Abderrahim GHADI | Faculté des sciences et techniques (original) (raw)
Papers by Abderrahim GHADI
Lecture notes in intelligent transportation and infrastructure, 2019
In field of mobile security android malware is well known as a problematic never can finally solv... more In field of mobile security android malware is well known as a problematic never can finally solved despite of many solutions that have been proposed over time by researchers because of revolution and development of attackers techniques used in codes of their malwares that override anti-malwares and malware detection techniques by hiding the real behavior of malware when it is getting to scan moreover by obfuscating the source code of this last which make it difficult for researchers to view the source code of malicious application in order to analyze the element of this last and required features by it. The revolution of this malicious techniques make the solution proposed even using newest technologies of machine learning and reverse engineering get more limited over time in detecting malwares especially new released ones. For this reason the main objective of researchers in this field is to find a new solutions that can bear with this revolution. In this paper we proposed an approach based on clustering android applications into malware or benign using permissions as features in order to detect malwares in android applications by the application of filter feature selection algorithms to select features and k-Mean machine learning algorithm for clustering purpose.
Proceedings of the 4th International Conference on Smart City Applications, Oct 2, 2019
The revolution and development of malwares over time necessitate an intensive researches on advan... more The revolution and development of malwares over time necessitate an intensive researches on advanced techniques to secure user's personal and critical information, the most challenging task is to build a strong and robust classifier allows to detect different types of malwares and being able to defeat zero-day malware attacks. Machine learning algorithms as SVM (support vector machine), Random Forest and Naïve Bayes are well-known choices for building the malware classifier, even though the deep learning which is a subfield of machine learning, has a portion in classifying android malwares with high precision. In this paper we present a modest study on difference between using both techniques and proposition of an approach based on deep learning technique applied on Apk of android applications belong to a heterogeneous data combined of benign and malware applications of different types.
IEEE Conference Proceedings, 2016
The mobile operation system Android is one of the most OS's used in the entire world, which m... more The mobile operation system Android is one of the most OS's used in the entire world, which make it the target of many malware projects and the mission of detecting those malware applications is getting harder over time due to evaluation and development of techniques that make possible for those malwares to hide their maliciousness activities from anti-malware techniques by obfuscating the code source of application or even hiding malicious activities when it's getting to scan by an anti-malware, for this purpose many researchers have paid attention to this subject by proposing different approaches using newest technologies of machine learning and reverse engineering to deal with this problematic. In this paper a permission-based approach is proposed for detecting malwares in android applications using filter feature selection algorithms to select features and machine learning algorithms Random Forest, SVM, J48 for classification of applications into malware or benign.
Lecture notes in intelligent transportation and infrastructure, 2020
Lecture notes in intelligent transportation and infrastructure, 2019
Today, the Web knows a rapid increase in data level that makes their processing and storage limit... more Today, the Web knows a rapid increase in data level that makes their processing and storage limited in traditional technologies. That is why future technology tries to exploit the notion of semantics and ontology by adapting them to big data technology to allow a fundamental change in the access to voluminous information in the web. That Intended to have a complete and relevant response to the user request. Our research work focuses on the semantic web. Focus exactly on the semantic search on many data expressed by RDF (Resource Description Framework) in distributed system. The semantic language proposed by W3C (World Wide Web Consortium) provides the formalism necessary for the representation of data for the Semantic Web. However, only a knowledge representation format is insufficient and we need powerful response mechanisms to manage effectively global and distributed queries across a set of stand-alone and heterogeneous RDF resources marked by the dynamic and scalable nature of their content.
Lecture notes in networks and systems, 2023
Nowadays, the internet has become the first source of information for most people, it plays a vit... more Nowadays, the internet has become the first source of information for most people, it plays a vital role in the teaching, research and learning process. MOOCs are probably the most important "novelty" in the field of e-learning of the last years, it represents an emerging methodology of online teaching and an important development in open education. MOOCs makes it possible for everyone to access to the education over the world, but due the large resources in the web, it becomes increasingly difficult for a learner to identify a suitable course for him. This task can be tedious because it involves access to each platform, search available courses, select some courses, read carefully each course syllabus, and choose the appropriate content. Web video mining is retrieving the content using data mining techniques from World Wide Web. There are two approaches for web video mining using traditional image processing (signal processing) and metadata based approach. In this work,...
With the immigration to IPv6 and the large range of addresses provided by this protocol, reducing... more With the immigration to IPv6 and the large range of addresses provided by this protocol, reducing the size of IP routing tables becomes one of the main and the most compelling challenges facing the internet.
