Conference Articles

Permanent URI for this collection

https://dspaceusad7.4science.cloud/handle/20.500.12458/19

Browse

Browsing Conference Articles by Title

Now showing 1 - 20 of 89
  • Publication
    A Lower Complexity Deep Learning Method for Drones Detection
    (2023)
    Mohamad Kassab
    ;
    Amal El Fallah Seghrouchni
    ;
    Frederic Barbaresco
    ;
    Abu Zitar, Raed 
    Detecting objects such as drones is a challenging task as their relative size and maneuvering capabilities can deceive machine learning models and cause them to misclassify drones as birds or other objects. In this work, we investigate applying several deep-learning techniques to benchmark real data sets of flying drones. A Deep learning paradigm is proposed for the purpose of mitigating the complexity of those systems. The proposed paradigm consists of a hybrid between the AdderNet deep learning paradigm and the SSD paradigm. The goal was to minimize multiplication operations numbers in the filtering layers within the proposed system and, hence, reduce complexity. Some standard machine learning techniques such as SVM is also tested and compared to other deep learning systems. The data sets used for training and testing were either complete or filtered in order to remove the images with mall objects. The types of data were either RGB or IR data. Comparisons were made between all these types and conclusions are presented.
      40Scopus© Citations 1
  • Publication
    A Review for the Genetic Algorithm and the Red Deer Algorithm Applications
    (2021)
    Abu Zitar, Raed 
    The Red Deer algorithm (RD), a contemporary population-based meta heuristic algorithm, applications are thoroughly examined in this paper. The RD algorithm blends evolutionary algorithms' survival of the fittest premise with the productivity and richness of heuristic search approaches. On the other a well-known and relatively older evolutionary based algorithm called the Genetic Algorithm applications are also shown. The contemporary algorithm; the RDA, and the older algorithm; the GA have wide applications in computer science and engineering. This paper sheds the light on all those applications and enable researchers to exploit the possibilities of adapting them in any applications they may have either in engineering, computer science, or business.
    Scopus© Citations 9  43
  • Publication
    A Review of the Genetic Algorithm and JAYA Algorithm Applications
    (2022)
    Abu Zitar, Raed 
    This study throws the light on two metaheuristic algorithms and enable researchers to leverage the potential of adapting them in whatever applications they may have either in engineering, computer science, or business. The two algorithms are the GA and the JAYA. The JAYA algorithm is a modern population-based meta heuristic algorithm, its applications are presented in this work. The JA Y A algorithm integrates evolutionary algorithms' survival of the fittest concept with the productivity and richness of heuristic search methodologies. On the other a well-known and somewhat older evolutionary based method called the Genetic Algorithm with applications is also presented here. The recent two algorithms; the JA Y A and the GA have broad comparable applications in computer science and engineering applications.
      19Scopus© Citations 4
  • Publication
    Analysis of the Performance of Four Filter Types for Drone Tracking
    (2023)
    Mohsen, Amani 
    ;
    Segrouchni, Amal El Fallah
    ;
    Barbaresco, Frederic
    ;
    Abu Zitar, Raed 
    In this work, extensive simulations are done to compare the performance of the 4 filter types; Linear Kalman filter (LKF), Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF), and Particle Filter (PF). A simple nearly constant velocity (NCV) motion model is used with a Gaussian noise measurement model. Simulations were done with different ground truths, different measurements covariance matrices, and different speeds of the drone. Stone soup software was used in the simulations. The analyses revealed informative results that gave us more understanding of the behavior of the four filters when a common type of motion model such as the NCV model is used.
      17
  • Publication
    Application of Red Deer Algorithm in Optimizing Complex functions
    (2021)
    Zitar, Raed 
    ;
    Abualigah, Laith
    The Red Deer algorithm (RDA), a recently developed population-based meta-heuristic algorithm, is examined in this paper with the optimization task of complex functions. The RD algorithm blends evolutionary algorithms' survival of the fittest concept with heuristic search techniques' productivity and richness. It is critical to assess this algorithm's performance in comparison with other well-known heuristic methods. The findings are presented along with additional recommendations for increasing RDA performance based on the analysis. The readers of this paper will gain a grasp of the RD algorithm and its optimization ability to determine whether this algorithm is appropriate for their particular business, research, or industrial needs.
