03.Forum of Artificial Intelligence and Its Applications
Permanent URI for this collectionhttps://dspace.univ-eloued.dz/handle/123456789/10731
Browse
Recent Submissions
Item Sentiment Analysis of Algerian Dialect Using a Deep Learning Approach(University of Eloued جامعة الوادي, 2022-01-24) Klouche, Badia; Benslimane, Sidi Mohamed; Mahammed, NadirNowadays the Internet has become an essential tool for exchanging information, both on a personal and professional level. Today, the analysis of sentiment offers us a great interest for research, marketing and industry. With millions of comments and tweeting published every day, the information available on the Internet and in social media has become a gold mine for companies developing in their production, management and distribution. In this article, we propose a novel approach to analyze the sentiments of the Algerian dialect for the benefit of the Algerian Telephone Operator Ooredoo. The proposed approach is based on a deep learning model, which provides state-of-the-art results on a dataset written in Algerian dialect. In this study, the Facebook comments shared in Modern Standard Arabic (MSA) and Algerian dialect of the customers of the Algerian telephone operator Ooredoo are analyzed in order to allow the operator to retain and satisfy its customers to the maximum. Experimental results show that deep learning approaches outperformed traditional methods of sentiment.Item Using a Direct Multiple Shooting Method to an Optimal control problem Direct Multiple Shooting Method(University of Eloued جامعة الوادي, 2022-01-24) Lounis, Abbes; Marthon, Philippe; Louadj, Kahina; Aidene, MohamedA multiple direct fire method is considered to solve optimal control problems. The multiple direct multiple shooting method is a numerical method for solving limit value problems. The method divides the interval over which a solution is sought into several smaller intervals, solves an initial value problem in each of the smaller intervals, and imposes additional matching conditions to form a solution over the entire interval. This method transforms an optimal control problem into a non-linear programming problem. To solve the latter problem, the zeros of the Lagrange Jacobian are computed using Newton’s method. Then, this method is illustrated by a numerical example and finally.Item Trajectory Tracking of a Reconfigurable Multirotor Using Optimal Robust Sliding Mode Controller(University of Eloued جامعة الوادي, 2022-01-24) Derrouaoui, Saddam Hocine; Bouzid, Yasser; Guiatni, Mohamed; Belmouhoub, AminaThis work aims to design a robust Sliding Mode Controller (SMC) in order to stabilize and follow the desired trajectory of a new reconfigurable multirotor. Due to changeable shape of the studied drone, the designed SMC in this work consists to ensure the robustness in the face of the parameters interaction, and various uncertainties of the system. In order to select the controller optimal parameters of each flight configuration, a Metaheuristic Algorithm based on Particle Swarm Optimization (PSO) is used. Nevertheless, the control architecture of this multirotor is different to the standard one, which makes it a very difficult task. To evaluate the effectiveness of the SMC, a simulation scenario is carried out, where the multirotor geometry is variable depending on the assigned tasks and environment.Item Theoretical Model of Traffic Signal Timing Optimisation Improved On ant colony Optimisation and Symbiotic Organism Search(University of Eloued جامعة الوادي, 2022-01-24) Kouidri, Chaimaa; Mahi, Faiza; Bouiadjra, Rochdi BachirDue to the increasing in the number of vehicules on a daily basis, road congestion is becoming a key challenge. Therefore, it becomes essential to develop a signal optimization method for multi-intersections. In this paper, the proposed model is capable of minimizing waiting time of vehicule.an hybrid meta-heuristic algorithm (Ant Colony, Symbiotic Organism Search) is employed to solve the model. We proposed a hybridization of two bio inspired methods, the first based on the use of ant colony to determine the critical path, the critical path is the input of the next step. The second step is based on the minimization of vehicles with the metaheuristic SOS. The main focus of this study is on improving the quality of solutions for the traffic light optimization problem to minimize the waiting time of all the vehicles within a certain time period.Item The Internet of Things Security Challenges: Survey(University of Eloued جامعة الوادي, 2022-01-24) Beggar, Inès; Riahla, Mohamed AmineThe Internet of Things (IoT) and its security issues are gaining interest in recent years. It is more than necessary to take charge of them as soon as possible and to find specific solutions to the IoT. These