Pub Date : 2013-05-08DOI: 10.1109/SITA.2013.6560792
Jaouad A. Mouloud, E. H. Bouyakhf, D. Misane
The existence of real distributed satisfaction problems motivates researchers to focus on DisCSPs works. But few works that consider the real aspect of these problems, whether iii the modeling phase or resolution. Works that handle the modeling are limited in practice, to represent the information of the problem in one file. While DisCSPs works that handle resolution are restricted to consider these problems are fIxed, whereas in reality these problems change over time, which requires giving to agents the freedom to modify the information which affect their variables in the problem. In this paper we present the global architecture of interface realistic use and two protocols, the first one intended to distribute the problem in the platform DisChoco in a real distributed environment, while the second one is to modeling dynamically a part of the problem.
{"title":"Two novel protocols for automatic distribution and solving of real DisCSPs problems","authors":"Jaouad A. Mouloud, E. H. Bouyakhf, D. Misane","doi":"10.1109/SITA.2013.6560792","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560792","url":null,"abstract":"The existence of real distributed satisfaction problems motivates researchers to focus on DisCSPs works. But few works that consider the real aspect of these problems, whether iii the modeling phase or resolution. Works that handle the modeling are limited in practice, to represent the information of the problem in one file. While DisCSPs works that handle resolution are restricted to consider these problems are fIxed, whereas in reality these problems change over time, which requires giving to agents the freedom to modify the information which affect their variables in the problem. In this paper we present the global architecture of interface realistic use and two protocols, the first one intended to distribute the problem in the platform DisChoco in a real distributed environment, while the second one is to modeling dynamically a part of the problem.","PeriodicalId":145244,"journal":{"name":"2013 8th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121057304","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 : 2013-05-08DOI: 10.1109/SITA.2013.6560799
M. Merras, N. El Akkad, A. Saaidi, A. G. Nazih, K. Satori
In this paper, we present a new method of camera self-calibration with varying intrinsic parameters by an improved genetic algorithm. Firstly, the simplified Kruppa equation (the case of varying intrinsic parameters) defined by Hartley is translated into the optimized cost function. Secondly, the minimization of the cost function is calculated by an optimized modified genetic algorithm. Finally, the intrinsic parameters of the camera are obtained. Comparing to traditional optimization methods, the camera self-calibration with varying intrinsic parameters by this approach can avoid being trapped in a local minimum and converge quickly to the optimal solution without initial estimates of the camera parameters. Our study is performed on synthetic and real data to demonstrate the validity and performance of the presented approach. The results show that the proposed technique is both accurate and robust.
{"title":"A new method of camera self-calibration with varying intrinsic parameters using an improved genetic algorithm","authors":"M. Merras, N. El Akkad, A. Saaidi, A. G. Nazih, K. Satori","doi":"10.1109/SITA.2013.6560799","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560799","url":null,"abstract":"In this paper, we present a new method of camera self-calibration with varying intrinsic parameters by an improved genetic algorithm. Firstly, the simplified Kruppa equation (the case of varying intrinsic parameters) defined by Hartley is translated into the optimized cost function. Secondly, the minimization of the cost function is calculated by an optimized modified genetic algorithm. Finally, the intrinsic parameters of the camera are obtained. Comparing to traditional optimization methods, the camera self-calibration with varying intrinsic parameters by this approach can avoid being trapped in a local minimum and converge quickly to the optimal solution without initial estimates of the camera parameters. Our study is performed on synthetic and real data to demonstrate the validity and performance of the presented approach. The results show that the proposed technique is both accurate and robust.","PeriodicalId":145244,"journal":{"name":"2013 8th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126682304","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 : 2013-05-08DOI: 10.1109/SITA.2013.6560816
Boushaba Souhail, M. Kabbaj, Z. Bakkoury
Modeling is practically time-consuming and error-prone task. To help making process modeling easier, the use of process discovery is considered to be an efficient way to create a fitting process model. In this paper, we propose a new method for process discovery based on a process matrix representation to reduce the complexity of discovered processes.
