A. Badji, Youssou Dieng, I. Diop, P. Cissé, Boubacar Diouf
This article focuses on the study and optimization of the monitoring system for People Living with HIV (PLWHIV) in the cross-border area between the Gambia, Senegal and Guinea Bissau. Difficulties in adherence to treatment are accentuated, among other things, by the stigmatization of HIV patients and the high mobility of the population. These two situations and the absence of a reliable identification system for PLWHIV lead to restarting treatment for certain patients, which can cause resistance. This article presents the problem of automatic speaker recognition in the monitoring of PLWHA to avoid resumption of treatment and reduce the number of patients on ART lost to removing duplicates of patients in follow-up. From the technical point of view, we presented the problem of identification by speech. We proposed a state of the arts pretty full on art methodology s existing. We proposed a model with a first implementation allowing to make the first analyzes. We also presented a set of related works.
{"title":"Automatic Speaker Recognition (ASR): Application in the monitoring of PLHIV in the cross-border area between the Gambia, Guinea-Bissau and Senegal","authors":"A. Badji, Youssou Dieng, I. Diop, P. Cissé, Boubacar Diouf","doi":"10.1145/3447568.3448544","DOIUrl":"https://doi.org/10.1145/3447568.3448544","url":null,"abstract":"This article focuses on the study and optimization of the monitoring system for People Living with HIV (PLWHIV) in the cross-border area between the Gambia, Senegal and Guinea Bissau. Difficulties in adherence to treatment are accentuated, among other things, by the stigmatization of HIV patients and the high mobility of the population. These two situations and the absence of a reliable identification system for PLWHIV lead to restarting treatment for certain patients, which can cause resistance. This article presents the problem of automatic speaker recognition in the monitoring of PLWHA to avoid resumption of treatment and reduce the number of patients on ART lost to removing duplicates of patients in follow-up. From the technical point of view, we presented the problem of identification by speech. We proposed a state of the arts pretty full on art methodology s existing. We proposed a model with a first implementation allowing to make the first analyzes. We also presented a set of related works.","PeriodicalId":335307,"journal":{"name":"Proceedings of the 10th International Conference on Information Systems and Technologies","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127326631","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}
In recent decade's recommendation systems (RSs) plays an essential role in many applications as World Wide Web. Also recommendation system is one of the most important research area in machine learning. Recommendation system functions as a helper to find the interest of users by making relevant suggestions to users. The RSs mainly use four filtering methods to provide personalized recommendations to users, the most popular ones are: Collaborative filtering (CF), Content-based filtering, Demographic filtering and hybrid filtering. Data mining is one of the important analysis techniques used in RSs to predict user interest in information, products and services among the vast amount of available items. The data mining techniques that are most commonly used in RSs are: classification, clustering and association rule discovery. This paper performs a survey on recommendation systems, techniques, challenges and issues and lists some research papers solve these obstacles, also data mining methods used in recommender systems.
{"title":"Survey on Recommendation Systems","authors":"Sara Gasmi, T. Bouhadada, Abdelmadjid Benmachiche","doi":"10.1145/3447568.3448518","DOIUrl":"https://doi.org/10.1145/3447568.3448518","url":null,"abstract":"In recent decade's recommendation systems (RSs) plays an essential role in many applications as World Wide Web. Also recommendation system is one of the most important research area in machine learning. Recommendation system functions as a helper to find the interest of users by making relevant suggestions to users. The RSs mainly use four filtering methods to provide personalized recommendations to users, the most popular ones are: Collaborative filtering (CF), Content-based filtering, Demographic filtering and hybrid filtering. Data mining is one of the important analysis techniques used in RSs to predict user interest in information, products and services among the vast amount of available items. The data mining techniques that are most commonly used in RSs are: classification, clustering and association rule discovery. This paper performs a survey on recommendation systems, techniques, challenges and issues and lists some research papers solve these obstacles, also data mining methods used in recommender systems.","PeriodicalId":335307,"journal":{"name":"Proceedings of the 10th International Conference on Information Systems and Technologies","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125512998","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}
The emergence of web technologies is generating a data deluge called Big Data. All this data is in fact a gold mine to be exploited. However, we are confronted with huge volumes of heterogeneous data (various formats) and varied data (various sources) and in continuous expansion. To deal with this, some research works have introduced ontologies: this is the purpose of this paper. We present the Big Data concept on the one hand and the ontology concept on the other. We first recalled the definitions of Big Data, its main dimensions known by the 3 V (volume, velocity, variety), the fields of application as well as the various problems related to it. We reviewed the different solutions proposed as well as the existing tools by using the NoSQL and the Map-Reduce paradigm implemented in Hadoop and Spark. We then looked at the concept of ontology, starting by recalling the definition of ontology, so an ontology is a conceptual model to represent reality and on which it is possible to develop systems that can be shared and reused. Ontologies are used to represent a domain and reason about its entities. Finally, we presented and discussed some research works that combined ontologies and Big Data. We have found that there is a very abundant literature that deals with big data and ontologies separately, but few studies combine the two concepts together. We will therefore focus on the latter in order to enrich the scientific literature in the domain.
