SAID Gadri

Douaa Hanane Kadi , Nada Erayhane Heltali

Facial Emotion Recognition Using Deep Learning Approach

Rania Agoune

Speech Emotion Recognition Using Deep Learning Models

Aymen Gasmi

Designing and Developing an Intelligent Chabot for Product Inquiry Analysis in E-store Using NLP and LLMs Models

Somia Dilmi

Smart Irrigation Based on Soil Moisture Detection

Achwak Berrah

An Academic Chatbot Using NLP and Deep Learning

Nada Chali , Rayane Aillane

Diagnosis of Dental State Using AI Techniques

Sohaib Haouam

ProtectIn: Smart AntiTheft System for Smartphones

Soufyane Bounab

New Diagnostic Tool for Cutaneous Leishmaniasis Based on Artificial Intelligence

Hamouda Hadjer , Djegham Fatima

Language Identification Using Bi-grams Technique, ML and DL Algorithms

Mekhalfia Mohamed Zakaria

An Innovative Smart System for the Safety of Driver

Chenene Soumia

Road Lane Line Detection Based on ML and DL Techniques

Babi Chaima

Fake News Detection Using ML and DL Techniques

Chergui Abdennour , Boutchicha Houssam Eddine

The Green Era: Towards a Smart Ecosystem

Benzahia Anfal ELdjabiria

Prédiction de la Résistance Bactérienne aux Antibiotiques Basée sur des approches ML et DL

Safia Chabira

Analyzing the sentiment polarity of watched movies based on viewers’ comments

Sara Ould Mehieddine , Khadidja Herizi

Développement d’un système intelligent pour prédire la satisfaction envers une agence touristique en se basant sur les avis des client

NourElhouda Adouane

Traffic Signs Recognition for Autonomous Cars

Nadjet Bouafia

Building an Efficient ML and DL Model to Classify Fashion clothing articles

Baya Laoues

Developing an Efficient ANN Model to Detect and Classify Diabetic Patients

Hassina Tahmi

Developing an Efficient CNN Model to Recognize Handwritten Digits

Khadidja Farhati

Applying Deep Learning Approach In Real Object Recognition to Assist Visual Perception for Robots

Imane Chouder

Search of The Optimum Itinerary on a Digitized Road Network

Abdelali AZIZI

Classification des textes arabes supervisée par l'ontologie lexicale WordNet,

Bensbaa Abdelaziz

Classification des textes arabes basée sur une ontologie de domaine

Abdelatif Djennaoui

Creation of an ontology from data base to assist medical diagnosis,

Lazhar Laredj

Development of an efficient approach for Arabic optical character recognizing,

Zineb Bourezg

Multilingual Information Retrieval supervised by an ontology,

Abir Haouas

La mise en place d’un SI basé sur la technique code à barres pour la gestion du personnel de la chambre d’artisanat de la wilaya de M’sila

Imane Laadjel

تصميم وإنجاز منصة تعليمية (البراق) لتعليم ونشر المعارف المقدسية ترتكز على منصة MOODLE

Imane O

Extraction de la racine des mots arabes en utilisant une approche statistique.

Meriem Baali

Utilisation de la technique des n-grammes dans l’extraction des racines en langue arabe

Assia Medjahed

La reconnaissance efficace de la langue dans un corpus de textes multilingue

Samia Baali

Conception et mise en place d’un stemmer pour la langue arabe dans le cadre de la catégorisation automatique de documents

Imane Djennaoui

Mise en place d’une plate-forme de e-learning pour préserver le patrimoine de la ville sainte AL-QUODS

Kharchi Asma

Catégorisation contextuelle de textes arabe par la méthode ADABOOST

Safia Sahraoui

Identification de la langue et catégorisation thématique de textes multilingues en utilisant les RNA

Hala Bouguerra

Modélisation des objets irréguliers avec les courbes de surfaces libres (Béziers, B-Splines)

Faiza Saadoune

Identification de la langue et catégorisation thématique de textes d’un corpus multilingue en utilisant les arbres de décision

Fares Dahoumi

Identification et catégorisation thématique de textes d’un corpus multilingue en utilisant les algorithmes : NB, SVM

Elhosseyn Benmokhtar

Conception et implémentation d’un SI basé sur la technique code à barres pour la gestion de la bibliothèque de la faculté MI, Université de M’sila

this paper concerns the SER system using deep learning to classify emotions from vocalizations. We designed and implemented a CNN trained by a hybrid dataset combining RAVDESS, SAVEE, and CASIA. In essence, MFCCs were extracted to capture salient audio features, and the data were further augmented with noise injections, pitch shifts, and time-stretching. The model could classify seven emotions, namely anger, disgust, fear, happiness, sadness, surprise, and neutral, with a classification accuracy of over 96%. The results thus prove CNN-based models to be effective for addressing the complexity and variation of human emotional expressions in speech.

Citation

SAID Gadri , ,(2025-12-16), Speech Emotion Recognition Using Deep Learning Models,26th International Arab Conference on Information Technology (ACIT 2025),Alexandria- Egypt

Early fire detection is critical to protecting people, property, and the environment. Recent advances in artificial intelligence (AI), the Internet of Things (IoT), and edge computing have enabled faster and more intelligent solutions than traditional smoke- or heat-based detectors. This survey reviews state-ofthe- art research and organizes it into three complementary categories: (i) vision-based systems, (ii) sensor-based and fusion systems, and (iii) AI- and IoT-enabled edge deployments. In addition, we summarize fire localization approaches and identify open challenges and research gaps related to evaluation metrics, real-world robustness, and deployment constraints. The goal is to provide researchers and practitioners with a comprehensive and practical reference for designing intelligent, reliable, and field-deployable fire detection systems. Index Terms—Fire Detection, IoT, Deep Learning, Edge AI, Sensor Fusion, Computer Vision, TinyML, Fire Localization, GIS

Citation

SAID Gadri , ,(2025-12-16), Fire Detection and Localization Using AI and IoT Trends and Future Directions (2021–2025),26th International Arab Conference on Information Technology (ACIT 2025),Alexandria- Egypt

RNA molecules are central to catalysis, cellular regulation, and novel treatment approaches, making their rational design a critical challenge in computational biology. Recent advances in deep learning have introduced generative models that can produce novel RNA molecules with unprecedented realism and functional potential. This survey provides a comprehensive overview of the latest developments in RNA design. After outlining the biological foundations of RNA and the principles of generative modeling, we classify existing approaches into four major categories: sequence-based models, structure-based models, joint sequence–structure models, and function-oriented models. For each category, representative studies are summarized and compared in terms of architectures, datasets used, evaluation metrics, and reported results. A comparative analysis highlights the unique contributions, strengths, and current limitations of these methods, including data scarcity, moderate structural validity, and limited functional optimization. Finally, we discuss emerging challenges and future research directions, such as scaling models to larger and more diverse datasets, integrating RNA-specific inductive biases, enabling multi-objective conditioning, and incorporating experimental feedback. Together, these advances position generative modeling as a transformative paradigm for accelerating RNA-based discovery in diagnostics, therapeutics, and synthetic biology.