    Scopus© Citations 4  20
  • Publication
    Assessing the Use of Oil and Gas Produced Water for Soil Aquifer Treatment in Abu Dhabi
    (2022)
    Pavlopoulos, Kosmas 
    ;
    Alomary, Hala
    ;
    Jisha, Ali
    ;
    Arangadi, Abdulfahim
    ;
    Moraitis, Daniel
    ;
    Alhseinat, Emad
    The United Arab Emirates originally lack for sufficient natural water resources. A major source of water in the UAE is groundwater, which includes water in surface wells that are normally renewed by seasonal rains, and deep wells which are refilled via ancient geological formations. The deficit in water availability due to the increasing demand and shortage in water resources availability can be met by utilizing non-conventional sources such as desalinated water, and recycling wastewater. This paper aims to present a scientific assessment of the possibility of using treated oil and gas-produced water for recharging the underground aquifer in Abu Dhabi through Soil aquifer treatment (SAT). Core samples from the unsaturated zone layers of sand, sandstone, siltstone, and conglomerates layers from the Abu Dhabi area were collected and characterized. Adsorption experiments have been carried out to investigate the capacity of the soil samples for the removal of hazardous contaminants i.e. heavy metals and dissolved organic from synthesized oil-produced water samples. The obtained data were used to calculate the required time for the hazardous contaminants to reach the underground water.
      103  77
  • Publication
    BioExcom: Detection and categorization of speculative sentences in biomedical literature
    (2011)
    Alrahabi, Al Moatasem 
    ;
    Desclés, Julien
    ;
    Desclés, Jean-Pierre
    Biological research papers are replete with speculative sentences. We present the BioExcom rule-based system, which detects speculations in biomedical literature. Furthermore, it enables to distinguish automatically between prior and new speculations in the analyzed paper. BioExcom is based on the Contextual Exploration processing (hierarchical research of linguistic surface markers with the EXCOM computational platform). To accomplish this task, BioExcom uses also specific linguistic resources established by concise semantic analysis performed by a biologist and a linguist. Our work shows that it is possible to detect and categorize speculative sentences without computational deep linguistic analyses. This work could be useful for biologists who are interested by finding new hypothesis in literature. © 2011 Springer-Verlag.
      77  64Scopus© Citations 5
  • Publication
    Classification automatique et stratégie d'annotation appliquées à un concept philosophique: la dimension psychologique du concept de LANGAGE dans l'oeuvre de Bergson 1
    (2010)
    Alrahabi, Al Moatasem 
    ;
    Danis, Jean
    ;
    Jean-Guy Chartier
    ;
    Chartier, Jean-François
    ;
    Desclés, Jean-pierre
    Les outils d'assistance à la lecture et à l'analyse experte des textes sont de plus en plus demandés dans le domaine des humanités. En philosophie, ces processus de lecture et d'analyse s'effectuent dans bien des cas par l'entremise d'analyses conceptuelles. Les approches lexicométriques et macrotextuelles offrent des pistes intéressantes mais demeurent limitées lorsqu'il s'agit d'analyser les multiples facettes d'un concept philosophique. Nous présentons dans cet article une méthode de fouille textuelle qui combine à l'analyse d'une concordance un algorithme de classification non supervisée (k-moyennes) et une stratégie d'annotation assistée par la plate-forme sémantique EXCOM. Le traitement est appliqué au concept de LANGAGE dans le corpus d'Henri Bergson. Abstract Assisting tools for analysis and expert reading of texts are more and more demanded by researchers in the Humanities. In philosophy, these expert reading processes are often carried out by conceptual analysis. Macro-textual approaches have given appealing results but remain limited when it's time to analyze the multifaceted properties of philosophical concepts. We present in this article a computer-assisted text mining method that allows researchers to explore the multifaceted contexts of a philosophical concept. The method aims at integrating to standard clustering methods a computer-assisted annotation strategy with the use of the platform called " EXCOM " . Our method is here applied to the concept of LANGUAGE in Henri Bergson's corpus.