allow it to wait for its full maturity and to take advantage of the simplicities it brings to our daily life. But to do so, it is necessary to identify and the master ins and outs of the problem which is developed in the present work. However, this paper aims on the one hand to present the Internet of Things in point form, and on the other hand to address the security of the same points as the presentation of the IoT. Moreover, the properties of the IoT are discussed and compared to traditional networks, also the level of security required according to the area of application and security from a point of view; actors of the IoT ecosystem. Besides, the existing architectures are examined in order to allow future research to selfpositioning and better understand the security issue.Item Segmentation of the Breast Masses in Mammograms Using Active Contour for Medical Practice: AR based surgery(University of Eloued جامعة الوادي, 2022-01-24) Guerroudji, Mohamed Amine; Amara, Kahina; Aouam, Djamel; Zenati, Nadia; Djekoune, Oualid; Benbelkacem, SamirImages have been one of the most important ways humans have used to communicate and impart knowledge and information since the dawn of mankind, as an image can encompass a large amount of information concerning the quality of life linked to health and particularly in oncology precisely the breast cancer. New technologies such as Augmented Reality (AR) guidance allows a surgeon to see sub-surface structures, by overlaying pre-operative imaging data on a live laparoscopic video. The presence of masses in mammography is particularly interesting for the early detection of the breast cancer. In this article, we propose to use a mass detection system, based on two main axes: segmentation and pretreatment. The latter is based on the suppression of the noise by a Gaussian filter and mathematical morphology (white Top-Hat transform) in order to bring out all the spots (Clear Spots) possible to be pathologies. In the second axis, we are interested in the segmentation of pathologies in mammography images. This consists of segmenting the object of interest by active contour models (Chunming Li). Visually, the obtained results are very clear, and show the good performance of the new approach suggested in this work. This latter allows extracting successfully the masses starting from the mammography referents from the database Mini MIAS. The proposed breasts masses detection can, thus, provide an acceptable accuracy for an AR-based surgery or medicine courses with scene augmentation of videos, which provides a seamless use of augmented-reality for surgeons in visualizing cancer tumors.Item Security issues in self-organized ad-hoc networks (MANET, VANET, and FANET): A survey(University of Eloued جامعة الوادي, 2022-01-24) GOUMIRI, Sihem; RIAHLA, Mohamed amine; HAMADOUCHE, M’hamedSelf-organized AdHoc networks have become one of the most interested and studied domains, especially with the rapid development of communication technologies and electronic devices. These networks regroup wireless and self-configuring nodes that communicate independently without a fixed infrastructure. Many applications operate with the AdHoc network due to its rapid deployment and low costs. Security in AdHoc networks is a crucial aspect that protects the exchanges between users and improves network performances. In this paper, a presentation of three AdHoc networks: MANET (Mobile AdHoc Network), VANET (Vehicle AdHoc Network), and FANET (Flaying AdHoc Network) is performed with the focus on their security issues. The paper blends the security requirements and the different attacks faced to the three reviewed networks.Item RONI-based medical image watermarking using DWT and LSB amgorithm(University of Eloued جامعة الوادي, 2022-01-24) Benyoucef, Aicha; Hamadouche, M’HamedIn recent years, hiding information in medical images is the largest usage to secure this information or garnet the integrity of the owner. But this embedding can distort the medical image and change the necessary patient information. In this paper, we propose a robust method for medical image watermarking; first of all. The original image is filtered by a sharpening filter for enhanced contrast then separate their two regions using snake segmentation. The embedding mark (an electronic patient record) is added to the frequency domain after applying Discrete Wavelet Transform (DWT) on the region of non-interest (RONI) using the last signification bit (LSB). This region has a predominantly black background where a region of interest (ROI) has the necessary patient information. This method preserves a high-quality watermarked image, and it improves authentication. Our method is evaluated by Pick Signal to Noise Ratio (PSNR = 46.4039 for 512*512 bits image