Pub Date : 2008-04-07DOI: 10.1109/ICTTA.2008.4530086
A. Bougarradh, S. M'hiri, F. Ghorbel
In this paper, we propose to introduce the bootstrap resampling technique in the generalized mixture estimation. The generalized aspect comes from the use of the probability density function (pdf) estimation coming from the Pearson system. The bootstrap sample is constructed by randomly selecting a small representative set of pixels from the original image. The application of the Bootstrapped Generalized Mixture Expectation Maximization algorithm BGMEM led us to define a new empirical criterion of representativity of the sample. We give some simulation results for the determination of the empirical criterion. We validate our criterion by the application of the algorithm to the problem of unsupervised image classification.
{"title":"Introduction of the bootstrap resampling in the generalized mixture estimation","authors":"A. Bougarradh, S. M'hiri, F. Ghorbel","doi":"10.1109/ICTTA.2008.4530086","DOIUrl":"https://doi.org/10.1109/ICTTA.2008.4530086","url":null,"abstract":"In this paper, we propose to introduce the bootstrap resampling technique in the generalized mixture estimation. The generalized aspect comes from the use of the probability density function (pdf) estimation coming from the Pearson system. The bootstrap sample is constructed by randomly selecting a small representative set of pixels from the original image. The application of the Bootstrapped Generalized Mixture Expectation Maximization algorithm BGMEM led us to define a new empirical criterion of representativity of the sample. We give some simulation results for the determination of the empirical criterion. We validate our criterion by the application of the algorithm to the problem of unsupervised image classification.","PeriodicalId":330215,"journal":{"name":"2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127512045","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 : 2008-04-07DOI: 10.1109/ICTTA.2008.4530164
R. Romadi, H. Berbia
A Wireless Sensor Network (WSN) is one that is in continual interaction with its environment, and executes at a pace determined by that environment. The use of rigorous formal method in specification and validation can help designers to limit the introduction of potentially faulty components during the construction of the system. Due to their complex nature, WSN are extremely difficult to specify and validate. In this paper, we propose a new formal model for the specification and the validation of such systems. This approach considers a WSN as a Reactive Multi-Agent System consisting of concurrent reactive agents that cooperate with each other to achieve the desired functionality. In addition, this approach uses formal synchronous specification and verification tools in order to specify and to verify the systems behaviors.
{"title":"Wireless Sensor Network A specification method based on Reactive Decisional Agents","authors":"R. Romadi, H. Berbia","doi":"10.1109/ICTTA.2008.4530164","DOIUrl":"https://doi.org/10.1109/ICTTA.2008.4530164","url":null,"abstract":"A Wireless Sensor Network (WSN) is one that is in continual interaction with its environment, and executes at a pace determined by that environment. The use of rigorous formal method in specification and validation can help designers to limit the introduction of potentially faulty components during the construction of the system. Due to their complex nature, WSN are extremely difficult to specify and validate. In this paper, we propose a new formal model for the specification and the validation of such systems. This approach considers a WSN as a Reactive Multi-Agent System consisting of concurrent reactive agents that cooperate with each other to achieve the desired functionality. In addition, this approach uses formal synchronous specification and verification tools in order to specify and to verify the systems behaviors.","PeriodicalId":330215,"journal":{"name":"2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127550858","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 : 2008-04-07DOI: 10.1109/ICTTA.2008.4530127
A. Chaari, M. Ahmed, S. Lelandais
We propose in this paper a search approach which aim to improve identification in biometric databases. We work with face images and we develop appearance-based Eigenfaces method to generate holistic and discriminant features. These feature vectors, which describe faces, are often used to establish the required identity in a recognition process. In this work, we introduce a clustering process which aims to split biometric databases into partitions and to simplify consequently recognition task within these databases. Various studies were undertaken on search strategies to adjust feature extraction and clustering parameters. We simulate four experts which learn differently and acquire various knowledge to recognize facial images. In addition, we evaluate the robustness and the performance of our approach against noise effect through different test series. We propose, finally, to combine and to fuse clustering classifiers and identification processes what improve and simplify our recognition system task.
