Pub Date : 2010-09-20DOI: 10.1109/ICMLC.2010.5581047
Yong-Hua Cai
The Bayesian classifier model is a class of probability classifier based on the Bayesian theory. Compared with more sophisticated classification algorithms, such as decision tree and neural network, Bayesian classifier can offer very good classification accuracy in many practical applications. In this article, we perform a methodologically sound comparison of the seven methods, which shows large mutual differences of each of the methods and no single method being universally better. The comparisons that are carried out in this paper include time complexity and classification accuracy of these seven algorithms.
{"title":"The comparative study of different Bayesian classifier models","authors":"Yong-Hua Cai","doi":"10.1109/ICMLC.2010.5581047","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5581047","url":null,"abstract":"The Bayesian classifier model is a class of probability classifier based on the Bayesian theory. Compared with more sophisticated classification algorithms, such as decision tree and neural network, Bayesian classifier can offer very good classification accuracy in many practical applications. In this article, we perform a methodologically sound comparison of the seven methods, which shows large mutual differences of each of the methods and no single method being universally better. The comparisons that are carried out in this paper include time complexity and classification accuracy of these seven algorithms.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130692439","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 : 2010-09-20DOI: 10.1109/ICMLC.2010.5580642
Jing Qiu, Jun-Kang Hao
This paper proposes a novel feature-based method for relation extraction task. Diverse lexical and syntactic features are defined to describe the context of the pair of entities. Dependency features are selected to capture the structure and dependency information of sentence. Hierarchical classifying strategy is used to reduce the weakness of the traditional approach, which treats training examples in different classes equally and independently, At the same time, correction mechanism is used to improve the performance of the system.
{"title":"Feature-based approach combined with hierarchical classifying strategy to relation extraction","authors":"Jing Qiu, Jun-Kang Hao","doi":"10.1109/ICMLC.2010.5580642","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5580642","url":null,"abstract":"This paper proposes a novel feature-based method for relation extraction task. Diverse lexical and syntactic features are defined to describe the context of the pair of entities. Dependency features are selected to capture the structure and dependency information of sentence. Hierarchical classifying strategy is used to reduce the weakness of the traditional approach, which treats training examples in different classes equally and independently, At the same time, correction mechanism is used to improve the performance of the system.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130215074","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 : 2010-09-20DOI: 10.1109/ICMLC.2010.5580742
Yong-Huai Huang, K. Chung
Inverse halftoning (IH) is used to reconstruct the gray image from an input halftone image. This paper presents a new texture-and lookup table-based (TLUT-based) IH (TLIH) algorithm to improve the quality of the reconstructed image. In the proposed TLUT-based approach, a DCT-based learning scheme is utilized to classify the training set into several kinds of textures. These classified textures are useful to build up the texture-based lookup table which is used to reconstruct high quality gray images. Under thirty real training images, experimental results demonstrated that the proposed TLIH algorithm has 1.13 dB and 0.75 dB image quality improvement when compared to the currently published two methods, one by Mese and Vaidyanathan and the other by Chung and Wu, respectively.
{"title":"New inverse halftoning using texture-and lookup table-based learning approach","authors":"Yong-Huai Huang, K. Chung","doi":"10.1109/ICMLC.2010.5580742","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5580742","url":null,"abstract":"Inverse halftoning (IH) is used to reconstruct the gray image from an input halftone image. This paper presents a new texture-and lookup table-based (TLUT-based) IH (TLIH) algorithm to improve the quality of the reconstructed image. In the proposed TLUT-based approach, a DCT-based learning scheme is utilized to classify the training set into several kinds of textures. These classified textures are useful to build up the texture-based lookup table which is used to reconstruct high quality gray images. Under thirty real training images, experimental results demonstrated that the proposed TLIH algorithm has 1.13 dB and 0.75 dB image quality improvement when compared to the currently published two methods, one by Mese and Vaidyanathan and the other by Chung and Wu, respectively.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132907595","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 : 2010-09-20DOI: 10.1109/ICMLC.2010.5580674
Yan Song, C. Kit
Transliteration is a challengeable task aimed at converting a proper name into another language with phonetic equivalence. Since the conversion relates to the phonetic aspect of a text, syllabification is considered a major factor affecting the performance of a transliteration system. In grapheme-based approaches, there are two routines to transliterate, one is to perform in a pipeline of separate syllabification and other components in generation process step by step, the other is to synchronously segment syllables and generating transliteration options. Usually, joint decoding outperforms the cascade processing in many natural language processing missions, however, syllabification is a special component in transliteration task. Thus in this paper, we investigate the two routines with a systematic analysis and compare their results to illustrate the strength of syllabification. A phrase-based statistical machine translation framework for joint decoding and a conditional random field syllabification system are used in this work for our investigation, which shows a different scenario on the issue of joint decoding versus cascade processing in transliteration.