{"title":"Process mining: Matrix representation for bloc discovery","authors":"Boushaba Souhail, M. Kabbaj, Z. Bakkoury","doi":"10.1109/SITA.2013.6560816","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560816","url":null,"abstract":"Modeling is practically time-consuming and error-prone task. To help making process modeling easier, the use of process discovery is considered to be an efficient way to create a fitting process model. In this paper, we propose a new method for process discovery based on a process matrix representation to reduce the complexity of discovered processes.","PeriodicalId":145244,"journal":{"name":"2013 8th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122251664","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 : 2013-05-08DOI: 10.1109/SITA.2013.6560803
Mohammed Moujabbir, M. Ramdani
In this paper, we propose a new method able to correct errors the dematerialization the documents, especially the invoice document. We use on Electronic document readers able to read and recognize the relevant information. The process consists on: digitizing an important quantity of documents and passing them through an electronic documents reader. Then treating (correcting) the error recognition. The final objective is to find an electronic document reflecting all information included in the original document (physical document). To achieve this issue we develop a new parser which is applicable to a large kind of documents, especially correcting the detected errors. This parser is based on the formal concept analysis.
{"title":"Fuzzy Galois connections for the extraction of temporal association rules","authors":"Mohammed Moujabbir, M. Ramdani","doi":"10.1109/SITA.2013.6560803","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560803","url":null,"abstract":"In this paper, we propose a new method able to correct errors the dematerialization the documents, especially the invoice document. We use on Electronic document readers able to read and recognize the relevant information. The process consists on: digitizing an important quantity of documents and passing them through an electronic documents reader. Then treating (correcting) the error recognition. The final objective is to find an electronic document reflecting all information included in the original document (physical document). To achieve this issue we develop a new parser which is applicable to a large kind of documents, especially correcting the detected errors. This parser is based on the formal concept analysis.","PeriodicalId":145244,"journal":{"name":"2013 8th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129451931","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 : 2013-05-08DOI: 10.1109/SITA.2013.6560800
M. Oujaoura, B. Minaoui, M. Fakir
Many features extraction method and classifiers are used singly, with modest results, for automatic image annotation. In order to improve the semantic image annotation accuracy, this document provides an automatic system to annotate image content by using a fusion of 3 classifier and a combination of some features extraction methods; multiclass support vector machine, multilayer neural network and nearest neighbour classifiers are combined together in order to classify and to find the appropriate keywords for this content. The color histograms and moments are used in this paper as features to represent image content. We support our case by experimental results obtained from two image databases (ETH-80 and coil-100 databases ).
{"title":"A semantic approach for automatic image annotation","authors":"M. Oujaoura, B. Minaoui, M. Fakir","doi":"10.1109/SITA.2013.6560800","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560800","url":null,"abstract":"Many features extraction method and classifiers are used singly, with modest results, for automatic image annotation. In order to improve the semantic image annotation accuracy, this document provides an automatic system to annotate image content by using a fusion of 3 classifier and a combination of some features extraction methods; multiclass support vector machine, multilayer neural network and nearest neighbour classifiers are combined together in order to classify and to find the appropriate keywords for this content. The color histograms and moments are used in this paper as features to represent image content. We support our case by experimental results obtained from two image databases (ETH-80 and coil-100 databases ).","PeriodicalId":145244,"journal":{"name":"2013 8th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114357591","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 : 2013-05-08DOI: 10.1109/SITA.2013.6560785
Ali Ouacha, J. El Abbadi, A. Habbani, B. Bouamoud
Energy consumption in mobile network might be excessive for some nodes acting as relays in OLSR network than others. This might have a considerable consequence on the network lifetime. Our approach is presented in the EDCR protocol. It is an extended version of OLSR which aims to increase the residual energy of the network by distributing forwarding tasks between MPRs. For that, we change the MPR procedure selection in order to favor nodes with the largest number of MPR-selector. Our hypothesis is experienced under NS2 and effectively results on less energy consumption.