{"title":"Appearance based face identification and classification. A Combining approach","authors":"A. Chaari, M. Ahmed, S. Lelandais","doi":"10.1109/ICTTA.2008.4530127","DOIUrl":"https://doi.org/10.1109/ICTTA.2008.4530127","url":null,"abstract":"We propose in this paper a search approach which aim to improve identification in biometric databases. We work with face images and we develop appearance-based Eigenfaces method to generate holistic and discriminant features. These feature vectors, which describe faces, are often used to establish the required identity in a recognition process. In this work, we introduce a clustering process which aims to split biometric databases into partitions and to simplify consequently recognition task within these databases. Various studies were undertaken on search strategies to adjust feature extraction and clustering parameters. We simulate four experts which learn differently and acquire various knowledge to recognize facial images. In addition, we evaluate the robustness and the performance of our approach against noise effect through different test series. We propose, finally, to combine and to fuse clustering classifiers and identification processes what improve and simplify our recognition system task.","PeriodicalId":330215,"journal":{"name":"2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125770600","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 : 2008-04-07DOI: 10.1109/ICTTA.2008.4530069
A. Lachouri, K. Baiche, R. Djeghader, N. Doghmane, S. Ouhtati
This paper introduces a new methodology for fault diagnosis of rotating machinery in complex industrial process. In this fault diagnosis system, multi-scale principal component analysis (MSPCA) is used. The main contribution of this paper is the use of the MSPCA technique in the fault diagnosis based on vibration analysis in rotating machinery. Their maintenance as well as their diagnosis then became an economic state. It is important to early detect the faults likely to appear in those motors and to implement a preventive maintenance.
{"title":"Analyze and Fault Diagnosis by Multi-scale PCA","authors":"A. Lachouri, K. Baiche, R. Djeghader, N. Doghmane, S. Ouhtati","doi":"10.1109/ICTTA.2008.4530069","DOIUrl":"https://doi.org/10.1109/ICTTA.2008.4530069","url":null,"abstract":"This paper introduces a new methodology for fault diagnosis of rotating machinery in complex industrial process. In this fault diagnosis system, multi-scale principal component analysis (MSPCA) is used. The main contribution of this paper is the use of the MSPCA technique in the fault diagnosis based on vibration analysis in rotating machinery. Their maintenance as well as their diagnosis then became an economic state. It is important to early detect the faults likely to appear in those motors and to implement a preventive maintenance.","PeriodicalId":330215,"journal":{"name":"2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications","volume":"30 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125818324","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 : 2008-04-07DOI: 10.1109/ICTTA.2008.4530018
Salah Kermiche, H. A. Abbassi
Real systems have in general significant characteristics such as high-order, nonlinearities, dead- time, etc. and they can be affected by noise, load disturbances and other environment conditions that cause parameter variations and sudden modifications of the model structure. One of the main difficulties in the tuning of the PID parameters is to address at the same time different control specifications. In particular, achieving a high load disturbance rejection performance generally results in an aggressive tuning that provides a too oscillatory set-point step response. A fuzzy inference system is adopted to determine the value of the weight that multiplies the set-point for the proportional action. This contribution introduces genetic algorithms to change the shapes of the membership of the fuzzy controller by changing their basic parameters.
{"title":"Fuzzy PID Controller Parameters Optimized by Genetic Algorithms","authors":"Salah Kermiche, H. A. Abbassi","doi":"10.1109/ICTTA.2008.4530018","DOIUrl":"https://doi.org/10.1109/ICTTA.2008.4530018","url":null,"abstract":"Real systems have in general significant characteristics such as high-order, nonlinearities, dead- time, etc. and they can be affected by noise, load disturbances and other environment conditions that cause parameter variations and sudden modifications of the model structure. One of the main difficulties in the tuning of the PID parameters is to address at the same time different control specifications. In particular, achieving a high load disturbance rejection performance generally results in an aggressive tuning that provides a too oscillatory set-point step response. A fuzzy inference system is adopted to determine the value of the weight that multiplies the set-point for the proportional action. This contribution introduces genetic algorithms to change the shapes of the membership of the fuzzy controller by changing their basic parameters.","PeriodicalId":330215,"journal":{"name":"2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125894850","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 : 2008-04-07DOI: 10.1109/ICTTA.2008.4530024
Messaoud Bengherabi, B. Tounsi, H. Bessalah, F. Harizi
Starting from the fact of the lack of Arabic databases dedicated to performance evaluation of speaker recognition and forensic reporting systems. We present in this paper our experience in constructing an Algerian dialect database and the motivation beyond this work. After that, the corpus based Bayesian framework for interpretation of evidence in forensic systems in terms of likelihood ratio (LR) is applied on this database under different recording conditions: microphone, fixed and cellular. Preliminary results in terms of Receiver Operating Characteristics (ROC) and TIPPET plots show higher accuracy in matched conditions of training and testing. However, the performance degrades significantly in mismatched conditions.
