Pub Date : 2010-07-11DOI: 10.1109/ICMLC.2010.5580889
Ji-Hui Li
Index tables on key words and bipartite graph matching are two existing methods on Web service discovery, but both of them have certain limitations. On the basis of common Web service descriptive standardized WSDL, a novel two-stage Web service discovery method is proposed in this paper. Related service is discovered based on index tables in the first stage. By taking semantic information into account together with bipartite graph matching, the needed Web service operations are discovered efficiently in the second stage. Experiments show that our method can not only discover required Web service operations accurately, but also provide alternative service operations.
{"title":"Discovering Web service operations by index tables and bipartite graphs","authors":"Ji-Hui Li","doi":"10.1109/ICMLC.2010.5580889","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5580889","url":null,"abstract":"Index tables on key words and bipartite graph matching are two existing methods on Web service discovery, but both of them have certain limitations. On the basis of common Web service descriptive standardized WSDL, a novel two-stage Web service discovery method is proposed in this paper. Related service is discovered based on index tables in the first stage. By taking semantic information into account together with bipartite graph matching, the needed Web service operations are discovered efficiently in the second stage. Experiments show that our method can not only discover required Web service operations accurately, but also provide alternative service operations.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"40 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":"131322623","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.2010.5581049
Yang Xia, Jianrong Wu
In the uncertainty space, some equivalent conditions on convergence in uncertain measure for the uncertain variable sequences are established, the results are the generalizations of the corresponding ones of the existing literatures.
{"title":"Some equivalent conditions on convergence in uncertain measure","authors":"Yang Xia, Jianrong Wu","doi":"10.1109/ICMLC.2010.5581049","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5581049","url":null,"abstract":"In the uncertainty space, some equivalent conditions on convergence in uncertain measure for the uncertain variable sequences are established, the results are the generalizations of the corresponding ones of the existing literatures.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"529 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":"127061422","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.2010.5580845
Yi-Hsing Chang, Bo-Kai Chen
An Automatic Teaching Materials Construction System based on Mashup is proposed in this paper. The main design concept is to establish a Mashup Data model to obtain the resources on Social Network. Furthermore, using ontology as a rule, the resources are effectively, automatically classified and integrated. The will be able to reduce the digital teaching materials required to spend large amount of manpower, time and other resources in the past by the way. We will finally come to the actual case of C language to explore and analyze the data model. This Automatic Teaching Materials Construction System is expected to achieve an efficient Web-based learning environment.
{"title":"An Automatic Teaching Materials Construction System based on Mashup","authors":"Yi-Hsing Chang, Bo-Kai Chen","doi":"10.1109/ICMLC.2010.5580845","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5580845","url":null,"abstract":"An Automatic Teaching Materials Construction System based on Mashup is proposed in this paper. The main design concept is to establish a Mashup Data model to obtain the resources on Social Network. Furthermore, using ontology as a rule, the resources are effectively, automatically classified and integrated. The will be able to reduce the digital teaching materials required to spend large amount of manpower, time and other resources in the past by the way. We will finally come to the actual case of C language to explore and analyze the data model. This Automatic Teaching Materials Construction System is expected to achieve an efficient Web-based learning environment.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"11 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":"115554864","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.2010.5580804
Chunyu Ren, Xiao-bo Wang
According to the individual and various demands of customers, establish single and mixed fleet single-depot vehicle routing problem with backhauls model. A hybrid heuristic algorithm is proposed to solving the problem, which combines the advantages of genetic algorithm and tabu search algorithm. Firstly, hybrid genetic algorithm is used to get the initialization solution. Namely, use natural number coding so as to simplify the problem; retain the best selection so as to guard the diversity of group, use essence cluster so as to generate more excellent chromosome. Secondly, the taboo searching algorithm is applied to optimizing the initialization solution, the best of which is taken by genetic algorithm. Consequently, the convergent speed and searching efficiency of algorithm are improved. Finally, the emulation and calculation prove that the hybrid heuristic algorithm is effective.
