Pub Date : 2019-10-01DOI: 10.1109/ICSSD47982.2019.9002771
S. Nasih, Sara Arezki, T. Gadi
Due to its wide involvement in different fields: industry, maritime industry, trade, supply chain management has been greatly expanded to cover a large and complex network of stakeholders in the production and distribution process. The multitude of intermediaries in this process leads difficulties in communication, control, time saving… In this paper, we propose the Blockchain technology as a solution for decentralization and disintermediation of operations in the supply chain, and its effect on the maritime industry.
{"title":"Enhancement of supply chain management by integrating Blockchain technology","authors":"S. Nasih, Sara Arezki, T. Gadi","doi":"10.1109/ICSSD47982.2019.9002771","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9002771","url":null,"abstract":"Due to its wide involvement in different fields: industry, maritime industry, trade, supply chain management has been greatly expanded to cover a large and complex network of stakeholders in the production and distribution process. The multitude of intermediaries in this process leads difficulties in communication, control, time saving… In this paper, we propose the Blockchain technology as a solution for decentralization and disintermediation of operations in the supply chain, and its effect on the maritime industry.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"193 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115729331","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 : 2019-10-01DOI: 10.1109/ICSSD47982.2019.9002846
Mimoun Lamrini, M. Chkouri
Data visualization has a crucial role in understanding and processing voluminous data (i.e., Big Data) and subsequently has become more important with the coincidence of the exponential growth of data analysis need.The problem of high-dimensional data visualization in a data processing software interface cannot be entirely displayed, in consideration that once the data size exceeds two-dimension, it cannot be projected into a two-dimension interface. Furthermore, the rough analysis and evaluation of high-dimensional data become considerably ambiguous, thus, making a precise decision on that data cannot be achieved. In order to overcome this anomaly, resorting to data dimensionality reduction is a plausible solution.In this paper, the integration of Principal Component Analysis (PCA) combined with the Matrix by Block Decomposition (MBD) method(A.K.A block segmentation). According to the literature, the MBD method turned out quite efficient in data segmentation, wherein a huge data can be divided into regular blocks. By doing so, it becomes easier to access and visualize a given part of data. In order to further enhance the visualization understanding, K-means segmentation has been integrated in our proposed algorithm.In our study, we took into account other data dimensionality reduction techniques such as Linear Discriminant Analysis (LDA), Multi-Dimensional Scaling(MDS).
{"title":"Decomposition and Visualization of High-Dimensional Data in a Two Dimensional Interface","authors":"Mimoun Lamrini, M. Chkouri","doi":"10.1109/ICSSD47982.2019.9002846","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9002846","url":null,"abstract":"Data visualization has a crucial role in understanding and processing voluminous data (i.e., Big Data) and subsequently has become more important with the coincidence of the exponential growth of data analysis need.The problem of high-dimensional data visualization in a data processing software interface cannot be entirely displayed, in consideration that once the data size exceeds two-dimension, it cannot be projected into a two-dimension interface. Furthermore, the rough analysis and evaluation of high-dimensional data become considerably ambiguous, thus, making a precise decision on that data cannot be achieved. In order to overcome this anomaly, resorting to data dimensionality reduction is a plausible solution.In this paper, the integration of Principal Component Analysis (PCA) combined with the Matrix by Block Decomposition (MBD) method(A.K.A block segmentation). According to the literature, the MBD method turned out quite efficient in data segmentation, wherein a huge data can be divided into regular blocks. By doing so, it becomes easier to access and visualize a given part of data. In order to further enhance the visualization understanding, K-means segmentation has been integrated in our proposed algorithm.In our study, we took into account other data dimensionality reduction techniques such as Linear Discriminant Analysis (LDA), Multi-Dimensional Scaling(MDS).","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114846805","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 : 2019-10-01DOI: 10.1109/ICSSD47982.2019.9003119
Said Ouiazzane, M. Addou, Fatimazahra Barramou
The objective of this paper is to propose a distributed intrusion detection model based on a multi agent system. Mutli Agent Systems (MAS) are very suitable for intrusion detection systems as they meet the characteristics required by the networks and Big Data issues. The MAS agents cooperate and communicate with each other to ensure the effective detection of network intrusions without the intervention of an expert as used to be in the classical intrusion detection systems relying on signature matching to detect known attacks. The proposed model helped to detect known and unknown attacks within big computer infrastructure by responding to the network requirements in terms of distribution, autonomy, responsiveness and communication. The proposed model is capable of achieving a good and a real time intrusion detection using multi-agents paradigm and Hadoop Distributed File System (HDFS).