size) SNR, NC, and Histogram analysis.Item Road Segments Traffic Dependencies Study Using Cross-Correlation(University of Eloued جامعة الوادي, 2022-01-24) Benabdallah Benarmas, Redouane; Beghdad Bey, KaddaTraffic Prediction on a urban road network become more complex face to exponential growth in the volume of traffic, it is necessary to study the relationship between road segments before the prediction calculation. The spatial correlation theory has been well developed to interpret the dependency for understanding how time series are related in multivariate model. In large scale road network modeled by Multivariate Time Series, the Spatialtemporal dependencies detection can limit the use of only data collected from points related to a target point to be predicted. This paper present a Cross- Correlation as method to dependency analysis between traffic road segments, Scatterplot of Cross-Correlation is proposed to reveal the dependency, we provide a comparative analysis between a three correlation coefficients sush as Spearman, Kendal and Person to conclude the best one. To illustrate our study, the methodology is applied to the 6th road ring as the most crowded area of Beijing.Item Residual Neural Network for Predicting Super-enhancers on Genome Scale(University of Eloued جامعة الوادي, 2022-01-24) Sabba, Sara; Hamrelaine, Amina; Smara, Maroua; Benhacine, MehdiResidual neural network (ResNet) is a Deep Learning model introduced by He et al. [13] in 2015 to enhance traditional Convolutional neural networks for computer vision problems. It uses skip connections over some layer blocks to avoid vanishing gradient problem. Currently, many researches are focused to test and prove the efficiency of the ResNet on different domains such as genomics. In this paper, we propose a new ResNet model for predicting super-enhancers on genome scale. In fact, the prediction of super-enhancers (SEs) has prominent roles in biological and pathological processes; especially that related to the detection and progression of tumors. The obtained results are very promising and they proved the performance of our proposal compared to the CNN results.Item Recognizing Arabic handwritten literal amount using Convolutional Neural Networks(University of Eloued جامعة الوادي, 2022-01-24) KORICHI, Aicha; SLATNIA, Sihem; TAGOUGUI, Najiba; ZOUARI, Ramzi; KHERALLAH, Monji; AIADI, OussamaCurrently, deep learning techniques have become the core of recent research in pattern recognition domain and especially for the handwriting recognition field where the challenges for the Arabic language are stilling. Despite their high importance and performances, for the best of our acknowledge, deep learning techniques have not been investigated in the context of Arabic handwritten literal amount recognition. The main aim of this paper is to investigate the effect of several Convolutional Neural Networks CNNs based on the proposed architecture with regularization parameters for such context. To achieve this aim, the AHDB database was used where very promising results were obtained outperforming the previous works on this database.Item Real-Time Speed Control of a Mobile Robot Using PID Controller(University of Eloued جامعة الوادي, 2022-01-24) MohandSaidi, Sabrina; Mellah, RabahThis paper presents PID control of speed implemented by PC on a unicycle mobile robot. The designed control has been applied to a nonholonomic mobile robot dr Robot i90. The results obtained from the experiment show the efficiency of this strategy control, even in the case where we introduce a disturbance for the system such as for example putting an overload for the robotItem Rational Function Model Optimization Based On Swarm Intelligence Metaheuristic Algorithms(University of Eloued جامعة الوادي, 2022-01-24) Mezouar, Oussama; Meskine, Fatiha; Boukerch, IssamThe Rrational Function Model (RFM) is progressively being familiar to the mapping and photogrammetric researchersand has been widely used as an approximate to rigorous Models. According to it ability to preserve the complete accuracy of various types of physical sensors and its independence of sensors and platforms, it can be had with any coordination system. Nevertheless, the RFM coefficients are also known as rational polynomial coefficients (RPCs) dependent on a large number of ground control points which makes the model susceptible to over parameterization error and a time-consuming also the RPCs have no physical meaning, as a result, selecting the best combination of RPCs is difficult. The intelligent algorithms based meta-heuristic optimization seem to be an effective approach for overcoming this problem. This paper focuses on the application of recent swarm intelligence based meta-heuristic algorithms for RFM optimization. The most popular optimization