Pub Date : 2018-11-01DOI: 10.1109/ICASS.2018.8651961
Matias Callara, P. Wira
This paper presents the use of machine learning algorithms to analyze the behaviors of users working in a distributed computer environment. The objective consists in discriminating groups of close users. These groups are composed of users with similar behaviors. Event related to the user’s behaviors are recorded and transferred to a database. An approach is developed to determine the groups of the users. A non-parametric method of estimating a probability density is used to predict application launches and session openings in an individual way for each user. These algorithms have been implemented and demonstrated their effectiveness within a complete virtualization environment for workstations and applications under real conditions in a hospital.
{"title":"User Behavior Analysis with Machine Learning Techniques in Cloud Computing Architectures","authors":"Matias Callara, P. Wira","doi":"10.1109/ICASS.2018.8651961","DOIUrl":"https://doi.org/10.1109/ICASS.2018.8651961","url":null,"abstract":"This paper presents the use of machine learning algorithms to analyze the behaviors of users working in a distributed computer environment. The objective consists in discriminating groups of close users. These groups are composed of users with similar behaviors. Event related to the user’s behaviors are recorded and transferred to a database. An approach is developed to determine the groups of the users. A non-parametric method of estimating a probability density is used to predict application launches and session openings in an individual way for each user. These algorithms have been implemented and demonstrated their effectiveness within a complete virtualization environment for workstations and applications under real conditions in a hospital.","PeriodicalId":358814,"journal":{"name":"2018 International Conference on Applied Smart Systems (ICASS)","volume":"165 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115478057","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 : 2018-11-01DOI: 10.1109/ICASS.2018.8652076
M. Mohamed, Bahri Nejmeddine, Batel Noureddine, Toubal Abdelmoughni, Masmoudi Nouri
High Efficiency Video Coding (HEVC) is the latest video coding standard released as a successor of H.264/AVC, it expected to reduce the bitrate by 50% for the same perceptual quality. One of the major contributors to the higher compression performance of HEVC is the introduction of larger Coding Units (CU) with recursive partitioning mechanisms. This achievement in performance is accompanied by a high computational complexity, making this new standard very difficult to be embedded in current multimedia services and broadcast platforms. In this paper, a performance evaluation of All-Intra (AI) parallel realization of HEVC encoder is proposed, using a heterogeneous Octa-core CubieBoard4 platform that includes two quad-core ARM A7 and ARM A15. We used the OpenMP paradigm for parallel realization where each thread is assigned to a core processor to encode a separate frame. AI configuration is used to break coding dependencies between successive frames, which allow the parallel processing of a set of images. Experimental results shows that the proposed parallel realization of HEVC encoder, using eight threads, reduces the computational complexity to about 4.35×, without any loss in coding performance. These results do not match to the expected acceleration due to the heterogeneity of the platform.
高效视频编码(High Efficiency Video Coding, HEVC)是继H.264/AVC之后发布的最新视频编码标准，它有望在相同的感知质量下将比特率降低50%。HEVC压缩性能提高的主要原因之一是引入了带有递归分区机制的更大的编码单元(CU)。这种性能上的成就伴随着较高的计算复杂度，使得这个新标准很难嵌入到当前的多媒体服务和广播平台中。本文利用异构八核CubieBoard4平台(包含两个四核ARM A7和ARM A15)，对HEVC编码器的AI并行实现进行了性能评估。我们使用OpenMP范式进行并行实现，其中每个线程被分配给一个核心处理器来编码一个单独的帧。AI配置用于打破连续帧之间的编码依赖，从而允许并行处理一组图像。实验结果表明，采用8个线程并行实现HEVC编码器，在不影响编码性能的前提下，将计算复杂度降低到4.35倍左右。由于平台的不均匀性，这些结果与预期的加速度不匹配。
{"title":"Performance Evaluation of Frame-level Parallelization in HEVC Intra Coding Using Heterogeneous Multicore Platforms","authors":"M. Mohamed, Bahri Nejmeddine, Batel Noureddine, Toubal Abdelmoughni, Masmoudi Nouri","doi":"10.1109/ICASS.2018.8652076","DOIUrl":"https://doi.org/10.1109/ICASS.2018.8652076","url":null,"abstract":"High Efficiency Video Coding (HEVC) is the latest video coding standard released as a successor of H.264/AVC, it expected to reduce the bitrate by 50% for the same perceptual quality. One of the major contributors to the higher compression performance of HEVC is the introduction of larger Coding Units (CU) with recursive partitioning mechanisms. This achievement in performance is accompanied by a high computational complexity, making this new standard very difficult to be embedded in current multimedia services and broadcast platforms. In this paper, a performance evaluation of All-Intra (AI) parallel realization of HEVC encoder is proposed, using a heterogeneous Octa-core CubieBoard4 platform that includes two quad-core ARM A7 and ARM A15. We used the OpenMP paradigm for parallel realization where each thread is assigned to a core processor to encode a separate frame. AI configuration is used to break coding dependencies between successive frames, which allow the parallel processing of a set of images. Experimental results shows that the proposed parallel realization of HEVC encoder, using eight threads, reduces the computational complexity to about 4.35×, without any loss in coding performance. These results do not match to the expected acceleration due to the heterogeneity of the platform.","PeriodicalId":358814,"journal":{"name":"2018 International Conference on Applied Smart Systems (ICASS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124933348","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 : 2018-11-01DOI: 10.1109/ICASS.2018.8652044
F. Hadjou, B. tabbache, N. Henini, M. Benbouzid
This paper deals with the implementation of fuzzy logic approach for diagnosis of three-phase power Inverter. The proposed is based on the analysis of the currents using Concordia transformation. In this context, two faults have been investigated: open and short circuit of the power switches (IGBTs) of three- phase power inverter.