Citation

SAID Gadri , ,(2025-12-16), A Survey on Generative Models for RNA Design,26th International Arab Conference on Information Technology (ACIT 2025),Alexandria- Egypt

A drowsiness detection system is an innovative solution for drivers especially those who drive their cars day and night. It detects the driver's drowsiness and gives feedback before it becomes dangerous for him. If it detects that a driver is getting drowsy, it warns him/her through a warning sound. In this paper, we proposed a smart innovative system based on the DL approach that helps to detect efficiently driver drowsiness. The main idea behind this system is to use eye movement’s analysis. In the first step, we propose a novel deep-learning approach based on Convolutional Neural Network (CNN) to detect drowsiness.

Citation

SAID Gadri , , (2025-12-15), Drowsiness Detection System: Developing an Innovative Model Based on Deep Learning Approaches., ELECTROTEHNICĂ, ELECTRONICĂ, AUTOMATICĂ (EEA), Vol:73, Issue:4, pages:121-128, ELECTROTEHNICĂ, ELECTRONICĂ, AUTOMATICĂ (EEA)

This study attempted the classification of facial emotions into seven categories with a deep learning approach using Convolutional Neural Networks: The classification task is performed on facial expressions with the Extended Cohn-Kanade (CK+) dataset. The Preprocessing of the images incorporated grayscale conversion, resizing, and image data augmentation. The proposed model has been attested to perform with significant accuracy both during training and testing. An interface featuring a simple application design was also created to allow testing both in real-time and on static images. Future work will focus on recognizing under hard circumstances, arising from multimodality.

Citation

SAID Gadri , ,(2025-11-25), Facial Emotion Recognition Using Deep Learning Approach,2nd International Workshop on Machine Learning and Deep Learning (WMLDL 2025),Mohamed Boudiaf University of M’sila, Algeria

AI is the new trend in technology AI is everywhere. AI is behind all the current technological advancements. Aspects (Innovation and Creativity, Technology, Economics)

Citation

SAIDGadri , ,(2025-10-27); AI Basic Concepts, Fields, and Applications,University Mohamed Boudiaf of M’sila,

In light of rapid technological developments, the university administrations are seeking to adopt new and sophisticated means to improve the student experience and facilitate administrative processes. One of these means is to use chatbots as an assistant to university students and employees. Chatbots allow immediate responses to student inquiries and provide technical and administrative support in full-time, which reduces costs and improves the student experience. Based on artificial intelligence technologies and natural language processing techniques, we have developed our own chatbot called UnivBot that permits to answer to a large range of students’ questions and reduces the large volume of work ensured by the dministrative staff so that they can devote themselves to other tasks. Among the characteristics of UnivBot that it is able to be improved constantly and quickly by updating the its knowledge base, and training language models and deep learning techniques to provide answers in real-time and with a high accuracy.

Citation

SAID Gadri , ,(2025-10-04), An Academic Chatbot Using NLP and Deep Learning UnivBot,Colloque international Education, Mutations mondiales et langues vivantes, Pratiques enseignantes, Politiques linguistiques et avancées numériques,Institut national des sciences appliquées et et de technologies INSAT & Université de Carthage, Tunis, Tunisie

Diabetes is a chronic disease that weakens the body’s ability to regulate blood sugar (glucose) levels. Severe complications may occur if diabetes re-mains untreated or undiagnosed. The traditional method to identify diabetes is to visit a diagnostic center or consult a doctor in the field. However, with the advancements in machine learning (ML) and deep learning (DL) approaches, this critical problem can be addressed more efficiently. In the pre-sent work, we have designed an intelligent predictive model that enables the detection of diabetes in patients with high accuracy. For this purpose, we have used several machine learning algorithms in the first stage, including LR, LDA, KNN, CART, NB, and SVM. In the second stage, we have developed a multi-layer ANN model to improve detection accuracy. Finally, we established a comparison between ML and DL algorithms in terms of detection accuracy.

Citation

SAID Gadri , , (2025-07-27), Advanced Diabetes Diagnosis Using Machine Learning and Deep Learning Approaches, International Journal of Hidden Data Mining and Scientific Knowledge Discovery (HDSKD),, Vol:9, Issue:2, pages:199-206, International Journal of Hidden Data Mining and Scientific Knowledge Discovery (HDSKD),

لم يكن أحد – حتى أشدّ الناس تفاؤلا – يتصور أنه يمكن للروبوتات والبرامج الذكية أن تقتحم عالم الإنسان وتنتهك خصوصيته، وتتمكن من محاكاته في كثير من سلوكاته ووظائفه، وحتى طريقة تفكيره وحله للمشكلات التي تَعْرِض له، بل وتتفوق عليه أحيانا، حتى ظهر مجال جديد في علم الحاسب الآلي يسمى التعلّم الآلي الذي يعطي الروبوتات والبرامج الذكية قدرات فائقة في محاكاة الإنسان والقيام بالكثير من الوظائف والمهام التي كانت إلى وقت قريب حكرا عليه لا ينازعه فيها أحد

Citation

SAID Gadri , , (2025-07-10), الذكاء الاصطناعي أو السباق المحموم نحو المجهول (2): التعلم الآلي: الروبوتات والبرامج المدربة تقتحم عالم الإنسان, Bachaer EL-Ouloum Magazine, Vol:15, Issue:1, pages:1-12, ENS Kouba, Algiers

