Pub Date : 2013-05-08DOI: 10.1109/SITA.2013.6560788
You-Jin Park, Ha-Ran Hwang
In this research, we consider a scheduling problem in photolithography process of semiconductor manufacturing. Generally, the photolithography process can be regarded as the most important processes since it may affect the fab productivity due to its various technological attributes. Physically, the photolithography equipment consists of three main parts: scanner, spinner, and developer, and it is designed to process different types of products as a machine for general purpose. However, in current semiconductor fab system, the same type of product is processed in order to reduce recipe change time incurred by changing masks in scanner module. So, in this study, the multi-product production case with different recipes is considered in photolithography process, and 4 different lot-wafer input methods are evaluated from makespan point of view.
{"title":"A rule-based simulation approach to scheduling problem in semiconductor photolithography process","authors":"You-Jin Park, Ha-Ran Hwang","doi":"10.1109/SITA.2013.6560788","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560788","url":null,"abstract":"In this research, we consider a scheduling problem in photolithography process of semiconductor manufacturing. Generally, the photolithography process can be regarded as the most important processes since it may affect the fab productivity due to its various technological attributes. Physically, the photolithography equipment consists of three main parts: scanner, spinner, and developer, and it is designed to process different types of products as a machine for general purpose. However, in current semiconductor fab system, the same type of product is processed in order to reduce recipe change time incurred by changing masks in scanner module. So, in this study, the multi-product production case with different recipes is considered in photolithography process, and 4 different lot-wafer input methods are evaluated from makespan point of view.","PeriodicalId":145244,"journal":{"name":"2013 8th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"9 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114024874","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.2013.6560801
Rdioud Boutaina, Oulad Haj Thami Rachid, E. Mohammed
In this article, we present a new method which allows tracking multiple people in real-time in a closed environment from their trajectory. The trajectory of each person is determined by his/her position occupied at each time t in order to trace the trajectory in real time. This method has the advantage of keeping track of people based on the combination of the method of the analysis of connected components and the points of interest detected by the method of Harris [6]. The position of these points in relation to the connected components can make the correspondence between the tracked people and connected components detected by subtracting the background. Then, the trajectory traversed by each person is determined from tracking the position of the center of gravity of the points of interest of each person.
{"title":"Tracking multiple people in real time based on their trajectory","authors":"Rdioud Boutaina, Oulad Haj Thami Rachid, E. Mohammed","doi":"10.1109/SITA.2013.6560801","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560801","url":null,"abstract":"In this article, we present a new method which allows tracking multiple people in real-time in a closed environment from their trajectory. The trajectory of each person is determined by his/her position occupied at each time t in order to trace the trajectory in real time. This method has the advantage of keeping track of people based on the combination of the method of the analysis of connected components and the points of interest detected by the method of Harris [6]. The position of these points in relation to the connected components can make the correspondence between the tracked people and connected components detected by subtracting the background. Then, the trajectory traversed by each person is determined from tracking the position of the center of gravity of the points of interest of each person.","PeriodicalId":145244,"journal":{"name":"2013 8th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"60 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":"126500324","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.2013.6560798
A. Naji, M. Ramdani
This paper is focused on the automatic recontextualization, and the conception and operationalization upgrade of learning scenarios in environment for human learning. On the one hand, the learners' levels knowledge allow designers and teachers to discover: blocking situations and steps leading students to fail. On the other hand, they are used to calculate a new scenario from the set of scenarios describing the same pedagogical objective. For this purpose, the choice of a modelling language and its infrastructure is relevant. The study of different modelling languages allows us to find that the adaptation of learning is far than the sought outcomes. In this paper, our choice is particularly fixed on the LDL model in which we provide some extensions to promote the adaptation and regulation of learning.
