Nous connaissons tous la domotique et le contrôle de la lumière à partir de dispositifs télécomma... more Nous connaissons tous la domotique et le contrôle de la lumière à partir de dispositifs télécommandés. Avec les technologies émergentes de l’internet des objets, il est aujourd’hui possible d’envisager de nouvelles applications liées à la lumière et à son utilisation dans l’habitat. Grâce à la collaboration entre les objets connectés, des cas d’utilisation comme l’adaptation de la couleur et de l’intensité de la lumière en fonction des émotions des habitants identifiées à l’aide d’une caméra vidéo sont devenus facilement réalisables.
Healthcare Informatics for Fighting COVID-19 and Future Epidemics, 2021
The latest advances of deep learning and particularly convolutional neural networks (CNNs) have p... more The latest advances of deep learning and particularly convolutional neural networks (CNNs) have proven more than once their high accuracy in disease detection. In this chapter, we propose a new deep learning-based approach for COVID-19 detection from chest X-ray images. The proposed approach applies, in an efficient way, the techniques of transfer learning and fine-tuning from pre-trained CNN models (InceptionV3, VGG16, MobileNet, EfficientNet, etc.). The dataset used for our experiments has three classes: normal, COVID-19, and other pathologies. The dataset is split into three sub-sets as follows: 70% for training, 15% for validation, and 15% for the final test. To avoid underfitting or overfitting problems during the training process, we apply regularization techniques (L1 & L2 regularizations, dropout, data augmentation, early stopping, cross-validation, etc.), which help in learning and providing a generalizable solution. As a result, we demonstrate the high efficiency of the pr...
ABSTRACT Résumé Dans cet article, nous proposons une nouvelle approche d'annotation séman... more ABSTRACT Résumé Dans cet article, nous proposons une nouvelle approche d'annotation sémantique de mouvements basée sur le lan-gage OWL (Ontology Web Language). Notre modèle em-ploie la notation de mouvements de Benesh et se com-pose de concepts d'ontologies de mouvements ainsi que de leurs relations. Afin de réaliser nos annotations, nous avons développé des règles sémantiques (SWRL : Seman-tic Web Rules Language). Les résultats montrent l'efficacité du système proposé en produisant un ensemble d'annota-tions cohérentes 1 . Mots clefs Fossé sémantique, ontologie, descriptions logiques, SWRL, annotation de mouvements, notation de mouve-ments de Benesh.
Numerous bibliographic reviews related to the use of AI for the behavioral detection of farm anim... more Numerous bibliographic reviews related to the use of AI for the behavioral detection of farm animals exist, but they only focus on a particular type of animal. We believe that some techniques were used for some animals that could also be used for other types of animals. The application and comparison of these techniques between animal species are rarely done. In this paper, we propose a review of machine learning approaches used for the detection of farm animals’ behaviors such as lameness, grazing, rumination, and so on. The originality of this paper is matched classification in the midst of sensors and algorithms used for each animal category. First, we highlight the most implemented approaches for different categories of animals (cows, sheep, goats, pigs, horses, and chickens) to inspire researchers interested to conduct investigation and employ the methods we have evaluated and the results we have obtained in this study. Second, we describe the current trends in terms of technol...
Abstract Agriculture 4.0 is a domain of IoT in full growth which produces large amounts of data f... more Abstract Agriculture 4.0 is a domain of IoT in full growth which produces large amounts of data from machines, robots and sensors networks. This data must be processed very quickly, especially for the systems that need to make real-time decisions. The Kappa architecture provides a way to process Agriculture 4.0 data at high speed in the cloud, and thus meets processing requirements. This paper presents an optimized version of the Kappa architecture allowing fast and efficient data management in Agriculture. The goal of this optimized version of the classical Kappa architecture is to improve memory management and processing speed. the Kappa architecture parameters are fine tuned in order to process data from a concrete use cases. The results of this work have shown the impact of parameters tweaking on the speed of treatment. We have also proven that the combination of Apache Samza with Apache Druid offers the better performances.
