Pub Date : 2006-04-01DOI: 10.1109/MMSE.2003.1254457
W. F. Huang, J. Tsai, Rouh-Mei Hu, Rong-Ming Chen
Gene transcription regulation impacts the final expression of gene. Generally gene expression is regulated via an interaction between regulatory proteins and specific DNA elements. If we find out the binding sites of regulatory factors, we could understand the mechanism of control of gene transcription more. For this reason, it is a very important issue to find out the regulatory factors of gene transcription. We propose a method to find out the regulatory protein binding sites from the comparisons of DNA sequence and scoring matrices with suitable bioconditions. The steepest ascent algorithm is adopted to search the possible locations of binding sites. The predicted results of regulatory protein binding sites are displayed with table and charts. The proposed system will help the biologists to analyze the regulatory protein binding sites more efficiently, and to develop effective drugs for genetic diseases.
{"title":"Searching the regulatory protein binding site by steepest ascent algorithm","authors":"W. F. Huang, J. Tsai, Rouh-Mei Hu, Rong-Ming Chen","doi":"10.1109/MMSE.2003.1254457","DOIUrl":"https://doi.org/10.1109/MMSE.2003.1254457","url":null,"abstract":"Gene transcription regulation impacts the final expression of gene. Generally gene expression is regulated via an interaction between regulatory proteins and specific DNA elements. If we find out the binding sites of regulatory factors, we could understand the mechanism of control of gene transcription more. For this reason, it is a very important issue to find out the regulatory factors of gene transcription. We propose a method to find out the regulatory protein binding sites from the comparisons of DNA sequence and scoring matrices with suitable bioconditions. The steepest ascent algorithm is adopted to search the possible locations of binding sites. The predicted results of regulatory protein binding sites are displayed with table and charts. The proposed system will help the biologists to analyze the regulatory protein binding sites more efficiently, and to develop effective drugs for genetic diseases.","PeriodicalId":322357,"journal":{"name":"Fifth International Symposium on Multimedia Software Engineering, 2003. Proceedings.","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126688966","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 : 2003-12-10DOI: 10.1109/MMSE.2003.1254445
Weihong Huang, M. O'Dea, A. Mille
Current multimedia information retrieval technologies to support e-learning can only provide basic low-level single type media retrieval services to common users, hence current e-learning services still lack intelligence and context-awareness. Much of the desired intelligent e-learning functionality needs further research and technical developments. The proposed framework ConKMel is expected to improve the current isolated learning information management status, by making the most use of related learning information, and enabling flexible knowledge communication and transfer between instructors and learners. To work with related existing e-learning content description standards and enable a semantic-based interactive learning environment, we explore a set of novel knowledge management techniques from a contextual knowledge engineering point of view. Based on knowledge communication model analysis, a contextual knowledge representation model is presented. Corresponding knowledge retrieval techniques are discussed afterwards to support modern learning approaches such as scenario-based learning.
{"title":"ConKMeL: a contextual knowledge management framework to support intelligent multimedia e-learning","authors":"Weihong Huang, M. O'Dea, A. Mille","doi":"10.1109/MMSE.2003.1254445","DOIUrl":"https://doi.org/10.1109/MMSE.2003.1254445","url":null,"abstract":"Current multimedia information retrieval technologies to support e-learning can only provide basic low-level single type media retrieval services to common users, hence current e-learning services still lack intelligence and context-awareness. Much of the desired intelligent e-learning functionality needs further research and technical developments. The proposed framework ConKMel is expected to improve the current isolated learning information management status, by making the most use of related learning information, and enabling flexible knowledge communication and transfer between instructors and learners. To work with related existing e-learning content description standards and enable a semantic-based interactive learning environment, we explore a set of novel knowledge management techniques from a contextual knowledge engineering point of view. Based on knowledge communication model analysis, a contextual knowledge representation model is presented. Corresponding knowledge retrieval techniques are discussed afterwards to support modern learning approaches such as scenario-based learning.","PeriodicalId":322357,"journal":{"name":"Fifth International Symposium on Multimedia Software Engineering, 2003. Proceedings.","volume":"281 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114488902","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 : 2003-12-10DOI: 10.1109/MMSE.2003.1254417
Ben Wang, Q. Gan
Efficient high-dimensional data indexing algorithms are crucial for image retrieval in large datasets. One of the state-of-the-art indexing methods is vector approximation file (VA-file), which indexes high-dimensional data by filtering feature vectors so that only a small fraction of them are visited in the search process. The VA-file uses a partition strategy that divides the data space on every dimension to make each partition equally full and assigns a same number of bits to each dimension. However, the strategy is not efficient to image datasets where the number of different vector components (granularity) in each dimension is largely diverse. The first two partition strategies are implemented in a practical way according to the description from the original VA-file method. The other two nonuniform partition strategies are proposed to resolve the problems of reduplicate coordinates and uniform bits assignment for each dimension, which assign more bits to represent dimensions with more vector components. Experimental results have shown that these strategies largely improve the performance of the VA-file for nonuniform datasets in terms of query time and filtering efficiency.
