Pub Date : 2021-12-15DOI: 10.1109/ICTAACS53298.2021.9715227
Yassamine Lala Bouali, Isra Boucetta, I. E. I. Bekkouch, Mourad Bouache, S. Mazouzi
Lung diseases are part of several fatal illnesses. Although there are advances in the healthcare domain, some of them still top the list of worldwide mortal diseases. This paper analyzes how X-ray images, processed according to Artificial Intelligence, can be used to assist medical physicians and radiologists in their diagnosis by automatic detection and classification of lung diseases. In this study, we present a new image dataset that consists of 1071 chest X-ray images with two common lung pathologies, i.e. pneumonia and tuberculosis. In addition, with the help of medical specialists, we manually provided each image with disease bounding boxes. We used the proposed dataset to train Deep Learning based object detection models to demonstrate that thoracic pathologies can be automatically detected, classified and most importantly, localized. Our results are promising and show that the proposed dataset allows training accurate lung disease detection models.
{"title":"An Image Dataset for Lung Disease Detection and Classification","authors":"Yassamine Lala Bouali, Isra Boucetta, I. E. I. Bekkouch, Mourad Bouache, S. Mazouzi","doi":"10.1109/ICTAACS53298.2021.9715227","DOIUrl":"https://doi.org/10.1109/ICTAACS53298.2021.9715227","url":null,"abstract":"Lung diseases are part of several fatal illnesses. Although there are advances in the healthcare domain, some of them still top the list of worldwide mortal diseases. This paper analyzes how X-ray images, processed according to Artificial Intelligence, can be used to assist medical physicians and radiologists in their diagnosis by automatic detection and classification of lung diseases. In this study, we present a new image dataset that consists of 1071 chest X-ray images with two common lung pathologies, i.e. pneumonia and tuberculosis. In addition, with the help of medical specialists, we manually provided each image with disease bounding boxes. We used the proposed dataset to train Deep Learning based object detection models to demonstrate that thoracic pathologies can be automatically detected, classified and most importantly, localized. Our results are promising and show that the proposed dataset allows training accurate lung disease detection models.","PeriodicalId":284572,"journal":{"name":"2021 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128899847","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 : 2021-12-15DOI: 10.1109/ICTAACS53298.2021.9715203
Cherif Benali, R. Maamri
with the rapid development in computing and networking capabilities, a new technology has been emerged known as internet of things (IoT). IoT is a giant network of connected and interacted devices, which collect data and send it using the internet. Today, IoT is playing important role in daily life; it adds intelligence to several domains, such as health care, smart homes and cities, and smart transportation.Nevertheless, several challenges are introduced by the new IoT system requirements, which cannot be adequately addressed by current models and architectures. Security and privacy present the main challenges of IoT, which are more important now than ever, due to the explosive growth of connected devices and the huge amount of generated data. All these challenges really should be taken in consideration. Good reference architecture is the main key to ensure security, privacy and many other emergent requirements, because it presents the functional view of IoT. So, IoT requires new architectures to address these new challenges and face these problems. Therefore, the aim of this paper is to suggest powerful architecture to build secure IoT system, and which guarantees the privacy of all its users. It tries to fulfill the new emergent requirements, and solve the previous challenges. In addition, it explains the role of each part to achieve a robust secure IoT system, and how it contributes in the integration of other technologies.
