Pub Date : 2012-07-15DOI: 10.1109/ICMLC.2012.6358976
Yan Li, Lan-Ming Su, Qiang He
Pathfinding is an important task in computer games, where the algorithm efficiency is the key issue. In this paper, we introduce case-based reasoning method in the process of A* algorithm in multi-task pathfinding. Firstly, we save some typical paths as cases. When a new task is coming, it no longer uses A* to find a path from scratch, but firstly computes the similarity of the new task and the stored cases to decide whether to go along the previous found paths or not. A solution to the new task will be obtained after adapting to the found similar case(s). Obviously, this memory-based pathfinding can reduce the search time at the cost of using more memory to store found paths as cases. Through experimental results, it is demonstrated that, as the number of stored paths is increasing, fewer nodes are needed to be searched during the pathfinding process.
{"title":"Case-based multi-task pathfinding algorithm","authors":"Yan Li, Lan-Ming Su, Qiang He","doi":"10.1109/ICMLC.2012.6358976","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6358976","url":null,"abstract":"Pathfinding is an important task in computer games, where the algorithm efficiency is the key issue. In this paper, we introduce case-based reasoning method in the process of A* algorithm in multi-task pathfinding. Firstly, we save some typical paths as cases. When a new task is coming, it no longer uses A* to find a path from scratch, but firstly computes the similarity of the new task and the stored cases to decide whether to go along the previous found paths or not. A solution to the new task will be obtained after adapting to the found similar case(s). Obviously, this memory-based pathfinding can reduce the search time at the cost of using more memory to store found paths as cases. Through experimental results, it is demonstrated that, as the number of stored paths is increasing, fewer nodes are needed to be searched during the pathfinding process.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"67 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":"124944709","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.2012.6359548
W. Liu, Jianjun Qi, Bo Tang, Li Zhao
More and more applications based on Deep Web data are developed recently. The key problem is the understanding and modeling of Deep Web capability in integrated environment Most recent papers only focus on the understanding and modeling of web query interfaces (e.g. interface modeling & extraction and so on). In fact, not only query interface capability should be considered but also the output schema of Deep Web, thus we propose a capability model of Deep Web in this paper. In query interface modeling, which is the input of Deep Web, we have considered the semantics and restriction of attributes in order to generate the corresponding query conditions. We use minimal query tree to describe the capability of Deep Web. In the query results page, we extract the data schema to describe richness of data and then to support Deep Web assembling.
{"title":"Understanding and modeling the Deep Web for integrated environment","authors":"W. Liu, Jianjun Qi, Bo Tang, Li Zhao","doi":"10.1109/ICMLC.2012.6359548","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359548","url":null,"abstract":"More and more applications based on Deep Web data are developed recently. The key problem is the understanding and modeling of Deep Web capability in integrated environment Most recent papers only focus on the understanding and modeling of web query interfaces (e.g. interface modeling & extraction and so on). In fact, not only query interface capability should be considered but also the output schema of Deep Web, thus we propose a capability model of Deep Web in this paper. In query interface modeling, which is the input of Deep Web, we have considered the semantics and restriction of attributes in order to generate the corresponding query conditions. We use minimal query tree to describe the capability of Deep Web. In the query results page, we extract the data schema to describe richness of data and then to support Deep Web assembling.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"41 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":"126157589","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}
For general patients, the physician information on clinics or large hospitals is very scarce. Because the physician in different medical fields, areas of expertise are different, and most patients are also have no similar or related symptoms produced by the experience of seeing patients. They usually spend a lot of time in the physician information search and compare. In this study, we combined the search engine, Intelligent Agent (IA) and Business Intelligence (BI) technologies to build a web-based medical information search and analysis system. The intelligent agent can at any time to the site of the medical institutions to retrieve data. BI systems can be real-time analysis and presents visual charts and trends of medical information and can quickly to provide the most immediate, reliable and complete medical information to assist users to obtain relevant medical information.