{"title":"Does joint decoding really outperform cascade processing in English-to-Chinese transliteration generation? The role of syllabification","authors":"Yan Song, C. Kit","doi":"10.1109/ICMLC.2010.5580674","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5580674","url":null,"abstract":"Transliteration is a challengeable task aimed at converting a proper name into another language with phonetic equivalence. Since the conversion relates to the phonetic aspect of a text, syllabification is considered a major factor affecting the performance of a transliteration system. In grapheme-based approaches, there are two routines to transliterate, one is to perform in a pipeline of separate syllabification and other components in generation process step by step, the other is to synchronously segment syllables and generating transliteration options. Usually, joint decoding outperforms the cascade processing in many natural language processing missions, however, syllabification is a special component in transliteration task. Thus in this paper, we investigate the two routines with a systematic analysis and compare their results to illustrate the strength of syllabification. A phrase-based statistical machine translation framework for joint decoding and a conditional random field syllabification system are used in this work for our investigation, which shows a different scenario on the issue of joint decoding versus cascade processing in transliteration.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117135246","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 : 2010-09-20DOI: 10.1109/ICMLC.2010.5581088
Ru Huang, Guang-Hui Xu
The transmission of massive highly related data could generally exist in gathering scenario of sensor networks and lead to the depletion of valuable energy resource. According to the above energy waste problem, an effective filtering mechanism is proposed in the paper to enhance the energy-efficiency of data-gathering. Many current researches adopt clustering method and aggregation technology to lower energy cost during the process in data transmission, while our proposed filtering framework mainly puts emphasis on inhibiting the production of redundant loads at the gathering source to greatly reduce energy cost using self-adaptive filtering scheme, which is constructed by prediction module for mining the time domain association, self-learning module for modifying model and driving module for executing filtering operation. We can prove the above filter components combined with the running of error-driving rule and threshold-distributing rule can effectively decrease the quantity of data transmission in networks based on QoS requirement. Finally, the simulation results show that the proposed filtering mechanism can do better than some classical data gathering approaches on the aspect of energy-saving effect.
{"title":"The design of energy-saving filtering mechanism for sensor networks","authors":"Ru Huang, Guang-Hui Xu","doi":"10.1109/ICMLC.2010.5581088","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5581088","url":null,"abstract":"The transmission of massive highly related data could generally exist in gathering scenario of sensor networks and lead to the depletion of valuable energy resource. According to the above energy waste problem, an effective filtering mechanism is proposed in the paper to enhance the energy-efficiency of data-gathering. Many current researches adopt clustering method and aggregation technology to lower energy cost during the process in data transmission, while our proposed filtering framework mainly puts emphasis on inhibiting the production of redundant loads at the gathering source to greatly reduce energy cost using self-adaptive filtering scheme, which is constructed by prediction module for mining the time domain association, self-learning module for modifying model and driving module for executing filtering operation. We can prove the above filter components combined with the running of error-driving rule and threshold-distributing rule can effectively decrease the quantity of data transmission in networks based on QoS requirement. Finally, the simulation results show that the proposed filtering mechanism can do better than some classical data gathering approaches on the aspect of energy-saving effect.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120951893","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 : 2010-07-11DOI: 10.1109/ICMLC.2010.5580566
Zhi-Chun Huang, P. Chan, Wing W. Y. Ng, D. Yeung
Aim to currently content-based image retrieval method having high computational complexity and low retrieval accuracy problem, this paper proposes a content-based image retrieval method based on color and texture features. As its color features, color moments of the Hue, Saturation and Value (HSV) component images in HSV color space are used. As its texture features, Gabor texture descriptors are adopted. Users assign the weights to each feature respectively and calculate the similarity with combined features of color and texture according to normalized Euclidean distance. Experiment results show that the proposed method has higher retrieval accuracy than conventional methods using color and texture features even though its feature vector dimension results in a lower rate than the conventional method.
