Pub Date : 2012-07-15DOI: 10.1109/ICMLC.2012.6359533
Chun-Mei Liu
This paper proposes a linguistic fuzzy method to evaluate the reliability of emergency logistics system based on incomplete weight information. The proposed methodology involves two mechanisms: (1). Establish the fuzzy comment set about sub-criteria and criteria by linguistics information; (2). Compute the aggregated ratings of the criteria and the emergency logistics system reliability of emergency logistics alternative using the linguistic weighted averaging. Empirical results are given to verify the practicality and effectiveness of the proposed approach.
{"title":"Evaluating the reliability of emergency logistics system based on fuzzy linguistic approach","authors":"Chun-Mei Liu","doi":"10.1109/ICMLC.2012.6359533","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359533","url":null,"abstract":"This paper proposes a linguistic fuzzy method to evaluate the reliability of emergency logistics system based on incomplete weight information. The proposed methodology involves two mechanisms: (1). Establish the fuzzy comment set about sub-criteria and criteria by linguistics information; (2). Compute the aggregated ratings of the criteria and the emergency logistics system reliability of emergency logistics alternative using the linguistic weighted averaging. Empirical results are given to verify the practicality and effectiveness of the proposed approach.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129870622","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 : 2012-07-15DOI: 10.1109/ICMLC.2012.6358929
Zhan-Jing Wang, Jiao-Ying Wang, Fachao Li
Aiming at the covering of the rough set attribute reduction and on the foundation of rough set model proposed by Zakowski, this paper builds a fuzzy similarity relation by using some properties of fuzzy sets. Moreover, we discuss the method of ascertaining fuzzy covering based on a family of fuzzy concepts, and propose the concept of fuzzy covering. The impact of precision change on coverings ascertained by fuzzy sets is analyzed. These results provide a foundation for the application of covering based rough set models to fuzzy attributes.
{"title":"A method of ascertaining fuzzy covering based on a family of fuzzy concepts","authors":"Zhan-Jing Wang, Jiao-Ying Wang, Fachao Li","doi":"10.1109/ICMLC.2012.6358929","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6358929","url":null,"abstract":"Aiming at the covering of the rough set attribute reduction and on the foundation of rough set model proposed by Zakowski, this paper builds a fuzzy similarity relation by using some properties of fuzzy sets. Moreover, we discuss the method of ascertaining fuzzy covering based on a family of fuzzy concepts, and propose the concept of fuzzy covering. The impact of precision change on coverings ascertained by fuzzy sets is analyzed. These results provide a foundation for the application of covering based rough set models to fuzzy attributes.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130259105","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 : 2012-07-15DOI: 10.1109/ICMLC.2012.6359646
Chia-Te Chou, C. Lee, C. Juan, T. Lin, M. Tsai
The paper presents both chrominance uniformity and color temperature compensation for RGB LED lighting illumination. A self-developed color optical sensing module and an integrating sphere were used to measure the color characteristics of LED pixels. Firstly, the transfer coefficients for each color measurement were calibrated. A calibrated sensing module was applied to inspect the color characteristics of 3 in 1 color LED modules. With the required target color chrominance or color temperature, the compensated RGB lighting ratio can be derived according to the mixed light formula associated with original RGB measurement. The experimental results from the 4×4 LEDs show that the deviation of white chrominance by using a 3 in 1 LED module is about 0.1001 before compensation, but the average color deviation is reduced to 0.002 and the average color temperature deviation is less than 71K after compensation by using the proposed method.
