Pub Date : 2021-02-09DOI: 10.1109/IHSH51661.2021.9378732
M. Ayad, Smail Medjedoub, Benziane Mourad, K. Saoudi, Abderrazak Arabi
With the development of different generation of mobile networks, the mobile telecommunications networks have known expanded growth. These networks have admitted the integration of new services. This rapid evolution has led operators to adapt their planning methods to new technologies that increase the network's complexity. The planning phase corresponds to ensure the best radio coverage, compatibility with existing networks, management of the handover, the anticipation of interference, cell size, and supported load. This will allows for adequate coverage and good service to support the potential increase in traffic. This work's main objective is to manage the optimization, planning, and sizing techniques of a 4G network. This study is based on experimental data of the different parameters (PDSCH Modulation; BLER (Block Error Rate).
{"title":"Evaluation of 4G / LTE mobile network performances based on experimental data","authors":"M. Ayad, Smail Medjedoub, Benziane Mourad, K. Saoudi, Abderrazak Arabi","doi":"10.1109/IHSH51661.2021.9378732","DOIUrl":"https://doi.org/10.1109/IHSH51661.2021.9378732","url":null,"abstract":"With the development of different generation of mobile networks, the mobile telecommunications networks have known expanded growth. These networks have admitted the integration of new services. This rapid evolution has led operators to adapt their planning methods to new technologies that increase the network's complexity. The planning phase corresponds to ensure the best radio coverage, compatibility with existing networks, management of the handover, the anticipation of interference, cell size, and supported load. This will allows for adequate coverage and good service to support the potential increase in traffic. This work's main objective is to manage the optimization, planning, and sizing techniques of a 4G network. This study is based on experimental data of the different parameters (PDSCH Modulation; BLER (Block Error Rate).","PeriodicalId":127735,"journal":{"name":"2020 2nd International Workshop on Human-Centric Smart Environments for Health and Well-being (IHSH)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123881601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-02-09DOI: 10.1109/IHSH51661.2021.9378747
Hayat Haroun, A. R. Ghomari, Meriem Belkihel, Ahlem Embarek
In recent years, the state's interest in preventing occupational risk has placed companies under the obligation to improve risk management in OHS (Occupational Health and Safety). This research explores ontologies' potential to solve data heterogeneity (risks, accidents, occupational diseases, preventive and corrective measures) in the OHS field. The paper presents an ontology-driven approach for OHS exploiting an ontology reuse methodology adapted to the SMT Company, a Sonelgaz Group subsidiary. We also provide SMT managers with an integrated application for better decision-making in occupational health.
{"title":"An ontology-driven approach for OHS, SMT Case","authors":"Hayat Haroun, A. R. Ghomari, Meriem Belkihel, Ahlem Embarek","doi":"10.1109/IHSH51661.2021.9378747","DOIUrl":"https://doi.org/10.1109/IHSH51661.2021.9378747","url":null,"abstract":"In recent years, the state's interest in preventing occupational risk has placed companies under the obligation to improve risk management in OHS (Occupational Health and Safety). This research explores ontologies' potential to solve data heterogeneity (risks, accidents, occupational diseases, preventive and corrective measures) in the OHS field. The paper presents an ontology-driven approach for OHS exploiting an ontology reuse methodology adapted to the SMT Company, a Sonelgaz Group subsidiary. We also provide SMT managers with an integrated application for better decision-making in occupational health.","PeriodicalId":127735,"journal":{"name":"2020 2nd International Workshop on Human-Centric Smart Environments for Health and Well-being (IHSH)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120951226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-02-09DOI: 10.1109/IHSH51661.2021.9378711
Selma Yahia, Yassine Meraihi, Asma Benmessaoud Gabis, A. Ramdane-Cherif
In this paper, we investigate the performance of the multi-directional vehicle-to-vehicle (V2V) visible light communication (VLC) system by deploying the angle diversity technology. We consider a road with a multi-lanes configuration where multiple cars utilize their headlights to transmit the signals to a receiving car. Such car uses an angle diversity receiver consisting of three photodetectors (PDs) and oriented in different directions. The effect of the field-of-view angle (FoV) of the PD same as the semi-half angle of the transmitter on the received signal-to-noise-ratio (SNR) are investigated. We also investigate the impact of higher data rates on the system performance. The results show that the system can achieve an SNR higher than 13.6 dB at a transmission distance of 50 m. Such SNR value is required to achieve a reliable communication system with bit error rate (BER) less than 10−3.