{"title":"Forensic Identification Reporting Using A GMM Based Speaker Recognition System Dedicated to Algerian Arabic Dialect Speakers","authors":"Messaoud Bengherabi, B. Tounsi, H. Bessalah, F. Harizi","doi":"10.1109/ICTTA.2008.4530024","DOIUrl":"https://doi.org/10.1109/ICTTA.2008.4530024","url":null,"abstract":"Starting from the fact of the lack of Arabic databases dedicated to performance evaluation of speaker recognition and forensic reporting systems. We present in this paper our experience in constructing an Algerian dialect database and the motivation beyond this work. After that, the corpus based Bayesian framework for interpretation of evidence in forensic systems in terms of likelihood ratio (LR) is applied on this database under different recording conditions: microphone, fixed and cellular. Preliminary results in terms of Receiver Operating Characteristics (ROC) and TIPPET plots show higher accuracy in matched conditions of training and testing. However, the performance degrades significantly in mismatched conditions.","PeriodicalId":330215,"journal":{"name":"2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125909754","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 : 2008-04-07DOI: 10.1109/ICTTA.2008.4530273
M. Guennoun, M. Zandi, K. El-Khatib
The fast improvements in a variety of technologies such as microprocessing, sensing material, and most importantly wireless technology resulted in development of the wireless sensor network technology. Wireless sensors that can be either implantable inside the human body or wearable by individuals are called the wireless biosensors. The wireless biosensors are used to gather real time and continuous medical data from different parts of the human beings. This medical data is typically sent to an external sensor and then to its associated destination where data processing and a final decision is carried out. Due to nature of medical data and their usage, ensuring the security of this data is extremely important. There are several limitations associated with biosensor networks such as limitation in power, memory, computation capability, and communication rate which makes the wireless biosensor security a real challenging problem. These security challenges form substantial barriers for the wide adoption of the technology. Biometrics approach is an efficient way to overcome the insecurity of the wireless biosensor networks. In this paper, we will look at how biometrics has helped securing data in wireless biosensor networks, and present the remaining challenges to have a workable biometric-based security framework for wireless biosensor networks.
{"title":"On the Use of Biometrics to Secure Wireless Biosensor Networks","authors":"M. Guennoun, M. Zandi, K. El-Khatib","doi":"10.1109/ICTTA.2008.4530273","DOIUrl":"https://doi.org/10.1109/ICTTA.2008.4530273","url":null,"abstract":"The fast improvements in a variety of technologies such as microprocessing, sensing material, and most importantly wireless technology resulted in development of the wireless sensor network technology. Wireless sensors that can be either implantable inside the human body or wearable by individuals are called the wireless biosensors. The wireless biosensors are used to gather real time and continuous medical data from different parts of the human beings. This medical data is typically sent to an external sensor and then to its associated destination where data processing and a final decision is carried out. Due to nature of medical data and their usage, ensuring the security of this data is extremely important. There are several limitations associated with biosensor networks such as limitation in power, memory, computation capability, and communication rate which makes the wireless biosensor security a real challenging problem. These security challenges form substantial barriers for the wide adoption of the technology. Biometrics approach is an efficient way to overcome the insecurity of the wireless biosensor networks. In this paper, we will look at how biometrics has helped securing data in wireless biosensor networks, and present the remaining challenges to have a workable biometric-based security framework for wireless biosensor networks.","PeriodicalId":330215,"journal":{"name":"2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123775262","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 : 2008-04-07DOI: 10.1109/ICTTA.2008.4530081
N. Atamena, Z. Tifedjadjine, Z. Dibi, A. Bouridane
Halftone images are often difficult to be processed without causing severe degradation contrary to grayscale images. This gives the purpose to improve many techniques to reconstruct from their corresponding halftones the continuous images that permits a wide range of operations during transmission or processing. The demand for fast image reproduction increases every day and much effort and research has been made on finding new methods and models for different tasks in the printing field. Since quality and speed are generally conflicting, it seems advantageous to come up with intermediate techniques providing better images in less time. The main work here emphasizes on the algorithm given in M. Mese and P.P. Vaidyanathan (2000), with new considerations in order to speed it up.
