N. Díaz-Díaz, J. Aguilar-Ruiz, Juan A. Nepomuceno, Jorge García
{"title":"Feature selection based on bootstrapping","authors":"N. Díaz-Díaz, J. Aguilar-Ruiz, Juan A. Nepomuceno, Jorge García","doi":"10.1109/CIMA.2005.1662338","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662338","url":null,"abstract":"The results of feature selection methods have a great influence on the success of data mining processes, especially when the data sets have high dimensionality. In order to find the optimal result from feature selection methods, we should check each possible subset of features to obtain the precision on classification, i.e., an exhaustive search through the search space. However, it is an unfeasible task due to its computational complexity. In this paper, we propose a novel method of feature selection based on bootstrapping techniques. Our approach shows that it is not necessary to try every subset of features, but only a very small subset of combinations to achieve the same performance as the exhaustive approach. The experiments have been carried out using very high-dimensional datasets (thousands of features) and they show that it is possible to maintain the precision at the same time that the complexity is reduced substantially","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114333176","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}
{"title":"How does cash flow volatility affect cost of debt and corporate earning management?","authors":"Chih-min Hung, Daiki Wakayama","doi":"10.1109/CIMA.2005.1662308","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662308","url":null,"abstract":"In this study, we explore the impact of cash flow volatility on the costs of debt. Further, we find that managers attempt to manage earnings for good financial performance according cash flow volatility","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128549740","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}
{"title":"Soft computing support in concurrent mold product developent","authors":"H. Qiu, X. Shao, P. Li, L. Gao","doi":"10.1109/CIMA.2005.1662351","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662351","url":null,"abstract":"Injection mold design is a knowledge-intensive process concerned with numerous expert experience which is hard to model. At the same time, the distribution and isolation of knowledge cause unnecessary design iterations, thus prolong the mold development time. In this paper, a Web service-based multi-agent framework for collaborative product development is proposed for efficient dynamic knowledge interaction. Within it, appropriate soft computing methods are used to acquire domain knowledge and wrapped as Web service components to provide intelligent early decision support for concurrent mold design","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130357221","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}
{"title":"Slab matching problem: a tabu search approach","authors":"Jiaxiang Luo, Lixin Tang","doi":"10.1109/CIMA.2005.1662311","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662311","url":null,"abstract":"This paper discusses matching orders against slabs problem which arises in integrated steel industry. The number of surplus slabs increases responding to varying customer needs for product customization and quantities. To deal with the surplus slabs, it is important to optimize the matching orders against slabs from an optimization perspective. It can be modeled as a partitioning problem with multiple objectives and constraints. In this paper we formulate this problem as a cost-minimizing integer mathematical programming. A heuristic method based on tabu search is proposed. The method combines the swap, insertion and cyclic transfers neighborhoods to determine good approximate solutions. Computational results on production data from an iron and steel factory are presented and analyzed. Comparison with actual slab matching indicates that the proposed method could produce significantly better matching","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129583932","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}
{"title":"Evolutionary predictive controller for ship control","authors":"Piotr Kaczynski, Pawel D. Domanski","doi":"10.1109/CIMA.2005.1662341","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662341","url":null,"abstract":"In this article, we present a predictive controller for a ship based on a global optimization using genetic algorithm. We briefly present the mathematical model of a ship used in testing the usability of the controller as well as a base to create a simplified model used for prediction purposes. The main task was to create a global optimization routine capable of returning a control signal in a short and constant time interval. It is managed by a particular genetic algorithm with properly designed genetic operators that meet the strict time constraints","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126453349","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}
