Salah Ihlou, H. Tizyi, A. Bakkali, A. Abbassi, J. Foshi
In this paper, an attempt has been made to design and develop a 1 X 2 rectangular linearly polarized microstrip patch antenna array for microwave power transmission (MPT). The antenna array is operating at 5.8 GHz frequency. The system was designed by means of simulation using CST MWS software. The results showed that the proposed antenna array achieves a gain of 9.19 dB, a return loss less than -25.05 dB, and a good axial ratio less than 0.63 dB at center frequency (5.8 GHz).
{"title":"Design and Development of a Microstrip Patch Antenna Array for Rectenna System","authors":"Salah Ihlou, H. Tizyi, A. Bakkali, A. Abbassi, J. Foshi","doi":"10.1145/3419604.3419766","DOIUrl":"https://doi.org/10.1145/3419604.3419766","url":null,"abstract":"In this paper, an attempt has been made to design and develop a 1 X 2 rectangular linearly polarized microstrip patch antenna array for microwave power transmission (MPT). The antenna array is operating at 5.8 GHz frequency. The system was designed by means of simulation using CST MWS software. The results showed that the proposed antenna array achieves a gain of 9.19 dB, a return loss less than -25.05 dB, and a good axial ratio less than 0.63 dB at center frequency (5.8 GHz).","PeriodicalId":250715,"journal":{"name":"Proceedings of the 13th International Conference on Intelligent Systems: Theories and Applications","volume":"192 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125851367","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 progress of IT technologies offers many means to collect and store an extremely large quantity of data and conveys a prodigious quantity of information in several sectors of activity. However, this progress is not only exposed to classic operational risks such as fire or blackouts, but also to various viruses and data theft. These extremely technologically complex risks have risen a big challenge at responding to a large-scale of intangible threats within an industry of perpetual change. Wherefore, the value of Security Risk Assessment "SRA" at ensuring the protection of the organizations' business services. However, conducting SRA is difficult and time-consuming and its results may not project the risky behaviors which often leads to unnecessary controls being implemented. Therefore, we tolerate using the Apriori algorithm as a prominent approach accurately determining the threat sources emerging within the risky behaviors. The Apriori algorithm is very useful at better mapping the relationship between organization critical assets and the potential threats-vulnerabilities. We use a history dataset of security risks in order to determine association rules between vulnerabilities and the potential threats. The algorithm performs classification which successfully reduces assessment time. As a result, the improved algorithm undertakes recommendations for a better SRA conduction.
{"title":"Evaluation of security risks using Apriori algorithm","authors":"W. Abbass, Amine Baïna, M. Bellafkih","doi":"10.1145/3419604.3419789","DOIUrl":"https://doi.org/10.1145/3419604.3419789","url":null,"abstract":"The progress of IT technologies offers many means to collect and store an extremely large quantity of data and conveys a prodigious quantity of information in several sectors of activity. However, this progress is not only exposed to classic operational risks such as fire or blackouts, but also to various viruses and data theft. These extremely technologically complex risks have risen a big challenge at responding to a large-scale of intangible threats within an industry of perpetual change. Wherefore, the value of Security Risk Assessment \"SRA\" at ensuring the protection of the organizations' business services. However, conducting SRA is difficult and time-consuming and its results may not project the risky behaviors which often leads to unnecessary controls being implemented. Therefore, we tolerate using the Apriori algorithm as a prominent approach accurately determining the threat sources emerging within the risky behaviors. The Apriori algorithm is very useful at better mapping the relationship between organization critical assets and the potential threats-vulnerabilities. We use a history dataset of security risks in order to determine association rules between vulnerabilities and the potential threats. The algorithm performs classification which successfully reduces assessment time. As a result, the improved algorithm undertakes recommendations for a better SRA conduction.","PeriodicalId":250715,"journal":{"name":"Proceedings of the 13th International Conference on Intelligent Systems: Theories and Applications","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126030698","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}
Discretization is a key pre-processing step in Machine Learning that transforms continuous attributes into discrete ones, through different methods available in the literature. In this regard, this work provides the ForestDisc framework that discretizes data based on a supervised, multivariate and hybrid approach. It uses, at first, a splitting process relying on a tree learning ensemble to generate a large set of cut points. It then uses a merging process based on moment matching optimization, to transform this set into a reduced and representative one. ForestDisc is a non-parametric discretizer in the sense that it does not require the user to introduce any initial setting parameters. We implemented ForestDisc algorithm in the "ForestDisc" R package.