{"title":"Content-based image retrieval using color moment and Gabor texture feature","authors":"Zhi-Chun Huang, P. Chan, Wing W. Y. Ng, D. Yeung","doi":"10.1109/ICMLC.2010.5580566","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5580566","url":null,"abstract":"Aim to currently content-based image retrieval method having high computational complexity and low retrieval accuracy problem, this paper proposes a content-based image retrieval method based on color and texture features. As its color features, color moments of the Hue, Saturation and Value (HSV) component images in HSV color space are used. As its texture features, Gabor texture descriptors are adopted. Users assign the weights to each feature respectively and calculate the similarity with combined features of color and texture according to normalized Euclidean distance. Experiment results show that the proposed method has higher retrieval accuracy than conventional methods using color and texture features even though its feature vector dimension results in a lower rate than the conventional method.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115270243","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 : 2010-07-11DOI: 10.1109/ICMLC.2010.5580503
Wei-Cheng Hu, Zhuan-Liu Cheng
An effective clustering algorithm called PWStream for probabilistic data stream over sliding window is developed in this paper. The algorithm uses exponential histogram of cluster feature to store the summary information of the most recently arrived tuples, and outdated information is deleted within a certain guaranteed range of error. For the uncertain tuples in data stream, the concepts of strong cluster, transitional cluster and weak cluster are proposed in the PWStream. With these concepts, an effective strategy of choosing cluster based on distance and existence probability is designed, which can find more strong clusters. Theoretical analysis and comprehensive experimental results demonstrate that the proposed method is of high quality and fast processing rate.
{"title":"Clustering algorithm for probabilistic data stream over sliding windows","authors":"Wei-Cheng Hu, Zhuan-Liu Cheng","doi":"10.1109/ICMLC.2010.5580503","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5580503","url":null,"abstract":"An effective clustering algorithm called PWStream for probabilistic data stream over sliding window is developed in this paper. The algorithm uses exponential histogram of cluster feature to store the summary information of the most recently arrived tuples, and outdated information is deleted within a certain guaranteed range of error. For the uncertain tuples in data stream, the concepts of strong cluster, transitional cluster and weak cluster are proposed in the PWStream. With these concepts, an effective strategy of choosing cluster based on distance and existence probability is designed, which can find more strong clusters. Theoretical analysis and comprehensive experimental results demonstrate that the proposed method is of high quality and fast processing rate.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115416210","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 : 2010-07-11DOI: 10.1109/ICMLC.2010.5580719
Z. G. Zhang, Y. Hung, S. Chan, Weichao Xu, Yong Hu
It is of increasing interest in systems biology to discover gene regulatory networks (GRNs) from time-series genomic data, i.e., to explore the interactions among a large number of genes and gene products over time. Currently, one common approach is based on Granger causality, which models the time-series genomic data as a vector autoregressive (VAR) process and estimates the GRNs from the VAR coefficient matrix. The main challenge for identification of VAR models is the high dimensionality of genes and limited number of time points, which results in statistically inefficient solution and high computational complexity. Therefore, fast and efficient variable selection techniques are highly desirable. In this paper, an introductory review of identification methods and variable selection techniques for VAR models in learning the GRNs will be presented. Furthermore, a dynamic VAR (DVAR) model, which accounts for dynamic GRNs changing with time during the experimental cycle, and its identification methods are introduced.