{"title":"Proactive routing based distributed energy consumption","authors":"Ali Ouacha, J. El Abbadi, A. Habbani, B. Bouamoud","doi":"10.1109/SITA.2013.6560785","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560785","url":null,"abstract":"Energy consumption in mobile network might be excessive for some nodes acting as relays in OLSR network than others. This might have a considerable consequence on the network lifetime. Our approach is presented in the EDCR protocol. It is an extended version of OLSR which aims to increase the residual energy of the network by distributing forwarding tasks between MPRs. For that, we change the MPR procedure selection in order to favor nodes with the largest number of MPR-selector. Our hypothesis is experienced under NS2 and effectively results on less energy consumption.","PeriodicalId":145244,"journal":{"name":"2013 8th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128936048","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 : 2013-05-08DOI: 10.1109/SITA.2013.6560812
N. C. Benabdellah, M. Gharbi, Mostafa Bellajkih
E-Iearning is currently in expansion. Several studies were conducted to adapt courses according to learner's profile. In this article, we propose an e-Iearning adaptive system: Ant Colony Adaptive E-Learning (ACAEL). ACAEL is composed of three parts. The first part defines learner's profile using multi-criteria evaluation. We propose four criteria: active time spent consulting course units, evaluation time, number of attempts and finally the test score. Learner takes a global test and other tests corresponding to learning unit, during his elearning path. In the second part of ACAEL, using ant colony algorithm we define the succession of units and propose them to the learner. For each unit, the trainer assigns weights and a description of prerequisites and acquired information. We define units' succession and finally we obtain the personalized learner path. In the third part of ACEAL, we develop satisfaction survey component for learners and trainers, in order to improve course content and adaptive system.
{"title":"Content adaptation and learner profile definition: Ant colony algorithm application","authors":"N. C. Benabdellah, M. Gharbi, Mostafa Bellajkih","doi":"10.1109/SITA.2013.6560812","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560812","url":null,"abstract":"E-Iearning is currently in expansion. Several studies were conducted to adapt courses according to learner's profile. In this article, we propose an e-Iearning adaptive system: Ant Colony Adaptive E-Learning (ACAEL). ACAEL is composed of three parts. The first part defines learner's profile using multi-criteria evaluation. We propose four criteria: active time spent consulting course units, evaluation time, number of attempts and finally the test score. Learner takes a global test and other tests corresponding to learning unit, during his elearning path. In the second part of ACAEL, using ant colony algorithm we define the succession of units and propose them to the learner. For each unit, the trainer assigns weights and a description of prerequisites and acquired information. We define units' succession and finally we obtain the personalized learner path. In the third part of ACEAL, we develop satisfaction survey component for learners and trainers, in order to improve course content and adaptive system.","PeriodicalId":145244,"journal":{"name":"2013 8th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127856948","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 : 2013-05-08DOI: 10.1109/SITA.2013.6560790
Lamia Ben Hiba, M. Idrissi
Ineffective communication practices are a recurrent issue for project virtual teams that solely communicate using social and collaborative platforms. Since that communication is critical in virtual structures, monitoring it closely is a key factor for the success of the project at hand. In previous works, we proposed a three-aspects (structural, intrinsic and functional) based framework that examines virtual teams through a network perspective using Social Network Analysis (SNA). We also suggested building an SNA system, which integrates some Business Intelligence concepts, for evaluating the structural aspect of project virtual teams, based on data collected from social collaborative platforms. As the system necessitates effective ways for data storage and rendering, we delve, in this paper, into more details of the BI component of the proposed system.