{"title":"An implementation of a multivariate discretization for supervised learning using Forestdisc","authors":"Maissae Haddouchi, A. Berrado","doi":"10.1145/3419604.3419772","DOIUrl":"https://doi.org/10.1145/3419604.3419772","url":null,"abstract":"Discretization is a key pre-processing step in Machine Learning that transforms continuous attributes into discrete ones, through different methods available in the literature. In this regard, this work provides the ForestDisc framework that discretizes data based on a supervised, multivariate and hybrid approach. It uses, at first, a splitting process relying on a tree learning ensemble to generate a large set of cut points. It then uses a merging process based on moment matching optimization, to transform this set into a reduced and representative one. ForestDisc is a non-parametric discretizer in the sense that it does not require the user to introduce any initial setting parameters. We implemented ForestDisc algorithm in the \"ForestDisc\" R package.","PeriodicalId":250715,"journal":{"name":"Proceedings of the 13th International Conference on Intelligent Systems: Theories and Applications","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126984422","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}
Regression is a machine learning model that predicts the target based on input data. Factorization Machines (FMs) are new class models that in addition to regression, present factorized interactions between a pair of features. FMs have been proven to accomplish good accuracy for the rating prediction tasks such as recommender systems. However, FM models all the interactions with the same weight which can be ineffective, since useless interactions may cause noisy results. In this paper, we propose a new model named: Latent Graph Predictor Factorization Machine (LGPFM) that capture the interaction weight of each pair of features using Convolutional Neural Network (CNN). LGPFM combines FM model with the benefits of the CNN that works efficiently in grid-type topology, which would improve significantly the accuracy of results.
{"title":"Latent Graph Predictor Factorization Machine (LGPFM) for modeling feature interactions weight","authors":"Abdessamad Chanaa, N. E. Faddouli","doi":"10.1145/3419604.3419618","DOIUrl":"https://doi.org/10.1145/3419604.3419618","url":null,"abstract":"Regression is a machine learning model that predicts the target based on input data. Factorization Machines (FMs) are new class models that in addition to regression, present factorized interactions between a pair of features. FMs have been proven to accomplish good accuracy for the rating prediction tasks such as recommender systems. However, FM models all the interactions with the same weight which can be ineffective, since useless interactions may cause noisy results. In this paper, we propose a new model named: Latent Graph Predictor Factorization Machine (LGPFM) that capture the interaction weight of each pair of features using Convolutional Neural Network (CNN). LGPFM combines FM model with the benefits of the CNN that works efficiently in grid-type topology, which would improve significantly the accuracy of results.","PeriodicalId":250715,"journal":{"name":"Proceedings of the 13th International Conference on Intelligent Systems: Theories and Applications","volume":"196 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123531179","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}
Text classification is the process of assigning appropriate categories to free text according to its content. It is one of the important task in Text mining. Numerous studies have been conducted for natural languages processing using Japanese, French, Latin and Turkish documents, but the number of works related to the text written in Arabic language is still limited. In this paper we conduct a comparative study of three methods of feature selection using four well-known classifiers namely: Decision Tree, Naive Bayes, K-Nearest Neighbors and Support Vector Machine. A corpus contained 250 Arabic text belonging into five classes: sport, politics, economics, culture and art, and society. The data set is used to evaluate and compare the effectiveness of the obtained model. The experimental results reveal that using improved Chi-square method as feature selection and Support Vector Machine as classifier outperforms other combinations in terms of precision. This combination significantly improves the performance of Arabic text classification model. The highest value of precision measure for this model is 89.9%.