{"title":"Multi-Directional Vehicle-To-Vehicle Visible Light Communication With Angular Diversity Technology","authors":"Selma Yahia, Yassine Meraihi, Asma Benmessaoud Gabis, A. Ramdane-Cherif","doi":"10.1109/IHSH51661.2021.9378711","DOIUrl":"https://doi.org/10.1109/IHSH51661.2021.9378711","url":null,"abstract":"In this paper, we investigate the performance of the multi-directional vehicle-to-vehicle (V2V) visible light communication (VLC) system by deploying the angle diversity technology. We consider a road with a multi-lanes configuration where multiple cars utilize their headlights to transmit the signals to a receiving car. Such car uses an angle diversity receiver consisting of three photodetectors (PDs) and oriented in different directions. The effect of the field-of-view angle (FoV) of the PD same as the semi-half angle of the transmitter on the received signal-to-noise-ratio (SNR) are investigated. We also investigate the impact of higher data rates on the system performance. The results show that the system can achieve an SNR higher than 13.6 dB at a transmission distance of 50 m. Such SNR value is required to achieve a reliable communication system with bit error rate (BER) less than 10−3.","PeriodicalId":127735,"journal":{"name":"2020 2nd International Workshop on Human-Centric Smart Environments for Health and Well-being (IHSH)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124189748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-02-09DOI: 10.1109/IHSH51661.2021.9378730
Fatima Zahra Benyelles, Amel Sekkal, N. Settouti
Late 2019, the world witnessed a new devastating outbreak: coronavirus (COVID19) that attacks the human lungs and causes respiratory infections like pneumonia pathologies. This disease is spreading rapidly in the globe, causing multiple damages, even on the healthcare sector, economic and social sectors. In this article, we present a framework dedicated to epidemiologists for the investigation of the Patient 0 infected and establish the propagation path in different areas of the country. A Content Based Medical Image Retrieval system is proposed based on the Stacked Auto-encoders for the recognition of the disease characteristics in medical images. Our model search target COVID Chest X-Ray and CT images using similarity measurements learned through an image database of different pathologies as SARS and other viral or bacterial species of pneumonia diseases.
{"title":"Content Based COVID-19 Chest X-Ray and CT Images Retrieval framework using Stacked Auto-Encoders","authors":"Fatima Zahra Benyelles, Amel Sekkal, N. Settouti","doi":"10.1109/IHSH51661.2021.9378730","DOIUrl":"https://doi.org/10.1109/IHSH51661.2021.9378730","url":null,"abstract":"Late 2019, the world witnessed a new devastating outbreak: coronavirus (COVID19) that attacks the human lungs and causes respiratory infections like pneumonia pathologies. This disease is spreading rapidly in the globe, causing multiple damages, even on the healthcare sector, economic and social sectors. In this article, we present a framework dedicated to epidemiologists for the investigation of the Patient 0 infected and establish the propagation path in different areas of the country. A Content Based Medical Image Retrieval system is proposed based on the Stacked Auto-encoders for the recognition of the disease characteristics in medical images. Our model search target COVID Chest X-Ray and CT images using similarity measurements learned through an image database of different pathologies as SARS and other viral or bacterial species of pneumonia diseases.","PeriodicalId":127735,"journal":{"name":"2020 2nd International Workshop on Human-Centric Smart Environments for Health and Well-being (IHSH)","volume":"42 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115874251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-02-09DOI: 10.1109/IHSH51661.2021.9378723
Kenza Hocini, M. Yazid
The technique of Full-Duplex is a promising technology for IEEE 802.11ax next generation of high-density wireless networks. It allows to send and receive data frames simultaneously on the same radio frequencies by using specific radio antennas named SIC (Self-Interference Cancellation). However, the imbalance between the lengths of Down-Link (DL) and Up-Link (UL) data streams impedes an effective use of this transmission technique, since an empty time interval is known as Opportunity Window (OW) is generated at the end of UL data stream and it lasts until the end of DL transmission. The aim of this paper is to extend the operation rules of the In-Frame Querying protocol, in order to bring modifications to fully take advantage of the Full-Duplex radio communications. The basic principle of the extended Full-Duplex MAC protocol is finding the candidate stations that will use the opportunity window with a minimum of overhead through a deterministic method. The simulation results show that the new version of In-Frame Querying protocol provides better performance, especially when the network is dense or the traffic from the access point is heavy.