{"title":"Study on single and mixed fleet strategy for single-depot vehicle routing problem with backhauls","authors":"Chunyu Ren, Xiao-bo Wang","doi":"10.1109/ICMLC.2010.5580804","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5580804","url":null,"abstract":"According to the individual and various demands of customers, establish single and mixed fleet single-depot vehicle routing problem with backhauls model. A hybrid heuristic algorithm is proposed to solving the problem, which combines the advantages of genetic algorithm and tabu search algorithm. Firstly, hybrid genetic algorithm is used to get the initialization solution. Namely, use natural number coding so as to simplify the problem; retain the best selection so as to guard the diversity of group, use essence cluster so as to generate more excellent chromosome. Secondly, the taboo searching algorithm is applied to optimizing the initialization solution, the best of which is taken by genetic algorithm. Consequently, the convergent speed and searching efficiency of algorithm are improved. Finally, the emulation and calculation prove that the hybrid heuristic algorithm is effective.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"27 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":"115888783","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.2010.5580953
Bingjing Cai, Haiying Wang, Huiru Zheng, Hui Wang
The repeated random walks algorithm (RRW) is a graph clustering algorithm proposed recently. RRW has been shown to achieve better performance on functional module discovery in protein-protein interaction networks than Markov Clustering Algorithm (MCL). There is however little work applying RRW to community detection in social networks. We ran RRW on some real-world social networks that are well-documented in the literature. We then analyzed the impact of different parameters on the quality of clustering, by using a set of cluster metrics. We also compared RRW with two other random walk based graph clustering algorithms. Our experiments showed that the RRW algorithm achieved higher precision but lower modularity. The experiments also revealed some weaknesses of the RRW algorithm, such as higher running cost, and “discarding nodes” method in its post-process stage, which greatly affects the quality of clustering.
{"title":"Evaluation repeated random walks in community detection of social networks","authors":"Bingjing Cai, Haiying Wang, Huiru Zheng, Hui Wang","doi":"10.1109/ICMLC.2010.5580953","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5580953","url":null,"abstract":"The repeated random walks algorithm (RRW) is a graph clustering algorithm proposed recently. RRW has been shown to achieve better performance on functional module discovery in protein-protein interaction networks than Markov Clustering Algorithm (MCL). There is however little work applying RRW to community detection in social networks. We ran RRW on some real-world social networks that are well-documented in the literature. We then analyzed the impact of different parameters on the quality of clustering, by using a set of cluster metrics. We also compared RRW with two other random walk based graph clustering algorithms. Our experiments showed that the RRW algorithm achieved higher precision but lower modularity. The experiments also revealed some weaknesses of the RRW algorithm, such as higher running cost, and “discarding nodes” method in its post-process stage, which greatly affects the quality of clustering.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"1 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":"115909009","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.2010.5580879
Shou-Hsiung Cheng
This paper presents a method for forecasting the change of intraday stock price by utilizing text mining news of stock. This method is based on text mining techniques coupled with rough sets theories and support vector machine classifier. The method can handle without difficulty unstructured news of Taiwan stock market through preprocessing, feature selection and mark. The method also extracts the core phrases by using rough sets theories after the unstructured information has been transformed into structured data. Then, a prediction model is established based on support vector machine classifier. The empirical results show that the proposed model can predict accurately the ups and downs of a stock price within one hour after the news released. The method presented in the study is straightforward, simple and valuable for the short-term investors.
{"title":"Forecasting the change of intraday stock price by using text mining news of stock","authors":"Shou-Hsiung Cheng","doi":"10.1109/ICMLC.2010.5580879","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5580879","url":null,"abstract":"This paper presents a method for forecasting the change of intraday stock price by utilizing text mining news of stock. This method is based on text mining techniques coupled with rough sets theories and support vector machine classifier. The method can handle without difficulty unstructured news of Taiwan stock market through preprocessing, feature selection and mark. The method also extracts the core phrases by using rough sets theories after the unstructured information has been transformed into structured data. Then, a prediction model is established based on support vector machine classifier. The empirical results show that the proposed model can predict accurately the ups and downs of a stock price within one hour after the news released. The method presented in the study is straightforward, simple and valuable for the short-term investors.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"65 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":"124442760","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}
The sensitivity analysis can help to construct a tightly neural network. There are several methods to define the sensitivity of input and weight for perturbations to the trained neural network. This paper proposed a sensitivity definition based on elastic function. This definition considers the measure of the variable of the reference network. The sensitivity calculating formulae are deduced for perceptron and MLP.
{"title":"Sensitivity analysis of multilayer percetron based on elastic function","authors":"Chun-Guo Li, Haifeng Li, Yu-Fen Zhang, Qun-Feng Zhang","doi":"10.1109/ICMLC.2010.5580843","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5580843","url":null,"abstract":"The sensitivity analysis can help to construct a tightly neural network. There are several methods to define the sensitivity of input and weight for perturbations to the trained neural network. This paper proposed a sensitivity definition based on elastic function. This definition considers the measure of the variable of the reference network. The sensitivity calculating formulae are deduced for perceptron and MLP.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"37 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":"114410536","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.2010.5580907
Tao Wu, Bin Li, Long-Wen Wang, Yu Huang
In order to improve production efficiency, inspecting and sorting of LED dies are done respectively in prober and sorter. During the inspection, dies may be broken, fragmentized, tiny moved, or deflected slightly, besides, visual scan can also lead to location deviation when the wafer is moved from prober to sorter. All of this can cause some dies mismatch in the sorting stage, which is never allowed. In order to get integrated match of dies, the position relations between adjacent dies are considered, techniques including diagnosing criterion of position relatives, redundant visual scanning, forward and backtrack algorithm with cross priority are put forward. It is proved with experimental results that such re-index approach is more applicable than traditional index method. When dies arrange in good order, match rate is more than 99.5%, by compassion, that of traditional index method is less than 92%. When the wafer is deflected slightly or locally fragmentized, match rate of the former is more than 92.5%, by contrast, that of the latter is less than 50% in same situation.