Lecture notes in networks and systems, 2023
International Journal of Future Generation Communication and Networking, 2014
A complex network is a interaction network of entities where global behavior is not deductible fr... more A complex network is a interaction network of entities where global behavior is not deductible from the individual behaviors of each entities, leading to new properties emergence. Our problem is the network analysis ad modeling. Network analysis needs a formalism to assemble together the structure (static approach) and the function (dynamic approach), and to have a better understanding of the networks characteristics. In this paper, we introduce common used network modeling based on graph theory, having the role to simulate complex networks.
Proceedings of the 4th International Conference on Smart City Applications, 2019
Due to the danger that represents breast cancer in the society and also due to the number of deat... more Due to the danger that represents breast cancer in the society and also due to the number of death that causes every year in women's sector, the proposition of solutions that aim to reduce this number of death has become a primordial need. In this paper we present an approach for breast cancer diagnosis using machines learning techniques that can be helpful in breast cancer detection in earlier stage and with the right way without errors to propose the suitable treatment for the patients. We will use machines learning techniques in our approach due to their performance in domain of medicine.
International Journal of Electrical and Computer Engineering (IJECE)
Sentiment analysis is a well-known and rapidly expanding study topic in natural language processi... more Sentiment analysis is a well-known and rapidly expanding study topic in natural language processing (NLP) and text classification. This approach has evolved into a critical component of many applications, including politics, business, advertising, and marketing. Most current research focuses on obtaining sentiment features through lexical and syntactic analysis. Word embeddings explicitly express these characteristics. This article proposes a novel method, improved words vector for sentiments analysis (IWVS), using XGboost to improve the F1-score of sentiment classification. The proposed method constructed sentiment vectors by averaging the word embeddings (Sentiment2Vec). We also investigated the Polarized lexicon for classifying positive and negative sentiments. The sentiment vectors formed a feature space to which the examined sentiment text was mapped to. Those features were input into the chosen classifier (XGboost). We compared the F1-score of sentiment classification using ou...
Springer International Publishing eBooks, Sep 1, 2022
Proceedings of the 3rd International Conference on Smart City Applications, 2018
Mobility of nodes in mobile ad hoc network constitutes a big challenge in the design of efficient... more Mobility of nodes in mobile ad hoc network constitutes a big challenge in the design of efficient routing protocol. Such issues reside in frequent and unpredictable links failure, which impact the overall network performance. Research community has proposed several scenarios to minimize the impact of mobility and deliver the quality of service required by MANET applications. However, efficiency of routing protocols must be assessed before their deployment. Actually, routing performances are evaluated using four main metrics: latency or end-to-end delay, Throughput, Packet delivery ratio and routing overhead. The purpose of this paper is the introduction of two new metrics that are devoted to evaluate how well routing protocol act in case of link failure triggered generally by high mobility. The first metric is path change factor (PCF), which characterize mobility adaptiveness and the second metric is route repair influence (RRI) that represent the effectiveness of route repair scheme. In addition we implemented the new metrics using an AWK script that uses as input NS2 trace file format.
Proceedings of the 2nd international Conference on Big Data, Cloud and Applications, 2017
In few years, the internet has become the first source of information for most people, Today MOOC... more In few years, the internet has become the first source of information for most people, Today MOOCs makes it possible for everyone to access to the education over the world, it's represents an emerging methodology of online teaching and an important development in open education. Due to the rapid development of Moocs and the rapid growth of digital data and video database over the Internet, it is becoming very difficult for learners to browsing and choosing the best training for them. The scientific community has increased the amount of research into new technologies, with a view to improve the digital video utilization: its archiving, indexing, accessibility, acquisition, store and even its process and usability. All these parts of the video utilization entail the necessity of the extraction of all important information of a video, especially in cases of lack of metadata information. Web video mining is retrieving the content using data mining techniques from World Wide Web. There are two approaches for web video mining using traditional image processing (signal processing) and metadata based approach. In this paper, we present the various research makes in this subject and we propose an effective methodology to extract the metadata from Moocs videos and classify them based on the extracted metadata by applying data mining techniques.
Advanced Intelligent Systems for Sustainable Development (AI2SD’2020), 2022
Emerging Trends in ICT for Sustainable Development, 2021
Innovations in Smart Cities Applications Edition 2, 2019
Mobile Ad Hoc Network plays a major role in facilitating communication between autonomous entitie... more Mobile Ad Hoc Network plays a major role in facilitating communication between autonomous entities in different application fields. Moreover, nowadays applications require nodes to move from their initial position. Therefore, mobility of nodes in mobile ad hoc network represents the main issue that should be addressed carefully while designing routing protocols. The purpose of this paper is the evaluation of the impact of node mobility on routing protocols. Hence, DSDV, DSR and AODV have been implemented using Network Simulators NS2 and then we assessed the efficiency of each protocol under a particular scenario in relation to performance the QoS metrics such as latency, Throughput, Packet delivery ratio and routing overhead. Moreover, simulations were carried out using several pause time value and Random Way Point (RWP) as mobility model. The study shows that AODV has better performances in high mobility level.
