Pub Date : 1999-09-23DOI: 10.1109/ICCIMA.1999.798543
S. Subramanya, A. Youssef, B. Narahari, R. Simha
The phenomenal increases in the amounts of audio data being generated, processed and used in several computer applications have necessitated the development of audio database systems with newer features, such as content-based queries and similarity searches, to manage and use such data. Fast and accurate retrieval for content-based queries is crucial in order for such systems to be useful. Efficient content-based indexing and similarity searching schemes are keys to providing fast and relevant data retrieval. This paper studies and evaluates the different parameters involved in an indexing scheme which uses transforms (as used in signal processing) for generating the audio data indexes which are to be used in searching and retrieval. A comparison of the performance of the indexing scheme with different parameters is presented.
{"title":"Use of transforms for indexing in audio databases","authors":"S. Subramanya, A. Youssef, B. Narahari, R. Simha","doi":"10.1109/ICCIMA.1999.798543","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798543","url":null,"abstract":"The phenomenal increases in the amounts of audio data being generated, processed and used in several computer applications have necessitated the development of audio database systems with newer features, such as content-based queries and similarity searches, to manage and use such data. Fast and accurate retrieval for content-based queries is crucial in order for such systems to be useful. Efficient content-based indexing and similarity searching schemes are keys to providing fast and relevant data retrieval. This paper studies and evaluates the different parameters involved in an indexing scheme which uses transforms (as used in signal processing) for generating the audio data indexes which are to be used in searching and retrieval. A comparison of the performance of the indexing scheme with different parameters is presented.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124376220","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 : 1999-09-23DOI: 10.1109/ICCIMA.1999.798514
A. Ribert, E. Stocker, Y. Lecourtier, A. Ennaji
This paper provides a guide to evolving-architecture neural networks for a beginner in multi-layer perceptrons. All the quoted methods aim at automatically fitting a neural network architecture to a particular classification task. Several kinds of evolving architectures are exposed. Some neural networks start small and become bigger and bigger during the learning, whereas others start over-dimensioned and undergo pruning. A last network category uses both methods alternately.
{"title":"A survey on supervised learning by evolving multi-layer perceptrons","authors":"A. Ribert, E. Stocker, Y. Lecourtier, A. Ennaji","doi":"10.1109/ICCIMA.1999.798514","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798514","url":null,"abstract":"This paper provides a guide to evolving-architecture neural networks for a beginner in multi-layer perceptrons. All the quoted methods aim at automatically fitting a neural network architecture to a particular classification task. Several kinds of evolving architectures are exposed. Some neural networks start small and become bigger and bigger during the learning, whereas others start over-dimensioned and undergo pruning. A last network category uses both methods alternately.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130360819","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 : 1999-09-23DOI: 10.1109/ICCIMA.1999.798539
Mi Hee, Y. Ik, Kio-Chung Kim
The article suggests a Hybrid Video System (HVS) which supports the semantic retrieval of all types of users and the similarity retrieval of indefinitely formed and very large amounts of video data. The HVS divides a set of video data into video documents, sequences, scenes and objects to model the metadata and suggests a Three layered Hybrid Object-oriented Metadata Model (THOMM) which is composed of the raw data layer for physical video stream. The metadata layer supports feature based retrieval and similarity retrieval and the semantic layer reforms queries. Grounded on this model, we suggest a video query language which makes content-based query and similarity query possible and Video Query Processor (VQP) to process the query. In particular, the similarity query processed by performing the annotation-based retrieval using the concept layer and then the feature-based retrieval using the object-feature layer. Thus search space and time can be reduced. Also we present the formula for degree of similarity. The suggested system is implemented with using the Visual C++, ActiveX and ORACLE under Windows NT.