{"title":"Diagnosis of PWM Power Inverter Based on Fuzzy Logic and Concordia Current Pattern","authors":"F. Hadjou, B. tabbache, N. Henini, M. Benbouzid","doi":"10.1109/ICASS.2018.8652044","DOIUrl":"https://doi.org/10.1109/ICASS.2018.8652044","url":null,"abstract":"This paper deals with the implementation of fuzzy logic approach for diagnosis of three-phase power Inverter. The proposed is based on the analysis of the currents using Concordia transformation. In this context, two faults have been investigated: open and short circuit of the power switches (IGBTs) of three- phase power inverter.","PeriodicalId":358814,"journal":{"name":"2018 International Conference on Applied Smart Systems (ICASS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125280697","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 : 2018-11-01DOI: 10.1109/ICASS.2018.8651998
M. Lazreg, A. Bentaallah
This paper presents a comparison between two control strategies, field oriented control (FOC) and sliding mode control (SMC). The first study has been done on controlling the double star induction machine (DSIM) by using field oriented control technique using a PI regulator. After, we present the theory of sliding mode control. We can see from the simulation results that the second proposed control system (SMC) is a robust nonlinear optimal controller. In order to reduce a torque ripple, the sign function is used, that is will be more explained in this paper. This present work was performed and simulated using our graphical interface ‘GUI’ realized under MATLAB.
{"title":"Differente control techniques for double star induction machine drive under GUI/Matlab","authors":"M. Lazreg, A. Bentaallah","doi":"10.1109/ICASS.2018.8651998","DOIUrl":"https://doi.org/10.1109/ICASS.2018.8651998","url":null,"abstract":"This paper presents a comparison between two control strategies, field oriented control (FOC) and sliding mode control (SMC). The first study has been done on controlling the double star induction machine (DSIM) by using field oriented control technique using a PI regulator. After, we present the theory of sliding mode control. We can see from the simulation results that the second proposed control system (SMC) is a robust nonlinear optimal controller. In order to reduce a torque ripple, the sign function is used, that is will be more explained in this paper. This present work was performed and simulated using our graphical interface ‘GUI’ realized under MATLAB.","PeriodicalId":358814,"journal":{"name":"2018 International Conference on Applied Smart Systems (ICASS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125396671","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 : 2018-11-01DOI: 10.1109/ICASS.2018.8652049
Meriem Ali Khoudja, Messaouda Fareh, Hafida Bouarfa
Ontology matching is an effective method to establish interoperability between heterogeneous ontologies. Artificial neural networks are powerful computational models biologically inspired from human brain, and the way how they learn and process information. They have proved their efficiency in many fields. In this paper, we aim at studying all the different ontology matching approaches based on neural networks, in order to conclude how to ideally make use of these machine learning models to match heterogeneous ontologies.
