting a survey in the sector of solar energy. The identified factors can be used to develop a knowledge-based model representing key concepts associated with shading conditions. In addition, the identification of important factors affecting the duration and severity of shading conditions addresses new research domains that need to be explored in the field of PV shading and power estimation. © 2021 IEEE.},
keywords = {Condition, Energy forecasting, Forecasting, Influential factors, Knowledge based systems, Partial shading, Photovoltaic planning, Photovoltaic power plant, Photovoltaics, Solar energy, Solar energy forecasting, Solar panels, Uniformly shading},
pubstate = {published},
tppubtype = {inproceedings}
}
Photovoltaic (PV) systems produce less energy when operating under shadings. PV planners need to identify important factors affecting the shadings to forecast power generations in various ambient conditions. Using a case study, we show that overlooking the impact of an environmental factor, herein snowfalls, will result in overestimations in the power forecasting. In this paper, we study the context of the shading from different perspectives and introduce parameters that can affect the duration and severity of shading conditions. To identify key notions of the shading and important factors involved, we implement a literature review and include experts' knowledge by exploring PV planning tools and conducting a survey in the sector of solar energy. The identified factors can be used to develop a knowledge-based model representing key concepts associated with shading conditions. In addition, the identification of important factors affecting the duration and severity of shading conditions addresses new research domains that need to be explored in the field of PV shading and power estimation. © 2021 IEEE.
4.
Khosrojerdi, F.; Gagnon, S.; Valverde, R.
Full Shading for Photovoltaic Systems Operating under Snow Conditions Article d'actes
Dans: 2021 9th IEEE International Conference on Smart Energy Grid Engineering, SEGE 2021, p. 82–87, Institute of Electrical and Electronics Engineers Inc., 2021, ISBN: 978-0-7381-4535-8.
Résumé | Liens | BibTeX | Étiquettes: Computer software, Condition, Energy consumer, Energy forecasting, Photovoltaic cells, Photovoltaic planning, Photovoltaic shading, Photovoltaic systems, Photovoltaics, Snow, Snow-covered module, Solar energy, Solar power generation, Solar power plants, USC
@inproceedings{khosrojerdi_full_2021,
title = {Full Shading for Photovoltaic Systems Operating under Snow Conditions},
author = {F. Khosrojerdi and S. Gagnon and R. Valverde},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85116021648&doi=10.1109%2fSEGE52446.2021.9534991&partnerID=40&md5=3a4487157a809d03ae5c46c10499f865},
doi = {10.1109/SEGE52446.2021.9534991},
isbn = {978-0-7381-4535-8},
year = {2021},
date = {2021-01-01},
booktitle = {2021 9th IEEE International Conference on Smart Energy Grid Engineering, SEGE 2021},
pages = {82–87},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Photovoltaic (PV) installers and non-technical solar energy consumers use PV planning software for the system design and simulation. End-users rely on the designed system and power estimations provided by these tools. However, most planning software products fail to consider shading conditions. This problem affects energy forecasting for solar power plants located in cold climates. In this paper, we define the status of full shading for a snow-covered panel and the minimum depth of snow creating it. Using a case study, we design the project by the most reliable planning software, System Advisor Model (SAM). We show that the simulation overestimates power generations for snowy months. To identify shading conditions and the correlated performance reductions, we compare the SAM results with the measured data collected onsite. As a result, the minimum depth of snow that can create full shading and zero production is detected. Moreover, comparing the measured data with the simulated power helps us to define a rule-base system providing PV performance reduction factors. It assists solar sector practitioners to plan a PV project accurately, especially for the locations where snowfall is an important environmental factor for several months. © 2021 IEEE.},
keywords = {Computer software, Condition, Energy consumer, Energy forecasting, Photovoltaic cells, Photovoltaic planning, Photovoltaic shading, Photovoltaic systems, Photovoltaics, Snow, Snow-covered module, Solar energy, Solar power generation, Solar power plants, USC},
pubstate = {published},
tppubtype = {inproceedings}
}
Photovoltaic (PV) installers and non-technical solar energy consumers use PV planning software for the system design and simulation. End-users rely on the designed system and power estimations provided by these tools. However, most planning software products fail to consider shading conditions. This problem affects energy forecasting for solar power plants located in cold climates. In this paper, we define the status of full shading for a snow-covered panel and the minimum depth of snow creating it. Using a case study, we design the project by the most reliable planning software, System Advisor Model (SAM). We show that the simulation overestimates power generations for snowy months. To identify shading conditions and the correlated performance reductions, we compare the SAM results with the measured data collected onsite. As a result, the minimum depth of snow that can create full shading and zero production is detected. Moreover, comparing the measured data with the simulated power helps us to define a rule-base system providing PV performance reduction factors. It assists solar sector practitioners to plan a PV project accurately, especially for the locations where snowfall is an important environmental factor for several months. © 2021 IEEE.