{"title":"Proposal for a metamodel of studied domain & automatic re-contextualization of learning scenarios","authors":"A. Naji, M. Ramdani","doi":"10.1109/SITA.2013.6560798","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560798","url":null,"abstract":"This paper is focused on the automatic recontextualization, and the conception and operationalization upgrade of learning scenarios in environment for human learning. On the one hand, the learners' levels knowledge allow designers and teachers to discover: blocking situations and steps leading students to fail. On the other hand, they are used to calculate a new scenario from the set of scenarios describing the same pedagogical objective. For this purpose, the choice of a modelling language and its infrastructure is relevant. The study of different modelling languages allows us to find that the adaptation of learning is far than the sought outcomes. In this paper, our choice is particularly fixed on the LDL model in which we provide some extensions to promote the adaptation and regulation of learning.","PeriodicalId":145244,"journal":{"name":"2013 8th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"42 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":"131152932","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.2013.6560820
A. A. E. Kalam, A. A. E. Hassani, A. A. Ouahman
OrBAC is becoming more successful thanks to the various benefits it offers. However, it does not enable expressing the different facets of integrity, an essential property for critical infrastructures (CIs). In this paper, we propose "IntegrityOrBAC", an OrBAC enhancement that takes into account integrity while expressing local security policies. We start, first, by focusing on the CIs integrity need and then we recall briefly the OrBAC model concepts. After that, we detail the I-OrBAC model by defining a lexicon related to the different integrity variations to better appreciate the importance of this property in the case of CIs. Next, we justify why we opt for multi integrity levels approach, we present the I-OrBAC components and then show an example of a policy expressed thanks to the proposed model. We also emphasize the flexibility offered by I-OrBAC.
{"title":"Integrity-OrBAC: An OrBAC enhancement that takes into account integrity","authors":"A. A. E. Kalam, A. A. E. Hassani, A. A. Ouahman","doi":"10.1109/SITA.2013.6560820","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560820","url":null,"abstract":"OrBAC is becoming more successful thanks to the various benefits it offers. However, it does not enable expressing the different facets of integrity, an essential property for critical infrastructures (CIs). In this paper, we propose \"IntegrityOrBAC\", an OrBAC enhancement that takes into account integrity while expressing local security policies. We start, first, by focusing on the CIs integrity need and then we recall briefly the OrBAC model concepts. After that, we detail the I-OrBAC model by defining a lexicon related to the different integrity variations to better appreciate the importance of this property in the case of CIs. Next, we justify why we opt for multi integrity levels approach, we present the I-OrBAC components and then show an example of a policy expressed thanks to the proposed model. We also emphasize the flexibility offered by I-OrBAC.","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":"133685381","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.2013.6560809
M. Merzougui, M. Nasri, B. Bouali
The lsodata algorithm is an unsupervised data classification algorithm. Its result depends strongly on two parameters: distance threshold for the union of clusters and threshold of typical deviation for the division of a cluster. A bad choice of these two parameters leads the algorithm to spiral out of control leaving the end only one class. To determine these parameters and improvements to this algorithm, evolution strategies are used. An evolutionary algorithm is adapted to estimate the two optimal thresholds to be used by the algorithm then lsodata. This approach is validated on simulation examples. The experimental results confirm the favorable convergence speed and good performance of the proposed algorithm.
{"title":"ISODATA classification with parameters estimated by evolutionary approach","authors":"M. Merzougui, M. Nasri, B. Bouali","doi":"10.1109/SITA.2013.6560809","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560809","url":null,"abstract":"The lsodata algorithm is an unsupervised data classification algorithm. Its result depends strongly on two parameters: distance threshold for the union of clusters and threshold of typical deviation for the division of a cluster. A bad choice of these two parameters leads the algorithm to spiral out of control leaving the end only one class. To determine these parameters and improvements to this algorithm, evolution strategies are used. An evolutionary algorithm is adapted to estimate the two optimal thresholds to be used by the algorithm then lsodata. This approach is validated on simulation examples. The experimental results confirm the favorable convergence speed and good performance of the proposed algorithm.","PeriodicalId":145244,"journal":{"name":"2013 8th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"992 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":"116449969","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.2013.6560806
M. Ettaouil, M. Lazaar, Zakariae En-Naimani
Thanks to Automatic Speech Recognition (ASR), a lot of machines can nowadays emulate human being ability to understand and speak natural language. However, ASR problematic could be as interesting as it is difficult. Its difficulty is precisely due to the complexity of speech processing, which takes into consideration many aspects: acoustic, phonetic, syntactic, etc. Thus, the most commonly used technology, in the context of speech recognition, is based on statistical models. Especially, the Hidden Markov Models that are capable of simultaneously modeling frequency and temporal characteristics of the speech signal. There is also the alternative of using Neuronal Networks. But another interesting framework applied in ASR is indeed the hybrid Artificial Neural Network (ANN) and Hidden Markov Model (HMM) speech recognizer that improves the accuracy of the two models. In the present work, we propose an Arabic digits recognition system based on hybrid Artificial Neural Network and Hidden Markov Model (ANN/HMM). The main innovation in this work is to use an optimal neural network to determine the optimal class, unlike in classical Kohonen approach. The numerical results are encouraging and satisfactory.
