Academic & Scientific Articles

Permanent URI for this communityhttp://dl.cerist.dz/handle/CERIST/3

Browse

Subject: search.filters.subject.Machine learning

Search Results

Now showing 1 - 9 of 9
  • Thumbnail Image
    Item
    Efficient Machine Learning-based Approach for Brain Tumor Detection Using the CAD System
    (Taylor & Francis, 2023-04) Guerroudji, Mohamed Amine; Hadjadj, Zineb; Lichouri, Mohamed; Amara, Kahina; Zenati, Nadia
    Medical research has focused on improving diagnosis through medical imaging in recent decades. Computer Assisted Diagnosis (CAD) systems have been developed to help doctors identify suspicious areas of interest, particularly those with cancer-like characteristics. CAD systems employ various algorithms and techniques to extract important numerical measurements from medical images that clinicians can use to evaluate patient conditions. This study proposes a statistical classification-based approach to efficient brain cancer detection. The proposed approach operates in three stages: first, Gradient Vector Flow (GVF) Snake models and mathematical morphology techniques retrieve regions of interest. The second stage characterizes these regions using morphological and textural parameters. Finally, a Bayesian network uses this description as input to identify malignant and benign cancer classes. We also compared the performance of the Bayesian network with other popular classification algorithms, including SVM, MLP, KNN, Random Forest, Decision Tree, XGBoost, LGBM, Gaussian Process, and RBF SVM. The results showed the superiority of the Bayesian network for the task of brain tumor classification. The proposed approach has been experimentally validated, with a sensitivity of 100% and a classification accuracy of over 98% for tumors, demonstrating the high efficiency of cancer cell segmentation.
  • Thumbnail Image
    Item
    TriDroid: a triage and classification framework for fast detection of mobile threats in android markets
    (Springer-Verlag, 2021) Amira, Abdelouahab; Derhab, Abdelouahid; Karbab, ElMouatez Billah; Nouali, Omar; Aslam Khan , Farrukh
    The Android platform is highly targeted by malware developers, which aim to infect the maximum number of mobile devices by uploading their malicious applications to different app markets. In order to keep a healthy Android ecosystem, app-markets check the maliciousness of newly submitted apps. These markets need to (a) correctly detect malicious app, and (b) speed up the detection process of the most likely dangerous applications among an overwhelming flow of submitted apps, to quickly mitigate their potential damages. To address these challenges, we propose TriDroid, a market-scale triage and classification system for Android apps. TriDroid prioritizes apps analysis according to their risk likelihood. To this end, we categorize the submitted apps as: botnet, general malware, and benign. TriDroid starts by performing a (1) Triage process, which applies a fast coarse-grained and less-accurate analysis on a continuous stream of the submitted apps to identify their corresponding queue in a three-class priority queuing system. Then, (2) the Classification process extracts fine-grained static features from the apps in the priority queue, and applies three-class machine learning classifiers to confirm with high accuracy the classification decisions of the triage process. In addition to the priority queuing model, we also propose a multi-server queuing model where the classification of each app category is run on a different server. Experiments on a dataset with more than 24K malicious and 3K benign applications show that the priority model offers a trade-off between waiting time and processing overhead, as it requires only one server compared to the multi-server model. Also it successfully prioritizes malicious apps analysis, which allows a short waiting time for dangerous applications compared to the FIFO policy.
  • Thumbnail Image
    Item
    Ontology learning: Grand tour and challenges
    (Elsevier, 2021-02-21) Chérifa Khadir, Ahlem; Aliane, Hassina; Guessoum, Ahmed
    Ontologies are at the core of the semantic web. As knowledge bases, they are very useful resources for many artificial intelligence applications. Ontology learning, as a research area, proposes techniques to automate several tasks of the ontology construction process to simplify the tedious work of manually building ontologies. In this paper we present the state of the art of this field. Different classes of approaches are covered (linguistic, statistical, and machine learning), including some recent ones (deep-learning-based approaches). In addition, some relevant solutions (frameworks), which offer strategies and built-in methods for ontology learning, are presented. A descriptive summary is made to point out the capabilities of the different contributions based on criteria that have to do with the produced ontology components and the degree of automation. We also highlight the challenge of evaluating ontologies to make them reliable, since it is not a trivial task in this field; it actually represents a research area on its own. Finally, we identify some unresolved issues and open questions.
  • Thumbnail Image
    Item
    Side Channel Attack using Machine Learning
    (IEEE, 2022-12-15) Amrouche, Amina; Boubchir, Larbi; Yahiaoui, Saïd
    The overwhelming majority of significant security threats are hardware-based, where the attackers attempt to steal information straight from the hardware that our secure and encrypted software operates on. Unquestionably, side-channel attacks are one of the most severe risks to hardware security. Rather than depending on bugs in the program itself, a side-channel attack exploits information leaked from the program implementation in order to exfiltrate sensitive secret information such as cryptographic keys. A side channel assault could manifest in different ways including electromagnetic radiation, power consumption, timing data, or even acoustic emanation. Ever since the side-channel attacks were introduced in the 1990s, a number of significant attacks on cryptographic implementations utilizing side-channel analysis have emerged, such as template attacks, and attacks based on power analysis and electromagnetic analysis. However, Artificial Intelligence has become more prevalent. Attackers are now more interested in machine learning and deep learning technologies that enable them to interpret the extracted raw data. The aim of this paper is to highlight the main methods of machine learning and deep learning that are used in the most recent studies that deal with different types of side-channel attacks.