{"title":"Ontology Matching using Neural Networks: Survey and Analysis","authors":"Meriem Ali Khoudja, Messaouda Fareh, Hafida Bouarfa","doi":"10.1109/ICASS.2018.8652049","DOIUrl":"https://doi.org/10.1109/ICASS.2018.8652049","url":null,"abstract":"Ontology matching is an effective method to establish interoperability between heterogeneous ontologies. Artificial neural networks are powerful computational models biologically inspired from human brain, and the way how they learn and process information. They have proved their efficiency in many fields. In this paper, we aim at studying all the different ontology matching approaches based on neural networks, in order to conclude how to ideally make use of these machine learning models to match heterogeneous ontologies.","PeriodicalId":358814,"journal":{"name":"2018 International Conference on Applied Smart Systems (ICASS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116194836","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 : 2018-11-01DOI: 10.1109/ICASS.2018.8652074
A. Morsli, A. Tlemçani, A. Moualdia, L. Zellouma, M. Boucherit, N. Henini
This paper proposes a study, simulation for MATLAB/Simulink and realization of a shunt active power filtering system to improve the energy quality of the system. Let’s start with the problematic imposed on the low-voltage power system where we see the harmonics in the power grid imposed by the non-linear load voltage rectifier, electric motor, transformer, etc These harmonics pollute the supply network on the one hand and deteriorate the electrical devices on the other hand. To solve this problem, we have mounted a voltage inverter in parallel in the network between the power source and the load (our case a rectifier). This produces currents by offsetting all harmonics by applying direct power control (DPC). The results obtained in the laboratory by a test bench clearly show us that the graphs are similar with those obtained by the simulation. Then, the choice of the parameters of the system gave us a good quality of electrical energy. Thus, they meet the necessary conditions (THDis) less than 5% and ($(cos varphi )$ is close to unity) according to the recommendation IEEE519.
本文提出了一种基于MATLAB/Simulink的并联有源电力滤波系统的研究、仿真和实现，以提高系统的电能质量。让我们从低压电力系统的问题开始，我们看到电网中由非线性负载电压整流器，电动机，变压器等施加的谐波，这些谐波一方面污染了供电网络，另一方面恶化了电气设备。为了解决这个问题，我们在电源和负载之间的网络中并联了一个电压逆变器(我们的情况是整流器)。通过应用直接功率控制(DPC)来抵消所有谐波，从而产生电流。在实验室的试验台上得到的结果与模拟得到的结果非常接近。然后，系统参数的选择给我们提供了良好的电能质量。因此它们满足小于5的必要条件(THDis)% and ($(cos varphi )$ is close to unity) according to the recommendation IEEE519.
{"title":"Experimental Validation of a Shunt Active Power Filtering System for Improvement the Energy Quality employing the Direct Power Control","authors":"A. Morsli, A. Tlemçani, A. Moualdia, L. Zellouma, M. Boucherit, N. Henini","doi":"10.1109/ICASS.2018.8652074","DOIUrl":"https://doi.org/10.1109/ICASS.2018.8652074","url":null,"abstract":"This paper proposes a study, simulation for MATLAB/Simulink and realization of a shunt active power filtering system to improve the energy quality of the system. Let’s start with the problematic imposed on the low-voltage power system where we see the harmonics in the power grid imposed by the non-linear load voltage rectifier, electric motor, transformer, etc These harmonics pollute the supply network on the one hand and deteriorate the electrical devices on the other hand. To solve this problem, we have mounted a voltage inverter in parallel in the network between the power source and the load (our case a rectifier). This produces currents by offsetting all harmonics by applying direct power control (DPC). The results obtained in the laboratory by a test bench clearly show us that the graphs are similar with those obtained by the simulation. Then, the choice of the parameters of the system gave us a good quality of electrical energy. Thus, they meet the necessary conditions (THDis) less than 5% and ($(cos varphi )$ is close to unity) according to the recommendation IEEE519.","PeriodicalId":358814,"journal":{"name":"2018 International Conference on Applied Smart Systems (ICASS)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122830912","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 : 2018-11-01DOI: 10.1109/icass.2018.8652018
{"title":"ICASS 2018 Committees","authors":"","doi":"10.1109/icass.2018.8652018","DOIUrl":"https://doi.org/10.1109/icass.2018.8652018","url":null,"abstract":"","PeriodicalId":358814,"journal":{"name":"2018 International Conference on Applied Smart Systems (ICASS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123016820","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 : 2018-11-01DOI: 10.1109/ICASS.2018.8652001
C. Yasser, B. Mourad, Guemana Mouloud, Brahim Attaf
due to their spectacular properties, carbon nanotubes (CNTs) will open a wide horizon and a new field of creativity, research and innovation in many high performance applications. Inspired by this feedback and to improve the mechanical characteristics of a laminatesd composite plate based on unidirectional fibers without adding additional weight, one of the plys constituting the laminates has been replaced by a ply in CNT single-layer in this approach, the chosen displacement field is based on the theory of Yang, Norris and Stavsky. as well a computer program using the finite element method for calculating natural frequency has been developed. Two parametric studies were carried out: one on the influence of the interchangeability of the ply in CNT and the other on the effect of the angle of orientation of fibers in CNT. A good correlation was observed by comparing the results obtained with those available in the literature.