      70  76
  • Publication
    Compétences plurilingues et métalinguistiques dans l'apprentissage des noms dérivés en italien langue étrangère dans un forum en ligne
    (2011)
    Colombo, Omar 
    Laboratoire Lidilem, université Stendhal-Grenoble 3 Elena Tea Laboratoire Lidilem, université Stendhal-Grenoble 3 Résumé : Le Service commun Lansad de l'Université Stendhal-Grenoble 3 propose parmi d'autres des formations en italien langue étrangère (LE) en présentiel et à distance. Après avoir décrit la place du forum au sein d'un des dispositifs de formation en langue italienne, nous analyserons le rôle du plurilinguisme (français LM, espagnol LE et italien LC –langue cible) et des compétences métalinguistiques dans le traitement morphosémantique des noms issus d'un procédé dérivationnel dans l'accomplissement des tâches de compréhension et de production écrites. Nous visons les transferts interlinguistiques dans l'apprentissage du lexique. Les étudiants mettraient en oeuvre des compensatory strategies (Kellerman, 1991), parmi lesquelles nous comptons le recours au lexique de la LM et d'autres LE. Les coïncidences morphosémantiques LM/LC faciliteraient l'activation des procédés linguistico-cognitifs ; même si c'est parfois de façon négative. Le recours à l'espagnol est une hypothèse réaliste, mais en association avec d'autres facteurs. La structure du forum permettrait à chaque message constituant l'interaction asynchrone en ligne d'être mis à profit dans l'exploitation des repères contextuels, du réseau anaphorique et des multi-occurrences. Nous terminons en montrant que les formateurs devraient mettre en valeur les compétences plurilingues des étudiants en association à l'utilisation, en contexte d'apprentissage, des supports multimédia tels que le forum. Mots clés : forum pédagogique, plurilinguisme, transfert, compétences métalinguistiques Title : Multilingual and metalinguictic skills while learning derived Italian nouns as a foreign language in an online forum. Abstract : The LANSAD Common Service of the University of Grenoble 3 offers a training course in Italian as foreign language with face to face as well as at distance lessons. After describing the forum on the Esprit Platform inside the training course, we will analyse the specific role of the multilingual and metalinguistic skills (French as mother tongue, Spanish as foreign language and Italian as target language) when dealing with nouns coming from derivations while doing written productions and comprehensions. Dejean, C., Mangenot, F., Soubrié, T. (2011, coord.). Actes du colloque Epal 2011 (Échanger pour apprendre en ligne), université Stendhal – Grenoble 3, 24-26 juin 2011. 2 We are aiming at the interliguistical transfers in learning the lexicons. The students would establish compensatory strategies (Kellerman, 1991) among which resorting to the mother tongue and other foreign lexicons. Some morphosemantic coincidences between the mother tongue and the foreign language would simplify the incentive of the linguistic and cognitive procedures; even if it is in a negative way. Resorting to the Spanish language is more than realistic but it has to be linked to other factors. The structure of the forum would enable each message on online, asynchronous interaction to be used and exploited according to contextual landmarks, the anaphoric net and the multi occurrences. We will finish by showing that the teachers should highlight the students' plurilingual skills linked to the use of multimedia supports such as a forum, while learning a language.
      62  92
  • Publication
    Deep Learning Techniques for Colorectal Cancer Detection: Convolutional Neural Networks vs Vision Transformers
    (2024)
    Sari, Meriem
    ;
    Moussaoui, Abdelouahab
    ;
    Hadid, Abdenour 
    Colorectal cancer (CRC) is one of the most common cancers among humans, its diagnosis is made through the visual analysis of tissue samples by pathologists; artificial intelligence (AI) can automate this analysis based on histological images generated from different tissue samples. In this paper we aim to enhance this digital pathology process by proposing two deep learning (DL) based methods that are extremely accurate and reliable despite several limitations. Our first method is based on Convolutional Neural Networks (CNN) in order to classify different classes of tissues into cancerous and non-cancerous cells based on histological images. Our second method is based on Vision Transformers and also classifies images into cancerous and non cancerous cells. Due to the sensitivity of the problem, the performance of our work will be estimated using accuracy, precision, recall and F -score metrics since they ensure more credibility to the classification results; our models have been tested and evaluated with a dataset collected from LC25000 database containing 10000 images of cancerous and non-cancerous tissues, our models achieved promising results with an overall accuracy of 99.84 % and 98.95 % respectively with precision= 100%, recall= 100% and Fl-score= 100%, we observed that both of our models overcame several state-of-the-art results.