{"title":"Automatic detectand match of LED dies basing on position relations betweenadjacent dies","authors":"Tao Wu, Bin Li, Long-Wen Wang, Yu Huang","doi":"10.1109/ICMLC.2010.5580907","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5580907","url":null,"abstract":"In order to improve production efficiency, inspecting and sorting of LED dies are done respectively in prober and sorter. During the inspection, dies may be broken, fragmentized, tiny moved, or deflected slightly, besides, visual scan can also lead to location deviation when the wafer is moved from prober to sorter. All of this can cause some dies mismatch in the sorting stage, which is never allowed. In order to get integrated match of dies, the position relations between adjacent dies are considered, techniques including diagnosing criterion of position relatives, redundant visual scanning, forward and backtrack algorithm with cross priority are put forward. It is proved with experimental results that such re-index approach is more applicable than traditional index method. When dies arrange in good order, match rate is more than 99.5%, by compassion, that of traditional index method is less than 92%. When the wafer is deflected slightly or locally fragmentized, match rate of the former is more than 92.5%, by contrast, that of the latter is less than 50% in same situation.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"44 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":"115010204","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.2010.5581078
Chunru Dong, P. Chan, Wing W. Y. Ng, D. Yeung
For the virtues such as simplicity, high generalization capability, and few training cost, the K-Nearest-Neighbor (KNN) classifier is widely used in pattern recognition and machine learning. However, the computation complexity of KNN classifier will become higher when dealing with large data sets classification problem. In consequence, its efficiency will be decreased greatly. This paper proposes a general two-stage training set condensing algorithm for general KNN classifier. First, we identify the noise data points and remove them from the original training set. Second, a general condensed nearest neighbor rule based on the so-called Nearest Unlike Neighbor (NUN) is presented to further eliminate the redundant samples in training set. In order to verify the performance of the proposed method, some numerical experiments are conducted on several UCI benchmark databases.
{"title":"2-Stage instance selection algorithm for KNN based on Nearest Unlike Neighbors","authors":"Chunru Dong, P. Chan, Wing W. Y. Ng, D. Yeung","doi":"10.1109/ICMLC.2010.5581078","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5581078","url":null,"abstract":"For the virtues such as simplicity, high generalization capability, and few training cost, the K-Nearest-Neighbor (KNN) classifier is widely used in pattern recognition and machine learning. However, the computation complexity of KNN classifier will become higher when dealing with large data sets classification problem. In consequence, its efficiency will be decreased greatly. This paper proposes a general two-stage training set condensing algorithm for general KNN classifier. First, we identify the noise data points and remove them from the original training set. Second, a general condensed nearest neighbor rule based on the so-called Nearest Unlike Neighbor (NUN) is presented to further eliminate the redundant samples in training set. In order to verify the performance of the proposed method, some numerical experiments are conducted on several UCI benchmark databases.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"40 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":"114519093","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.2010.5580711
Seong-Hoon Kim, Ji-Hyun Lee, ByoungChul Ko, J. Nam
This paper presents a novel algorithm for the efficient classification of X-ray images to enhance the accuracy and performance. As for describing the characteristics of X-ray image, new Local Binary Patterns (LBP) is employed that allows simple and efficient feature extraction for texture information. To achieve fast and accurate classification task, Random Forests that is decision tree based ensemble classifier is applied. Comparing with other feature descriptors and classifiers, the testing results show that the proposed method improves accuracy, especially the speed for either training or testing.
{"title":"X-ray image classification using Random Forests with Local Binary Patterns","authors":"Seong-Hoon Kim, Ji-Hyun Lee, ByoungChul Ko, J. Nam","doi":"10.1109/ICMLC.2010.5580711","DOIUrl":"https://doi.org/10.1109/ICMLC.2010.5580711","url":null,"abstract":"This paper presents a novel algorithm for the efficient classification of X-ray images to enhance the accuracy and performance. As for describing the characteristics of X-ray image, new Local Binary Patterns (LBP) is employed that allows simple and efficient feature extraction for texture information. To achieve fast and accurate classification task, Random Forests that is decision tree based ensemble classifier is applied. Comparing with other feature descriptors and classifiers, the testing results show that the proposed method improves accuracy, especially the speed for either training or testing.","PeriodicalId":126080,"journal":{"name":"2010 International Conference on Machine Learning and Cybernetics","volume":"24 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":"114722376","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：