Pub Date : 2019-10-01DOI: 10.1109/icssd47982.2019.9003065
{"title":"[Copyright notice]","authors":"","doi":"10.1109/icssd47982.2019.9003065","DOIUrl":"https://doi.org/10.1109/icssd47982.2019.9003065","url":null,"abstract":"","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"184 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":"121036919","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/ICSSD47982.2019.9002735
Tabbakh Zineb, Ellaia Rachid, E. Talbi
Improving performance and reducing costs are major challenges in many engineering design problems. The processes or accurate models are usually time-consuming and computationally expensive; therefore, the objective function requires a large number of evaluations. This paper considers surrogate modeling to approximate the expensive function and to ensure the quality of results in a reduced CPU time for mono-objective optimization. The Basic idea of surrogate models, also known as a meta-model, is to build a model from a sampled data, then, the outputs of other design data can be predicted by the approximated model instead of using the heavy one. Once the surrogate model is built, an optimization method is used to look for new design points until convergence. In this work, we propose a surrogate-based optimization algorithm using backtracking search algorithm optimization, and the thin spline basis function to build the surrogate model. During the construction of the surrogate, a minimization problem of error is carried out by updating the position of the node that produces the maximum error. Experiments are carried out on many test functions.
{"title":"Thin-Plate Spline RBF surrogate model for global optimization algorithms","authors":"Tabbakh Zineb, Ellaia Rachid, E. Talbi","doi":"10.1109/ICSSD47982.2019.9002735","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9002735","url":null,"abstract":"Improving performance and reducing costs are major challenges in many engineering design problems. The processes or accurate models are usually time-consuming and computationally expensive; therefore, the objective function requires a large number of evaluations. This paper considers surrogate modeling to approximate the expensive function and to ensure the quality of results in a reduced CPU time for mono-objective optimization. The Basic idea of surrogate models, also known as a meta-model, is to build a model from a sampled data, then, the outputs of other design data can be predicted by the approximated model instead of using the heavy one. Once the surrogate model is built, an optimization method is used to look for new design points until convergence. In this work, we propose a surrogate-based optimization algorithm using backtracking search algorithm optimization, and the thin spline basis function to build the surrogate model. During the construction of the surrogate, a minimization problem of error is carried out by updating the position of the node that produces the maximum error. Experiments are carried out on many test functions.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"7 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":"122646142","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}
Smart city technologies are reshaping our everyday life. New application and systems architectures appears to enhance information and communications technologies, allowing cities to harness their resources more intelligently, also to include citizens in the development of their environments by analyzing the tremendous amount of data generated by people, which cover wide diversity of domains, thus, providing valuable contribution to tackle environmental and socio-economic problems efficiently. The problem encountered under these circumstances is that continuously analyzing users content, especially text content to extract expressed sentiment in real-time is a challenging task that needs scalable and high performance distributed systems, also the opinion of a person concerning a particular city service, politic decision or even a street reputation may not be binary, e.g., positive or negative, due to the fuzzy character of our language. To this end we propose an architecture that will take advantage of distributed and streaming computing framework combined with applying fuzzy logic to classify expressed sentiments in real time, thus to offer insight to city governance and to expand citizen participation in the evolution of their cities.
{"title":"Smart City Services Monitoring Framework using Fuzzy Logic Based Sentiment Analysis and Apache Spark","authors":"Bahra Mohamed, Fennan Abdelhadi, Bouktaib Adil, Hmami Haytam","doi":"10.1109/ICSSD47982.2019.9002687","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9002687","url":null,"abstract":"Smart city technologies are reshaping our everyday life. New application and systems architectures appears to enhance information and communications technologies, allowing cities to harness their resources more intelligently, also to include citizens in the development of their environments by analyzing the tremendous amount of data generated by people, which cover wide diversity of domains, thus, providing valuable contribution to tackle environmental and socio-economic problems efficiently. The problem encountered under these circumstances is that continuously analyzing users content, especially text content to extract expressed sentiment in real-time is a challenging task that needs scalable and high performance distributed systems, also the opinion of a person concerning a particular city service, politic decision or even a street reputation may not be binary, e.g., positive or negative, due to the fuzzy character of our language. To this end we propose an architecture that will take advantage of distributed and streaming computing framework combined with applying fuzzy logic to classify expressed sentiments in real time, thus to offer insight to city governance and to expand citizen participation in the evolution of their cities.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"9 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":"125127863","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/ICSSD47982.2019.9003052
S. Hamida, B. Cherradi, A. Raihani, H. Ouajji
the recognition of handwritten characters has always been a very difficult task because of the many variations of handwritten characters with different writing styles. This type of intelligent systems is applied in various fields: check processing, processing of forms, automatic processing of handwritten answers to an examination, etc. This last application is the subject of this work. We compared in this paper the performances of some machine learning algorithms, used for the classification of complex and multiclass problems. In this work, we exploited four machine learning algorithms (K-Nearest Neighbors, Deep Neural Network, Decision Tree and Support Vector Machine) to predict handwritten digits. The training and testing data were extracted from the MNIST digit database containing pre-processed images. The results obtained using different similarity measures such as accuracy, sensitivity and specificity confirm that the classification obtained by deep neural networks is the most accurate compared to the other classifiers studied in this paper.