Lecture notes in intelligent transportation and infrastructure, 2019
In field of mobile security android malware is well known as a problematic never can finally solv... more In field of mobile security android malware is well known as a problematic never can finally solved despite of many solutions that have been proposed over time by researchers because of revolution and development of attackers techniques used in codes of their malwares that override anti-malwares and malware detection techniques by hiding the real behavior of malware when it is getting to scan moreover by obfuscating the source code of this last which make it difficult for researchers to view the source code of malicious application in order to analyze the element of this last and required features by it. The revolution of this malicious techniques make the solution proposed even using newest technologies of machine learning and reverse engineering get more limited over time in detecting malwares especially new released ones. For this reason the main objective of researchers in this field is to find a new solutions that can bear with this revolution. In this paper we proposed an approach based on clustering android applications into malware or benign using permissions as features in order to detect malwares in android applications by the application of filter feature selection algorithms to select features and k-Mean machine learning algorithm for clustering purpose.
Proceedings of the 4th International Conference on Smart City Applications, Oct 2, 2019
The revolution and development of malwares over time necessitate an intensive researches on advan... more The revolution and development of malwares over time necessitate an intensive researches on advanced techniques to secure user's personal and critical information, the most challenging task is to build a strong and robust classifier allows to detect different types of malwares and being able to defeat zero-day malware attacks. Machine learning algorithms as SVM (support vector machine), Random Forest and Naïve Bayes are well-known choices for building the malware classifier, even though the deep learning which is a subfield of machine learning, has a portion in classifying android malwares with high precision. In this paper we present a modest study on difference between using both techniques and proposition of an approach based on deep learning technique applied on Apk of android applications belong to a heterogeneous data combined of benign and malware applications of different types.
IEEE Conference Proceedings, 2016
The mobile operation system Android is one of the most OS's used in the entire world, which m... more The mobile operation system Android is one of the most OS's used in the entire world, which make it the target of many malware projects and the mission of detecting those malware applications is getting harder over time due to evaluation and development of techniques that make possible for those malwares to hide their maliciousness activities from anti-malware techniques by obfuscating the code source of application or even hiding malicious activities when it's getting to scan by an anti-malware, for this purpose many researchers have paid attention to this subject by proposing different approaches using newest technologies of machine learning and reverse engineering to deal with this problematic. In this paper a permission-based approach is proposed for detecting malwares in android applications using filter feature selection algorithms to select features and machine learning algorithms Random Forest, SVM, J48 for classification of applications into malware or benign.
Lecture notes in intelligent transportation and infrastructure, 2020
Lecture notes in intelligent transportation and infrastructure, 2019
Today, the Web knows a rapid increase in data level that makes their processing and storage limit... more Today, the Web knows a rapid increase in data level that makes their processing and storage limited in traditional technologies. That is why future technology tries to exploit the notion of semantics and ontology by adapting them to big data technology to allow a fundamental change in the access to voluminous information in the web. That Intended to have a complete and relevant response to the user request. Our research work focuses on the semantic web. Focus exactly on the semantic search on many data expressed by RDF (Resource Description Framework) in distributed system. The semantic language proposed by W3C (World Wide Web Consortium) provides the formalism necessary for the representation of data for the Semantic Web. However, only a knowledge representation format is insufficient and we need powerful response mechanisms to manage effectively global and distributed queries across a set of stand-alone and heterogeneous RDF resources marked by the dynamic and scalable nature of their content.
Lecture notes in networks and systems, 2023
Nowadays, the internet has become the first source of information for most people, it plays a vit... more Nowadays, the internet has become the first source of information for most people, it plays a vital role in the teaching, research and learning process. MOOCs are probably the most important "novelty" in the field of e-learning of the last years, it represents an emerging methodology of online teaching and an important development in open education. MOOCs makes it possible for everyone to access to the education over the world, but due the large resources in the web, it becomes increasingly difficult for a learner to identify a suitable course for him. This task can be tedious because it involves access to each platform, search available courses, select some courses, read carefully each course syllabus, and choose the appropriate content. Web video mining is retrieving the content using data mining techniques from World Wide Web. There are two approaches for web video mining using traditional image processing (signal processing) and metadata based approach. In this work,...
With the immigration to IPv6 and the large range of addresses provided by this protocol, reducing... more With the immigration to IPv6 and the large range of addresses provided by this protocol, reducing the size of IP routing tables becomes one of the main and the most compelling challenges facing the internet.
Lecture notes in networks and systems, 2023
International Journal of Future Generation Communication and Networking, 2014
A complex network is a interaction network of entities where global behavior is not deductible fr... more A complex network is a interaction network of entities where global behavior is not deductible from the individual behaviors of each entities, leading to new properties emergence. Our problem is the network analysis ad modeling. Network analysis needs a formalism to assemble together the structure (static approach) and the function (dynamic approach), and to have a better understanding of the networks characteristics. In this paper, we introduce common used network modeling based on graph theory, having the role to simulate complex networks.