Background: Cutaneous leishmaniasis (CL) is a parasitic disease caused by protozoan parasites of the genus Leishmania, leading to significant morbidity in endemic regions. While effective, traditional diagnostic methods often suffer from limitations such as the requirement for specialized expertise and prolonged processing times. Artificial intelligence (AI) methodologies have recently emerged to enhance CL’s diagnostic accuracy and efficiency. Objective: This project aims to develop and make available to biologists a new, rapid, more efficient, and more precise cutaneous leishmaniasis diagnosis method and tool based on the latest techniques of artificial intelligence AI and computer vision (CV). Methods: We used a deep learning model (YOLO 8) to detect Leishmania parasite bodies in microscopic images; we trained the model on microscopic images collected at the Algerian Pasteur Institute, Annex of M’sila. We implemented the proposed model on a mobile application to validate its performance. Results: YOLO v8’s application to the detection of Leishmania parasite bodies in microscopic images gives a high accuracy of 97 % over the entire test dataset. Conclusion: This research demonstrated the significant potential of AI-based object detection models, particularly YOLOv8, for accurately detecting Leishmania parasites in microscopic images. The obtained results pave the way for promising clinical applications and further research in this field.

Citation

SAID Gadri , , (2025-06-05), A new diagnostic method and tool for cutaneous leishmaniasis based on artificial intelligence techniques, Computers in Biology and Medicine, Vol:192, Issue:3, pages:110313, Elsevier ScienceDirect

What does mean the term Artificial Intelligence? Make the machine acts, thinks like a human. Having more or less intelligent autonomous machines and programs AI is the new trend in technology AI is behind all the current technological advancements. Application of AI in such domain requires: More and more data Applying a machine learning algorithm on data Building a model that helps to classify, predict, and make decision

Citation

SAIDGadri , ,(2025-05-26); Artificial Intelligence in Environment,Mohamed University of M’sila,

Today the world is experiencing a massive digital and Technological revolution. Artificial intelligence is contributing greatly to this revolution.

Citation

SAIDGadri , ,(2024-04-23); AI and its Applications in Teaching and Learning,University Mohamed Boudiaf of M’sila,

يعتبر العقل من أفضل النّعم التي حبا الله بها الإنسان في هذه الحياة وميّزه بموجبها على كثير مما خلق، قال تعالى: (ولقد كرمنا بني آدم وحملناهم في البر والبحر وفضّلناهم على كثير ممن خلقنا تفضيلا) الإسراء قال المفسّرون محلّ التكريم هنا هو العقل. ومن لوازم العقل الذكاء الذي يتمتّع به الإنسان. والذكاء غير العقل كما يذهب إليه علماء النفس والتربية والفلاسفة. فالعقل من عَقَل الناقة أي لَجَمها، والعاقل من لَجَم نفسه وجوارحه ووجّهها لما فيه مصلحته وخيره، فهو عاقل أو مُتعقّل. أمّا الذكاء فهو القدرات التي يمتلكها الإنسان في الفهم والتحليل والتعلّم وحلّ المشكلات التي تواجهه بشكل أمثل وعقلاني وفي آماد قصيرة. كما يطلق الذكاء على القدرة على فهم الحياة، والاستفادة من تجاربها، وتوجيه أحداثها بما يحقّق مصلحته الآنية والبعيدة. وبعضهم تحدّث عن أنواع عدّة من الذكاء منها: الرياضي واللغوي والاجتماعي والاقتصادي وغيرها. ومن هنا أمكن القول أنّ كل عاقل ذكي وليس كل ذكي عاقل، فلربما وجدنا عالما متمكّنا في مجال تخصّصه العلمي، مُلّما بمفاهيمه، محيطا بأصوله وفروعه، لكنّه خفيف العقل، سفيه الرأي، متهوّر، مُتبّع لغرائزه ونزواته وانفعالاته، عاجز على أن يعقلها ويلجمها ويوجهها لما يخدم مصالحه. وحينها ربما كان في علمه هلكته وهلكة البشرية بأسرها.

Citation

SAID Gadri , , (2024-04-12), الذكاء الاصطناعي أو السباق المحموم نحو المجهول (1), Bachaer EL-Ouloum Magazine, Vol:10, Issue:1, pages:1-14, ENS Kouba, Algiers

Un support de cours pour: Licence, Master, Ingénieurs

Citation

SAIDGadri , ,(2024-01-20); Les fondements de la théorie des graphes : Cours, Exercices corrigés, Examens corrigés,,Pages Blues

Relationship beteween Mathematics and AI

Citation

SAID Gadri , ,(2023-10-23), keynote talk entitled “Artificial Intelligence and Mathematics”,Artificial Intelligence and Mathematics MMS'23,ENS, Bou Saada, Algeria

How to prepare an article? How to publish in a Q1 journals (Nature&Science)?

Citation

SAID Gadri , ,(2023-09-20), Invited Guest,Seminar on Submission of a Scientific Article to Nature or Science Journals,Cerist, Algiers, Algeria

Basics and Fundamental Concepts, Subfields, Advances

Citation

SAID Gadri , ,(2023-03-16), Artificial Intelligence : Concepts, Subfields, Applications, Advances,Artificial Intelligence Week 2023,Mohamed Boudiaf University of M’sila

Cette rencontre est une coopération entre l'université de Oued Souf et un Laboratoire de recherche de l'université Paris XII

Citation

SAID Gadri , ,(2023), Invited Participant,Smart Agri-Tech’23,University of El-Oued, Algeria

A drowsiness detection system is an innovative solution for drivers especially those who drive their cars day and night. It detects the driver's drows-iness and gives feedback before it becomes dangerous for him. If it detects that a driver is getting drowsy, it warns him/her through a warning sound. In this paper, we proposed a smart innovative system based on the DL approach that helps to detect efficiently driver drowsiness. The main idea behind this system is to use eye movements analysis. In the first step, we propose a novel deep-learning approach based on Convolutional Neural Network (CNN) to detect drowsiness.

Citation

SAID Gadri , ,(2023), Drowsiness Detection System: Developing an Innovative Model Based on Deep Learning Approach,The First International Workshop on Machine Learning and Deep Learning WMLDL 2023,Mohamed Boudiaf University of M'sila, Algeria

AI is everywhere. We are heading towards fully intelligent societies. In a few years, our whole life will be artificial. We must join this evolution and this technological revolution as quickly as possible Schedule AI as a fundamental subject in all specialties.