{"title":"Performance Evaluation of Machine Learning Algorithms in Handwritten Digits Recognition","authors":"S. Hamida, B. Cherradi, A. Raihani, H. Ouajji","doi":"10.1109/ICSSD47982.2019.9003052","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9003052","url":null,"abstract":"the recognition of handwritten characters has always been a very difficult task because of the many variations of handwritten characters with different writing styles. This type of intelligent systems is applied in various fields: check processing, processing of forms, automatic processing of handwritten answers to an examination, etc. This last application is the subject of this work. We compared in this paper the performances of some machine learning algorithms, used for the classification of complex and multiclass problems. In this work, we exploited four machine learning algorithms (K-Nearest Neighbors, Deep Neural Network, Decision Tree and Support Vector Machine) to predict handwritten digits. The training and testing data were extracted from the MNIST digit database containing pre-processed images. The results obtained using different similarity measures such as accuracy, sensitivity and specificity confirm that the classification obtained by deep neural networks is the most accurate compared to the other classifiers studied in this paper.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"11 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":"131434677","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/ICSSD47982.2019.9002690
Sara Ouaftouh, Imad Sassi, A. Zellou, S. Anter
Recommender systems are more and more used in different domains of computer science. The collaborative filtering remains a highly prized recommendation technique used by the e-services on the internet. This technique is mainly based on deducing a part of the user interests from the preferences of other users with similar profiles. Among the different approaches, the clustering technique is used to implement collaborative filtering. We propose in this work a comparison between hierarchical and flat user profile clustering based on a case study. The proposed approach is implemented basing on a dataset of user profiles in an e-commerce context.
{"title":"Flat and hierarchical user profile clustering in an e-commerce recommender system","authors":"Sara Ouaftouh, Imad Sassi, A. Zellou, S. Anter","doi":"10.1109/ICSSD47982.2019.9002690","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9002690","url":null,"abstract":"Recommender systems are more and more used in different domains of computer science. The collaborative filtering remains a highly prized recommendation technique used by the e-services on the internet. This technique is mainly based on deducing a part of the user interests from the preferences of other users with similar profiles. Among the different approaches, the clustering technique is used to implement collaborative filtering. We propose in this work a comparison between hierarchical and flat user profile clustering based on a case study. The proposed approach is implemented basing on a dataset of user profiles in an e-commerce context.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"16 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":"132460353","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/ICSSD47982.2019.9003069
Amina Ouatiq, Bouchaib Riyami, K. Mansouri, Mohammed Qbadou
All current trends are oriented towards the use of innovative pedagogical approaches, such as e-learning, MOOC integration, hybrid or mixed learning... in teaching and training modules.many universities around the world use MOOC in their cursus. The Moroccan educational system faces numerous problems and obstructions in its attempt to integrating online learning into its educational programs, despite the government initiatives and the humble attempts of some Moroccan universitiesOur contribution tries to focus on the difficulties and problems that block the success of the integration of new teaching approaches including MOOC in the Moroccan educational system. It proposes also a hybrid model to better benefit from MOOC and ICT
{"title":"Towards ICT Integration in Higher Education in Morocco, Challenges and Opportunities","authors":"Amina Ouatiq, Bouchaib Riyami, K. Mansouri, Mohammed Qbadou","doi":"10.1109/ICSSD47982.2019.9003069","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9003069","url":null,"abstract":"All current trends are oriented towards the use of innovative pedagogical approaches, such as e-learning, MOOC integration, hybrid or mixed learning... in teaching and training modules.many universities around the world use MOOC in their cursus. The Moroccan educational system faces numerous problems and obstructions in its attempt to integrating online learning into its educational programs, despite the government initiatives and the humble attempts of some Moroccan universitiesOur contribution tries to focus on the difficulties and problems that block the success of the integration of new teaching approaches including MOOC in the Moroccan educational system. It proposes also a hybrid model to better benefit from MOOC and ICT","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"123 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":"115783525","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}
Solenoids are widely used in many domestic and industrial equipment and predictive maintenance is necessary to avoid eventual failures of these actuators. We propose to study the monitoring of solenoid parameters using the fiber optic press. To this end, we first propose a PID control system to correct the response of a solenoid used as a mechanical actuator on an optical fiber. Then, a simulation study is proposed to examine the influence of the system parameters on the correction constants to finally use this application in the real-time monitoring of any parametric variation of this actuator used in another industrial or domestic system. The results of the simulation show that in order to maintain a corrected dynamic response, it is necessary to provide an automatic adjustment system making it possible to adjust the constants Kp, Ki and Kd of the PID corrector in case of variation of the solenoid parameters. This system will eventually be used to visualize and communicate to the user any parametric modification of this actuator to ensure adequate preventive maintenance.
