Pub Date : 1999-09-23DOI: 10.1109/ICCIMA.1999.798521
P. Pudil, K. Fuka, K. Beránek, P. Dvorak
Pattern recognition based on learning approaches is regarded as one of the disciplines of AI. Floating search methods, developed originally for feature selection problems in statistical pattern recognition, are applicable to a much wider class of problems outside pattern recognition. They have the potential to find an optimal subset of variables maximizing any criterion adopted for the problem at hand-eliminating the so-called nesting effect from which traditional algorithms suffer. One such application area is multiple regression, where floating search methods represent a computationally feasible alternative to classical methods for finding the optimal set of regressors.
{"title":"Potential of artificial intelligence based feature selection methods in regression models","authors":"P. Pudil, K. Fuka, K. Beránek, P. Dvorak","doi":"10.1109/ICCIMA.1999.798521","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798521","url":null,"abstract":"Pattern recognition based on learning approaches is regarded as one of the disciplines of AI. Floating search methods, developed originally for feature selection problems in statistical pattern recognition, are applicable to a much wider class of problems outside pattern recognition. They have the potential to find an optimal subset of variables maximizing any criterion adopted for the problem at hand-eliminating the so-called nesting effect from which traditional algorithms suffer. One such application area is multiple regression, where floating search methods represent a computationally feasible alternative to classical methods for finding the optimal set of regressors.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"20 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":"134538105","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.1999.798489
A. Tsoi, M. Hagenbuchner
Many artificial and natural systems are often more adequately modelled using data structures, e.g., graphs, trees. For example, it is often more convenient to represent an image using data structures than by representing it using pixels. The data structure can serve as a prelude to scene analysis, image retrieval, etc. There are, broadly speaking, two ways in which data structures can be processed. One way is to consider it as generated by an underlying grammar, with defined syntax; and the other way is to consider it as an input output system, which may be modelled using neural networks. In this talk, we will discuss both approaches. We will first discuss how data structures can be modelled using an attributed grammar. Then, we will discuss the modelling of a data structure using neural networks. It is shown that both approaches are closely related. We will then derive training algorithms for the neural network models, and discuss the universal approximation properties of such models. We will demonstrate the neural network approach on a number of synthesized and practical examples.
{"title":"Adaptive processing of data structures","authors":"A. Tsoi, M. Hagenbuchner","doi":"10.1109/ICCIMA.1999.798489","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798489","url":null,"abstract":"Many artificial and natural systems are often more adequately modelled using data structures, e.g., graphs, trees. For example, it is often more convenient to represent an image using data structures than by representing it using pixels. The data structure can serve as a prelude to scene analysis, image retrieval, etc. There are, broadly speaking, two ways in which data structures can be processed. One way is to consider it as generated by an underlying grammar, with defined syntax; and the other way is to consider it as an input output system, which may be modelled using neural networks. In this talk, we will discuss both approaches. We will first discuss how data structures can be modelled using an attributed grammar. Then, we will discuss the modelling of a data structure using neural networks. It is shown that both approaches are closely related. We will then derive training algorithms for the neural network models, and discuss the universal approximation properties of such models. We will demonstrate the neural network approach on a number of synthesized and practical examples.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"24 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":"134286026","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.1999.798576
L. J. Peniche-Ruiz, P.R. Mendoza E, R. Pinto Elias
Holographic technology has been successfully applied on a number of applications in the fields of pattern recognition and prediction. A short review of the face recognition problem introduces one to the fundamental aspects of holographic technology, which are briefly discussed so that their similarities and differences from typical neural nets are shown. Some of the applications of this tool are mentioned in this paper. The image base used is of 31 images of 10 different faces with different facial expressions (happiness, anger and sadness). Data describing these human faces is explained including the sets of data for supervised training and generalization of the holographic cell. The results of applying this technology to face location, for this data set, show that performance is well above 99% accuracy which supports holographic cells as a sound tool for pattern recognition.