{"title":"A Multi-Agent Model for Network Intrusion Detection","authors":"Said Ouiazzane, M. Addou, Fatimazahra Barramou","doi":"10.1109/ICSSD47982.2019.9003119","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9003119","url":null,"abstract":"The objective of this paper is to propose a distributed intrusion detection model based on a multi agent system. Mutli Agent Systems (MAS) are very suitable for intrusion detection systems as they meet the characteristics required by the networks and Big Data issues. The MAS agents cooperate and communicate with each other to ensure the effective detection of network intrusions without the intervention of an expert as used to be in the classical intrusion detection systems relying on signature matching to detect known attacks. The proposed model helped to detect known and unknown attacks within big computer infrastructure by responding to the network requirements in terms of distribution, autonomy, responsiveness and communication. The proposed model is capable of achieving a good and a real time intrusion detection using multi-agents paradigm and Hadoop Distributed File System (HDFS).","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129650613","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 : 2019-10-01DOI: 10.1109/ICSSD47982.2019.9003171
Oumaima Hourrane, Nouhaila Idrissi, E. Benlahmar
Sentiment classification is one of the new absorbing parts appeared in natural language processing with the emergence of community sites on the web. Taking advantage of the amount of information now available, research and industry have been seeking ways to automatically analyze the sentiments expressed in texts. The challenge for this task is the human language ambiguity, and also the lack of labeled data. In order to solve this issue, Deep learning models appeared to be effective due to their automatic learning capability. In this paper, we provide a comparative study on IMDB movie review dataset, we compare word embeddings methods and further deep learning models on sentiment analysis and give broad empirical outcomes for those keen on taking advantage of deep learning for sentiment analysis in real-world settings.
{"title":"An Empirical Study of Deep Neural Networks Models for Sentiment Classification on Movie Reviews","authors":"Oumaima Hourrane, Nouhaila Idrissi, E. Benlahmar","doi":"10.1109/ICSSD47982.2019.9003171","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9003171","url":null,"abstract":"Sentiment classification is one of the new absorbing parts appeared in natural language processing with the emergence of community sites on the web. Taking advantage of the amount of information now available, research and industry have been seeking ways to automatically analyze the sentiments expressed in texts. The challenge for this task is the human language ambiguity, and also the lack of labeled data. In order to solve this issue, Deep learning models appeared to be effective due to their automatic learning capability. In this paper, we provide a comparative study on IMDB movie review dataset, we compare word embeddings methods and further deep learning models on sentiment analysis and give broad empirical outcomes for those keen on taking advantage of deep learning for sentiment analysis in real-world settings.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125325322","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 : 2019-10-01DOI: 10.1109/ICSSD47982.2019.9002902
O. El Idrissi, Abdellatif Mezrioui, A. Belmekki
Industrial Control Systems (ICS) are currently integrated into critical infrastructures and are designed to support industrial processes, monitor and control in real time a large number of processes and operations such as gas and electricity distribution (conventional and nuclear), water treatment, etc. ICSs have evolved significantly in recent years and have embraced new technologies such as IoT and have been made accessible through the Internet to allow remote access to administrators, service providers, etc. The aim of this paper is to illustrate, through the use of EBIOS risk analysis method that such infrastructures are subject to vulnerabilities, overwhelming threats and potentials risks. The paper also proposes a number of recommendations and organizational and technological security measures to reduce these risks to an acceptable level and to decrease both their impacts and potentialities.