{"title":"Color temperature compensation for LED lighting illumination","authors":"Chia-Te Chou, C. Lee, C. Juan, T. Lin, M. Tsai","doi":"10.1109/ICMLC.2012.6359646","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359646","url":null,"abstract":"The paper presents both chrominance uniformity and color temperature compensation for RGB LED lighting illumination. A self-developed color optical sensing module and an integrating sphere were used to measure the color characteristics of LED pixels. Firstly, the transfer coefficients for each color measurement were calibrated. A calibrated sensing module was applied to inspect the color characteristics of 3 in 1 color LED modules. With the required target color chrominance or color temperature, the compensated RGB lighting ratio can be derived according to the mixed light formula associated with original RGB measurement. The experimental results from the 4×4 LEDs show that the deviation of white chrominance by using a 3 in 1 LED module is about 0.1001 before compensation, but the average color deviation is reduced to 0.002 and the average color temperature deviation is less than 71K after compensation by using the proposed method.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129492441","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 : 2012-07-15DOI: 10.1109/ICMLC.2012.6359522
Xiang Chen, Wei Bu, Xiangqian Wu, Baisheng Dai, Y. Teng
Diabetic Retinopathy (DR) is one of the major causes of blindness, and Hard Exudates (HEs) which are common and early clinical signs of DR. This paper presented a novel method to automatically detect HEs in color retinal images. We first extract HEs candidate regions by combining histogram segmentation with morphological reconstruction. Next, we define 44 significant features for each candidate region. A supervised support vector machine (SVM) is finally trained based on these features to classify the candidate regions for HEs. We evaluate the proposed method on the public DIARETDB1 database and achieve an sensitivity of 94.7% and an positive predictive value of 90.0%. Experimental results show that our method can produce reliable detection of HEs.
{"title":"A novel method for automatic Hard Exudates detection in color retinal images","authors":"Xiang Chen, Wei Bu, Xiangqian Wu, Baisheng Dai, Y. Teng","doi":"10.1109/ICMLC.2012.6359522","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359522","url":null,"abstract":"Diabetic Retinopathy (DR) is one of the major causes of blindness, and Hard Exudates (HEs) which are common and early clinical signs of DR. This paper presented a novel method to automatically detect HEs in color retinal images. We first extract HEs candidate regions by combining histogram segmentation with morphological reconstruction. Next, we define 44 significant features for each candidate region. A supervised support vector machine (SVM) is finally trained based on these features to classify the candidate regions for HEs. We evaluate the proposed method on the public DIARETDB1 database and achieve an sensitivity of 94.7% and an positive predictive value of 90.0%. Experimental results show that our method can produce reliable detection of HEs.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128433353","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 : 2012-07-15DOI: 10.1109/ICMLC.2012.6359017
Yanxia Lu, Huifeng Shi
In this paper, the linear gaussian state space model is used to forecast the hourly electricity load. Since the weather variables have significant impacts on electricity demand, thus in our forecasting model, the weather variables are considered as explanatory variables and added to the state space model. The variance parameters of the linear gaussian state space are estimated by the Markov chain Monte Carlo method. Given the estimated parameters, the linear gaussian state space is used to forecast the electricity load on two hours SAM and 14PM respectively. The result shows that this model has higher forecasting precision than the one to four days ahead forecasting, and the state space model estimated by Gibbs sampling algorithm has better performance than the model based on the MH algorithm.
{"title":"The hourly load forecasting based on linear Gaussian state space model","authors":"Yanxia Lu, Huifeng Shi","doi":"10.1109/ICMLC.2012.6359017","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359017","url":null,"abstract":"In this paper, the linear gaussian state space model is used to forecast the hourly electricity load. Since the weather variables have significant impacts on electricity demand, thus in our forecasting model, the weather variables are considered as explanatory variables and added to the state space model. The variance parameters of the linear gaussian state space are estimated by the Markov chain Monte Carlo method. Given the estimated parameters, the linear gaussian state space is used to forecast the electricity load on two hours SAM and 14PM respectively. The result shows that this model has higher forecasting precision than the one to four days ahead forecasting, and the state space model estimated by Gibbs sampling algorithm has better performance than the model based on the MH algorithm.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128484189","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 : 2012-07-15DOI: 10.1109/ICMLC.2012.6358971
Xu Zhou, Shuxia Lu, Lisha Hu, Meng Zhang
For the problem of imbalanced data classification which was not discussed in the standard Extreme Support Vector Machines (ESVM), an imbalanced extreme support vector machines (IESVM) was proposed. Firstly, a preliminary normal vector of separating hyperplane is obtained directly by geometric analysis. Secondly, penalty factors are obtained which are based on the information provided by data sets projecting onto the preliminary normal vector. Finally, the final separation hyperplane is got through the improved ESVM training. IESVM can overcome disadvantages of traditional designing methods which only consider the imbalance of samples size and can improve the generalization ability of ESVM. Experimental results show that the method can effectively enhance the classification performance on imbalanced data sets.