{"title":"Holographic technology applied to face location and identification","authors":"L. J. Peniche-Ruiz, P.R. Mendoza E, R. Pinto Elias","doi":"10.1109/ICCIMA.1999.798576","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798576","url":null,"abstract":"Holographic technology has been successfully applied on a number of applications in the fields of pattern recognition and prediction. A short review of the face recognition problem introduces one to the fundamental aspects of holographic technology, which are briefly discussed so that their similarities and differences from typical neural nets are shown. Some of the applications of this tool are mentioned in this paper. The image base used is of 31 images of 10 different faces with different facial expressions (happiness, anger and sadness). Data describing these human faces is explained including the sets of data for supervised training and generalization of the holographic cell. The results of applying this technology to face location, for this data set, show that performance is well above 99% accuracy which supports holographic cells as a sound tool for pattern recognition.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"151 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":"132636967","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.1999.798547
C. Ng, Vincent Ng, Y. Lau
Braille, a touch-reading system for visually impaired people was first introduced in 1825 by Louis Braille. Editing and reprinting Braille text that was originally embossed on paper is both time consuming and labour intensive. This paper presents an automatic system to recognize Braille pages and to convert Braille documents into English or Chinese text for editing.
{"title":"Regular feature extraction for recognition of Braille","authors":"C. Ng, Vincent Ng, Y. Lau","doi":"10.1109/ICCIMA.1999.798547","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798547","url":null,"abstract":"Braille, a touch-reading system for visually impaired people was first introduced in 1825 by Louis Braille. Editing and reprinting Braille text that was originally embossed on paper is both time consuming and labour intensive. This paper presents an automatic system to recognize Braille pages and to convert Braille documents into English or Chinese text for editing.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"23 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":"125123657","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.1999.798532
H. Selvaraj, M. Venkatesan, B. Bignall, B. Verma
Functional decomposition plays an important role in the design of FPGA-based circuits because their structure only imposes constraints on the number of inputs. Several decomposition techniques have been developed, and they show better area and level optimization. In a multi-level decomposition method, the coding of the decomposed function is an important factor that influences further decomposition at lower levels. It is particularly important for real-life functions that have a lot of "don't cares". In this paper, we propose a coding strategy that retains as many "don't cares" as possible. The resulting truth table is smaller in size.
{"title":"Functional decomposition for FPGA based designs: a weighted graph approach for encoding of compatible classes","authors":"H. Selvaraj, M. Venkatesan, B. Bignall, B. Verma","doi":"10.1109/ICCIMA.1999.798532","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798532","url":null,"abstract":"Functional decomposition plays an important role in the design of FPGA-based circuits because their structure only imposes constraints on the number of inputs. Several decomposition techniques have been developed, and they show better area and level optimization. In a multi-level decomposition method, the coding of the decomposed function is an important factor that influences further decomposition at lower levels. It is particularly important for real-life functions that have a lot of \"don't cares\". In this paper, we propose a coding strategy that retains as many \"don't cares\" as possible. The resulting truth table is smaller in size.","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":"122221212","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.1999.798537
Chetan Arora, P. Nirankari, Hiranmay Ghosh, S. Chaudhury
We present a generic architecture for content based retrieval of images, which can be extended to the requirements of large distributed and heterogeneous collections. The system is modeled as a multi agent system where an autonomous search agent encapsulates independent image retrieval algorithms. An optimal team of agents is dynamically selected for every retrieval problem. A flexible protocol allows for dynamic addition of search agents incorporating new pattern recognition techniques. These agents are coded as mobile agents, so that they can travel across a wide area network and analyze the documents at their sources. The separation of physical image forms and their logical structural composition allows the search agents to operate over heterogeneous repositories. A prototype implementation validates the effectiveness of the architecture.
{"title":"Content based image retrieval using mobile agents","authors":"Chetan Arora, P. Nirankari, Hiranmay Ghosh, S. Chaudhury","doi":"10.1109/ICCIMA.1999.798537","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798537","url":null,"abstract":"We present a generic architecture for content based retrieval of images, which can be extended to the requirements of large distributed and heterogeneous collections. The system is modeled as a multi agent system where an autonomous search agent encapsulates independent image retrieval algorithms. An optimal team of agents is dynamically selected for every retrieval problem. A flexible protocol allows for dynamic addition of search agents incorporating new pattern recognition techniques. These agents are coded as mobile agents, so that they can travel across a wide area network and analyze the documents at their sources. The separation of physical image forms and their logical structural composition allows the search agents to operate over heterogeneous repositories. A prototype implementation validates the effectiveness of the architecture.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"28 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":"121774074","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.1999.798566
N. Braun, R. Dorner
Multimedia applications within the World Wide Web (WWW) have to deal with difficulties like executing within Web pages and being transferred via the Internet. However, the temporal aspects of hypermedia features for continuous media like audio and video resemble all other kinds of multimedia applications. These temporal aspects are discussed in consideration of presentation and authoring facilities. A system architecture and implementation relying on commercial WWW technology is presented.