{"title":"Towards a Full-Duplex MAC protocol efficiently handling the imbalance between the lengths of data streams in High-Efficiency WLANs","authors":"Kenza Hocini, M. Yazid","doi":"10.1109/IHSH51661.2021.9378723","DOIUrl":"https://doi.org/10.1109/IHSH51661.2021.9378723","url":null,"abstract":"The technique of Full-Duplex is a promising technology for IEEE 802.11ax next generation of high-density wireless networks. It allows to send and receive data frames simultaneously on the same radio frequencies by using specific radio antennas named SIC (Self-Interference Cancellation). However, the imbalance between the lengths of Down-Link (DL) and Up-Link (UL) data streams impedes an effective use of this transmission technique, since an empty time interval is known as Opportunity Window (OW) is generated at the end of UL data stream and it lasts until the end of DL transmission. The aim of this paper is to extend the operation rules of the In-Frame Querying protocol, in order to bring modifications to fully take advantage of the Full-Duplex radio communications. The basic principle of the extended Full-Duplex MAC protocol is finding the candidate stations that will use the opportunity window with a minimum of overhead through a deterministic method. The simulation results show that the new version of In-Frame Querying protocol provides better performance, especially when the network is dense or the traffic from the access point is heavy.","PeriodicalId":127735,"journal":{"name":"2020 2nd International Workshop on Human-Centric Smart Environments for Health and Well-being (IHSH)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133664388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-02-09DOI: 10.1109/IHSH51661.2021.9378754
Abdelmoula Saggai, Samir Zeghlache, L. Benyettou, A. Djerioui
Fault-tolerant control (FTC) has earned increasing interest in the last few years for its reliability. A fault tolerant control system for operating a quadrotor aircraft in the presence of actuator faults and external disturbances is proposed in this paper. Firstly, the dynamic model of the quadrotor and types of actuator faults are presented. Secondly, an interval type-2- fuzzy sliding mode control (IT2FSMC) is proposed to stabilize the quadrotor if actuator faults occur. Compared to conventional sliding mode control (SMC), The results obtained confirm the validity and capabilities of the proposed FTC. Thirdly, by using the Lyapunov theory, asymptotic stability is confirmed. The efficiency of the proposed FTC is clarified by simulation results.
{"title":"Fault Tolerant Control against Actuator Faults Based on Interval Type-2 Fuzzy Sliding Mode Controller for a Quadrotor Aircraft","authors":"Abdelmoula Saggai, Samir Zeghlache, L. Benyettou, A. Djerioui","doi":"10.1109/IHSH51661.2021.9378754","DOIUrl":"https://doi.org/10.1109/IHSH51661.2021.9378754","url":null,"abstract":"Fault-tolerant control (FTC) has earned increasing interest in the last few years for its reliability. A fault tolerant control system for operating a quadrotor aircraft in the presence of actuator faults and external disturbances is proposed in this paper. Firstly, the dynamic model of the quadrotor and types of actuator faults are presented. Secondly, an interval type-2- fuzzy sliding mode control (IT2FSMC) is proposed to stabilize the quadrotor if actuator faults occur. Compared to conventional sliding mode control (SMC), The results obtained confirm the validity and capabilities of the proposed FTC. Thirdly, by using the Lyapunov theory, asymptotic stability is confirmed. The efficiency of the proposed FTC is clarified by simulation results.","PeriodicalId":127735,"journal":{"name":"2020 2nd International Workshop on Human-Centric Smart Environments for Health and Well-being (IHSH)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116249454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-02-09DOI: 10.1109/IHSH51661.2021.9378740
Imene Mezenner, Samia Bouyakoub, F. M. Bouyakoub
The adoption of the Web of Things (WoT) has revolutionized the medical sector by giving rise to a number of easy-to-use solutions. In this context, improving remote patient health monitoring in a hospital is a recurring consideration, due to various difficulties encountered by medical staff during the performance of their duties, such as heavy workload, manual input of patient data, delays in treatments or interventions, and possible human errors (diagnostic, dosage, etc.). For this matter, we propose a platform that allows to permanently monitor the vital signs of hospitalized patients using sensors. Automatic intervention scenarios are developed to provide the necessary treatment to the patient remotely. In case of life-threatening circumstances, the medical staff is alerted by receiving notifications summarizing the patient's condition. Based on a service-oriented architecture (SOA), the successful sequencing of these functionalities depends on the composition of the different Web services exposed by the smart things connected to the Web.