{"title":"Internet of Things: new Architecture to ensure Robustness, Security and Privacy of IoT Systems","authors":"Cherif Benali, R. Maamri","doi":"10.1109/ICTAACS53298.2021.9715203","DOIUrl":"https://doi.org/10.1109/ICTAACS53298.2021.9715203","url":null,"abstract":"with the rapid development in computing and networking capabilities, a new technology has been emerged known as internet of things (IoT). IoT is a giant network of connected and interacted devices, which collect data and send it using the internet. Today, IoT is playing important role in daily life; it adds intelligence to several domains, such as health care, smart homes and cities, and smart transportation.Nevertheless, several challenges are introduced by the new IoT system requirements, which cannot be adequately addressed by current models and architectures. Security and privacy present the main challenges of IoT, which are more important now than ever, due to the explosive growth of connected devices and the huge amount of generated data. All these challenges really should be taken in consideration. Good reference architecture is the main key to ensure security, privacy and many other emergent requirements, because it presents the functional view of IoT. So, IoT requires new architectures to address these new challenges and face these problems. Therefore, the aim of this paper is to suggest powerful architecture to build secure IoT system, and which guarantees the privacy of all its users. It tries to fulfill the new emergent requirements, and solve the previous challenges. In addition, it explains the role of each part to achieve a robust secure IoT system, and how it contributes in the integration of other technologies.","PeriodicalId":284572,"journal":{"name":"2021 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130414878","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 : 2021-12-15DOI: 10.1109/ICTAACS53298.2021.9715214
Ismail Bouacha, Safia Bekhouche
A recommender system aims to satisfy its users by offering them relevant items (films, books, products, etc). This is done by comparing the items deemed satisfactory by the user with all of the items (content-based filtering), or by searching for similar users (collaborative filtering). We propose a genetic based approach to recommend relevant items without needing an explicit request from the user. Our approach looks for the most similar users using a genetic algorithm. Then, a recommendation space is constructed by grouping the items preferred by each similar user, and removing those preferred by the active user. After that, the system predicts a rating for each unrated item. The recommendation space will be reduced by keeping only relevant items using a threshold. An experimental study has been made in comparison with KNN algorithm. Experimental results seem interesting and show an improvement in precision, recall and F-Measure. Also Mean Absolute Error (MAE) has been reduced.
{"title":"An Evolutionary Based Recommendation Approach","authors":"Ismail Bouacha, Safia Bekhouche","doi":"10.1109/ICTAACS53298.2021.9715214","DOIUrl":"https://doi.org/10.1109/ICTAACS53298.2021.9715214","url":null,"abstract":"A recommender system aims to satisfy its users by offering them relevant items (films, books, products, etc). This is done by comparing the items deemed satisfactory by the user with all of the items (content-based filtering), or by searching for similar users (collaborative filtering). We propose a genetic based approach to recommend relevant items without needing an explicit request from the user. Our approach looks for the most similar users using a genetic algorithm. Then, a recommendation space is constructed by grouping the items preferred by each similar user, and removing those preferred by the active user. After that, the system predicts a rating for each unrated item. The recommendation space will be reduced by keeping only relevant items using a threshold. An experimental study has been made in comparison with KNN algorithm. Experimental results seem interesting and show an improvement in precision, recall and F-Measure. Also Mean Absolute Error (MAE) has been reduced.","PeriodicalId":284572,"journal":{"name":"2021 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124714728","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 : 2021-12-15DOI: 10.1109/ICTAACS53298.2021.9715177
Djallel Hamouda, M. Ferrag, Nadjette Benhamida, Hamid Seridi
Industrial Internet of Things (IIoT) applies Internet of Things (IoT) technology in industrial systems, to optimize business processes efficiency, service quality, and reliability. However, with a large of isolated IoT networks deployed in various industries, many vulnerabilities have been exposed to security incidents and posed threats to IIoT security. An intrusion detection system (IDS) is a security monitoring mechanism that promotes cyber security solutions for information systems. The system’s role is to detect abnormal activities of intruders and enable preventive measures to avoid risks. However, applying a traditional IDS-based solution to IIoT is challenging due to its particular characteristics such as resource-constrained, data privacy, and heterogeneity. Researchers are using the new emerging technologies such as Fog/Edge computing, Machine Learning (ML), Deep Learning (DL) to deploy an effective and adaptive IDS for various IIoT operating environments. This study focus is on the development of IDS in particular industrial environments. To this end, we provide a systemic review that addresses IDS deployment strategies, detection approaches, and methodologies and data sources used for evaluation. We also present some suggestions and challenges to be considered when designing IDS-based security for Industrial IoT as future research.