      9
  • Publication
    Deepfakes Signatures Detection in the Handcrafted Features Space
    (2023)
    Hamadene, Assia
    ;
    Ouahabi, Abdeldjalil
    ;
    Hadid, Abdenour 
    In the Handwritten Signature Verification (HSV) literature, several synthetic databases have been developed for data-augmentation purposes, where new specimens and new identities were generated using bio-inspired algorithms, neuromotor synthesizers, Generative Adversarial Networks (GANs) as well as several deep learning methods. These synthetic databases contain synthetic genuine and forgeries specimens which are used to train and build signature verification systems. Researches on generative data assume that synthetic data are as close as possible to real data, this is why, they are either used for training systems when used for data augmentation tasks or are used to fake systems as synthetic attacks. It is worth, however, to point out the existence of a relationship between the handwritten signature authenticity and human behavior and brain. Indeed, a genuine signature is characterised by specific features that are related to the owner’s personality. The fact which makes signature verification and authentication achievable. Handcrafted features had demonstrated a high capacity to capture personal traits for authenticating real static signatures. We, therefore, Propose in this paper, a handcrafted feature based Writer-Independent (WI) signature verification system to detect synthetic writers and signatures through handcrafted features. We also aim to assess how realistic are synthetic signatures as well as their impact on HSV system’s performances. Obtained results using 4000 synthetic writers of GPDS synthetic database show that the proposed handcrafted features have considerable ability to detect synthetic signatures vs. two widely used real individuals signatures databases, namely CEDAR and GPDS-300, which reach 98.67% and 94.05% of successful synthetic detection rates respectively.
      14Scopus© Citations 1
  • Publication
    Deploying model obfuscation: towards the privacy of decision-making models on shared platforms
    (2024)
    Sadhukhan, Payel
    ;
    Chakraborty, Tanujit 
    ;
    Sengupta, Kausik
    The automation of the industrial paradigms characterizes the era of Industry 4.0. The implementation nuances involve data and model sharing among allies and partners working on the same domain. Privacy and security of data and models are fundamental necessities that must be satisfied for this protocol's proper functioning. To this end, we propose a conceptual and algorithmic framework of a model obfuscation scheme. It is built upon the extant data obfuscation paradigm. The future work lies with the implementation and establishment of its viability. This research is expected to develop into deployable model obfuscation technique which practitioners from the industrial domain can adopt.
      24  2
  • Publication
    Dictionnaire multilingue de proverbes: Premier retour d’expérience
    (2014)
    Alrahabi, Al Moatasem 
    Ce projet est réalisé au département de FLE à l’université Paris-Sorbonne Abou Dhabi. L’objectif est la création d’un dictionnaire thématique de proverbes en français et en arabe. Pour définir l’objet de notre travail, nous avons opté dans un premier temps pour le terme générique « proverbe » qui couvrirait à la fois différents concepts de la parémiologie, tels le dicton, la devinette, le précepte ou la maxime. Chaque entrée du dictionnaire contient: un proverbe français avec sa traduction approximative en arabe ; le proverbe équivalent en arabe (s’il existe) avec sa traduction approximative en français. Les apprenants (niveaux A2-B2) trouveraient dans ce travail différents intérêts pédagogiques et culturels: découverte de l’autre culture et de ses stéréotypes représentatifs à travers l’échange autour de l’imaginaire des proverbes; travailler sur la traduction des formes et des idées entre langues... Ce travail s’effectue entièrement sur une plateforme d’enseignement en ligne (forums et wikis). D’autres outils de traduction collaborative sont également utilisés. L’objectif est de diffuser en ligne un dictionnaire avec des entrées vérifiées et de le mettre à disposition du public à des fins pédagogiques (enrichissement ou introduction d’autres langues). Une évaluation de l’intérêt pédagogique de ce travail collaboratif à distance devrait également être effectuée afin de mesurer l’impact de son utilisation sur le progrès des apprenants, la modification de leur façon de travailler et l'évolution du rôle de l'enseignant.