Citation

SAIDGadri , ,(2023); Artificial Intelligence and its Applications in the Field of Humanities and Social Sciences ChatGPT as Model,Faculty of Humanities and Sociology,

Information retrieval IR is the process of finding information (generally documents) that matches the needs of the user. One way to improve the search effectiveness, as well as the quality of text categorization is to build an effective stemmer that helps to match users’ queries with relevant documents in IR and reduce the space of textual representation in TC. This has been always an interesting research topic in IR and TC. We can define stemming as the process of reducing inflected and derived words to their reduced forms (stems or roots). Many stemmers have been developed for different languages, but there is always many weaknesses and problems. In the present work, we have developed a multilingual stemming approach, based on the extraction of the word root and that exploits the technique of n-grams of characters. Our experiments have been done on three languages which are: Arabic, English, and French.

Citation

SAID Gadri , , (2022-06-20), Developing a Multilingual Stemmer for the Requirement of Text Categorization and Information Retrieval, International Journal on Electrical Engineering and Informatics, Vol:14, Issue:2, pages:165 - 170, International Journal on Electrical Engineering and Informatics

Deep learning DL is a new subfield of machine learning ML area which is used during the last decades to develop more sophisticated algorithms allowing high performance in some popular recognition fields, such as: pattern recognition, computer vision and image classification. Among the most used methods in DL, we find CNNs (Convolutional Neural Networks) which can be considered as the best used technique. In the present work, we have developed an automatic classifier that permits to classify some given grayscale images representing handwritten digits into one of 10 classes (digits from 0 to 9), inclusively. For this purpose, we have used ML and DL approaches. First, we proceeded to the classification task using many ML algorithms including: LR, LDA, KNN, CART, NB, and SVM. Second, we proposed a new CNN model composed of many convolutional layers. Finally, we established a comparison between different algorithms.

Citation

SAID Gadri , , (2022-01-05), Handwritten Digit Recognition: Developing an Efficient ML and DL Model to Recognize Handwritten Digits, Revue Algérienne des Sciences Section A, Vol:7, Issue:1, pages:165 - 170, Revue Algérienne des Sciences Section A

Conférence des chercheurs algériens à l'étranger

Citation

SAID Gadri , ,(2022), Invited participant,TC’22,Moufdi Zakaria Palace, Algiers, Algeria

Deep learning DL is a subfield of machine learning ML area which is used to perform much more sophisticated algorithms allowing high performance pattern recognition and image classification than classic machine learning approach. Among the most used methods, CNNs are for a special interest. In this work, we have developed an automatic classifier that permits to classify some given grayscale images representing handwritten digits into one of 10 classes representing integer values from 0 to 9, inclusively. For this purpose, we have used ML approach and DL approach. Initially, we proceeded to the classification task using many ML algorithms including: LR, LDA, KNN, CART, NB, and SVM. Then we proposed a CNN model composed of: many convolutional layers, one maxpooling layer and one full connected layer. Finally, we established a comparison between different algorithms. As programming tools, we have used Python, Tensoflow, and Keras which are the most used in the field. Keywords: machine learning, deep learning, Arabic character recognition, convolutional neural networks Machine Learning, Deep Learning, Pattern Recognition, Neural Networks, Convolutional Neural Networks

Citation

SAID Gadri , , (2022), Handwritten Digit Recognition: Developing an Efficient ML and DL Model to Recognize Handwritten Digits, Revue Algérienne des Sciences Section A, Vol:7, Issue:7, pages:pp.165 - 170, University Chadli Ben Djedid, Al-Taref

: Information retrieval IR is the process of finding information (generally documents) that matches the needs of the user. One way to improve the search effectiveness, as well as the quality of text categorization is to build an effective stemmer that helps to match users’ queries with relevant documents in IR and reduce the space of textual representation in TC. This has been always an interesting research topic in IR and TC. We can define stemming as the process of reducing inflected and derived words to their reduced forms (stems or roots). Many stemmers have been developed for different languages, but there is always many weaknesses and problems. In the present work, we have developed a multilingual stemming approach, based on the extraction of the word root and that exploits the technique of n-grams of characters. Our experiments have been done on three languages which are: Arabic, English, and French. Keywords: Information retrieval, Machine learning, Natural language processing, Root extraction, Stemming

Citation

SAID Gadri , , (2022), Developing a Multilingual Stemmer for the Requirement of Text Categorization and Information Retrieval, International Journal on Electrical Engineering and Informatics, Vol:14, Issue:2, pages:pp.165, School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Indonesia

Self-Driving Cars or Autonomous Cars provide many benefits for humanity, such as reduction of deaths and injuries in road accidents, reduction of air pol-lution, increasing the quality of car control. For this purpose, some cameras or sensors are placed on the car, and an efficient control system must be set up, this system allows to receive images from different cameras and/or sensors in real-time especially those representing traffic signs, and process them to allows high autonomous control and driving of the car. Among the most promising al-gorithms used in this field, we find convolutional neural networks CNN. In the present work, we have proposed a CNN model composed of many convolu-tional layers, max-pooling layers, and fully connected layers. As programming tools, we have used python, Tensorflow, and Keras which are currently the most used in the field.