{"title":"Towards an SNA-BI based support system for the structural evaluation of project virtual teams","authors":"Lamia Ben Hiba, M. Idrissi","doi":"10.1109/SITA.2013.6560790","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560790","url":null,"abstract":"Ineffective communication practices are a recurrent issue for project virtual teams that solely communicate using social and collaborative platforms. Since that communication is critical in virtual structures, monitoring it closely is a key factor for the success of the project at hand. In previous works, we proposed a three-aspects (structural, intrinsic and functional) based framework that examines virtual teams through a network perspective using Social Network Analysis (SNA). We also suggested building an SNA system, which integrates some Business Intelligence concepts, for evaluating the structural aspect of project virtual teams, based on data collected from social collaborative platforms. As the system necessitates effective ways for data storage and rendering, we delve, in this paper, into more details of the BI component of the proposed system.","PeriodicalId":145244,"journal":{"name":"2013 8th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121505617","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 : 2013-05-08DOI: 10.1109/SITA.2013.6560791
A. Berrado, Safae Elfahli, Wafa El Garah
Mobile payment has proven to be successful all over the world not only in developed countries but also in developing ones. In Morocco, some banks have already launched an offer related to money transfer via mobiles and have the intention to suggest mobile payment solutions to their clients. But before implementing such a technology, it is important to know if Moroccans are willing to adopt it or not. In this work, we explore factors that affect future users' intention towards mobile payment. To this end, we adopted technology acceptance model to assess whether ease of use, usefulness, risk perception and transaction fees affect their willingness to adopt this technology. To investigate the relationship between these variables, an empirical analysis was conducted based on data mining techniques. Our results indicate that ease of use, usefulness, risk perception and transaction fees affect Moroccans' intention to adopt mobile payment but with different degrees of impact. Empirical evidence indicated that ease of use and risk perception are the most influent factors.
{"title":"Using data mining techniques to investigate the factors influencing mobile payment adoption in Morocco","authors":"A. Berrado, Safae Elfahli, Wafa El Garah","doi":"10.1109/SITA.2013.6560791","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560791","url":null,"abstract":"Mobile payment has proven to be successful all over the world not only in developed countries but also in developing ones. In Morocco, some banks have already launched an offer related to money transfer via mobiles and have the intention to suggest mobile payment solutions to their clients. But before implementing such a technology, it is important to know if Moroccans are willing to adopt it or not. In this work, we explore factors that affect future users' intention towards mobile payment. To this end, we adopted technology acceptance model to assess whether ease of use, usefulness, risk perception and transaction fees affect their willingness to adopt this technology. To investigate the relationship between these variables, an empirical analysis was conducted based on data mining techniques. Our results indicate that ease of use, usefulness, risk perception and transaction fees affect Moroccans' intention to adopt mobile payment but with different degrees of impact. Empirical evidence indicated that ease of use and risk perception are the most influent factors.","PeriodicalId":145244,"journal":{"name":"2013 8th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132423004","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 : 2013-05-08DOI: 10.1109/SITA.2013.6560810
A. Abdelli, L. Benabbou, Z. Dahani, K. Dalli, A. Berrado
The Moroccan financial system has undergone major changes since the early 90s. The financial market authority makes available a multitude of public information and statistics on the financial operations of the issuers. Other than the classification by sector or by type and / or amount of the issue, there is no classification model to predict the behavior of an issuer based on financial indicators. In this context, this work aims to develop an actionable classification scheme to explain and predict the behavior of issuers in the Moroccan financial market. A database of financial operations of various issuers between 1995 and 2011 was built. Thereafter, classes of these issuers were constructed via unsupervised learning techniques. Clustering of time series of issuers and their corresponding amounts reported by year, allowed for finely learning and defining classes of issuers, taking into account the temporal dimension. Based on the clusters from the first step, a supervised tree based classification model was developed to predict the class of new issuers on the Moroccan financial market.
{"title":"A classification framework of issuers in the Moroccan financial market","authors":"A. Abdelli, L. Benabbou, Z. Dahani, K. Dalli, A. Berrado","doi":"10.1109/SITA.2013.6560810","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560810","url":null,"abstract":"The Moroccan financial system has undergone major changes since the early 90s. The financial market authority makes available a multitude of public information and statistics on the financial operations of the issuers. Other than the classification by sector or by type and / or amount of the issue, there is no classification model to predict the behavior of an issuer based on financial indicators. In this context, this work aims to develop an actionable classification scheme to explain and predict the behavior of issuers in the Moroccan financial market. A database of financial operations of various issuers between 1995 and 2011 was built. Thereafter, classes of these issuers were constructed via unsupervised learning techniques. Clustering of time series of issuers and their corresponding amounts reported by year, allowed for finely learning and defining classes of issuers, taking into account the temporal dimension. Based on the clusters from the first step, a supervised tree based classification model was developed to predict the class of new issuers on the Moroccan financial market.","PeriodicalId":145244,"journal":{"name":"2013 8th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130888426","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：