{"title":"Exploitation of ontological approaches in Big Data: A State of the Art","authors":"Djamila Djebouri, Nabil Keskes","doi":"10.1145/3447568.3448553","DOIUrl":"https://doi.org/10.1145/3447568.3448553","url":null,"abstract":"The emergence of web technologies is generating a data deluge called Big Data. All this data is in fact a gold mine to be exploited. However, we are confronted with huge volumes of heterogeneous data (various formats) and varied data (various sources) and in continuous expansion. To deal with this, some research works have introduced ontologies: this is the purpose of this paper. We present the Big Data concept on the one hand and the ontology concept on the other. We first recalled the definitions of Big Data, its main dimensions known by the 3 V (volume, velocity, variety), the fields of application as well as the various problems related to it. We reviewed the different solutions proposed as well as the existing tools by using the NoSQL and the Map-Reduce paradigm implemented in Hadoop and Spark. We then looked at the concept of ontology, starting by recalling the definition of ontology, so an ontology is a conceptual model to represent reality and on which it is possible to develop systems that can be shared and reused. Ontologies are used to represent a domain and reason about its entities. Finally, we presented and discussed some research works that combined ontologies and Big Data. We have found that there is a very abundant literature that deals with big data and ontologies separately, but few studies combine the two concepts together. We will therefore focus on the latter in order to enrich the scientific literature in the domain.","PeriodicalId":335307,"journal":{"name":"Proceedings of the 10th International Conference on Information Systems and Technologies","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126756966","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}
In this paper, we present the implementation of an application of augmented reality which makes it possible to measure objects in a scene captured using cameras. The implementation is based on a standard planar (Pattern) introduced into the scene. Initially, the detection and the follow-up of the pattern make it possible to use the last to calibrate the camera and to extract its parameters. This allows the passage between the different references (scene, camera, and image) and gives us the possibility of measuring existing objects in the acquired scene. Finally, some tests are presented to prove the validity and to evaluate our method.
{"title":"A Vision Based Optical Measurement Technique With Augmented Reality Concepts","authors":"Imad Rezzoug, B. Nini, Taki Eddine Berrahil","doi":"10.1145/3447568.3448550","DOIUrl":"https://doi.org/10.1145/3447568.3448550","url":null,"abstract":"In this paper, we present the implementation of an application of augmented reality which makes it possible to measure objects in a scene captured using cameras. The implementation is based on a standard planar (Pattern) introduced into the scene. Initially, the detection and the follow-up of the pattern make it possible to use the last to calibrate the camera and to extract its parameters. This allows the passage between the different references (scene, camera, and image) and gives us the possibility of measuring existing objects in the acquired scene. Finally, some tests are presented to prove the validity and to evaluate our method.","PeriodicalId":335307,"journal":{"name":"Proceedings of the 10th International Conference on Information Systems and Technologies","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121903952","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}
Abdelkader Khobzaoui, M. Benhamouda, Mahmoud Fahsi
Intrusion detection has become one of the most prominent components in computer security field. In order to improve intrusion detection systems performances, Data mining techniques have been massively used. Actually, the massive integration of data mining technique in intrusion detection has quickly emerged due to the fact that intrusion detection task is a classification problem by nature and Data mining provides tools to discover consistent and useful patterns of system features that describe program and user behavior, and use the set of relevant system features to build classifiers able to recognize abnormal or suspicious activities. In this paper, we will stress the role of the data mining in intrusion detection systems development and promotion.
{"title":"Data mining Contribution to Intrusion Detection Systems Improvement","authors":"Abdelkader Khobzaoui, M. Benhamouda, Mahmoud Fahsi","doi":"10.1145/3447568.3448514","DOIUrl":"https://doi.org/10.1145/3447568.3448514","url":null,"abstract":"Intrusion detection has become one of the most prominent components in computer security field. In order to improve intrusion detection systems performances, Data mining techniques have been massively used. Actually, the massive integration of data mining technique in intrusion detection has quickly emerged due to the fact that intrusion detection task is a classification problem by nature and Data mining provides tools to discover consistent and useful patterns of system features that describe program and user behavior, and use the set of relevant system features to build classifiers able to recognize abnormal or suspicious activities. In this paper, we will stress the role of the data mining in intrusion detection systems development and promotion.","PeriodicalId":335307,"journal":{"name":"Proceedings of the 10th International Conference on Information Systems and Technologies","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130931911","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}
Wiem Ben Khalifa, Najet Medssia, D. S. Boumiza, M. Neji
The purpose of this article is to present a method for assessing a short and open Arabic question during a learning activity. The proposed method is based on a combination of data presentation and a conceptual map of ontologies. The proposed method is based on the following steps: Process the text of the student's response by removing the stop words and sound from the text. Extract information about the student's response and plan in the form of a conceptual table; comparison between the reference and the student's response and assignment of points by semantic proportions; the score is calculated on the basis of the positional similarity of the measurement results.