{"title":"A lightweight risk analysis of a critical infrastructure based ICSs","authors":"O. El Idrissi, Abdellatif Mezrioui, A. Belmekki","doi":"10.1109/ICSSD47982.2019.9002902","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9002902","url":null,"abstract":"Industrial Control Systems (ICS) are currently integrated into critical infrastructures and are designed to support industrial processes, monitor and control in real time a large number of processes and operations such as gas and electricity distribution (conventional and nuclear), water treatment, etc. ICSs have evolved significantly in recent years and have embraced new technologies such as IoT and have been made accessible through the Internet to allow remote access to administrators, service providers, etc. The aim of this paper is to illustrate, through the use of EBIOS risk analysis method that such infrastructures are subject to vulnerabilities, overwhelming threats and potentials risks. The paper also proposes a number of recommendations and organizational and technological security measures to reduce these risks to an acceptable level and to decrease both their impacts and potentialities.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116116527","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 : 2019-10-01DOI: 10.1109/ICSSD47982.2019.9002676
Mdarbi Fatima Ezzahra, Afifi Nadia, Hilal Imane
Big Data is a very large data set, its analysis exceeds the capabilities of traditional database management systems. Big Data is linked to the need for large computing and storage capacity.Big Data dependability is one of the major concerns of organizations. It reflects the confidence that can be placed in these data. Nowadays, companies find a major interest in Big Data, but dependability challenge remains a major obstacle.In this article, we present different works that have addressed Big Data dependability aspects. This study highlights new opportunities in this field as well as different challenges.
{"title":"Big Data Dependability Opportunities & Challenges","authors":"Mdarbi Fatima Ezzahra, Afifi Nadia, Hilal Imane","doi":"10.1109/ICSSD47982.2019.9002676","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9002676","url":null,"abstract":"Big Data is a very large data set, its analysis exceeds the capabilities of traditional database management systems. Big Data is linked to the need for large computing and storage capacity.Big Data dependability is one of the major concerns of organizations. It reflects the confidence that can be placed in these data. Nowadays, companies find a major interest in Big Data, but dependability challenge remains a major obstacle.In this article, we present different works that have addressed Big Data dependability aspects. This study highlights new opportunities in this field as well as different challenges.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132734198","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 : 2019-10-01DOI: 10.1109/ICSSD47982.2019.9003149
Nouhaila Idrissi, Oumaima Hourrane, A. Zellou, E. Benlahmar
With the explosive growth of the Internet and the Web, assisting users and facilitate their access to resources that might be of their interest and that are adapted to their personal needs is a tedious task. Efficient management of large amounts of information becomes an increasingly significant challenge. Hence, recommender systems have proved, in recent years, to be a valuable asset to dealing with the problem of information overload by assisting the users and providing them with more effective access to information. To this end, these systems must be able to predict users’ interests based on their prior feedback. However, sparsity issues arise when necessary transactional information is not available for inferring users and items similarities, which deteriorate the quality and accuracy of the recommender system. To fill these gaps, we propose in this paper a Restricted Boltzmann Machine-based model to learn hidden factors and reconstruct sparse input rating data. Experimental results show that our proposed approach can effectively deal with data sparsity in MovieLens dataset, containing a massive amount of scarce information.
{"title":"A Restricted Boltzmann Machine-based Recommender System For Alleviating Sparsity Issues","authors":"Nouhaila Idrissi, Oumaima Hourrane, A. Zellou, E. Benlahmar","doi":"10.1109/ICSSD47982.2019.9003149","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9003149","url":null,"abstract":"With the explosive growth of the Internet and the Web, assisting users and facilitate their access to resources that might be of their interest and that are adapted to their personal needs is a tedious task. Efficient management of large amounts of information becomes an increasingly significant challenge. Hence, recommender systems have proved, in recent years, to be a valuable asset to dealing with the problem of information overload by assisting the users and providing them with more effective access to information. To this end, these systems must be able to predict users’ interests based on their prior feedback. However, sparsity issues arise when necessary transactional information is not available for inferring users and items similarities, which deteriorate the quality and accuracy of the recommender system. To fill these gaps, we propose in this paper a Restricted Boltzmann Machine-based model to learn hidden factors and reconstruct sparse input rating data. Experimental results show that our proposed approach can effectively deal with data sparsity in MovieLens dataset, containing a massive amount of scarce information.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124669331","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 : 2019-10-01DOI: 10.1109/icssd47982.2019.9002832
{"title":"ICSSD 2019 Committees","authors":"","doi":"10.1109/icssd47982.2019.9002832","DOIUrl":"https://doi.org/10.1109/icssd47982.2019.9002832","url":null,"abstract":"","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121838923","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 : 2019-10-01DOI: 10.1109/ICSSD47982.2019.9003014
M. Atify, M. Bennani, A. Abouabdellah
In this paper, we studied the motion of a hexapod robot taking into account its dynamics in Matlab’s SimMechanics. The software allows visualizing the moving system in Mechanics Explorers of Matlab with the possibility to measure many interesting physical terms. The kinematics and dynamics of the hexapod robot is well defined in the SimMechanics software as well as the functional schemes. We can thus connect them with the joints data elaborated from the kinematics modeling. This a powerful tool to have a deeper view in the dynamic behavior of the propelling motion of the hexapod robot. Therefore, we have been particularly interested in joint torques in response to specific propelling motion. This task was well established and validated by simulation. So, we can use all this information in the control process of the robot, a task that was too complex with the analytical approach.