{"title":"Hybrid video system supporting content-based retrieval","authors":"Mi Hee, Y. Ik, Kio-Chung Kim","doi":"10.1109/ICCIMA.1999.798539","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798539","url":null,"abstract":"The article suggests a Hybrid Video System (HVS) which supports the semantic retrieval of all types of users and the similarity retrieval of indefinitely formed and very large amounts of video data. The HVS divides a set of video data into video documents, sequences, scenes and objects to model the metadata and suggests a Three layered Hybrid Object-oriented Metadata Model (THOMM) which is composed of the raw data layer for physical video stream. The metadata layer supports feature based retrieval and similarity retrieval and the semantic layer reforms queries. Grounded on this model, we suggest a video query language which makes content-based query and similarity query possible and Video Query Processor (VQP) to process the query. In particular, the similarity query processed by performing the annotation-based retrieval using the concept layer and then the feature-based retrieval using the object-feature layer. Thus search space and time can be reduced. Also we present the formula for degree of similarity. The suggested system is implemented with using the Visual C++, ActiveX and ORACLE under Windows NT.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131181489","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 : 1999-09-23DOI: 10.1109/ICCIMA.1999.798512
R. Kumar
Generalisation is a non-trivial problem in machine learning and more so with neural networks which have the capabilities of inducing varying degrees of freedom. It is influenced by many factors in network design, such as network size, initial conditions, learning rate, weight decay factor, pruning algorithms, and many more. In spite of continuous research efforts, we could not arrive at a practical solution which can offer a superior generalisation. We present a novel approach for handling complex problems of machine learning. A multiobjective genetic algorithm is used for identifying (near-) optimal subspaces for hierarchical learning. This strategy of explicitly partitioning the data for subsequent mapping onto a hierarchical classifier is found both to reduce the learning complexity and the classification time. The classification performance of various algorithms is compared and it is argued that the neural modules are superior for learning the localised decision surfaces of such partitions and offer better generalisation.
{"title":"On generalisation of machine learning with neural-evolutionary computations","authors":"R. Kumar","doi":"10.1109/ICCIMA.1999.798512","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798512","url":null,"abstract":"Generalisation is a non-trivial problem in machine learning and more so with neural networks which have the capabilities of inducing varying degrees of freedom. It is influenced by many factors in network design, such as network size, initial conditions, learning rate, weight decay factor, pruning algorithms, and many more. In spite of continuous research efforts, we could not arrive at a practical solution which can offer a superior generalisation. We present a novel approach for handling complex problems of machine learning. A multiobjective genetic algorithm is used for identifying (near-) optimal subspaces for hierarchical learning. This strategy of explicitly partitioning the data for subsequent mapping onto a hierarchical classifier is found both to reduce the learning complexity and the classification time. The classification performance of various algorithms is compared and it is argued that the neural modules are superior for learning the localised decision surfaces of such partitions and offer better generalisation.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131886863","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 : 1999-09-23DOI: 10.1109/ICCIMA.1999.798577
B. Kusumoputro, M. R. Widyanto, M. I. Fanany, H. Budiarto
An artificial odor recognition system is developed in order to mimic the human sensory test in cosmetics, perfume and beverage industries. A backpropagation neural network is used as the pattern recognition system and shows high recognition capability. However, the system only works efficiently when it is used to discriminate a limited number of odors. The unlearned odor will be classified as one of the already learned category. To improve the system's capability, a fuzzy learning vector quantization neural network is developed and utilized in experiments on four different ethanol concentrations, and three different kinds of fragrance odor from Martha Tilaar Cosmetics. The results shows that the FLVQ has a comparable ability for recognizing the already known category of odors. However, the FLVQ algorithm can cluster the unknown odor in a different new class of odor.