{"title":"Towards a Web of Things-based system for a smart hospital","authors":"Imene Mezenner, Samia Bouyakoub, F. M. Bouyakoub","doi":"10.1109/IHSH51661.2021.9378740","DOIUrl":"https://doi.org/10.1109/IHSH51661.2021.9378740","url":null,"abstract":"The adoption of the Web of Things (WoT) has revolutionized the medical sector by giving rise to a number of easy-to-use solutions. In this context, improving remote patient health monitoring in a hospital is a recurring consideration, due to various difficulties encountered by medical staff during the performance of their duties, such as heavy workload, manual input of patient data, delays in treatments or interventions, and possible human errors (diagnostic, dosage, etc.). For this matter, we propose a platform that allows to permanently monitor the vital signs of hospitalized patients using sensors. Automatic intervention scenarios are developed to provide the necessary treatment to the patient remotely. In case of life-threatening circumstances, the medical staff is alerted by receiving notifications summarizing the patient's condition. Based on a service-oriented architecture (SOA), the successful sequencing of these functionalities depends on the composition of the different Web services exposed by the smart things connected to the Web.","PeriodicalId":127735,"journal":{"name":"2020 2nd International Workshop on Human-Centric Smart Environments for Health and Well-being (IHSH)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123207899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-02-09DOI: 10.1109/IHSH51661.2021.9378727
Djilali Moussaoui, B. Kadri, M. Feham, Boucif Ammar Bensaber
Among the important challenges for Vehicular Adhoc Network (VANET) Security and Privacy. Most of the solutions for privacy in vanet are based on pseudonyms. And the pseudonyms are digital certificates with very limited information, valid for a short time, and hide the identity of the vehicle. The pseudonym operations (issuing, changing, and revoking) are centralized by a certification authority. In our paper, we propose a fully distributed management for pseudonyms in VANETs. We use the blockchain technology to perform the different operations related to pseudonyms. Our proposal use two blockchains, one for registering pseudonyms, the second for revoked ones. The vehicles are considered as miners in the blockchain. Our approach makes the vehicles in VANET more autonomous in managing the security, and reduce the exchanged data with a centralized authority (Certificate Authority-CA)
{"title":"A Distributed Blockchain Based PKI (BCPKI) architecture to enhance privacy in VANET","authors":"Djilali Moussaoui, B. Kadri, M. Feham, Boucif Ammar Bensaber","doi":"10.1109/IHSH51661.2021.9378727","DOIUrl":"https://doi.org/10.1109/IHSH51661.2021.9378727","url":null,"abstract":"Among the important challenges for Vehicular Adhoc Network (VANET) Security and Privacy. Most of the solutions for privacy in vanet are based on pseudonyms. And the pseudonyms are digital certificates with very limited information, valid for a short time, and hide the identity of the vehicle. The pseudonym operations (issuing, changing, and revoking) are centralized by a certification authority. In our paper, we propose a fully distributed management for pseudonyms in VANETs. We use the blockchain technology to perform the different operations related to pseudonyms. Our proposal use two blockchains, one for registering pseudonyms, the second for revoked ones. The vehicles are considered as miners in the blockchain. Our approach makes the vehicles in VANET more autonomous in managing the security, and reduce the exchanged data with a centralized authority (Certificate Authority-CA)","PeriodicalId":127735,"journal":{"name":"2020 2nd International Workshop on Human-Centric Smart Environments for Health and Well-being (IHSH)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124465347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-02-09DOI: 10.1109/IHSH51661.2021.9378712
Benzekri Azzouz, Belaidi Hadjira
The paper aims to address the design, simulation and implementation processes of a fuzzy logic controller to regulate in real-time the speed of an armature-controlled DC motor using hardware/software codesign methodology. A fuzzy logic control law and a digital pulse width modulation (DPWM) technique are used as a computational solution, while the implementation is carried on a reconfigurable computing hardware platform. The computationally intensive tasks are implemented as custom hardware accelerators using VHDL, while data flow and data control are implemented in software using the system-on-programmable-chip (SoPC) approach. Computer simulation results show the effectiveness and merit of this design flow. In addition, the real-time applicability of this heterogeneous controller is exemplified on an armature-controlled DC motor platform.