methods considered are ant colony algorithm, genetic algorithms and particle swarm optimization.Furthermore in this research we proposed an parallel hybrid metaheuristic optimization algorithm that combines the genetic algorithm and particle swarm optimization concepts to overcoming the swarm intelligent limitations for RFM optimization. The different algorithms are applied for two data sets provided from the Algerian satellite (ALSAT2).The results demonstrated that the proposed method is more accurate than the threesuggested based meta-heuristic methods.Item Ranking social media news feeds: A comparative study of Personalized and Non-Personalized prediction models(University of Eloued جامعة الوادي, 2022-01-24) Belkacem, Sami; Boukhalfa, Kamel; Boussaid, OmarRanking news feed updates by relevance has been proposed to help social media users catch up with the content they may nd inter- esting. For this matter, a single non-personalized model has been used to predict the relevance for all users. However, as user interests and pref- erences are di erent, we believe that using a personalized model for each user is crucial to re ne the ranking. In this work, to predict the relevance of news feed updates and improve user experience, we use the random forest algorithm to train and introduce a personalized prediction model for each user. Then, we compare personalized and non-personalized mod- els according to six criteria: (1) the overall prediction performance; (2) the amount of data in the training set; (3) the cold-start problem; (4) the incorporation of user preferences over time; (5) the model ne-tuning; and (6) the personalization of feature importance for users. Experimen- tal results on Twitter show that a single non-personalized model for all users is easy to manage and ne-tune, is less likely to over t, and it ad- dresses the problem of cold-start and inactive users. On the other hand, the personalized models we introduce allow personalized feature impor- tance, take into consideration the preferences of each user, and allow to track changes in user preferences over time. Furthermore, personalized models give a higher prediction accuracy than non-personalized models.Item Penguins Search Optimization Algorithm (PeSOA) for chaotic synchronization system(University of Eloued جامعة الوادي, 2022-01-24) Maamri, Fouzia; Bououden, Sofiane; Djellab, Hanane; Boulkaibet, IlyesInformation encryption is a security process where data is encoded using chaotic signal. stabilization and synchronization in chaotic systems for secure information can be achieved using the metaheuristic algorithms. In this work Penguins Search Optimization Algorithm (PeSOA) which is inspired by penguin’s social behavior is applied to synchronize chaotic encryption signal. PeSOA algorithm explores space with random and iterative search in order to find symmetric encryption key of the chaotic system in both transmission and reception. Identification based on metaheristic optimization Algorithm (PeSOA) is used to improve the accuracy of initial conditions and control parameters of Chua’s chaotic generator by minimizing errors between the estimated and identified value. Simulation results show the effectiveness of the PeSOA algorithm to generating symmetric key of encryption process and synchronizing both chaotic circuit of transmitter and receiver one.Item Passive fault tolerant control of a new reconfigurable quadrotor(University of Eloued جامعة الوادي, 2022-01-24) Salmi, Abdenour; Bouzid, Yasser; Guiatni, MohamedThe purpose of this paper is to improve the control performance of a new reconfigurable quadrotor subject to change of configuration and under actuator Loss of Effectiveness (LOE) using Integral Sliding Mode Controller (ISMC). First, we present the design of the UAV which is capable of folding its arms instantaneously during the flight which result variation in its different parameters such as Center of Gravity (CoG), inertia and control matrix. Then, the ISMC controller based Passive Fault Tolerant Control (PFTC) is designed to control and stabilize the position and the attitude of the UAV in some possible configurations and under actuator fault conditions. The four servomotors used to rotate the quadrotor arms are controlled by PID controller. Finlay, we present simulation results using Matlab/Simulink environment which demonstrate the effectiveness and the robustness of the ISMC-PFTC controller compared to the regular SMC one.Item ParPredict: A partially-ordered sequential rules based framework for mobility prediction(University of Eloued جامعة الوادي, 2022-01-24) Amirat, HananePredicting the future movement of mobile users has emerged as an important technology topic in many applications related to intelligent transportation systems (ITS) and