  • Thumbnail Image
    Item
    UDEPLOY: User-Driven Learning for Occupancy Sensors DEPLOYment In Smart Buildings
    (IEEE, 2018-03) Laidi, Roufaida; Djenouri, Djamel
    A solution for motion sensors deployment in smart buildings is proposed. It differentiates the monitored zones according to their occupancy, where highly-occupied zones have higher coverage requirements over low-occupied zones, and thus are assigned higher granularity in the targeted coverage (weights). The proposed solution is the first that defines a user-driven approach, which uses sampling of occupants’ behavior to determine the zones and the coverage weights. The samples are acquired during a short learning phase and then used to derive a graph model. The latter is plugged into a greedy, yet effective, algorithm that seeks optimal placement for maximizing detection accuracy while reducing the cost (number of sensors). Practical aspects such as the scalability and the applicability of the solution are considered. A simulation study that compares the proposed solution with two state-of-the-art solutions shows the superiority of the proposed approach in the accuracy of detection (increased coverage), and scalability (reduced runtime).
  • No Thumbnail Available
    Item
    UDEPLOY: User-Driven Learning for Occupancy Sensors DEPLOYment In Smart Buildings
    (CERIST, 2017-12-25) Laidi, Roufaida; Djenouri, Djamel
    A solution for motion sensors deployment in smart buildings is proposed. It diferentiates the monitored zones according to their occupancy, where highly-occupied zones have higher coverage requirements over low-occupied zones, and thus are assigned higher granularity in the targeted coverage (weights). The proposed solution is the rst that de nes a user-driven approach, which uses sampling of occupants' behavior to determine the zones and the coverage weights. The samples are acquired during a short learning phase and then used to derive a graph model. The latter is plugged into a greedy, yet e ective, algorithm that seeks optimal placement for maximizing detection accuracy while reducing the cost (number of sensors). Practical aspects such as the scalability and the applicability of the solution are considered. A simulation study that compares the proposed solution with two state-of-the-art solutions shows the superiority of the proposed approach in the accuracy of detection (increased coverage), and scalability (reduced runtime).
  • Thumbnail Image
    Item
    Filtrage cognitif de l’information électronique
    (ECIG 2007, 2007-10-19) Nouali, Omar; Toursel, B.
    L'objectif des travaux de recherche présentés dans cet article est l’automatisation du processus de filtrage de l’information en prenant en compte l’importance relative de l'information et les besoins en ressources linguistiques pour son traitement. Nous proposons une solution ouverte, dynamique et évolutive qui offre au processus de filtrage la possibilité d’apprendre, d’exploiter ces connaissances apprises et de s’adapter à la nature de l’application. Nous l’avons modélisé à l’aide d’agents pour offrir un gain de temps par rapport à une solution algorithmique séquentielle. Pour la validation de notre approche de filtrage, nous avons mené un ensemble d’expériences pour évaluer les performances des techniques et outils proposés et développés.
  • Thumbnail Image
    Item
    Automatic Classification and Filtering of Electronic Information: Knowledge-Based Filtering Approach
    (Zarqa Private University, Jordan, 2004) Nouali, Omar; Blache, Philippe
    In this paper we propose an artificial intelligent approach focusing on information filtering problem. First, we give an overview of the information filtering process and a survey of different models of textual information filtering. Second, we present our E-mail filtering tool. It consists of an expert system in charge of driving the filtering process in cooperation with a knowledge-based model. Neural networks are used to model all system knowledge. The system is based on machine learning techniques to continuously learn and improve its knowledge all along its life cycle. This email filtering tool assists the user in managing, selecting, classify and discarding non-desirable messages in a professional or non-professional context. The modular structure makes it portable and easy to adapt to other filtering applications such as web browsing. The performance of the system is discussed.
  • Thumbnail Image
    Item
    A Semantic vector space and features-based approach for automatic information filtering
    (Elsevier, 2004) Nouali, Omar; Blache, Philippe
    With advances in communication technology, the amount of electronic information available to the users will become increasingly important. Users are facing increasing difficulties in searching and extracting relevant and useful information. Obviously, there is a strong demand for building automatic tools that capture, filter, control and disseminate the information that will most likely match a user's interest. In this paper we propose two kinds of knowledge to improve the efficiency of information filtering process. A features-based model for representing, evaluating and classifying texts. A semantic vector space to complement the features-based model on taking into account the semantic aspect. We used a neural network to model the user's interests (profiles) and a set of genetic algorithms for the learning process to improve filtering quality. To show the efficacy of such knowledge to deal with information filtering problem, particularly we present an intelligent and dynamic email filtering tool. It assists the user in managing, selecting, classifying and discarding non-desirable messages in a professional or non-professional context. The modular structure makes it portable and easy to adapt to other filtering applications such as the web browsing. We illustrate and discuss the system performance by experimental evaluation results