工业物联网(Industrial Internet of Things, IIoT)是将物联网技术应用于工业系统中，以优化业务流程效率、服务质量和可靠性。然而，随着大量孤立的物联网网络部署在各个行业，许多漏洞暴露在安全事件中，对物联网安全构成威胁。入侵检测系统(IDS)是一种促进信息系统网络安全解决方案的安全监控机制。系统的作用是检测入侵者的异常活动，并启用预防措施以避免风险。然而，将传统的基于ids的解决方案应用于工业物联网是具有挑战性的，因为它具有资源约束、数据隐私和异构性等特殊特征。研究人员正在使用雾/边缘计算、机器学习(ML)、深度学习(DL)等新兴技术，为各种工业物联网操作环境部署有效且自适应的IDS。本研究的重点是IDS在特定工业环境中的发展。为此，我们提供了一个系统的审查，涉及IDS部署策略，检测方法，以及用于评估的方法和数据源。我们还提出了一些建议和挑战，在设计基于ids的工业物联网安全作为未来的研究时需要考虑。
{"title":"Intrusion Detection Systems for Industrial Internet of Things: A Survey","authors":"Djallel Hamouda, M. Ferrag, Nadjette Benhamida, Hamid Seridi","doi":"10.1109/ICTAACS53298.2021.9715177","DOIUrl":"https://doi.org/10.1109/ICTAACS53298.2021.9715177","url":null,"abstract":"Industrial Internet of Things (IIoT) applies Internet of Things (IoT) technology in industrial systems, to optimize business processes efficiency, service quality, and reliability. However, with a large of isolated IoT networks deployed in various industries, many vulnerabilities have been exposed to security incidents and posed threats to IIoT security. An intrusion detection system (IDS) is a security monitoring mechanism that promotes cyber security solutions for information systems. The system’s role is to detect abnormal activities of intruders and enable preventive measures to avoid risks. However, applying a traditional IDS-based solution to IIoT is challenging due to its particular characteristics such as resource-constrained, data privacy, and heterogeneity. Researchers are using the new emerging technologies such as Fog/Edge computing, Machine Learning (ML), Deep Learning (DL) to deploy an effective and adaptive IDS for various IIoT operating environments. This study focus is on the development of IDS in particular industrial environments. To this end, we provide a systemic review that addresses IDS deployment strategies, detection approaches, and methodologies and data sources used for evaluation. We also present some suggestions and challenges to be considered when designing IDS-based security for Industrial IoT as future research.","PeriodicalId":284572,"journal":{"name":"2021 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"14 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127842672","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 : 2021-12-15DOI: 10.1109/ICTAACS53298.2021.9715226
Roumaysa Bousselidj, Soufiane Boulehoueche
The Self-Switching Multi-Strategic Pedagogical Agent is designed following the Autonomic Computing and the Component-Based Agents approaches. It is comprised of two sub-components: Manager (MrSS) and Managed (MdSS) Sub-Systems. These sub-systems are built independently, but they constantly interact with one another. The Multiple Pedagogical Strategies (MPSs) that are used by the system are implemented by MdSS. While the Switching Logic (SL), that is used to (re)conFigure the MdSS, is implemented by the MrSS as an Autonomic Control Loop (ACL). The MPSs and the SL permit to trigger the appropriate PS regarding the crisp values of the Student Knowledge Level (SKL). However, the SKL is characterized by a high degree of uncertainty. To overcome this deficiency, we integrate fuzzy control in the MrSS to handle the uncertainty and consequently improve the strategy selection process. Fuzzy MrSS links the different context parameters and SKL through fuzzy rules taking into account the system’s fuzziness and uncertainties. We will present experiments carried with the Math sub-domain.
{"title":"Fuzzy Logic Based self-switching multi-strategic pedagogical agent","authors":"Roumaysa Bousselidj, Soufiane Boulehoueche","doi":"10.1109/ICTAACS53298.2021.9715226","DOIUrl":"https://doi.org/10.1109/ICTAACS53298.2021.9715226","url":null,"abstract":"The Self-Switching Multi-Strategic Pedagogical Agent is designed following the Autonomic Computing and the Component-Based Agents approaches. It is comprised of two sub-components: Manager (MrSS) and Managed (MdSS) Sub-Systems. These sub-systems are built independently, but they constantly interact with one another. The Multiple Pedagogical Strategies (MPSs) that are used by the system are implemented by MdSS. While the Switching Logic (SL), that is used to (re)conFigure the MdSS, is implemented by the MrSS as an Autonomic Control Loop (ACL). The MPSs and the SL permit to trigger the appropriate PS regarding the crisp values of the Student Knowledge Level (SKL). However, the SKL is characterized by a high degree of uncertainty. To overcome this deficiency, we integrate fuzzy control in the MrSS to handle the uncertainty and consequently improve the strategy selection process. Fuzzy MrSS links the different context parameters and SKL through fuzzy rules taking into account the system’s fuzziness and uncertainties. We will present experiments carried with the Math sub-domain.","PeriodicalId":284572,"journal":{"name":"2021 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"203 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121086777","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：