{"title":"Non-uniform partition strategies for indexing high-dimensional data with different distributions","authors":"Ben Wang, Q. Gan","doi":"10.1109/MMSE.2003.1254417","DOIUrl":"https://doi.org/10.1109/MMSE.2003.1254417","url":null,"abstract":"Efficient high-dimensional data indexing algorithms are crucial for image retrieval in large datasets. One of the state-of-the-art indexing methods is vector approximation file (VA-file), which indexes high-dimensional data by filtering feature vectors so that only a small fraction of them are visited in the search process. The VA-file uses a partition strategy that divides the data space on every dimension to make each partition equally full and assigns a same number of bits to each dimension. However, the strategy is not efficient to image datasets where the number of different vector components (granularity) in each dimension is largely diverse. The first two partition strategies are implemented in a practical way according to the description from the original VA-file method. The other two nonuniform partition strategies are proposed to resolve the problems of reduplicate coordinates and uniform bits assignment for each dimension, which assign more bits to represent dimensions with more vector components. Experimental results have shown that these strategies largely improve the performance of the VA-file for nonuniform datasets in terms of query time and filtering efficiency.","PeriodicalId":322357,"journal":{"name":"Fifth International Symposium on Multimedia Software Engineering, 2003. Proceedings.","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117067456","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 : 2003-12-01DOI: 10.1109/MMSE.2003.1254416
Chih-Fong Tsai, K. McGarry, J. Tait
We present a two-stage mapping model (TSMM), which is intended to minimise the semantic gap for content-based image retrieval (CBIR) by reducing recognition errors during the image indexing stage. This model is composed of a feature extraction module based on our image segmentation and feature extraction algorithm, a colour and texture classification modules based on support vector machines (SVMs), and an inference module based on fuzzy logic to make final decisions as high level concepts from the colour and texture concepts. The experimental results show that the proposed method outperforms general approaches by using one single SVM classifier as direct mapping between the combined colour and texture feature vectors and high level concepts directly.
{"title":"Using neuro-fuzzy techniques based on a two-stage mapping model for concept-based image database indexing","authors":"Chih-Fong Tsai, K. McGarry, J. Tait","doi":"10.1109/MMSE.2003.1254416","DOIUrl":"https://doi.org/10.1109/MMSE.2003.1254416","url":null,"abstract":"We present a two-stage mapping model (TSMM), which is intended to minimise the semantic gap for content-based image retrieval (CBIR) by reducing recognition errors during the image indexing stage. This model is composed of a feature extraction module based on our image segmentation and feature extraction algorithm, a colour and texture classification modules based on support vector machines (SVMs), and an inference module based on fuzzy logic to make final decisions as high level concepts from the colour and texture concepts. The experimental results show that the proposed method outperforms general approaches by using one single SVM classifier as direct mapping between the combined colour and texture feature vectors and high level concepts directly.","PeriodicalId":322357,"journal":{"name":"Fifth International Symposium on Multimedia Software Engineering, 2003. Proceedings.","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128419978","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 : 2003-12-01DOI: 10.1109/MMSE.2003.1254447
Ang Chee Siang, Radha Krishna
Computer games provide a good environment for learning. Players learn to play the game without being taught didactically as the learning process takes place naturally in the virtual world. Learning is no longer a process of knowledge transfer from the expert to the novice. Learners need to construct the knowledge themselves by interacting with the environment. It is beneficial to study the theory underpinning computer games: how players learn and respond in the game environment. We elucidate the theories of learning, i.e. behavioural learning theory, cognitive learning theory and motivation theory in the context of computer games. Psychology provides a way to understand the learning that occurs naturally in games and also helps in developing an environment in which the player can learn a particular domain of knowledge extrinsically. By studying the psychology and its relation to computer games, we can understand players more comprehensively, and thus predict their responses. The understanding of psychology offers a framework to developing an educational game that promotes learning while maintaining high player motivation. We also attempt to shed some light on how players learn in computer games based on the theory, and thus infer better techniques in supporting game-based learning.