Citation

SAID Gadri , ,(2021), Efficient Traffic Signs Recognition Based on CNN Model for Self-Driving Cars,Intelligent Computing & Optimization. ICO 2021. 30-31 Dec, 2021,Thailande

Sentiment analysis is a subfield of text mining. It is the process of categorizing opinions expressed in a piece of text. a simple form of such analysis would be to predict whether the opinion about something is positive or negative (polari-ty). The present paper proposes an efficient sentiment analysis model based on machine learning ML and deep learning DL approaches. A DNN (Deep Neural Network) model is used to extract the relevant features from customer reviews, perform a training task on almost of samples of the dataset, validate the model on a small subset called the test set and consequently compute the accuracy of sentiment classification. For the programming stage, we benefited from the large opportunities offered by Python language, as well as Tensorflow and Keras libraries

Citation

SAID Gadri , ,(2021), Sentiment Analysis: Developing an Efficient Model Based on Machine Learning and Deep Learning Approaches,Intelligent Computing & Optimization. ICO 2021. 30-31 Dec, 2021,Thailande

During the last decade, some important progress in machine learning ML area has been made, especially with the apparition of a new subfield called deep learning DL and CNN networks (Convolutional Neural Networks). This new tendency is used to perform much more sophisticated algorithms allowing high performance in many disciplines such as; pattern recognition, image classification, computer vision, as well as other supervised and unsupervised classification tasks. In this work, we have developed an automatic classifier that permits the classification of a large number of diabetic patients based on some blood characteristics by using ML and DL approaches. Initially, we have proceeded to the classification task using many ML algorithms. Then we proposed a simple DNN model composed of many layers. Finally, we established a comparison between ML and DL algorithms, as well as our model with other existing models. For the programming task, we have used Python, Tensorflow, and Keras which are the most used in the field.

Citation

SAID Gadri , , (2021), Developing an efficient Predictive model based on ML and DL approaches to detect diabetes, The International Journal of Computing and Informatics Informatica, Vol:45, Issue:3, pages:433–440, Slovensko društvo INFORMATIKA

Deep learning DL is a new subfield of machine learning ML area which is used during the last decades to develop more sophisticated algorithms allowing high performance in some popular recognition fields, such as: pattern recognition, computer vision and image classification. Among the most used methods in DL, we find CNNs (Convolutional Neural Networks) which can be considered as the best used technique. In the present work, we have developed an automatic classifier that permits to classify some given grayscale images representing handwritten digits into one of 10 classes (digits from 0 to 9), inclusively. For this purpose, we have used ML and DL approaches. First, we proceeded to the classification task using many ML algorithms including: LR, LDA, KNN, CART, NB, and SVM. Second, we proposed a new CNN model composed of many convolutional layers. Finally, we established a comparison between different algorithms.

Citation

SAID Gadri , ,(2021), Handwritten Digit Recognition: Developing an Efficient ML and DL Model to Recognize Handwritten Digits,CNIATI'21 Conférence Nationale sur l ’Intelligence artificielle et les technologies de l'information, 24 Mai 2021, University Chadli Ben Djedid, Al-Taref,University Chadli Ben Djedid, Al-Taref.

In the last decade, neural networks NNs become a favorable solution for many applications in artificial intelligence AI. For instance, the majority of tourism companies have professional websites where customers can book: flights, bus and taxi trips, hotels, restaurants, etc. they can also compare services in terms of prices, locations, services quality, and other interesting criterion. For this purpose, the used dataset consists of a sample of hotel reviews provided by customers who have reserved recently. Analyzing these reviews will help companies to know if their services are suitable for customers, satisfy their needs and what is the degree of this satisfaction. i.e., customers are happy or not? Satisfied or not? Our main objective in this work is to develop an efficient and intelligent system based on NNs which allows us to predict how customers feel about the provided services. To accomplish this work, we have proceeded to the classification task using many machine learning algorithms, including LDA, KNN, CART, NB, and SVM. Then, we proposed in the second stage a deep neural network DNN model to perform the same task. Finally, we established a short comparison between the different algorithms. In the programming stage, we benefited from the large opportunities offered by Python language, as well as Tensorflow and Keras libraries. Keywords: machine learning, deep learning, Artificial Neural Networks, Natural Language Processing, Social media;

Citation

SAID Gadri , ,(2021), An Efficient System to Predict Customers’ Satisfaction on Touristic Services Using ML and DL Approaches,22rd Arabic International Conference on Information Technology (ACIT 2021), 21-23 Dec, IEEE Conference, Quabos University, Sultanate Oman,Quabos University, Sultanate Oman

Habilitation thesis

Citation

SAIDGadri , ,(2021); Habilitation Thesis,University Mohamed Boudiaf of M'sila,

Arabic Handwritten character recognition is one of the most studied topics since many decades, there exists many difficulties which prevent to have significant advances in this important field such as: the variability of handwriting from a person to another, the large availability of databases, the complicated morphology of Arabic as a very rich Semitic language. In this paper, we proposed a deep learning model based on convolutional neural networks CNN which permits to achieve a high performance in Arabic handwritten characters recognition.

Citation

SAID Gadri , ,(2020), Efficient Arabic handwritten character recognition based on machine learning and deep learning approaches,The 2nd International Conference on Advances in Intelligent Systems, Soft Computing and Optimization Techniques 2020 (ICAISCO 2020) held in Penang, Malaysia, 01 - 02, April 2020 (Scopus Indexed Conference).,Penang, Malaysia

Today Deep learning approach DL becomes the new tendency of ma-chine learning approach ML which is used since it gives much more sophisticated pattern recognition and image classification than classic machine learning ap-proach. Among the most used methods in DL, CNNs are for a special interest. In this work, we have developed an automatic classifier that permits to classify a large number of fashion clothing articles based on ML and DL approaches. Ini-tially, we proceeded to the classification task using many ML algorithms, then we proposed a new CNN model composed of many convolutional layers, one maxpooling layer, and one full connected layer. Finally, we established a com-parison between different algorithms. As programming tools, we have used Py-thon, Tensoflow, and Keras which are the most used in the field.

Citation

SAID Gadri , ,(2020), Building Best Predictive Models Using ML and DL Approaches to Categorize Fashion Clothes,The 19th International Conference on Artificial Intelligence and Soft Computing ICAISC 2020 (H5-index = 20) (Springer Conference). held in Zakopane, Poland, 12 - 14, October 2020,Zakopane, Poland

Arabic Handwritten character recognition is one of the most studied topics since many decades, there exists many difficulties which prevent to have significant advances in this important field such as: the variability of handwriting from a person to another, the large availability of databases, the complicated morphology of Arabic as a very rich Semitic language. In this paper, we proposed a deep learning model based on convolutional neural networks CNN which permits to achieve a high performance in Arabic handwritten characters recognition.