{"title":"Vibration analysis of hybrid composite plates reinforced with one ply of single-walled carbon nanotubes","authors":"C. Yasser, B. Mourad, Guemana Mouloud, Brahim Attaf","doi":"10.1109/ICASS.2018.8652001","DOIUrl":"https://doi.org/10.1109/ICASS.2018.8652001","url":null,"abstract":"due to their spectacular properties, carbon nanotubes (CNTs) will open a wide horizon and a new field of creativity, research and innovation in many high performance applications. Inspired by this feedback and to improve the mechanical characteristics of a laminatesd composite plate based on unidirectional fibers without adding additional weight, one of the plys constituting the laminates has been replaced by a ply in CNT single-layer in this approach, the chosen displacement field is based on the theory of Yang, Norris and Stavsky. as well a computer program using the finite element method for calculating natural frequency has been developed. Two parametric studies were carried out: one on the influence of the interchangeability of the ply in CNT and the other on the effect of the angle of orientation of fibers in CNT. A good correlation was observed by comparing the results obtained with those available in the literature.","PeriodicalId":358814,"journal":{"name":"2018 International Conference on Applied Smart Systems (ICASS)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129526772","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 : 2018-11-01DOI: 10.1109/ICASS.2018.8651947
Brahim Sahmadi, D. Boughaci
In medical data classification system, several parameters can affect its performance, notably, the quality of the features which poses problems in real applications. Some of the attributes are redundant while others are irrelevant, or are even unnecessary to the classification problem. Feature selection plays a crucial role in medical data analysis by identifying and removing irrelevant features from the training data. In this work, a feature subset selection method is proposed using hybridization of a genetic algorithm with a simulated annealing meta-heuristic and combined with SVM classifier. It tries to reduce the initial size of data and to select a set of relevant features to enhance the accuracy and speed of classification system. For evaluation, the proposed method is applied to eleven public medical datasets and then compared to two other methods of feature selection applied on the same datasets. Experimental results have shown that the proposed method with optimized SVM parameters gives competitive results and finds good quality solutions with small size.
{"title":"Hybrid Genetic Algorithm with SVM for Medical Data Classification","authors":"Brahim Sahmadi, D. Boughaci","doi":"10.1109/ICASS.2018.8651947","DOIUrl":"https://doi.org/10.1109/ICASS.2018.8651947","url":null,"abstract":"In medical data classification system, several parameters can affect its performance, notably, the quality of the features which poses problems in real applications. Some of the attributes are redundant while others are irrelevant, or are even unnecessary to the classification problem. Feature selection plays a crucial role in medical data analysis by identifying and removing irrelevant features from the training data. In this work, a feature subset selection method is proposed using hybridization of a genetic algorithm with a simulated annealing meta-heuristic and combined with SVM classifier. It tries to reduce the initial size of data and to select a set of relevant features to enhance the accuracy and speed of classification system. For evaluation, the proposed method is applied to eleven public medical datasets and then compared to two other methods of feature selection applied on the same datasets. Experimental results have shown that the proposed method with optimized SVM parameters gives competitive results and finds good quality solutions with small size.","PeriodicalId":358814,"journal":{"name":"2018 International Conference on Applied Smart Systems (ICASS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128381369","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 : 2018-11-01DOI: 10.1109/ICASS.2018.8652071
Y. Chiba, Y. Marif, A. Boukaoud, Laid Meredef, Youcef Kaidi
The present work deal to study the impact of green buildings on air conditioning type HVAC system. For this purpose, thermal balance based on Algerian norm has been used to predict the efficiency of installation of air conditioning system. The governing equations of thermal balance are described in detail in order to show the impact of green buildings. The obtain results including comparison between thermal coefficient of construction and thermal balance without and with using of the plants.
{"title":"Impact of green buildings on HVAC system located in Algeria","authors":"Y. Chiba, Y. Marif, A. Boukaoud, Laid Meredef, Youcef Kaidi","doi":"10.1109/ICASS.2018.8652071","DOIUrl":"https://doi.org/10.1109/ICASS.2018.8652071","url":null,"abstract":"The present work deal to study the impact of green buildings on air conditioning type HVAC system. For this purpose, thermal balance based on Algerian norm has been used to predict the efficiency of installation of air conditioning system. The governing equations of thermal balance are described in detail in order to show the impact of green buildings. The obtain results including comparison between thermal coefficient of construction and thermal balance without and with using of the plants.","PeriodicalId":358814,"journal":{"name":"2018 International Conference on Applied Smart Systems (ICASS)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121180584","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：