{"title":"Theories of learning: a computer game perspective","authors":"Ang Chee Siang, Radha Krishna","doi":"10.1109/MMSE.2003.1254447","DOIUrl":"https://doi.org/10.1109/MMSE.2003.1254447","url":null,"abstract":"Computer games provide a good environment for learning. Players learn to play the game without being taught didactically as the learning process takes place naturally in the virtual world. Learning is no longer a process of knowledge transfer from the expert to the novice. Learners need to construct the knowledge themselves by interacting with the environment. It is beneficial to study the theory underpinning computer games: how players learn and respond in the game environment. We elucidate the theories of learning, i.e. behavioural learning theory, cognitive learning theory and motivation theory in the context of computer games. Psychology provides a way to understand the learning that occurs naturally in games and also helps in developing an environment in which the player can learn a particular domain of knowledge extrinsically. By studying the psychology and its relation to computer games, we can understand players more comprehensively, and thus predict their responses. The understanding of psychology offers a framework to developing an educational game that promotes learning while maintaining high player motivation. We also attempt to shed some light on how players learn in computer games based on the theory, and thus infer better techniques in supporting game-based learning.","PeriodicalId":322357,"journal":{"name":"Fifth International Symposium on Multimedia Software Engineering, 2003. Proceedings.","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2003-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128290758","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 : 1900-01-01DOI: 10.1109/MMSE.2003.1254450
Ying-Zhe Hsu, Yuh-Jyh Hu
One of the major challenges in molecular biology is to understand the precise mechanism by which gene expression is regulated. Reconstruction of transcription networks is essential to modelling this mechanism. We describe a novel approach for building transcription networks from transcription modules by combining expression profile correlations with probabilistic element assessment. To demonstrate its performance, we systematically tested it on 27 transcription modules and reconstructed the transcription network for 6 transcription factors and 15 genes involved in the yeast cell cycle. The experimental results show that our combinatorial approach can better filter false positives to increase the selectivity in prediction of target genes. The regulatory control relationships described by the network reconstructed also mostly agree with those in earlier studies.
{"title":"Reconstruct transcription networks by combining gene expression correlations with TF binding sites","authors":"Ying-Zhe Hsu, Yuh-Jyh Hu","doi":"10.1109/MMSE.2003.1254450","DOIUrl":"https://doi.org/10.1109/MMSE.2003.1254450","url":null,"abstract":"One of the major challenges in molecular biology is to understand the precise mechanism by which gene expression is regulated. Reconstruction of transcription networks is essential to modelling this mechanism. We describe a novel approach for building transcription networks from transcription modules by combining expression profile correlations with probabilistic element assessment. To demonstrate its performance, we systematically tested it on 27 transcription modules and reconstructed the transcription network for 6 transcription factors and 15 genes involved in the yeast cell cycle. The experimental results show that our combinatorial approach can better filter false positives to increase the selectivity in prediction of target genes. The regulatory control relationships described by the network reconstructed also mostly agree with those in earlier studies.","PeriodicalId":322357,"journal":{"name":"Fifth International Symposium on Multimedia Software Engineering, 2003. Proceedings.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124394169","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 : 1900-01-01DOI: 10.1109/MMSE.2003.1254432
Peter P. Chen
The current practice of graphical icon design is more an art than a science. We propose a scientific-oriented methodology for graphical icon design. It incorporates several ideas from data/system modeling and natural languages in the design and interpretation of icons. Specifically, it incorporates ideas of multileveling modeling and type-instance concepts. It also incorporates the concepts of grammar structures from alphabetic-based languages such as English and the principles of ideogram construction of graphical icon-based natural languages such as Chinese and ancient Egyptian hieroglyphs. The methodology also draws on other scientific disciplines such as cognitive science and user testing.
{"title":"Toward a methodology of graphical icon design","authors":"Peter P. Chen","doi":"10.1109/MMSE.2003.1254432","DOIUrl":"https://doi.org/10.1109/MMSE.2003.1254432","url":null,"abstract":"The current practice of graphical icon design is more an art than a science. We propose a scientific-oriented methodology for graphical icon design. It incorporates several ideas from data/system modeling and natural languages in the design and interpretation of icons. Specifically, it incorporates ideas of multileveling modeling and type-instance concepts. It also incorporates the concepts of grammar structures from alphabetic-based languages such as English and the principles of ideogram construction of graphical icon-based natural languages such as Chinese and ancient Egyptian hieroglyphs. The methodology also draws on other scientific disciplines such as cognitive science and user testing.","PeriodicalId":322357,"journal":{"name":"Fifth International Symposium on Multimedia Software Engineering, 2003. Proceedings.","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124793721","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 : 1900-01-01DOI: 10.1109/MMSE.2003.1254444
C. Ngo, Feng Wang, T. Pong
We present an automatic and novel approach in structuring and indexing lecture videos for distance learning applications. By structuring video content, we can support both topic indexing and semantic querying of multimedia documents. our aim is to link the discussion topics extracted from the electronic slides with their associated video and audio segments. Two major techniques in our proposed approach include video text analysis and speech recognition. Initially, a video is partitioned into shots based on slide transitions. For each shot, the embedded video texts are detected, reconstructed and segmented as high-resolution foreground texts for commercial OCR recognition. The recognized texts can then be matched with their associated slides for video indexing. Meanwhile, both phrases (title) and keywords (content) are also extracted from the electronic slides to spot the speech signals. The spotted phrases and keywords are further utilized as queries to retrieve the most similar slide for speech indexing.