Location-based services (LBS). Numerous prediction models were proposed relying on probabilistic models (e.g. Markov Chain) or data mining techniques (e.g. neural network, sequential patterns mining). Mining sequential patterns and rules is one of the data mining techniques used. Mining sequential rules from sequence databases is an active research topic that is broadly applied for many real-world scenarios. In this paper, we propose to adapt a novel kind of sequential rules called partially order sequential rules for route prediction problem. We aim to further compare this kind with standard sequential rule for the task of mobility prediction. An experimental evaluation conducted on real and synthetic datasets show that the proposed model outperforms a state-of-the-art sequential model in terms of accuracy and prediction coverage.Item On the use of the convolutional autoencoder for Arabic writer identification using handwritten text fragments(University of Eloued جامعة الوادي, 2022-01-24) Briber, Amina; Chibani, YoucefConvolutional autoencoders (CAE) are designed to reconstruct the input image to the output in a near-perfect way via a compact data namely encoded data containing relevant features. The encoded data can be used in various applications as for compressing or classifying the image. The present paper tries to investigate the use of the CAE for writer identification using handwritten text fragments. Hence, the CAE is used for generating features, which is fed to the distance-based classifier. Experimental evaluation is performed on the wellknown IFN/ENIT dataset containing 411 writers. During training, a subset is selected from the 411 writers containing only 11 writers allowing to produce a lite CAE. Experimental results show an identification rate of 92.70% using the whole dataset when the feature vector is appropriately normalized.Item Offline Arabic Handwriting Recognition Using a Deep Neural Approach(University of Eloued جامعة الوادي, 2022-01-24) Benbakreti, Samir; Benouis, Mohamed; Benkaddour, Mohammed KamelArabic handwritten recognition systems face several challenges such as the very diverse scripting styles, the presence of pseudo-words and the position- dependent shape of a character inside a given word. These characteristics complicated the task of features extraction. The paper presents a deep neural approach for the handwritten recognition of Arabic words. This work is focusing on the offline recognition, thereby, the processed information represents an image. We chose the CNN method, which is one of the deep architectures which permits to remove several steps from the recognition process, including preprocessing and feature extraction. The used database is NOUN v3 contained images represented the Algerian cities. A CNN architecture was trained and then tested on the database to accomplish this task. The advantage of a CNN is that it can extract specific features from each image while compressing it to lower its initial size. Our experimental study, gives a satisfactory word recognition rate.Item OAIDS: An Ontology-Based Framework for Building an Intelligent Urban Road Traffic Automatic Incident Detection System(University of Eloued جامعة الوادي, 2022-01-24) HIRECHE, Samia; DENNAI, Abdeslem; KADRI, BoufeldjaHandling interoperability of data exchange among road traffic sensor devices, connected vehicles, infrastructure components and heterogeneous traffic management center applications has become an important and basic requirement nowadays. To meet this requirement, this paper proposes an ontology based framework to capture the knowledge domain about traffic automatic incident detection system (AIDS) based on Connected Vehicles (CVs) technology. This ontology addresses the semantic data interoperability needed between different heterogeneous entities constituent this AIDS. This contribution aims at modeling and capturing the semantic of the anomaly information used in the incident detection process and describing the AIDS components, their observations, measurements and communications messages features. First, to achieve this goal, NeOn methodology was adopted. Then, we defined the basic concepts and observations of a traffic sensor and CVs that has been extended to define concepts related to the data sensing and gathering layer of this framework based on ontology concepts. In addition, to ensure data interoperability and identify ontology’s restrictions, we used the OWL (Web Ontology Language) language. Furthermore, to build this ontology, we used the OWL under Protégé tool. Finally, OAIDS consisted of 93 concepts and 33 object properties. OntoMetrics was used to confirm the effectiveness of this proposed ontology to carry out the interoperability of CV’s sensor data in the urban road AIDS domain.