{"title":"Imbalanced extreme support vector machine","authors":"Xu Zhou, Shuxia Lu, Lisha Hu, Meng Zhang","doi":"10.1109/ICMLC.2012.6358971","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6358971","url":null,"abstract":"For the problem of imbalanced data classification which was not discussed in the standard Extreme Support Vector Machines (ESVM), an imbalanced extreme support vector machines (IESVM) was proposed. Firstly, a preliminary normal vector of separating hyperplane is obtained directly by geometric analysis. Secondly, penalty factors are obtained which are based on the information provided by data sets projecting onto the preliminary normal vector. Finally, the final separation hyperplane is got through the improved ESVM training. IESVM can overcome disadvantages of traditional designing methods which only consider the imbalance of samples size and can improve the generalization ability of ESVM. Experimental results show that the method can effectively enhance the classification performance on imbalanced data sets.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"55 32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124758234","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 : 2012-07-15DOI: 10.1109/ICMLC.2012.6359595
Chih-Chin Lai, Chung-Hung Ko, C. Yeh
Digital watermarking has emerged as a leading technique for copyright protection or authentication of multimedia data. It is known that there is a trade off between the imperceptibility and robustness of a digital watermarking scheme. Trying to deal with this problem, an adaptive improved singular value decomposition-based watermarking method by applying local image statistics and the genetic algorithm is presented. The local image statistics can be used not only to measure the perceptibility of watermarks once they are embedded, but also to control the perceptibility during the embedding process. Watermarking components with proper strength factors are the most critical aspect in the whole process and the genetic algorithm is employed to find the appropriate watermarking strength factors. Experimental results confirm the imperceptibility of the proposed method and its robustness against a variety of image-processing attacks.
{"title":"An adaptive SVD-based watermarking scheme based on genetic algorithm","authors":"Chih-Chin Lai, Chung-Hung Ko, C. Yeh","doi":"10.1109/ICMLC.2012.6359595","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359595","url":null,"abstract":"Digital watermarking has emerged as a leading technique for copyright protection or authentication of multimedia data. It is known that there is a trade off between the imperceptibility and robustness of a digital watermarking scheme. Trying to deal with this problem, an adaptive improved singular value decomposition-based watermarking method by applying local image statistics and the genetic algorithm is presented. The local image statistics can be used not only to measure the perceptibility of watermarks once they are embedded, but also to control the perceptibility during the embedding process. Watermarking components with proper strength factors are the most critical aspect in the whole process and the genetic algorithm is employed to find the appropriate watermarking strength factors. Experimental results confirm the imperceptibility of the proposed method and its robustness against a variety of image-processing attacks.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130047556","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 : 2012-07-15DOI: 10.1109/ICMLC.2012.6359667
Po-Lun Chang, Fei-Hu Hsieh, I-Ta Tsai
With wireless communication network and GPS positioning technology, most of current existing systems using IP protocol to provide various information services such as traffic and navigation. In this paper, we propose a location-based system with WAVE/DSRC present a low delay and high mobility system architecture constructed on the road. It provides vehicles with more intelligent real time information such as news and location-based contents. We also implement the system, which shows location-based content in the service area.