{"title":"The intelligent agents in the study of web-based medical information search system","authors":"Chun-Jung Lin, Yi-Ling Jhao, Shou-Hsiung Cheng, Wen-Ni Yeh","doi":"10.1109/ICMLC.2012.6359649","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359649","url":null,"abstract":"For general patients, the physician information on clinics or large hospitals is very scarce. Because the physician in different medical fields, areas of expertise are different, and most patients are also have no similar or related symptoms produced by the experience of seeing patients. They usually spend a lot of time in the physician information search and compare. In this study, we combined the search engine, Intelligent Agent (IA) and Business Intelligence (BI) technologies to build a web-based medical information search and analysis system. The intelligent agent can at any time to the site of the medical institutions to retrieve data. BI systems can be real-time analysis and presents visual charts and trends of medical information and can quickly to provide the most immediate, reliable and complete medical information to assist users to obtain relevant medical information.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"55 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":"126712792","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.2012.6359485
Shao-Dong Chen, Jin-Xing Liu
The real-time performance of the decision of striking a Time-Sensitive Target (TST) is crucial. In this paper, we propose the cooperative strike strategy to TST based on the proactive information delivery to decrease the decision time and improve the real-time capability of striking decision. Firstly, we present the model of the organization and proactive information delivery (PID) behaviors of the strike team by means of AML (Agent Modeling Language). Then, we propose the cooperation strike strategy to the TST which includes cooperative tracking, role adjusting and striking behavior adjusting strategy. The proposed method decreases the decision and communication payload while enhances the real time performance. The simulation results show that the communication payloads can be decreased, and the real-time capability of the strike decision has been enhanced.
{"title":"Study on cooperative attack strategy to time-sensitive target based proactive information delivery","authors":"Shao-Dong Chen, Jin-Xing Liu","doi":"10.1109/ICMLC.2012.6359485","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359485","url":null,"abstract":"The real-time performance of the decision of striking a Time-Sensitive Target (TST) is crucial. In this paper, we propose the cooperative strike strategy to TST based on the proactive information delivery to decrease the decision time and improve the real-time capability of striking decision. Firstly, we present the model of the organization and proactive information delivery (PID) behaviors of the strike team by means of AML (Agent Modeling Language). Then, we propose the cooperation strike strategy to the TST which includes cooperative tracking, role adjusting and striking behavior adjusting strategy. The proposed method decreases the decision and communication payload while enhances the real time performance. The simulation results show that the communication payloads can be decreased, and the real-time capability of the strike decision has been enhanced.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"177 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":"126831914","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.2012.6359534
S. Shaik, F. Y. Xu, Chun Sing Lai, N. Sinha, L. L. Lai
This paper reported the use of artificial bee colony to short-term hydro-thermal scheduling problem. Simulation studies demonstrated that it is possible to find a workable solution and the approach to implement the algorithm will be discussed too.
{"title":"Short-term hydro -thermal scheduling with Artificial Bee Colony","authors":"S. Shaik, F. Y. Xu, Chun Sing Lai, N. Sinha, L. L. Lai","doi":"10.1109/ICMLC.2012.6359534","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359534","url":null,"abstract":"This paper reported the use of artificial bee colony to short-term hydro-thermal scheduling problem. Simulation studies demonstrated that it is possible to find a workable solution and the approach to implement the algorithm will be discussed too.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"97 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":"115216064","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.2012.6359005
Xuemei Wang, Mei Yang, Jiangtao Li
Credit problem is the main bottleneck which hinders the development of e-commerce. Credit evaluation system is the credibility backbone of e-commerce website, which sets up a standard for inspecting the sellers' credit and makes an important reference for consumers shopping. Based on the rule of combining mathematics and psychology, this paper analyzes the current representative C2C credit evaluation system of Taobao, e-Bay and Paipai, and builds a hierarchical model by AHP, exploring how to establish the C2C e-commerce credit evaluation system effectively. This paper, by comparing functionalities of c2c e-commerce systems, attempts to provide theoretical basis for improved research of C2C credit evaluation system. Therefore, it can provide the reference for enterprises and the users' trade decision.