{"title":"Online evaluation method based on open and short answers","authors":"Wiem Ben Khalifa, Najet Medssia, D. S. Boumiza, M. Neji","doi":"10.1145/3447568.3448525","DOIUrl":"https://doi.org/10.1145/3447568.3448525","url":null,"abstract":"The purpose of this article is to present a method for assessing a short and open Arabic question during a learning activity. The proposed method is based on a combination of data presentation and a conceptual map of ontologies. The proposed method is based on the following steps: Process the text of the student's response by removing the stop words and sound from the text. Extract information about the student's response and plan in the form of a conceptual table; comparison between the reference and the student's response and assignment of points by semantic proportions; the score is calculated on the basis of the positional similarity of the measurement results.","PeriodicalId":335307,"journal":{"name":"Proceedings of the 10th International Conference on Information Systems and Technologies","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124088021","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}
Cloud computing is an emerging computational model for delivering services over the internet to clients at any time and any location on a pay-per-use basis. Load balancing is a set of techniques used to improve resource utilization and affect the overall performance of the cloud computing platform. In this paper, comparative study is performed for existing Round Robin algorithm, throttled algorithm and Equally Spread Current Execution Load algorithm on the basis of following metrics: overall response time, data center processing time, data center request servicing times and the overall processing cost.
云计算是一种新兴的计算模型，用于在任何时间、任何地点以按次付费的方式通过互联网向客户提供服务。负载平衡是一组用于提高资源利用率和影响云计算平台整体性能的技术。本文以总体响应时间、数据中心处理时间、数据中心请求服务时间和总体处理成本为指标，对现有的Round Robin算法、throttted算法和equal Spread Current Execution Load算法进行了对比研究。
{"title":"A Comparative Study on Load Balancing Algorithms in Cloud Environment","authors":"Mostefa Hamdani, Youcef Aklouf, Hichem Chaalal","doi":"10.1145/3447568.3448466","DOIUrl":"https://doi.org/10.1145/3447568.3448466","url":null,"abstract":"Cloud computing is an emerging computational model for delivering services over the internet to clients at any time and any location on a pay-per-use basis. Load balancing is a set of techniques used to improve resource utilization and affect the overall performance of the cloud computing platform. In this paper, comparative study is performed for existing Round Robin algorithm, throttled algorithm and Equally Spread Current Execution Load algorithm on the basis of following metrics: overall response time, data center processing time, data center request servicing times and the overall processing cost.","PeriodicalId":335307,"journal":{"name":"Proceedings of the 10th International Conference on Information Systems and Technologies","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129902814","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}
Every year many accidents involving all categories of road users. However, some accidents are related to the blind spot, due to the deficiency of visibility in this zone, also lack of information or negligence. In this work, we focused on the road safety applications. The main of our researches is to alert the risk of blind spot collision. For this we designed a new approach, namely FBSCA, Forecasting Blind Spot Collision Alert, the driver alerts his neighbors for a possible accident related to the blind spot. The most interesting scenario testing includes the case where the vehicles need to exchange information in real-time in order to avoid traffic collisions when their visibility is hindered by road obstacles. For the implementation and testing of our approach we used popular network simulation tools such MOVE, SUMO and Ns2, we provided an assessment of proposed solution in order to alert the blind spot collisions for all neighboring vehicles.