{"title":"Research and development of location-based system","authors":"Po-Lun Chang, Fei-Hu Hsieh, I-Ta Tsai","doi":"10.1109/ICMLC.2012.6359667","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359667","url":null,"abstract":"With wireless communication network and GPS positioning technology, most of current existing systems using IP protocol to provide various information services such as traffic and navigation. In this paper, we propose a location-based system with WAVE/DSRC present a low delay and high mobility system architecture constructed on the road. It provides vehicles with more intelligent real time information such as news and location-based contents. We also implement the system, which shows location-based content in the service area.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130148212","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}
Large coal-fired power unit is a complex nonlinear system with more uncertainties to describe, evaluate and optimize. It is essential and difficult to determine the optimal targets in operation optimization of power units, especially considering the boundary constraints, operation conditions and system features. Fuzzy rough set (FRS)-based decision table reduction was introduced to clean the historian operation data efficiently without information losses. The result shows that the derived energy consumption decision rules can be used to determine the optimal targets quickly and dynamically for different boundary and operation conditions. It makes significant reference and promising prospects in energy-consumption diagnosis and operation optimization of power units.
{"title":"FRS-based decision table reduction for the operation optimization of large coal-fired power units","authors":"Ning-Ling Wang, De-gang Chen, Yongping Yang, Ting Zhang","doi":"10.1109/ICMLC.2012.6359492","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359492","url":null,"abstract":"Large coal-fired power unit is a complex nonlinear system with more uncertainties to describe, evaluate and optimize. It is essential and difficult to determine the optimal targets in operation optimization of power units, especially considering the boundary constraints, operation conditions and system features. Fuzzy rough set (FRS)-based decision table reduction was introduced to clean the historian operation data efficiently without information losses. The result shows that the derived energy consumption decision rules can be used to determine the optimal targets quickly and dynamically for different boundary and operation conditions. It makes significant reference and promising prospects in energy-consumption diagnosis and operation optimization of power units.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122000079","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 : 2012-07-15DOI: 10.1109/ICMLC.2012.6359612
R. Wai, Yu-Chih Huang, Yi-Chang Chen
In recent years, an intelligent micro-grid system composed of renewable energy sources is becoming one of the interesting research topics. The success design of long-term load forecasting (LTLF) enables the intelligent micro-grid system to manipulate an optimized loading and unloading control by measuring the electrical supply for achieving the best economical and power efficiency. In this study, intelligent forecasting structures via a similar time method with historical load change rates are developed based on the basic frameworks of fuzzy neural network (FNN) and particle swarm optimization (PSO). In the regulative aspect of network parameters, conventional back-propagation (BP) and PSO tuning algorithms are used, and varied learning rates are designed in the sense of discrete-time Lyapunov stability theory. The performance comparisons of different intelligent forecasting structures including neural network (NN) structure with BP tuning algorithm (NN-BP), FNN structure with BP tuning algorithm (FNN-BP), FNN structure with BP tuning algorithm and varied learning rates (FNN-BP-V), FNN structure with PSO tuning algorithm (FNN-PSO) and PSO structure are given by numerical simulations of a real case in Taiwan campus.
{"title":"Design of intelligent long-term load forecasting with fuzzy neural network and particle swarm optimization","authors":"R. Wai, Yu-Chih Huang, Yi-Chang Chen","doi":"10.1109/ICMLC.2012.6359612","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359612","url":null,"abstract":"In recent years, an intelligent micro-grid system composed of renewable energy sources is becoming one of the interesting research topics. The success design of long-term load forecasting (LTLF) enables the intelligent micro-grid system to manipulate an optimized loading and unloading control by measuring the electrical supply for achieving the best economical and power efficiency. In this study, intelligent forecasting structures via a similar time method with historical load change rates are developed based on the basic frameworks of fuzzy neural network (FNN) and particle swarm optimization (PSO). In the regulative aspect of network parameters, conventional back-propagation (BP) and PSO tuning algorithms are used, and varied learning rates are designed in the sense of discrete-time Lyapunov stability theory. The performance comparisons of different intelligent forecasting structures including neural network (NN) structure with BP tuning algorithm (NN-BP), FNN structure with BP tuning algorithm (FNN-BP), FNN structure with BP tuning algorithm and varied learning rates (FNN-BP-V), FNN structure with PSO tuning algorithm (FNN-PSO) and PSO structure are given by numerical simulations of a real case in Taiwan campus.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115946309","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：