{"title":"Hardware/Software Codesign for Intelligent Motor Drive on an FPGA","authors":"Benzekri Azzouz, Belaidi Hadjira","doi":"10.1109/IHSH51661.2021.9378712","DOIUrl":"https://doi.org/10.1109/IHSH51661.2021.9378712","url":null,"abstract":"The paper aims to address the design, simulation and implementation processes of a fuzzy logic controller to regulate in real-time the speed of an armature-controlled DC motor using hardware/software codesign methodology. A fuzzy logic control law and a digital pulse width modulation (DPWM) technique are used as a computational solution, while the implementation is carried on a reconfigurable computing hardware platform. The computationally intensive tasks are implemented as custom hardware accelerators using VHDL, while data flow and data control are implemented in software using the system-on-programmable-chip (SoPC) approach. Computer simulation results show the effectiveness and merit of this design flow. In addition, the real-time applicability of this heterogeneous controller is exemplified on an armature-controlled DC motor platform.","PeriodicalId":127735,"journal":{"name":"2020 2nd International Workshop on Human-Centric Smart Environments for Health and Well-being (IHSH)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123466156","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-02-09DOI: 10.1109/IHSH51661.2021.9378721
Abid Saber, Moncef Abbas, B. Fergani
The rapid increase and expansion of cyber-attacks requires the development of new quality tools to reduce, combat, and eventually stop their risks. In this context, an Intrusion Prevention Systems (IPS) is introduced. It is an extended IDS solutions network security technology characterized by adding the ability to block threats and detect vulnerabilities exploits. Unlike its predecessor, the IPS is placed as an inline security component where it actively processes via analyzing and taking automated actions on all traffic flows that enter the network. Needless to say, speed and efficiency are a necessity in the IPS to avoid degrading network performance. On one hand, signature-based detection and statistical anomaly-based detection, two dominant detection methods mechanisms, are responsible for finding exploits whenever statistical features are extracted to characterize network traffic flows. The computation cost of the classifier, therefore, will be overlarge. On the other hand, the feature selection problem, a critical component in reducing features and improving overall classification accuracy, is about a highly complex NP-hard problem in a Data science. In this paper, a novel intrusion detection system is proposed. It is a double-action system with meta-classifier based feature selection as well as an ensemble learning meta-classifier for stacking via cross-validation to prevent overfitting. Therefore, a better subset of informative features for each type of attacks was selected rather than the features common to all attacks. Finally, this work, through the several experiments, demonstrates that our proposed model not only reaches high detection rates and significantly reduces false alarms, but also accelerates the learning and the testing process thereby directly contributing to the overall ability to work in online mode and scalability.
{"title":"Two-dimensional Intrusion Detection System: A New Feature Selection Technique","authors":"Abid Saber, Moncef Abbas, B. Fergani","doi":"10.1109/IHSH51661.2021.9378721","DOIUrl":"https://doi.org/10.1109/IHSH51661.2021.9378721","url":null,"abstract":"The rapid increase and expansion of cyber-attacks requires the development of new quality tools to reduce, combat, and eventually stop their risks. In this context, an Intrusion Prevention Systems (IPS) is introduced. It is an extended IDS solutions network security technology characterized by adding the ability to block threats and detect vulnerabilities exploits. Unlike its predecessor, the IPS is placed as an inline security component where it actively processes via analyzing and taking automated actions on all traffic flows that enter the network. Needless to say, speed and efficiency are a necessity in the IPS to avoid degrading network performance. On one hand, signature-based detection and statistical anomaly-based detection, two dominant detection methods mechanisms, are responsible for finding exploits whenever statistical features are extracted to characterize network traffic flows. The computation cost of the classifier, therefore, will be overlarge. On the other hand, the feature selection problem, a critical component in reducing features and improving overall classification accuracy, is about a highly complex NP-hard problem in a Data science. In this paper, a novel intrusion detection system is proposed. It is a double-action system with meta-classifier based feature selection as well as an ensemble learning meta-classifier for stacking via cross-validation to prevent overfitting. Therefore, a better subset of informative features for each type of attacks was selected rather than the features common to all attacks. Finally, this work, through the several experiments, demonstrates that our proposed model not only reaches high detection rates and significantly reduces false alarms, but also accelerates the learning and the testing process thereby directly contributing to the overall ability to work in online mode and scalability.","PeriodicalId":127735,"journal":{"name":"2020 2nd International Workshop on Human-Centric Smart Environments for Health and Well-being (IHSH)","volume":"191 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121730595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：