{"title":"Modeling and identification of gene regulatory networks: A Granger causality approach","authors":"Z. G. Zhang, Y. Hung, S. Chan, Weichao Xu, Yong Hu","doi":"10.1109/ICMLC.2010.5580719","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5580719","url":null,"abstract":"It is of increasing interest in systems biology to discover gene regulatory networks (GRNs) from time-series genomic data, i.e., to explore the interactions among a large number of genes and gene products over time. Currently, one common approach is based on Granger causality, which models the time-series genomic data as a vector autoregressive (VAR) process and estimates the GRNs from the VAR coefficient matrix. The main challenge for identification of VAR models is the high dimensionality of genes and limited number of time points, which results in statistically inefficient solution and high computational complexity. Therefore, fast and efficient variable selection techniques are highly desirable. In this paper, an introductory review of identification methods and variable selection techniques for VAR models in learning the GRNs will be presented. Furthermore, a dynamic VAR (DVAR) model, which accounts for dynamic GRNs changing with time during the experimental cycle, and its identification methods are introduced.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"2011 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114668060","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 : 2010-07-11DOI: 10.1109/ICMLC.2010.5580788
Chun-Fei Hsu, P. Lee, Chih-Hu Wang
Human beings to face with oil and coal depletion of fossil fuels. With the development of society, energy saving and environmental protection have become a topical issue. The sun energy using is in the rapid development and application; however, the amount of power produced by a sun tracker depends upon the amount of sun light. This paper proposes a fuzzy sliding-mode controller (FSMC) with a time-varying sliding surface to control a light tacking system via the sliding-mode control approach. The proposed FSMC system is composed of a fuzzy controller and a slope regulator. The fuzzy controller infers the control action to control the system states to reach the sliding surface without large overshoot, and the slope regulator tunes the slope of the sliding surface to govern small convergence time of the system trajectories. Thus, the proposed FSMC system can achieve satisfactory tracking performance with fast transient response and good robustness. Finally, the proposed FSMC system is implemented based on a field programmable gate array chip for low-cost and high-performance industrial applications. The experimental results show the proposed FSMC can achieve favorable tracking performance for the light tracking system even under a payload onto the platform of the light tracking system.
{"title":"Design of an FPGA-based fuzzy sliding-mode controller for light tracking systems","authors":"Chun-Fei Hsu, P. Lee, Chih-Hu Wang","doi":"10.1109/ICMLC.2010.5580788","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5580788","url":null,"abstract":"Human beings to face with oil and coal depletion of fossil fuels. With the development of society, energy saving and environmental protection have become a topical issue. The sun energy using is in the rapid development and application; however, the amount of power produced by a sun tracker depends upon the amount of sun light. This paper proposes a fuzzy sliding-mode controller (FSMC) with a time-varying sliding surface to control a light tacking system via the sliding-mode control approach. The proposed FSMC system is composed of a fuzzy controller and a slope regulator. The fuzzy controller infers the control action to control the system states to reach the sliding surface without large overshoot, and the slope regulator tunes the slope of the sliding surface to govern small convergence time of the system trajectories. Thus, the proposed FSMC system can achieve satisfactory tracking performance with fast transient response and good robustness. Finally, the proposed FSMC system is implemented based on a field programmable gate array chip for low-cost and high-performance industrial applications. The experimental results show the proposed FSMC can achieve favorable tracking performance for the light tracking system even under a payload onto the platform of the light tracking system.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117161306","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 : 2010-07-11DOI: 10.1109/ICMLC.2010.5580786
Chih-Min Lin, Chang-Chih Chung, Yu-Ju Liu, D. Yeung
This paper presents a learning approach using cerebellar model articulation controller (CMAC) to accommodate faults for a class of multivariable nonlinear systems. A CMAC is proposed to estimate the unknown fault. Then, an adaptive fault accommodation controller is derived based on Lyapunov function, so that the proposed control system can accommodate the faults with desired system stability. Finally, the proposed fault accommodation control system is applied to a tank control system. Simulation results show that the proposed method can effectively achieve the fault accommodation for this system.
{"title":"CMAC-based fault accommodation control for tank system","authors":"Chih-Min Lin, Chang-Chih Chung, Yu-Ju Liu, D. Yeung","doi":"10.1109/ICMLC.2010.5580786","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5580786","url":null,"abstract":"This paper presents a learning approach using cerebellar model articulation controller (CMAC) to accommodate faults for a class of multivariable nonlinear systems. A CMAC is proposed to estimate the unknown fault. Then, an adaptive fault accommodation controller is derived based on Lyapunov function, so that the proposed control system can accommodate the faults with desired system stability. Finally, the proposed fault accommodation control system is applied to a tank control system. Simulation results show that the proposed method can effectively achieve the fault accommodation for this system.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121056232","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：