      56
  • Publication
    Direct reported speech in multilingual texts: Automatic annotation and semantic categorization
    (2010)
    Alrahabi, Al Moatasem 
    ;
    Suh, J.
    ;
    Desclés, J.-P.
    We propose an application for the automatic identification and categorization of quotations. The categorization is based on a semantic map of enunciative modalities. The texts are treated in three languages: Arabic, Korean and French.
      102  54
  • Publication
    Driver's Facial Expression Recognition Using Global Context Vision Transformer
    (2023)
    Saadi, Ibtissam
    ;
    Cunningham, Douglas W
    ;
    Abdelmalik, Taleb-Ahmed
    ;
    Hadid, Abdenour 
    ;
    El Hillali, Yassin
    Driver's facial expression recognition plays a critical role in enhancing driver safety, comfort, and overall driving experience by proactively mitigating potential road risks. While most existing works in this domain rely on CNN - based approaches, this paper proposes a novel method for driver facial expression recognition using Global Context Vision Transformer (DFER-GCViT). With its inherent capabilities of transformer-based architectures and global context modeling, the proposed method handles challenges commonly encountered in real-world driving scenarios, including occlusions, head pose variations, and illumination conditions. Our method consists of three modules: preprocessing for face detection and data augmentation, facial feature extraction of local and global features, and expression classification using a modified GC-ViT classifier. To evaluate the performance of DFER-GCViT, extensive experiments are conducted on two benchmarking datasets namely the KMU-FED driver facial expression dataset and FER2013 general facial expression dataset. The experimental results demonstrate the superiority of DFER-GCViT in accurately recognizing driver's facial expressions, achieving an average accuracy of 98.27 % on the KMU-FED dataset and 73.78% on the FER2013 dataset, outperforming several state-of-the-art methods on these two benchmarking datasets.
    Scopus© Citations 1  4
  • Publication
    Drone Tracking Based on the Fusion of Staring Radar and Camera Data: An Experimental Study
    (2023)
    De Rouchechouart, Maxence 
    ;
    Ahmad, Bashar I.
    ;
    Seghrouchni, Amal El Fallah
    ;
    Barbaresco, Frederic
    ;
    Harman, Stephen
    ;
    Abu Zitar, Raed 
    This paper presents an experimental study on tracking a small drone target with a high resolution camera and a staring radar. The objective is to assess the benefits of fusing the outputs of both sensors using real data collected during live drone trials. We examine the impact of losing the signal from one sensor, which often occurs in practice for various reasons such as occlusions, high background noise-clutter, target sharp maneuvers, etc. We demonstrate that fusion with filtering, namely employing interacting multiple models with unscented Kalman filter in modified spherical coordinates or a simple extended Kalman filter, can deliver improved overall target tracking performance under such degraded sensing conditions.
      21Scopus© Citations 1
  • Publication
    Drone/Bird Classification Based on Features of Tracks Trajectories
    (2023)
    Kengeskanov, Maksat
    ;
    Seghrouchni, Amal El Fallah
    ;
    Abu Zitar, Raed 
    ;
    Barbaresco, Frederic
    This paper presents the outcome of several machine learning techniques used for the task of bird/drone classification based on their tracks. Instead of using static images, the dynamics and features extracted from the trajectories captured in videos are used to provide a more accurate and reliable recognition task. Standard Machine Learning methods such as SVM and Random Forest are used for learning this classification. Features based on the kinematics, Gabor filter, and Gray Level Co-occurrence Matrix are utilized. Several comparisons and experiments based on benchmark data sets are show
      39