Citation

SAID Gadri , , (2020), Efficient Arabic handwritten character recognition based on machine learning and deep learning approaches, Journal of Advanced Research in Dynamical & Control Systems, Vol:12, Issue:7, pages:9-17, Journal of Advanced Research in Dynamical & Control Systems

During the last decade, some important progress on machine learning ML area have been made, especially with the apparition of a new subfield called deep learning DL and CNN networks (Convolutional Neural Networks). This new tendency is used to perform much more sophisticated algorithms allowing high performance in many disciplines such as: pattern recognition, image classification, computer vision, as well as other supervised and unsupervised classification tasks. In this work, we have developed an automatic classifier that permits to classify a number of diabetic patients based on some blood characteristics by using ML approach and DL approach. Initially, we have proceeded to the classification task using many ML algorithms. Then we proposed a simple CNN model composed of many layers. Finally, we established a comparison between ML and DL algorithms. For programming, we have used Python, Tensorflow and Keras which are the most used in the field.

Citation

SAID Gadri , , (2020), Diabetic patient classification: an efficient algorithm based on deep learning approach, International Journal of Advances in Electronics and Computer Science IJAECS, Vol:7, Issue:3, pages:2394-2835, International Journal of Advances in Electronics and Computer Science IJAECS

During the last decade, some important progress on machine learning ML area have been made, especially with the apparition of a new subfield called deep learning DL and CNN networks (Convolutional Neural Networks). This new tendency is used to perform much more sophisticated algorithms allowing high performance in many disciplines such as: pattern recognition, image classification, computer vision, as well as other supervised and unsupervised classification tasks. In this work, we have developed an automatic classifier that permits to classify a number of diabetic patients based on some blood characteristics by using ML approach and DL approach. Initially, we have proceeded to the classification task using many ML algorithms. Then we proposed a simple CNN model composed of many layers. Finally, we established a comparison between ML and DL algorithms. For programming, we have used Python, Tensorflow and Keras which are the most used in the field.

Citation

SAID Gadri , ,(2019), Diabetic Patient Classification: An Efficient Algorithm Based on Deep Learning Approach,International Conference on Science, Engineering&Technology (ICSET),Istanbul, Turkey

Stemming is a technique which permits to improve the quality of categorization in TC and the effectiveness of search in information retrieval systems IRS. In Arabic, two families of methods are used to find the stem of a word; morphological methods which are difficult to implement and require a deep linguistic knowledge in Arabic such as: morphological rules, and statistical methods which are easy to implement, more practical, and do not require prior linguistic knowledge, but only some calculations of probabilities. In this paper we propose a new Arabic stemmer based on the extraction of the root, and completely statistical. So, it does not require any morphological rule or grammatical patterns.

Citation

SAID Gadri , ,(2018), Arabic Information Retrieval: Influence of Stemming on the Effectiveness of Search in IRS,,7th International Conference on advanced Technology ICAT'18,,Antalya, Turkey

Information retrieval IR is the process of finding information (generally documents) that matches the needs of the user. One way to improve the search effectiveness as well as the quality of text categorization is to build an effective stemmer that helps to match user’s queries with relevant documents in IR and reduce the space of textual representation in TC. This has been always an interesting research topic in IR and TC. We can define stemming as the process of reducing inflected and derived words to their reduced forms (stems or roots). Many stemmers have been developed for different languages, but still there arethere is always many weakness and problems. In the present work, we have developed a new multilingual stemming approach, based on the extraction of the word root and that exploits the technique of n-grams of characters. Our experiments have been done on three languages which are: Arabic, English and French

Citation

SAID Gadri , ,(2018), A New Multilingual Stemmer to Improve the Effectiveness of Text Categorization and Information Retrieval,Doctoral seminar of Vienna University,University of Vienna, Austria

One of the methods used to reduce the size of terms vocabulary in Arabic text categorization is to replace the different variants (forms) of words by their common root. This process is called stemming based on the extraction of the root. Therefore, the search of the root in Arabic or Arabic word root extraction is more difficult than in other languages since the Arabic language has a very different and difficult structure, that is because it is a very rich language with complex morphology. Many algorithms are proposed in this field. Some of them are based on morphological rules and grammatical patterns, thus they are quite difficult and require deep linguistic knowledge. Others are statistical, so they are less difficult and based only on some calculations. In this paper we propose an improved stemming algorithm based on the extraction of the root and the technique of n-grams which permit to return Arabic words’ stems without using any morphological rules or grammatical patterns.

Citation

SAID Gadri , Abdelouhab Moussaoui, , (2017), Arabic Text Categorization: An Improved Algorithm Based on Ngrams technique to Extract Arabic Words Roots,, International Arab Journal of Information Technology IAJIT, Vol:14, Issue:6, pages:7, Zarqa University, Jordan

Automatic text classication is a very important task that consists in assigning labels (categories, groups, classes) to a given text based on a set of previ- ously labeled texts called training set. The work presented in this paper treats the problem of automatic topical text categorization. It is a supervised classication because it works on a predened set of classes and topical because it uses topics or subjects of texts as classes. In this context, we used a new approach based on k-NN algorithm, as well as a new set of pseudo-distances (distance metrics) known in the eld of language identication. We also proposed a simple and eective method to improve the quality of performed categorization.

Citation

SAID Gadri , Abdelouahab Moussaoui, , (2017), Application of a New Set of Pseudo-Distances in Documents Categorization,, Neural Network World NNW, Vol:1, Issue:2, pages:231-245, Czech Technical University in Prague Faculty of Transportation Sciences

Text categorization is an important task in text mining process that consists in assigning a set of texts to a set of predefined categories based on learning algorithms. There exist two kinds of text categorization: monolingual and multilingual text categorization. The main problematic of this manuscript is how to exploit concepts and algorithms of machine learning in contextual categorization of multilingual texts. Our study on this subject allowed us to propose many solutions and provide many contributions, notably: (1) a simple, fast and effective algorithm to identify the language of a text in multilingual corpus. (2) An improved algorithm for Arabic stemming based on a statistical approach. Its main objective is to reduce the size of term vocabulary and thus increase the quality of the obtained categorization in TC and the effectiveness of search in IR. (3) A new multilingual stemmer which is general and completely independent of any language. (4) Application of new panoply of pseudo-distances to categorize texts of a big corpus such as Reuters21578 collection. All these solutions were the subject of many academic papers published in international conferences and journals

Citation

SAIDGadri , ,(2017); Multilingual Text Categorization: (Based on Machine Learning Algorithms and Ontologies),,Noor Publishing

Text categorization is an important task in text mining process that consists in assigning a set of texts to a set of predefined categories based on learning algorithms. There exist two kinds of text categorization: monolingual and multilingual text categorization. The main problematic of this thesis is how to exploit concepts and algorithms of machine learning in contextual categorization of multilingual texts. Our study on this subject allowed us to propose many solutions and provide many contributions, notably: a simple, fast and effective algorithm to identify the language of a text in multilingual corpus. An improved algorithm for Arabic stemming based on a statistical approach, its main objective is to reduce the size of term vocabulary and thus increase the quality of the obtained categorization in TC and the effectiveness of search in IR. A new multilingual stemmer which is general and completely independent of any language. Application of new panoply of pseudo-distances to categorize texts of a big corpus such as Reuters21578 collection. All these solutions were the subject of many academic papers published in international conferences and journals.