{"title":"Comparative Study of Arabic Text Categorization Using Feature Selection Techniques and Four Classifier Models","authors":"Said Bahassine, Abdellah Madani, M. Kissi","doi":"10.1145/3419604.3419778","DOIUrl":"https://doi.org/10.1145/3419604.3419778","url":null,"abstract":"Text classification is the process of assigning appropriate categories to free text according to its content. It is one of the important task in Text mining. Numerous studies have been conducted for natural languages processing using Japanese, French, Latin and Turkish documents, but the number of works related to the text written in Arabic language is still limited. In this paper we conduct a comparative study of three methods of feature selection using four well-known classifiers namely: Decision Tree, Naive Bayes, K-Nearest Neighbors and Support Vector Machine. A corpus contained 250 Arabic text belonging into five classes: sport, politics, economics, culture and art, and society. The data set is used to evaluate and compare the effectiveness of the obtained model. The experimental results reveal that using improved Chi-square method as feature selection and Support Vector Machine as classifier outperforms other combinations in terms of precision. This combination significantly improves the performance of Arabic text classification model. The highest value of precision measure for this model is 89.9%.","PeriodicalId":250715,"journal":{"name":"Proceedings of the 13th International Conference on Intelligent Systems: Theories and Applications","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129733314","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}
Using appropriate tools to verify and ascertain the accuracy of the estimated time of arrival (ETA) provided by ships during their approach to ports has never been more needed than it is today. This is owed to the traffic increase and the considerable variations in ETAs that port actors are suffering from. But now the opportunity presents itself with the maritime digital transformation enabling ports and ships to produce important amounts of data that can serve in building predictive systemsfor ships' arrival time projection. This paper presents the existing approaches to predict ETAs, outlines three of the data sources that can serve in ETAs' prediction, and shows the results of Neural Networks (NN) models prediction of the arrival time of a ship to its destination using AIS data.
{"title":"Predicting Ships Estimated Time of Arrival based on AIS Data","authors":"Sara El Mekkaoui, L. Benabbou, A. Berrado","doi":"10.1145/3419604.3419768","DOIUrl":"https://doi.org/10.1145/3419604.3419768","url":null,"abstract":"Using appropriate tools to verify and ascertain the accuracy of the estimated time of arrival (ETA) provided by ships during their approach to ports has never been more needed than it is today. This is owed to the traffic increase and the considerable variations in ETAs that port actors are suffering from. But now the opportunity presents itself with the maritime digital transformation enabling ports and ships to produce important amounts of data that can serve in building predictive systemsfor ships' arrival time projection. This paper presents the existing approaches to predict ETAs, outlines three of the data sources that can serve in ETAs' prediction, and shows the results of Neural Networks (NN) models prediction of the arrival time of a ship to its destination using AIS data.","PeriodicalId":250715,"journal":{"name":"Proceedings of the 13th International Conference on Intelligent Systems: Theories and Applications","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133898658","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}
Sports and international tournaments have gained world attention in the past decade. Enhancing sports activities and promoting sports to participate in international events, competitions, and tournaments play a substantial role in the development and advancement of nations around the globe. In this paper, we applied different deep learning models for predicting athletes' performance in tournaments to help them improve their results. We propose a deep learning selection algorithm to evaluate the effectiveness of the athletes' current training by predicting their race results upon completing each additional training, which potentially improves their performance. We gathered public training data for athletes who participated in the 2017 Boston Marathon within a five-month window prior to the race. Deep learning models were applied and evaluated to predict marathon finishing times. These include Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRU). Results show that Deep Learning models give improved race time prediction accuracy over the baseline machine learning model, such as standard Linear Regression (LR).
{"title":"Deep Learning Approach for Forecasting Athletes' Performance in Sports Tournaments","authors":"Hadeel T. El Kassabi, Khaled Khalil, M. Serhani","doi":"10.1145/3419604.3419786","DOIUrl":"https://doi.org/10.1145/3419604.3419786","url":null,"abstract":"Sports and international tournaments have gained world attention in the past decade. Enhancing sports activities and promoting sports to participate in international events, competitions, and tournaments play a substantial role in the development and advancement of nations around the globe. In this paper, we applied different deep learning models for predicting athletes' performance in tournaments to help them improve their results. We propose a deep learning selection algorithm to evaluate the effectiveness of the athletes' current training by predicting their race results upon completing each additional training, which potentially improves their performance. We gathered public training data for athletes who participated in the 2017 Boston Marathon within a five-month window prior to the race. Deep learning models were applied and evaluated to predict marathon finishing times. These include Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRU). Results show that Deep Learning models give improved race time prediction accuracy over the baseline machine learning model, such as standard Linear Regression (LR).","PeriodicalId":250715,"journal":{"name":"Proceedings of the 13th International Conference on Intelligent Systems: Theories and Applications","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124832606","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}
Automatic speech recognition for the Arabic language is a field that is in a current remarkable development and still attracts many researchers who try to improve year after year the recognition rate. Many works, nowadays, have been focused on automatic speech recognition (ASR) for the Arabic language. The paper presents the significance of the ASR systems built in the past few years. This work also aims to introduce a new Arabic database for isolated word by defining a new concept of phonetic units: semi-syllable units. Thus, the corpus contains a collection of semi-syllable audio files as well as their corresponding transcription files. This database will help us in future works.