{"title":"Study and simulation of fiber press control for solenoid parameters monitoring for Smart preventive maintenance","authors":"Zahidi Abedallah, Amrane Said, Azami Nawfel, Nasser Naoual","doi":"10.1109/ICSSD47982.2019.9003157","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9003157","url":null,"abstract":"Solenoids are widely used in many domestic and industrial equipment and predictive maintenance is necessary to avoid eventual failures of these actuators. We propose to study the monitoring of solenoid parameters using the fiber optic press. To this end, we first propose a PID control system to correct the response of a solenoid used as a mechanical actuator on an optical fiber. Then, a simulation study is proposed to examine the influence of the system parameters on the correction constants to finally use this application in the real-time monitoring of any parametric variation of this actuator used in another industrial or domestic system. The results of the simulation show that in order to maintain a corrected dynamic response, it is necessary to provide an automatic adjustment system making it possible to adjust the constants Kp, Ki and Kd of the PID corrector in case of variation of the solenoid parameters. This system will eventually be used to visualize and communicate to the user any parametric modification of this actuator to ensure adequate preventive maintenance.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"45 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":"130077243","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/ICSSD47982.2019.9003118
Oumaima Hourrane, Nouhaila Idrissi, E. Benlahmar
Sentiment classification refers to the act of putting in for natural language processing and text mining strategies to distinguish subjective textual data. Due to the huge availability of online data that coincide with the growth of social media, there has been a big interest from researchers in sentiment analysis and its applications. In this paper, we review the state of the art to determine how the previous researches have addressed this task. we also introduce an empirical study on two annotated datasets; 25,000 IMDB movie reviews and 25,000 tweets, where we used nine supervised learning models, the next step was to implement a voting ensemble classifier using the top four models we get from the previous steps. In the end, we outline a benchmark evaluation, the results show that the ensemble classifier outperforms all the machine learning models.
{"title":"Sentiment Classification on Movie Reviews and Twitter: An Experimental Study of Supervised Learning Models","authors":"Oumaima Hourrane, Nouhaila Idrissi, E. Benlahmar","doi":"10.1109/ICSSD47982.2019.9003118","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9003118","url":null,"abstract":"Sentiment classification refers to the act of putting in for natural language processing and text mining strategies to distinguish subjective textual data. Due to the huge availability of online data that coincide with the growth of social media, there has been a big interest from researchers in sentiment analysis and its applications. In this paper, we review the state of the art to determine how the previous researches have addressed this task. we also introduce an empirical study on two annotated datasets; 25,000 IMDB movie reviews and 25,000 tweets, where we used nine supervised learning models, the next step was to implement a voting ensemble classifier using the top four models we get from the previous steps. In the end, we outline a benchmark evaluation, the results show that the ensemble classifier outperforms all the machine learning models.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"51 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":"134039092","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/ICSSD47982.2019.9002731
Zineb Moubariki, Lahcen Beljadid, Mohammed El Haj Tirari, M. Kaicer, R. Thami
Cash management is a complicated task since it is the interaction between multiple monetary activities including collections, disbursements, concentration, investments and funding [1], moreover, it can be easily influenced by several unpredictable internal and external factors from different areas. A misuse or underestimation may lead to devastating financial consequences. To manage the cash requires painstaking approaches, to approximate its size requires advanced and meticulous tools.By relying on machine learning concepts, we attempt to build an intelligent tool adapted to the public expenditure management sector. Giving a set of payment orders in progress, the model is conceived to allow the cash managers to predict the amounts to be drawn in a period of time, thus, to have a clear vision over cash trend.The experiments demonstrate the applicability of the model and exhibit encouraging prediction results. Yet, we believe that still there are unexplored features to be considered and leveraged to enhance the model performance and specially the accuracy which is valuable for a crucial financial decision.
{"title":"Enhancing cash management using machine learning","authors":"Zineb Moubariki, Lahcen Beljadid, Mohammed El Haj Tirari, M. Kaicer, R. Thami","doi":"10.1109/ICSSD47982.2019.9002731","DOIUrl":"https://doi.org/10.1109/ICSSD47982.2019.9002731","url":null,"abstract":"Cash management is a complicated task since it is the interaction between multiple monetary activities including collections, disbursements, concentration, investments and funding [1], moreover, it can be easily influenced by several unpredictable internal and external factors from different areas. A misuse or underestimation may lead to devastating financial consequences. To manage the cash requires painstaking approaches, to approximate its size requires advanced and meticulous tools.By relying on machine learning concepts, we attempt to build an intelligent tool adapted to the public expenditure management sector. Giving a set of payment orders in progress, the model is conceived to allow the cash managers to predict the amounts to be drawn in a period of time, thus, to have a clear vision over cash trend.The experiments demonstrate the applicability of the model and exhibit encouraging prediction results. Yet, we believe that still there are unexplored features to be considered and leveraged to enhance the model performance and specially the accuracy which is valuable for a crucial financial decision.","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"1 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":"130427165","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/icssd47982.2019.9002819
{"title":"ICSSD 2019 Index","authors":"","doi":"10.1109/icssd47982.2019.9002819","DOIUrl":"https://doi.org/10.1109/icssd47982.2019.9002819","url":null,"abstract":"","PeriodicalId":342806,"journal":{"name":"2019 1st International Conference on Smart Systems and Data Science (ICSSD)","volume":"7 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":"132371038","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：