Citation

SAIDGadri , ,(2016); • Automatic Contextual Categorization of Multilingual Semi-Structured Documents,University Farhat Abbes of Setif,

One of methods used to reduce the size of terms vocabulary in Arabic text categorization is to replace the different variants (forms) of words by their common root. The search of root in Arabic or Arabic word root extraction is more difficult than other languages since Arabic language has a very different and difficult structure, that is because it is a very rich language with complex morphology. Many algorithms are proposed in this field. Some of them are based on morphological rules and grammatical patterns, thus they are quite difficult and require deep linguistic knowledge. Others are statistical, so they are less difficult and based only on some calculations. In this paper we propose a new statistical algorithm which permits to extract roots of Arabic words using the technique of n-grams of characters without using any morphological rule or grammatical patterns.

Citation

SAID Gadri , Abdelouahab Moussaoui, ,(2015), Arabic Texts Categorization: Features Selection Based on the Extraction of Words’ Roots,5th IFIP International Conference on Computer Science and its Applications (CIIA’2015),TaharMoulay University, Saida - Algeria

Stemming is a technique used to reduce inflected and derived words to their basic forms (stem or root). It is a very important step of pre-processing in text mining, and generally used in many areas of research such as: Natural language Processing NLP, Text Categorization TC, Text Summarizing TS, Information Retrieval IR, and other tasks in text mining. Stemming is frequently useful in text categorization to reduce the size of terms vocabulary, and in information retrieval to improve the search effectiveness and then gives us relevant results. In this paper, we propose a new multilingual stemmer based on the extraction of word root and in which we use the technique of n-grams. We validated our stemmer on three languages which are: Arabic, French and English.

Citation

SAID Gadri , Abdelouahab Moussaoui, ,(2015), Information Retrieval: A New Multilingual Stemmer Based on a Statistical Approach,3rd International Conference on control, engineering & information Technology (CEIT2015), IEEE Conference,Tlemcen, Algeria

Stemming is a technique used to reduce inflected and derived words to their basic forms (stem or root). It is a very important step of pre-processing in text mining, and generally used in many areas of research such as: Natural language Processing NLP, Text Categorization TC, Text Summarizing TS, Information Retrieval IR, and other tasks in text mining. Stemming is frequently useful in text categorization to reduce the size of terms vocabulary, and in information retrieval to improve the search effectiveness and then gives us relevant results. In this paper, we propose a new multilingual stemmer based on the extraction of word root and in which we use the technique of n-grams. We validated our stemmer on three languages which are: Arabic, French and English.

Citation

SAID Gadri , Abdelouahab Moussaoui, ,(2015), A new Multilingual Stemmer Based on the Extraction of the Root and the N-grams Technique,ICIPCE’2015 International Conference on Information Processing and Control Engineering,Moscow, Russia

Stemming is a technique used to reduce inflected and derived words to their basic forms (stem or root). It is a very important step of pre-processing in text mining, and generally used in many areas of research such as: Natural language Processing NLP, Text Categorization TC, Text Summarizing TS, Information Retrieval IR, and other tasks in text mining. Stemming is useful in text categorization to reduce the size of terms vocabulary, and in information retrieval to improve the search effectiveness and then gives us relevant results.

Citation

SAID Gadri , Abdelouahab Moussaoui, ,(2015), Multilingual information retrieval: increasing the effectiveness of search by stemming,19th International Conference onCircuits, Systems, Communications and Computers (CSCC 2015),Zakynthos Island, Greece

Stemming is a technique used to reduce inflected and derived words to their basic forms (stem or root). It is a very important step of pre-processing in text mining, and generally used in many areas of research such as: Natural language Processing NLP, Text Categorization TC, Text Summarizing TS, Information Retrieval IR, and other tasks in text mining. Stemming is useful in text categorization to reduce the size of terms vocabulary, and in information retrieval to improve the search effectiveness and then gives us relevant results. In this paper, we propose a new multilingual stemmer based on the extraction of word root and in which we use the technique of n-grams. We validated our stemmer on three languages which are: Arabic, French and English.

Citation

SAID Gadri , Abdelouahab Moussaoui, ,(2015), Multilingual Text Categorization: Increasing the Quality of Categorization by a Statistical Stemming Approach,International Conference on intelligent Information Processing Security and Advanced Communication (IPAC 2015), ACM Conference,Batna, Algeria

Stemming is a technique used to reduce inflected and derived words to their basic forms (stem or root). It is a very important step of pre-processing in text mining, and generally used in many areas of research such as: Natural language Processing NLP, Text Categorization TC, Text Summarizing TS, Information Retrieval IR, and other tasks in text mining. Stemming is useful in text categorization to reduce the size of terms vocabulary, and in information retrieval to improve the search effectiveness and then gives us relevant results. In this paper, we propose a new multilingual stemmer based on the extraction of word root and in which we use the technique of n-grams. We

Citation

SAID Gadri , Abdelouahab Moussaoui, ,(2015), An Effective Multilingual Stemmer Based on the Extraction of the Root and the N-grams Technique,AIST’2015 international scientific conference Analysis of Images, Social networks, and Texts,Yekaterinburg, Russia.

Le travail présenté dans ce papier traite le problème de la classification automatique de documents, il s’agit ici d’une classification supervisée (catégorisation) puisqu’elle opère sur un ensemble prédéfini de classes. Nous avons utilisé une nouvelle approche basée sur les métriques de distance connues dans le domaine de l’identification de la langue. Nous avons proposé également une méthode simple et efficace pour améliorer la qualité de la catégorisation effectuée.