{"title":"Construction of a database for speech recognition of isolated Arabic words","authors":"Ahmed Boumehdi, A. Yousfi","doi":"10.1145/3419604.3419752","DOIUrl":"https://doi.org/10.1145/3419604.3419752","url":null,"abstract":"Automatic speech recognition for the Arabic language is a field that is in a current remarkable development and still attracts many researchers who try to improve year after year the recognition rate. Many works, nowadays, have been focused on automatic speech recognition (ASR) for the Arabic language. The paper presents the significance of the ASR systems built in the past few years. This work also aims to introduce a new Arabic database for isolated word by defining a new concept of phonetic units: semi-syllable units. Thus, the corpus contains a collection of semi-syllable audio files as well as their corresponding transcription files. This database will help us in future works.","PeriodicalId":250715,"journal":{"name":"Proceedings of the 13th International Conference on Intelligent Systems: Theories and Applications","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129889880","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}
Today mobile ad hoc networks (MANETs) and its derivatives such as vehicular ad-hoc networks (VANETs), wireless sensor network (WSN), are more interesting subject for researchers, seen particularly from the appearance of the paradigm of smart cities, smart homes, and Internet of Things (IoT). In addition to this widespread use, several vulnerabilities and attacks appear like for instance black hole attack and data flooding attack. Nevertheless, the limitations of hardware generally used in MANETs make many views the tasks of detection and countermeasure of attacks. In this paper, using the technology of deep neural network (DNN) deep learning, we try to propose an intrusion detection system (IDS) for the subclass of the big class DDoS: Data flooding attack, with using the dataset CICDDoS2019. Our obtained results show that the proposed architecture model can achieve very interesting performance (Accuracy, Precision, Recall and F1-score).
{"title":"Data Flooding Intrusion Detection System for MANETs Using Deep Learning Approach","authors":"Oussama Sbai, M. Elboukhari","doi":"10.1145/3419604.3419777","DOIUrl":"https://doi.org/10.1145/3419604.3419777","url":null,"abstract":"Today mobile ad hoc networks (MANETs) and its derivatives such as vehicular ad-hoc networks (VANETs), wireless sensor network (WSN), are more interesting subject for researchers, seen particularly from the appearance of the paradigm of smart cities, smart homes, and Internet of Things (IoT). In addition to this widespread use, several vulnerabilities and attacks appear like for instance black hole attack and data flooding attack. Nevertheless, the limitations of hardware generally used in MANETs make many views the tasks of detection and countermeasure of attacks. In this paper, using the technology of deep neural network (DNN) deep learning, we try to propose an intrusion detection system (IDS) for the subclass of the big class DDoS: Data flooding attack, with using the dataset CICDDoS2019. Our obtained results show that the proposed architecture model can achieve very interesting performance (Accuracy, Precision, Recall and F1-score).","PeriodicalId":250715,"journal":{"name":"Proceedings of the 13th International Conference on Intelligent Systems: Theories and Applications","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121333821","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 Set Program Mask instruction, SPM, is used to change the 2-bit condition code and 4-bit program mask in the current PSW. Before executing SPM, you should set bits 34 and 35 of general register R1 to the desired value of the condition code. You should also initialize bits 3639 of general register R1 – these values will replace the program mask. Bits 0-33 and 40-63 of general register R1 are ignored. Here is an example:
{"title":"SPM","authors":"Aola Yousfi, Moulay Hafid El Yazidi, A. Zellou","doi":"10.1145/3419604.3419782","DOIUrl":"https://doi.org/10.1145/3419604.3419782","url":null,"abstract":"The Set Program Mask instruction, SPM, is used to change the 2-bit condition code and 4-bit program mask in the current PSW. Before executing SPM, you should set bits 34 and 35 of general register R1 to the desired value of the condition code. You should also initialize bits 3639 of general register R1 – these values will replace the program mask. Bits 0-33 and 40-63 of general register R1 are ignored. Here is an example:","PeriodicalId":250715,"journal":{"name":"Proceedings of the 13th International Conference on Intelligent Systems: Theories and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126651889","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：