{"title":"Structuring lecture videos for distance learning applications","authors":"C. Ngo, Feng Wang, T. Pong","doi":"10.1109/MMSE.2003.1254444","DOIUrl":"https://doi.org/10.1109/MMSE.2003.1254444","url":null,"abstract":"We present an automatic and novel approach in structuring and indexing lecture videos for distance learning applications. By structuring video content, we can support both topic indexing and semantic querying of multimedia documents. our aim is to link the discussion topics extracted from the electronic slides with their associated video and audio segments. Two major techniques in our proposed approach include video text analysis and speech recognition. Initially, a video is partitioned into shots based on slide transitions. For each shot, the embedded video texts are detected, reconstructed and segmented as high-resolution foreground texts for commercial OCR recognition. The recognized texts can then be matched with their associated slides for video indexing. Meanwhile, both phrases (title) and keywords (content) are also extracted from the electronic slides to spot the speech signals. The spotted phrases and keywords are further utilized as queries to retrieve the most similar slide for speech indexing.","PeriodicalId":322357,"journal":{"name":"Fifth International Symposium on Multimedia Software Engineering, 2003. Proceedings.","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127094714","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}
Protein clustering has been widely exploited to facilitate in-depth analysis of protein functions and families. We discuss the design of an incremental protein clustering package that provides comprehensive features for protein function and family analysis. Specifically, the package offers alternative options for carrying out high-quality protein clustering from different aspects. The incremental nature of the clustering algorithm is essential for efficient analysis of those contemporary protein databases whose sizes are growing rapidly. Concerning the quality of clustering results, experimental results from applying the incremental clustering algorithm to protein sequence analysis show that the incremental algorithm is able to identify protein sequence clusters that match protein families more consistently than the single-link algorithm, which is the most widely used hierarchical clustering algorithm for protein sequence analysis. We also address the implementation techniques employed to improve the system performance.
{"title":"Design of an incremental clustering package for protein function and family analysis","authors":"Chien-Yu Chen, Hsueh‐Fen Juan, Po-Jen Hsiao, Shui-Tein Chen, Hsiang-Wen Tseng, Yen-Jen Oyang","doi":"10.1109/MMSE.2003.1254454","DOIUrl":"https://doi.org/10.1109/MMSE.2003.1254454","url":null,"abstract":"Protein clustering has been widely exploited to facilitate in-depth analysis of protein functions and families. We discuss the design of an incremental protein clustering package that provides comprehensive features for protein function and family analysis. Specifically, the package offers alternative options for carrying out high-quality protein clustering from different aspects. The incremental nature of the clustering algorithm is essential for efficient analysis of those contemporary protein databases whose sizes are growing rapidly. Concerning the quality of clustering results, experimental results from applying the incremental clustering algorithm to protein sequence analysis show that the incremental algorithm is able to identify protein sequence clusters that match protein families more consistently than the single-link algorithm, which is the most widely used hierarchical clustering algorithm for protein sequence analysis. We also address the implementation techniques employed to improve the system performance.","PeriodicalId":322357,"journal":{"name":"Fifth International Symposium on Multimedia Software Engineering, 2003. Proceedings.","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122164482","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 : 1900-01-01DOI: 10.1109/MMSE.2003.1254430
J. Ke
As Taiwan's manufacturing-based economy is facing fierce competition and challenges, building a well-balanced economy has become an urgent issue to the country's survival in the next decades. With key elements such as diverse culture, capable workforce, abundant capital, and technical innovation in place, Taiwan has chosen knowledge-based service industry as the strategic driving force to complement and transform its traditional production and logistics operations.
{"title":"Creating a balanced and diverse economy in Taiwan with knowledge-based service industry","authors":"J. Ke","doi":"10.1109/MMSE.2003.1254430","DOIUrl":"https://doi.org/10.1109/MMSE.2003.1254430","url":null,"abstract":"As Taiwan's manufacturing-based economy is facing fierce competition and challenges, building a well-balanced economy has become an urgent issue to the country's survival in the next decades. With key elements such as diverse culture, capable workforce, abundant capital, and technical innovation in place, Taiwan has chosen knowledge-based service industry as the strategic driving force to complement and transform its traditional production and logistics operations.","PeriodicalId":322357,"journal":{"name":"Fifth International Symposium on Multimedia Software Engineering, 2003. Proceedings.","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131770787","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：