{"title":"Improvement of artificial odor discrimination system using fuzzy-LVQ neural network","authors":"B. Kusumoputro, M. R. Widyanto, M. I. Fanany, H. Budiarto","doi":"10.1109/ICCIMA.1999.798577","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798577","url":null,"abstract":"An artificial odor recognition system is developed in order to mimic the human sensory test in cosmetics, perfume and beverage industries. A backpropagation neural network is used as the pattern recognition system and shows high recognition capability. However, the system only works efficiently when it is used to discriminate a limited number of odors. The unlearned odor will be classified as one of the already learned category. To improve the system's capability, a fuzzy learning vector quantization neural network is developed and utilized in experiments on four different ethanol concentrations, and three different kinds of fragrance odor from Martha Tilaar Cosmetics. The results shows that the FLVQ has a comparable ability for recognizing the already known category of odors. However, the FLVQ algorithm can cluster the unknown odor in a different new class of odor.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"58 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126003102","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 : 1999-09-23DOI: 10.1109/ICCIMA.1999.798536
Mário Flecha, J. Pinheiro, J. L. Braga
The paper reports on an experienced and evaluated three layer architectural solution for co-operative database access in real use environment. It looks for mediator software independence from idiosyncrasies of user application interfaces and specific database schemata. The cornerstone to implement this architecture is a set of relational databases and views manipulated by a Relational Inference Machine-RIM. Conceptually It is supported by a semantic model implemented as a modelling technique we have named Content Semantics-CS-which supports pragmatic concept ontology to be expressed as contextualized terms in well-defined semantic domains. Several public databases are daily accessed by mediation services working over millions of data records stored in large databases.
{"title":"Schema-independent mediators using content semantics to access data resources","authors":"Mário Flecha, J. Pinheiro, J. L. Braga","doi":"10.1109/ICCIMA.1999.798536","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798536","url":null,"abstract":"The paper reports on an experienced and evaluated three layer architectural solution for co-operative database access in real use environment. It looks for mediator software independence from idiosyncrasies of user application interfaces and specific database schemata. The cornerstone to implement this architecture is a set of relational databases and views manipulated by a Relational Inference Machine-RIM. Conceptually It is supported by a semantic model implemented as a modelling technique we have named Content Semantics-CS-which supports pragmatic concept ontology to be expressed as contextualized terms in well-defined semantic domains. Several public databases are daily accessed by mediation services working over millions of data records stored in large databases.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123672200","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 : 1999-09-23DOI: 10.1109/ICCIMA.1999.798534
Chengqi Zhang, Yuefeng Li
A model of horizontal cooperation under uncertainty in distributed expert systems is presented. This model uses the synthesis of solutions under uncertainty and decision-making to fulfil horizontal cooperation. Firstly, a Boolean algebra is used in order to represent the solution synthesis hypothesis space in the model. Then, a generalization of evidence theory is used as a mathematical model to synthesize all conclusions which come from other expert systems. Finally, a competing mechanism is introduced to make the decisions.
{"title":"Horizontal cooperation under uncertainties in distributed expert systems","authors":"Chengqi Zhang, Yuefeng Li","doi":"10.1109/ICCIMA.1999.798534","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798534","url":null,"abstract":"A model of horizontal cooperation under uncertainty in distributed expert systems is presented. This model uses the synthesis of solutions under uncertainty and decision-making to fulfil horizontal cooperation. Firstly, a Boolean algebra is used in order to represent the solution synthesis hypothesis space in the model. Then, a generalization of evidence theory is used as a mathematical model to synthesize all conclusions which come from other expert systems. Finally, a competing mechanism is introduced to make the decisions.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122119434","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 : 1999-09-23DOI: 10.1109/ICCIMA.1999.798578
S. Ng, C. Ng, H.W. Tsang, L.M. Hung
The recent emergence of the World Wide Web (WWW) and Internet is changing the studying habits of people. More and more institutions require an effective and flexible application to launch their distance learning programs on the WWW. Learn@Net is a possible solution. Learn@Net is a server-based distance learning system designed to provide centralized, flexible control and easy administration of online distance learning applications. It relies on an open architecture based on TCP/IP, HTML, Java and SQL. It involves functions such as virtual classroom, assignment handler, course material browser, discussion forum and online chat room to facilitate both online teaching and online learning through the WWW.