Citation

SAID Gadri , Abdelouahab Moussaoui, ,(2014), Utilisation des Métriques de l’Identification de la Langue dans la Catégorisation Contextuelle de Documents,1st International Symposium on Informatics and its Applications, ISIA 2014,University of M’sila, M’sila

Identifying the language of a text is a very important preliminary phase in the categorization of multilingual documents or even in information retrieval. This phase becomes difficult if we just consider the word as a basic unit of information in texts. Because It could be possible for some languages as French or English but very difficult for some other languages as German, Chinese and Arabic. In this paper, we present the most known identification methods, and we propose a new optimized and effective variant of the method of Cavenar and Trenkle based on n-grams of characters. We also evaluate the obtained results with other methods by adopting the two approaches of texts segmentation: words approach, n-grams approach.

Citation

SAID Gadri , Abdelouahab Moussaoui, ,(2014), Language Identification: Proposition of a New Optimized Variant for the Method of Cavenar and Trenkle,International Conference on Artificial Intelligence and Information Technology ICAIIT’14,University Kasdi Merbah, Ouargla, Algeria

Identifying the language of a text is a very important preliminary phase in the categorization of multilingual documents or even in information retrieval. This phase becomes difficult if we just consider the word as a basic unit of information in texts. Because It could be possible for some languages as French or English but very difficult for some other languages as German, Chinese and Arabic. In this paper, we present the most known identification methods, and we propose a new fast and effective method based on n-grams of characters. We also evaluate the obtained results with other methods by adopting the two approaches of texts segmentation: words approach, n-grams approach.

Citation

SAID Gadri , Abdelouahab Moussaoui, ,(2014), Language Identification: A New Fast Algorithm to Identify the Language of a Text in a Multilingual Corpus,The 4thInternational Conference on Multimedia Computing and Systems ICMCS’14, IEEE Conference,University of Marrakesh, Marrakesh, Morocco

In this paper, we study the problem of automatic supervised classification of documents (Documents’ categorization). We propose a new panoply of similarity metrics which are inspired from the domain of language identification. We also propose a simple, optimal and effective method to improve the quality of categorization.

Citation

SAID Gadri , Abdelouhab Moussaoui, ,(2014), Contextual Categorization of Documents Using a New Panoply of Similarity Metrics,International Conference on Advanced Technology & Sciences (ICAT’14),Antalya, Turkey.

Identifying the text language means that we assign this text to a language in which it is written. This identification became important because of the increased diversity of textual data in different languages on the web. In addition, a real recognition of the text language is not possible if we only consider the word as a basic unit of information. It could be possible for some languages as French or English but very difficult for some other languages as German or Arabic. The approach of text segmentation into characteristic n-grams represents a very efficient alternative solution in this field. It also becomes a favorite tool to extract knowledge from texts. In this paper, we present the most known identification methods and we propose a new method based on a new metric of similarity. We also evaluate the obtained results with other methods while adopting the two approaches respectively : the segmentation of texts into words and their segmentation into n-grams.

Citation

SAID Gadri , Abdelouahab Moussaoui, ,(2013), Une méthode flexible pour l’identification de la langue d’un texte dans un corpus hétérogène multilingue,2ème Conférence nationale des études doctorales en Informatique CNEDI2013,,Université de Sekikda

Identifying the language of a text means that we assign this text to a language in which it is written. This identification becomes important because of the increased diversity of textual data in different languages on the web. A real recognition of the text language is not possible if we just consider the word as a basic unit of information. It could be possible in some languages but very difficult for some other languages. The approach of the segmentation of the text into characteristic n-grams represents a very efficient alternative solution in this field. It also becomes a preferred tool in language acquisition and the extraction of knowledge from texts. In this paper, we present the most known identification methods and we propose a new method based on n-grams of characters. We also evaluate the obtained results with other methods by adopting the two approaches respectively: the segmentation into words and the segmentation into n-grams.

Citation

SAID Gadri , Abdelouahab Moussaoui, ,(2013), An Effective Method to Recognize the Language of a Text in a collection of Multilingual Documents,,10th International Conférence on Electronics, Computer and Computation ICECCO 2013, IEEE conference,,TurgutOzal University, Ankara, Turkey,

L'interopérabilité des bases de données et des SGBD, ou d'une manière générale entre systèmes d'informations hétérogènes et répartis, est devenue une nécessité pour répondre aux besoins d'échange et de communication. elle prend aujourd'hui une large place surtout avec l'interconnexion massive des systèmes d'informations via Internet et intranet ou extranet . l'interopérabilité peut être définie par la capacité des systèmes d'informations à se collaborer, même s'ils ont des natures très différentes, afin de réaliser des fonctionnalités communes . Notre étude est concentrée sur l'interopérabilité des bases de données hétérogènes et réparties. On est arrivé à présenter un état de l'art du domaine, à exposer les différentes approches conçues pour réaliser cette interopérabilité, dont les plus connues sont : * l'approche de médiation de schémas qui met l'accent sur deux composants fondamentaux : le médiateur et l'adaptateur . * L'approche de médiation de contexte orientée sémantique, qui exploite les capacités des ontologies, des contextes de coopération, et qui peut résoudre la plupart des conflits sémantiques . * L'approche de fédération qui base essentiellement sur la notion de l'intégration des données suivant un modèle commun appelé modèle pivot . * L'approche entrepôt de données orientée beaucoup plus aux besoins des systèmes décisionnels, surtout au niveau des entreprises qui reçoivent et traitent des flux très importants d'informations . L'étude comparative sur ces différentes approches a aboutit à un résultat très évident en faveur de l'approche XML, comme étant un standard très répandu d'échange et d'interopérabilité . L'étude est terminée par la proposition d'une nouvelle approche qui combine entre les trois approches, à savoir : l'approche de médiation de schémas, de médiation de contexte, et l'approche XML, et qui adopte une architecture multi-agents

Citation

SAIDGadri , ,(2006); INTEROPERABILITE DES BASES DE DONNEES HETEROGENES ET REPARTIES,University Mohamed Boudiaf of M'sila,