{"title":"Identification of convection heat transfer coefficient parameters based on hybrid particle swarm algorithm in the secondary cooling zone for steel continuous casting process","authors":"Guoshan Wu, Rong-Yang Wu","doi":"10.1109/CIMA.2005.1662305","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662305","url":null,"abstract":"Solidification model is developed based on control volume method for steel continuous casting process, which is nonlinear and non-differential, and parameters of convective heat transfer coefficient for each segment of the secondary cooling zone are ascertained, a new hybrid particle swarm algorithm (CPSO) is introduced to improve the optimizing performance by embedding the chaotic search in the particles swarm algorithm. It is used to identify the convective heat transfer coefficients according to billet surface temperature and shell thickness. Compared with the empirical formula method, it has a better agreement with trail data","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124143176","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}
{"title":"Telemedicine needs for multimedia and integrated services digital network (ISDN)","authors":"M. Al-Taei","doi":"10.1109/CIMA.2005.1662348","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662348","url":null,"abstract":"Telemedicine applications are based on multimedia systems and a variety of networks. Multimedia and transmission technology are very necessary to telemedicine applications. Since the delay is the enemy for patients, so the integrated and high-speed telecommunication is an optimal option for telemedicine systems. For that, ISDN is chosen as an infrastructure for many telemedicine applications. The objective of this paper is to present economically alternative to the current network that would allow experts fast and easily access to the medical data of their remote patients through ISDN network with the help of suitable multimedia system. We discuss the role and necessity of multimedia and ISDN technology for medical applications in telemedicine. Multimedia communications in medicine and solutions provided by ISDN, which are necessary to telemedicine, are discussed in this paper with some technical issues. Some of the current popular ISDN-based telemedicine systems are mentioned, with some discussion of the future ISDN telemedicine applications","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117346447","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}
{"title":"Minimum message length moving average time series data mining","authors":"M. Sak, D. Dowe, S. Ray","doi":"10.1109/CIMA.2005.1662352","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662352","url":null,"abstract":"This paper considers a criterion for selection of moving average (MA) time series models based upon the information-theoretic principle of minimum message length (MML). We derive an MML model selection criterion for invertible MA time series models using the Wallace and Freeman (1987) MML approximation, MML87. The MML model order selection performance is compared with other well-known model selection criteria such as Akaike's information criterion (AIC), corrected AIC (AICc), Bayesian information criterion (BIC), minimum description length (MDL, 1978), and the Hannan-Quinn (HQ) criterion. Our experiments show that the MML-based criterion achieves the lowest average mean squared prediction error and the best average log likelihood, and has the best ability to choose the true MA model order for smaller sample sizes","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"34 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120928869","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}
{"title":"An efficient framework for intrusion detection based on data mining","authors":"Weidong Li, Kejun Zhang, Boqun Li, Bingru Yang","doi":"10.1109/CIMA.2005.1662306","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662306","url":null,"abstract":"A multi-layer intrusion detection framework is proposed in this paper. Comparing to the traditional system, the framework has sources from all the respects of host computer and network, and calculates connecting volume for each active connection, thus only the suspicious connections would be analyzed, more than 80% packets are normal, and don't need processing, influence to the system speed is very little. All the information of the host computer is combined to a union, and the properties are expanded and enhanced for the data mining engine, so the mining process is efficient and accurate. Fuzzy mining can also be used in intrusion detecting and rule sets comparing. The framework provides abilities of detection, report and response. Experimental results show the rapidness and accuracy of the proposed framework","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131503709","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}
{"title":"Analysis of the Dynamic Motion for Biosignal Measurement in Wearable system","authors":"Y. Kim, Jeun-Woo Lee","doi":"10.1109/CIMA.2005.1662314","DOIUrl":"https://doi.org/10.1109/CIMA.2005.1662314","url":null,"abstract":"When measuring a bio-signal at wearable system, it is very important that considering variation differs from people's posture and the gain of the signal acquired by the position of a sensor. In this paper, framework for resolving the bio-signal with a dynamic motion is shown, and we suggest an analyzed data by man's motion and posture. The distortion mixed with the bio-signal is classed by two factors that one is motion artifact produced by motion of people, other is variation of signal by change of sensor position. In order to remove these distortions, we should have to quantify and analyze the signal being measured in given condition","PeriodicalId":306045,"journal":{"name":"2005 ICSC Congress on Computational Intelligence Methods and Applications","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128140937","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}