Nous connaissons tous la domotique et le contrôle de la lumière à partir de dispositifs télécomma... more Nous connaissons tous la domotique et le contrôle de la lumière à partir de dispositifs télécommandés. Avec les technologies émergentes de l’internet des objets, il est aujourd’hui possible d’envisager de nouvelles applications liées à la lumière et à son utilisation dans l’habitat. Grâce à la collaboration entre les objets connectés, des cas d’utilisation comme l’adaptation de la couleur et de l’intensité de la lumière en fonction des émotions des habitants identifiées à l’aide d’une caméra vidéo sont devenus facilement réalisables.
Healthcare Informatics for Fighting COVID-19 and Future Epidemics, 2021
The latest advances of deep learning and particularly convolutional neural networks (CNNs) have p... more The latest advances of deep learning and particularly convolutional neural networks (CNNs) have proven more than once their high accuracy in disease detection. In this chapter, we propose a new deep learning-based approach for COVID-19 detection from chest X-ray images. The proposed approach applies, in an efficient way, the techniques of transfer learning and fine-tuning from pre-trained CNN models (InceptionV3, VGG16, MobileNet, EfficientNet, etc.). The dataset used for our experiments has three classes: normal, COVID-19, and other pathologies. The dataset is split into three sub-sets as follows: 70% for training, 15% for validation, and 15% for the final test. To avoid underfitting or overfitting problems during the training process, we apply regularization techniques (L1 & L2 regularizations, dropout, data augmentation, early stopping, cross-validation, etc.), which help in learning and providing a generalizable solution. As a result, we demonstrate the high efficiency of the pr...
ABSTRACT Résumé Dans cet article, nous proposons une nouvelle approche d'annotation séman... more ABSTRACT Résumé Dans cet article, nous proposons une nouvelle approche d'annotation sémantique de mouvements basée sur le lan-gage OWL (Ontology Web Language). Notre modèle em-ploie la notation de mouvements de Benesh et se com-pose de concepts d'ontologies de mouvements ainsi que de leurs relations. Afin de réaliser nos annotations, nous avons développé des règles sémantiques (SWRL : Seman-tic Web Rules Language). Les résultats montrent l'efficacité du système proposé en produisant un ensemble d'annota-tions cohérentes 1 . Mots clefs Fossé sémantique, ontologie, descriptions logiques, SWRL, annotation de mouvements, notation de mouve-ments de Benesh.
Numerous bibliographic reviews related to the use of AI for the behavioral detection of farm anim... more Numerous bibliographic reviews related to the use of AI for the behavioral detection of farm animals exist, but they only focus on a particular type of animal. We believe that some techniques were used for some animals that could also be used for other types of animals. The application and comparison of these techniques between animal species are rarely done. In this paper, we propose a review of machine learning approaches used for the detection of farm animals’ behaviors such as lameness, grazing, rumination, and so on. The originality of this paper is matched classification in the midst of sensors and algorithms used for each animal category. First, we highlight the most implemented approaches for different categories of animals (cows, sheep, goats, pigs, horses, and chickens) to inspire researchers interested to conduct investigation and employ the methods we have evaluated and the results we have obtained in this study. Second, we describe the current trends in terms of technol...
Abstract Agriculture 4.0 is a domain of IoT in full growth which produces large amounts of data f... more Abstract Agriculture 4.0 is a domain of IoT in full growth which produces large amounts of data from machines, robots and sensors networks. This data must be processed very quickly, especially for the systems that need to make real-time decisions. The Kappa architecture provides a way to process Agriculture 4.0 data at high speed in the cloud, and thus meets processing requirements. This paper presents an optimized version of the Kappa architecture allowing fast and efficient data management in Agriculture. The goal of this optimized version of the classical Kappa architecture is to improve memory management and processing speed. the Kappa architecture parameters are fine tuned in order to process data from a concrete use cases. The results of this work have shown the impact of parameters tweaking on the speed of treatment. We have also proven that the combination of Apache Samza with Apache Druid offers the better performances.
Uploads
Papers by Said Mahmoudi