{"title":"A hybrid ANN/HMM models for arabic speech recognition using optimal codebook","authors":"M. Ettaouil, M. Lazaar, Zakariae En-Naimani","doi":"10.1109/SITA.2013.6560806","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560806","url":null,"abstract":"Thanks to Automatic Speech Recognition (ASR), a lot of machines can nowadays emulate human being ability to understand and speak natural language. However, ASR problematic could be as interesting as it is difficult. Its difficulty is precisely due to the complexity of speech processing, which takes into consideration many aspects: acoustic, phonetic, syntactic, etc. Thus, the most commonly used technology, in the context of speech recognition, is based on statistical models. Especially, the Hidden Markov Models that are capable of simultaneously modeling frequency and temporal characteristics of the speech signal. There is also the alternative of using Neuronal Networks. But another interesting framework applied in ASR is indeed the hybrid Artificial Neural Network (ANN) and Hidden Markov Model (HMM) speech recognizer that improves the accuracy of the two models. In the present work, we propose an Arabic digits recognition system based on hybrid Artificial Neural Network and Hidden Markov Model (ANN/HMM). The main innovation in this work is to use an optimal neural network to determine the optimal class, unlike in classical Kohonen approach. The numerical results are encouraging and satisfactory.","PeriodicalId":145244,"journal":{"name":"2013 8th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"81 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":"122898550","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.2013.6560818
I. Bellamine, H. Tairi
Among all the features which can be extracted from videos, we propose to use Space-Time Interest Points (STIP), these ones are particularly interesting because they are simple and robust. They allow a good characterization of a set of regions of interest corresponding to moving objects in a three-dimensional observed scene. In this paper, we propose to apply the algorithm of the detection of spatiotemporal interest points for a good detection of moving objects on both components of the decomposition: a geometric structure component and a texture component. Proposed results are obtained from very different types of videos, namely sport videos and animation movies.
{"title":"Detecting motion using the Structure-Texture Image Decomposition and Space-Time Interest Points","authors":"I. Bellamine, H. Tairi","doi":"10.1109/SITA.2013.6560818","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560818","url":null,"abstract":"Among all the features which can be extracted from videos, we propose to use Space-Time Interest Points (STIP), these ones are particularly interesting because they are simple and robust. They allow a good characterization of a set of regions of interest corresponding to moving objects in a three-dimensional observed scene. In this paper, we propose to apply the algorithm of the detection of spatiotemporal interest points for a good detection of moving objects on both components of the decomposition: a geometric structure component and a texture component. Proposed results are obtained from very different types of videos, namely sport videos and animation movies.","PeriodicalId":145244,"journal":{"name":"2013 8th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"17 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":"129847111","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.2013.6560811
Hicham Gueddah, Abdallah Yousfi
Following a statistical study carried out on the typographical errors committed when typing documents in Arabic language, it was found that most of these typos are character permutation errors, accounting for 65% of overall errors. Similarly, in the aim to overcome this situation and while analyzing such errors, it turned out that character permutation resulting in a misspelled word can be imputed either to character proximity on an Arabic keyboard or to calligraphic similarity between such Arabic characters. In order to remedy this problem, we suggest, in this article, that a measurement of proximity and similarity between Arabic characters be integrated into Levenshtein algorithm, in the aim of enhancing the suggestions and the scheduling of the solutions returned by the spelling correction. The experimental outcomes are very satisfactory and attest of the necessity of integrating inter-character proximity and similarity measures for Arabic within spell-checking systems.