{"title":"A Fast Inverse Halftoning Algorithm using LUT Approach for Grey-level Images","authors":"N. Atamena, Z. Tifedjadjine, Z. Dibi, A. Bouridane","doi":"10.1109/ICTTA.2008.4530081","DOIUrl":"https://doi.org/10.1109/ICTTA.2008.4530081","url":null,"abstract":"Halftone images are often difficult to be processed without causing severe degradation contrary to grayscale images. This gives the purpose to improve many techniques to reconstruct from their corresponding halftones the continuous images that permits a wide range of operations during transmission or processing. The demand for fast image reproduction increases every day and much effort and research has been made on finding new methods and models for different tasks in the printing field. Since quality and speed are generally conflicting, it seems advantageous to come up with intermediate techniques providing better images in less time. The main work here emphasizes on the algorithm given in M. Mese and P.P. Vaidyanathan (2000), with new considerations in order to speed it up.","PeriodicalId":330215,"journal":{"name":"2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125320390","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 : 2008-04-07DOI: 10.1109/ICTTA.2008.4529947
Niels Bjørn-Andersen, Liana Razmerita
One of the largest barriers in international trade are the security risks, the huge costs in administration and the high level of fraud. An EU project has been established with the objective of improving matters dramatically. The paper will present the challenges in more detail, and will discuss three set of EU initiatives in creating e-Customs solutions. The main part of the paper deals with the so-called Living Lab (action research project) in the ARLA company, where we are testing out the possibilities of improved customs systems using e-government systems.
{"title":"Advanced e-Governmental Solutions for Global Trade","authors":"Niels Bjørn-Andersen, Liana Razmerita","doi":"10.1109/ICTTA.2008.4529947","DOIUrl":"https://doi.org/10.1109/ICTTA.2008.4529947","url":null,"abstract":"One of the largest barriers in international trade are the security risks, the huge costs in administration and the high level of fraud. An EU project has been established with the objective of improving matters dramatically. The paper will present the challenges in more detail, and will discuss three set of EU initiatives in creating e-Customs solutions. The main part of the paper deals with the so-called Living Lab (action research project) in the ARLA company, where we are testing out the possibilities of improved customs systems using e-government systems.","PeriodicalId":330215,"journal":{"name":"2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126737257","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 : 2008-04-07DOI: 10.1109/ICTTA.2008.4530107
D. Chikouche, R. Benzid, M. Bentoumi
This paper presents an application of the discrete cosine transform compression technique on medical images of the IRM type. The arithmetic coding method is used to encode the coefficients. The tests of this lossy compression/ decompression technique are performed on two IRM images representing the brain, in axial and sagital views, of a patient suffering from a cerebral hemorhage. The obtained results on these images show that the DCT technique permits to considerably improve the compression rate while mainting a good image quality when threshold varies in the interval: 0 les TH les 20 for bloc sizes: [16times16] and [32times32]. However, a severe degradation of the quality of the reconstructed medical image is observed when the threshold is greater than 30.
{"title":"Application of the DCT and Arithmetic Coding to Medical Image Compression","authors":"D. Chikouche, R. Benzid, M. Bentoumi","doi":"10.1109/ICTTA.2008.4530107","DOIUrl":"https://doi.org/10.1109/ICTTA.2008.4530107","url":null,"abstract":"This paper presents an application of the discrete cosine transform compression technique on medical images of the IRM type. The arithmetic coding method is used to encode the coefficients. The tests of this lossy compression/ decompression technique are performed on two IRM images representing the brain, in axial and sagital views, of a patient suffering from a cerebral hemorhage. The obtained results on these images show that the DCT technique permits to considerably improve the compression rate while mainting a good image quality when threshold varies in the interval: 0 les TH les 20 for bloc sizes: [16times16] and [32times32]. However, a severe degradation of the quality of the reconstructed medical image is observed when the threshold is greater than 30.","PeriodicalId":330215,"journal":{"name":"2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115207684","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：