Proceedings of the 4th International Conference on Smart City Applications, 2019
Due to the danger that represents breast cancer in the society and also due to the number of deat... more Due to the danger that represents breast cancer in the society and also due to the number of death that causes every year in women's sector, the proposition of solutions that aim to reduce this number of death has become a primordial need. In this paper we present an approach for breast cancer diagnosis using machines learning techniques that can be helpful in breast cancer detection in earlier stage and with the right way without errors to propose the suitable treatment for the patients. We will use machines learning techniques in our approach due to their performance in domain of medicine.
International Journal of Electrical and Computer Engineering (IJECE)
Sentiment analysis is a well-known and rapidly expanding study topic in natural language processi... more Sentiment analysis is a well-known and rapidly expanding study topic in natural language processing (NLP) and text classification. This approach has evolved into a critical component of many applications, including politics, business, advertising, and marketing. Most current research focuses on obtaining sentiment features through lexical and syntactic analysis. Word embeddings explicitly express these characteristics. This article proposes a novel method, improved words vector for sentiments analysis (IWVS), using XGboost to improve the F1-score of sentiment classification. The proposed method constructed sentiment vectors by averaging the word embeddings (Sentiment2Vec). We also investigated the Polarized lexicon for classifying positive and negative sentiments. The sentiment vectors formed a feature space to which the examined sentiment text was mapped to. Those features were input into the chosen classifier (XGboost). We compared the F1-score of sentiment classification using ou...
Springer International Publishing eBooks, Sep 1, 2022
Proceedings of the 3rd International Conference on Smart City Applications, 2018
Mobility of nodes in mobile ad hoc network constitutes a big challenge in the design of efficient... more Mobility of nodes in mobile ad hoc network constitutes a big challenge in the design of efficient routing protocol. Such issues reside in frequent and unpredictable links failure, which impact the overall network performance. Research community has proposed several scenarios to minimize the impact of mobility and deliver the quality of service required by MANET applications. However, efficiency of routing protocols must be assessed before their deployment. Actually, routing performances are evaluated using four main metrics: latency or end-to-end delay, Throughput, Packet delivery ratio and routing overhead. The purpose of this paper is the introduction of two new metrics that are devoted to evaluate how well routing protocol act in case of link failure triggered generally by high mobility. The first metric is path change factor (PCF), which characterize mobility adaptiveness and the second metric is route repair influence (RRI) that represent the effectiveness of route repair scheme. In addition we implemented the new metrics using an AWK script that uses as input NS2 trace file format.
Proceedings of the 2nd international Conference on Big Data, Cloud and Applications, 2017
In few years, the internet has become the first source of information for most people, Today MOOC... more In few years, the internet has become the first source of information for most people, Today MOOCs makes it possible for everyone to access to the education over the world, it's represents an emerging methodology of online teaching and an important development in open education. Due to the rapid development of Moocs and the rapid growth of digital data and video database over the Internet, it is becoming very difficult for learners to browsing and choosing the best training for them. The scientific community has increased the amount of research into new technologies, with a view to improve the digital video utilization: its archiving, indexing, accessibility, acquisition, store and even its process and usability. All these parts of the video utilization entail the necessity of the extraction of all important information of a video, especially in cases of lack of metadata information. Web video mining is retrieving the content using data mining techniques from World Wide Web. There are two approaches for web video mining using traditional image processing (signal processing) and metadata based approach. In this paper, we present the various research makes in this subject and we propose an effective methodology to extract the metadata from Moocs videos and classify them based on the extracted metadata by applying data mining techniques.
Advanced Intelligent Systems for Sustainable Development (AI2SD’2020), 2022
Emerging Trends in ICT for Sustainable Development, 2021
Innovations in Smart Cities Applications Edition 2, 2019
Mobile Ad Hoc Network plays a major role in facilitating communication between autonomous entitie... more Mobile Ad Hoc Network plays a major role in facilitating communication between autonomous entities in different application fields. Moreover, nowadays applications require nodes to move from their initial position. Therefore, mobility of nodes in mobile ad hoc network represents the main issue that should be addressed carefully while designing routing protocols. The purpose of this paper is the evaluation of the impact of node mobility on routing protocols. Hence, DSDV, DSR and AODV have been implemented using Network Simulators NS2 and then we assessed the efficiency of each protocol under a particular scenario in relation to performance the QoS metrics such as latency, Throughput, Packet delivery ratio and routing overhead. Moreover, simulations were carried out using several pause time value and Random Way Point (RWP) as mobility model. The study shows that AODV has better performances in high mobility level.