{"title":"The impact of arabic inter-character proximity and similarity on spell-checking","authors":"Hicham Gueddah, Abdallah Yousfi","doi":"10.1109/SITA.2013.6560811","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560811","url":null,"abstract":"Following a statistical study carried out on the typographical errors committed when typing documents in Arabic language, it was found that most of these typos are character permutation errors, accounting for 65% of overall errors. Similarly, in the aim to overcome this situation and while analyzing such errors, it turned out that character permutation resulting in a misspelled word can be imputed either to character proximity on an Arabic keyboard or to calligraphic similarity between such Arabic characters. In order to remedy this problem, we suggest, in this article, that a measurement of proximity and similarity between Arabic characters be integrated into Levenshtein algorithm, in the aim of enhancing the suggestions and the scheduling of the solutions returned by the spelling correction. The experimental outcomes are very satisfactory and attest of the necessity of integrating inter-character proximity and similarity measures for Arabic within spell-checking systems.","PeriodicalId":145244,"journal":{"name":"2013 8th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"104 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":"128586817","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.2013.6560802
I. Abdelbaki, E. Benlahmar, E. Labriji
Searching for information on the Internet is not only an essential way to get information, but also a strategic tool to obtain a wide variety of information. Unfortunately, Web is so huge and so unstructured that the collection of specific, fair and useful information becomes a daunting ant time-wasting task. To define information research tool (metasearch engine) which has the aim to combine several sources of information, the main interest should be brought to the fusion step of results from search engines. Several reasons led us to define a fusion method based on user profile. Indeed, the major problem of fusion approaches is that the information is so general that the specific needs of the user could not be fitted.
{"title":"Result merging for meta-search engine","authors":"I. Abdelbaki, E. Benlahmar, E. Labriji","doi":"10.1109/SITA.2013.6560802","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560802","url":null,"abstract":"Searching for information on the Internet is not only an essential way to get information, but also a strategic tool to obtain a wide variety of information. Unfortunately, Web is so huge and so unstructured that the collection of specific, fair and useful information becomes a daunting ant time-wasting task. To define information research tool (metasearch engine) which has the aim to combine several sources of information, the main interest should be brought to the fusion step of results from search engines. Several reasons led us to define a fusion method based on user profile. Indeed, the major problem of fusion approaches is that the information is so general that the specific needs of the user could not be fitted.","PeriodicalId":145244,"journal":{"name":"2013 8th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"28 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":"115077400","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 : 2012-03-03DOI: 10.1109/SITA.2013.6560789
A. Mouzoune
Most of the work has emphasized upon of the underlying Information and Communication Technologies ICT infrastructure since the concept of e-maintenance was introduced. The main issue of the carried out works related to "emaintenance" is integrating different systems relative to maintenance into one information system. This paper aims to reconsider the predominance of ICT within e-maintenance projects and literature and highlights the importance of intelligence as a fundamental dimension of e-maintenance that is to be considered in a holistic predefined manner rather than isolated efforts within ICT driven approaches. This work also proposes a model of e-maintenance system as a contribution towards an intelligence based e-maintenance conceptual framework based on CogAff architecture for intelligent agents. Furthermore, a case study is defined sustaining the use of the proposed model in relation to the classification of existing emaintenance platforms which underlines two issues of existing emaintenance solutions regarding to real integration of the system into human teams and more integration at the management strategic level.
{"title":"Towards an intelligence based conceptual framework for e-maintenance","authors":"A. Mouzoune","doi":"10.1109/SITA.2013.6560789","DOIUrl":"https://doi.org/10.1109/SITA.2013.6560789","url":null,"abstract":"Most of the work has emphasized upon of the underlying Information and Communication Technologies ICT infrastructure since the concept of e-maintenance was introduced. The main issue of the carried out works related to \"emaintenance\" is integrating different systems relative to maintenance into one information system. This paper aims to reconsider the predominance of ICT within e-maintenance projects and literature and highlights the importance of intelligence as a fundamental dimension of e-maintenance that is to be considered in a holistic predefined manner rather than isolated efforts within ICT driven approaches. This work also proposes a model of e-maintenance system as a contribution towards an intelligence based e-maintenance conceptual framework based on CogAff architecture for intelligent agents. Furthermore, a case study is defined sustaining the use of the proposed model in relation to the classification of existing emaintenance platforms which underlines two issues of existing emaintenance solutions regarding to real integration of the system into human teams and more integration at the management strategic level.","PeriodicalId":145244,"journal":{"name":"2013 8th International Conference on Intelligent Systems: Theories and Applications (SITA)","volume":"7 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127993010","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：