{"title":"Temporal hypermedia for multimedia applications in the World Wide Web","authors":"N. Braun, R. Dorner","doi":"10.1109/ICCIMA.1999.798566","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798566","url":null,"abstract":"Multimedia applications within the World Wide Web (WWW) have to deal with difficulties like executing within Web pages and being transferred via the Internet. However, the temporal aspects of hypermedia features for continuous media like audio and video resemble all other kinds of multimedia applications. These temporal aspects are discussed in consideration of presentation and authoring facilities. A system architecture and implementation relying on commercial WWW technology is presented.","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":"124967196","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.1999.798520
L. Giraffa, M. Mora, R. Viccari
This paper shows how a multi-agent systems (MAS) approach may be used to build an interactive intelligent tutoring system (ITS) designed as a game. We model the ITS as a society of both reactive and cognitive agents that interact through a graphical interface. We present an experiment carried out in a school in order to test our hypothesis about the architecture's pedagogical potential, and we present the results obtained.
{"title":"Modelling an interactive ITS using a MAS approach: from design to pedagogical evaluation","authors":"L. Giraffa, M. Mora, R. Viccari","doi":"10.1109/ICCIMA.1999.798520","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798520","url":null,"abstract":"This paper shows how a multi-agent systems (MAS) approach may be used to build an interactive intelligent tutoring system (ITS) designed as a game. We model the ITS as a society of both reactive and cognitive agents that interact through a graphical interface. We present an experiment carried out in a school in order to test our hypothesis about the architecture's pedagogical potential, and we present the results obtained.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"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":"121440923","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.1999.798526
Keiji Yanai
An image understanding system for real world images which has an ability to recognize various kinds of images is proposed. We propose a multi-agent architecture to integrate and cooperate object recognition modules for individual target objects. In our system, object candidates generated by different agents are integrated not only on the evaluations by each modules themselves but also on spatial relations among objects. By checking spatial relation, the agents also estimate actual objects from parts seen in the image. Such mechanisms are realized by autonomous cooperation among the agents, and the most reliable result is selected after the arbitration between them. We implemented an experimental system on a PC cluster system, and achieved recognition for both indoor and outdoor images.
{"title":"An image understanding system for various images based on multi-agent architecture","authors":"Keiji Yanai","doi":"10.1109/ICCIMA.1999.798526","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798526","url":null,"abstract":"An image understanding system for real world images which has an ability to recognize various kinds of images is proposed. We propose a multi-agent architecture to integrate and cooperate object recognition modules for individual target objects. In our system, object candidates generated by different agents are integrated not only on the evaluations by each modules themselves but also on spatial relations among objects. By checking spatial relation, the agents also estimate actual objects from parts seen in the image. Such mechanisms are realized by autonomous cooperation among the agents, and the most reliable result is selected after the arbitration between them. We implemented an experimental system on a PC cluster system, and achieved recognition for both indoor and outdoor images.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"40 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":"114165279","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.1999.798561
R. Simon, A. Sood, P. Mundur
An important question in the development of system support for distributed multimedia is the type of network service offered to applications. This paper compares two network service disciplines: weighted fair queueing (WFQ) and non-preemptive earliest deadline first (NEDF). We show that, for a broad class of high-bandwidth distributed multimedia applications, WFQ outperforms NEDF in terms of network throughput while still providing an application-adequate end-to-end service. This result holds despite the fact that NEDF offers applications far greater flexibility in terms of control over end-to-end delivery delay.
{"title":"Network service selection for distributed multimedia applications","authors":"R. Simon, A. Sood, P. Mundur","doi":"10.1109/ICCIMA.1999.798561","DOIUrl":"https://doi.org/10.1109/ICCIMA.1999.798561","url":null,"abstract":"An important question in the development of system support for distributed multimedia is the type of network service offered to applications. This paper compares two network service disciplines: weighted fair queueing (WFQ) and non-preemptive earliest deadline first (NEDF). We show that, for a broad class of high-bandwidth distributed multimedia applications, WFQ outperforms NEDF in terms of network throughput while still providing an application-adequate end-to-end service. This result holds despite the fact that NEDF offers applications far greater flexibility in terms of control over end-to-end delivery delay.","PeriodicalId":110736,"journal":{"name":"Proceedings Third International Conference on Computational Intelligence and Multimedia Applications. ICCIMA'99 (Cat. No.PR00300)","volume":"61 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":"123185061","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：