{"title":"Forecasting approach for Blind Spot Collision Alert","authors":"Bektache Djamel, Mohamed Amine Yakoubi, Ghoualmi Nacera Zine","doi":"10.1145/3447568.3448520","DOIUrl":"https://doi.org/10.1145/3447568.3448520","url":null,"abstract":"Every year many accidents involving all categories of road users. However, some accidents are related to the blind spot, due to the deficiency of visibility in this zone, also lack of information or negligence. In this work, we focused on the road safety applications. The main of our researches is to alert the risk of blind spot collision. For this we designed a new approach, namely FBSCA, Forecasting Blind Spot Collision Alert, the driver alerts his neighbors for a possible accident related to the blind spot. The most interesting scenario testing includes the case where the vehicles need to exchange information in real-time in order to avoid traffic collisions when their visibility is hindered by road obstacles. For the implementation and testing of our approach we used popular network simulation tools such MOVE, SUMO and Ns2, we provided an assessment of proposed solution in order to alert the blind spot collisions for all neighboring vehicles.","PeriodicalId":335307,"journal":{"name":"Proceedings of the 10th International Conference on Information Systems and Technologies","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130662788","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}
M. Benmedjahed, R. Maouedj, S. Mouhadjer, A. Dahbi, D. Saba, T. Touahri
This paper1 presents a statistical analysis of wind potential of four locations at Adrar region in Southern Algeria (Adrar, B.B.Mokhtar, Reggane and Timimoun); we used the Weibull distribution to estimate the monthly, seasonal and annual wind energy produced by Whisper 200 wind turbines. Taking into account the location of these areas and the difference in air density, the treatment of the data collected (wind and temperature) every 3 hours. After calculated the wind energy, we estimated the quantity of equivalent fossil energy (natural gas, Gasoil and Gasoline), finally we estimated the quantity of CO2 that can be avoided. The annual electricity produced by wind turbines Whisper 200 range from 0.24 toe to 0.37 toe, that means we keep a quantity of natural gas range from 2401.25 m3to 3660.89 m3, If we give up diesel generators, it is possible to avoid burning a quantity of Gasoil range from 0.24 tons to 0.36 tons, in the case of gasoline generators, the depleted quantity ranges from 0.23 tons to 0.35 tons
{"title":"Wind Energy Source Assessment for Four Locations in the Adrar Region: Southern Algeria","authors":"M. Benmedjahed, R. Maouedj, S. Mouhadjer, A. Dahbi, D. Saba, T. Touahri","doi":"10.1145/3447568.3448535","DOIUrl":"https://doi.org/10.1145/3447568.3448535","url":null,"abstract":"This paper1 presents a statistical analysis of wind potential of four locations at Adrar region in Southern Algeria (Adrar, B.B.Mokhtar, Reggane and Timimoun); we used the Weibull distribution to estimate the monthly, seasonal and annual wind energy produced by Whisper 200 wind turbines. Taking into account the location of these areas and the difference in air density, the treatment of the data collected (wind and temperature) every 3 hours. After calculated the wind energy, we estimated the quantity of equivalent fossil energy (natural gas, Gasoil and Gasoline), finally we estimated the quantity of CO2 that can be avoided. The annual electricity produced by wind turbines Whisper 200 range from 0.24 toe to 0.37 toe, that means we keep a quantity of natural gas range from 2401.25 m3to 3660.89 m3, If we give up diesel generators, it is possible to avoid burning a quantity of Gasoil range from 0.24 tons to 0.36 tons, in the case of gasoline generators, the depleted quantity ranges from 0.23 tons to 0.35 tons","PeriodicalId":335307,"journal":{"name":"Proceedings of the 10th International Conference on Information Systems and Technologies","volume":"223 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120891813","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}
Mobile robot navigation is a method of guiding a robot to accomplish a mission through an environment with obstacles in a good and safe manner. The main challenge of current mobile robotics is to develop intelligent navigation systems, where autonomous navigation is a research focus that aims to give a machine the ability to move in an unassisted environment, without human intervention to accomplish the desired goal. The task of navigation is to give the robot the opportunity to obtain the information it needs to reason and equip it with a locomotion capacity adapted to its environment. However, it implies complex systems in the realization, where their control poses important problems not only technological but also scientific. An autonomous mobile robot is a mechanical system that must be able to make decisions to perform movements based on information about its position and the environment in which it operates. The problem addressed in this article is that of autonomous navigation in a dynamic environment "The objective is to study models and computer techniques allowing a mobile robot to move autonomously, that is to say without intervention in an uncertain environment and in the presence of obstacles.
{"title":"A survey on Navigation Systems in Dynamic Environments","authors":"A. Mellouk, Abdelmadjid Benmachiche","doi":"10.1145/3447568.3448527","DOIUrl":"https://doi.org/10.1145/3447568.3448527","url":null,"abstract":"Mobile robot navigation is a method of guiding a robot to accomplish a mission through an environment with obstacles in a good and safe manner. The main challenge of current mobile robotics is to develop intelligent navigation systems, where autonomous navigation is a research focus that aims to give a machine the ability to move in an unassisted environment, without human intervention to accomplish the desired goal. The task of navigation is to give the robot the opportunity to obtain the information it needs to reason and equip it with a locomotion capacity adapted to its environment. However, it implies complex systems in the realization, where their control poses important problems not only technological but also scientific. An autonomous mobile robot is a mechanical system that must be able to make decisions to perform movements based on information about its position and the environment in which it operates. The problem addressed in this article is that of autonomous navigation in a dynamic environment \"The objective is to study models and computer techniques allowing a mobile robot to move autonomously, that is to say without intervention in an uncertain environment and in the presence of obstacles.","PeriodicalId":335307,"journal":{"name":"Proceedings of the 10th International Conference on Information Systems and Technologies","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116193781","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：