{"title":"Learn@Net: an integrated multimedia system for distance learning","authors":"S. Ng, C. Ng, H.W. Tsang, L.M. Hung","doi":"10.1109/ICCIMA.1999.798578","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798578","url":null,"abstract":"The recent emergence of the World Wide Web (WWW) and Internet is changing the studying habits of people. More and more institutions require an effective and flexible application to launch their distance learning programs on the WWW. Learn@Net is a possible solution. Learn@Net is a server-based distance learning system designed to provide centralized, flexible control and easy administration of online distance learning applications. It relies on an open architecture based on TCP/IP, HTML, Java and SQL. It involves functions such as virtual classroom, assignment handler, course material browser, discussion forum and online chat room to facilitate both online teaching and online learning through the WWW.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"16 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124617240","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 : 1999-09-23DOI: 10.1109/ICCIMA.1999.798573
A. Kumar Bisoi, J. Mishra
Fractals are famous for their beauty and fractal techniques are employed for smaller storage space requirements when storing images. Fractal geometry has gradually established its importance in the study of image characteristics. The concept of multiple reduction copy machine (MRCM) has been used for creating fractals for a long time. A modified MRCM has been designed to generate fractal patterns. Using the concept of modified MRCM, we generate a new range of fractal images, which enhances the beauty of some well known fractals. This paper explains the way in which one can enhance the beauty by providing a nice looking shape with color to some black and white fractals.
{"title":"Enhancing the beauty of fractals","authors":"A. Kumar Bisoi, J. Mishra","doi":"10.1109/ICCIMA.1999.798573","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798573","url":null,"abstract":"Fractals are famous for their beauty and fractal techniques are employed for smaller storage space requirements when storing images. Fractal geometry has gradually established its importance in the study of image characteristics. The concept of multiple reduction copy machine (MRCM) has been used for creating fractals for a long time. A modified MRCM has been designed to generate fractal patterns. Using the concept of modified MRCM, we generate a new range of fractal images, which enhances the beauty of some well known fractals. This paper explains the way in which one can enhance the beauty by providing a nice looking shape with color to some black and white fractals.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116518226","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 : 1999-09-23DOI: 10.1109/ICCIMA.1999.798529
Se Hyun Park, K. Jung, Junhui Hea, Hang-Joon Kim
Many research projects are currently in progress on the application of machine vision to traffic surveillance systems. We present a vision based traffic surveillance system on the Internet. Our system consists of FPAs (Field Processing Agents) and TSM (Traffic Surveillance Manager). The FPAs and TSM both communicate with each other on the Internet. The FPA is a Web server which serves real time video data, vehicle velocity and vehicle density when the TSM requests them. An FPA consists of a communication module and an image processing module. The image processing module in the FPA performs traffic parameter estimation. Traffic parameters are estimated by just processing groups of image pixels without any understanding of the image. Although this has an accuracy limitation, it can be used in applications requiring an approximate vehicle density and vehicle velocity.
{"title":"Vision-based traffic surveillance system on the Internet","authors":"Se Hyun Park, K. Jung, Junhui Hea, Hang-Joon Kim","doi":"10.1109/ICCIMA.1999.798529","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798529","url":null,"abstract":"Many research projects are currently in progress on the application of machine vision to traffic surveillance systems. We present a vision based traffic surveillance system on the Internet. Our system consists of FPAs (Field Processing Agents) and TSM (Traffic Surveillance Manager). The FPAs and TSM both communicate with each other on the Internet. The FPA is a Web server which serves real time video data, vehicle velocity and vehicle density when the TSM requests them. An FPA consists of a communication module and an image processing module. The image processing module in the FPA performs traffic parameter estimation. Traffic parameters are estimated by just processing groups of image pixels without any understanding of the image. Although this has an accuracy limitation, it can be used in applications requiring an approximate vehicle density and vehicle velocity.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"431 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123439067","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：