{"title":"Propelling motion modeling of an Hexapod robot","authors":"M. Atify, M. Bennani, A. Abouabdellah","doi":"10.1109/ICSSD47982.2019.9003014","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9003014","url":null,"abstract":"In this paper, we studied the motion of a hexapod robot taking into account its dynamics in Matlab’s SimMechanics. The software allows visualizing the moving system in Mechanics Explorers of Matlab with the possibility to measure many interesting physical terms. The kinematics and dynamics of the hexapod robot is well defined in the SimMechanics software as well as the functional schemes. We can thus connect them with the joints data elaborated from the kinematics modeling. This a powerful tool to have a deeper view in the dynamic behavior of the propelling motion of the hexapod robot. Therefore, we have been particularly interested in joint torques in response to specific propelling motion. This task was well established and validated by simulation. So, we can use all this information in the control process of the robot, a task that was too complex with the analytical approach.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125572575","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 : 2019-10-01DOI: 10.1109/ICSSD47982.2019.9002827
I. Lafram, N. Berbiche, Jamila El Alami
Information systems are becoming more and more complex and closely linked. These systems are encountering an enormous amount of nefarious traffic while ensuring real - time connectivity. Therefore, a defense method needs to be in place. One of the commonly used tools for network security is intrusion detection systems (IDS). An IDS tries to identify fraudulent activity using predetermined signatures or pre-established user misbehavior while monitoring incoming traffic. Intrusion detection systems based on signature and behavior cannot detect new attacks and fall when small behavior deviations occur. Many researchers have proposed various approaches to intrusion detection using machine learning techniques as a new and promising tool to remedy this problem. In this paper, the authors present a combination of two machine learning methods, unsupervised clustering followed by a supervised classification framework as a Fast, highly scalable and precise packets classification system. This model’s performance is assessed on the new proposed dataset by the Canadian Institute for Cyber security and the University of New Brunswick (CICIDS2017). The overall process was fast, showing high accuracy classification results.
{"title":"Artificial Neural Networks Optimized with Unsupervised Clustering for IDS Classification","authors":"I. Lafram, N. Berbiche, Jamila El Alami","doi":"10.1109/ICSSD47982.2019.9002827","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9002827","url":null,"abstract":"Information systems are becoming more and more complex and closely linked. These systems are encountering an enormous amount of nefarious traffic while ensuring real - time connectivity. Therefore, a defense method needs to be in place. One of the commonly used tools for network security is intrusion detection systems (IDS). An IDS tries to identify fraudulent activity using predetermined signatures or pre-established user misbehavior while monitoring incoming traffic. Intrusion detection systems based on signature and behavior cannot detect new attacks and fall when small behavior deviations occur. Many researchers have proposed various approaches to intrusion detection using machine learning techniques as a new and promising tool to remedy this problem. In this paper, the authors present a combination of two machine learning methods, unsupervised clustering followed by a supervised classification framework as a Fast, highly scalable and precise packets classification system. This model’s performance is assessed on the new proposed dataset by the Canadian Institute for Cyber security and the University of New Brunswick (CICIDS2017). The overall process was fast, showing high accuracy classification results.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116441158","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：