{"title":"Comparative study on C2C e-commerce credit evaluation system","authors":"Xuemei Wang, Mei Yang, Jiangtao Li","doi":"10.1109/ICMLC.2012.6359005","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359005","url":null,"abstract":"Credit problem is the main bottleneck which hinders the development of e-commerce. Credit evaluation system is the credibility backbone of e-commerce website, which sets up a standard for inspecting the sellers' credit and makes an important reference for consumers shopping. Based on the rule of combining mathematics and psychology, this paper analyzes the current representative C2C credit evaluation system of Taobao, e-Bay and Paipai, and builds a hierarchical model by AHP, exploring how to establish the C2C e-commerce credit evaluation system effectively. This paper, by comparing functionalities of c2c e-commerce systems, attempts to provide theoretical basis for improved research of C2C credit evaluation system. Therefore, it can provide the reference for enterprises and the users' trade decision.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"4 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":"116016147","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.2012.6358978
Elmira Mohyedinbonab, O. Ghasemi, M. Jamshidi, Yufang Jin
Estimation of unknown parameters associated with a distributed sensor network using its noisy measurements has been an active research area recently. Several estimation algorithms, such as the incremental and diffusion algorithms, have been proposed to address this problem. Incremental algorithms require less communication among nodes of the networks while diffusion algorithms are more robust and require large amounts of energy for communication. In this study, we have proposed a hybrid methodology that combines incremental and diffusion algorithms based on the property of a priori error, where is the difference of output error and noise variance of each sensor. The proposed network started with an incremental communication scheme and switched to diffusion scheme to complete the rest of the estimation. Simulation results showed that the proposed algorithm largely improved the convergence rate as well as the estimation accuracy.
{"title":"Adaptive estimation over distributed sensor networks with a hybrid algorithm","authors":"Elmira Mohyedinbonab, O. Ghasemi, M. Jamshidi, Yufang Jin","doi":"10.1109/ICMLC.2012.6358978","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6358978","url":null,"abstract":"Estimation of unknown parameters associated with a distributed sensor network using its noisy measurements has been an active research area recently. Several estimation algorithms, such as the incremental and diffusion algorithms, have been proposed to address this problem. Incremental algorithms require less communication among nodes of the networks while diffusion algorithms are more robust and require large amounts of energy for communication. In this study, we have proposed a hybrid methodology that combines incremental and diffusion algorithms based on the property of a priori error, where is the difference of output error and noise variance of each sensor. The proposed network started with an incremental communication scheme and switched to diffusion scheme to complete the rest of the estimation. Simulation results showed that the proposed algorithm largely improved the convergence rate as well as the estimation accuracy.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"30 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":"122308873","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.2012.6359524
Yong-Hui Xu, Ronghua Luo, Huaqing Min
With the information from labeled RGB image an unsupervised method based on label transfer technology is proposed for 3D object recognition and segmentation in RGB-D images. We first use scale invariant features extracted from color space to retrieve a set of nearest neighbors of the input image from the labeled image database. Based on the projection matrix between the labeled image and the input image, the labels of the pixels in the labeled image are transferred to input image. And then a segmentation model and a clustering algorithm based on the geometric characteristics are designed to obtain the spatial and semantic consistent object regions in the RGB-D images. Compared to supervised object recognition, our method does not need to train a classifier using a lot of training images.
{"title":"Label transfer for joint recognition and segmentation of 3D object","authors":"Yong-Hui Xu, Ronghua Luo, Huaqing Min","doi":"10.1109/ICMLC.2012.6359524","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359524","url":null,"abstract":"With the information from labeled RGB image an unsupervised method based on label transfer technology is proposed for 3D object recognition and segmentation in RGB-D images. We first use scale invariant features extracted from color space to retrieve a set of nearest neighbors of the input image from the labeled image database. Based on the projection matrix between the labeled image and the input image, the labels of the pixels in the labeled image are transferred to input image. And then a segmentation model and a clustering algorithm based on the geometric characteristics are designed to obtain the spatial and semantic consistent object regions in the RGB-D images. Compared to supervised object recognition, our method does not need to train a classifier using a lot of training images.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"27 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":"122950489","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.2012.6359551
Li Meng, Dongfeng Wang, P. Han
This paper presents the identification of fractional order system in frequency domain by using Particle Swarm Optimization (PSO) algorithm. PSO is extended to estimate the fractional derivative order. Meanwhile, recursive least squares algorithm is associated to calculate the denominator and numerator coefficients of transfer function. Simulation examples with noise-free and noisy data are given to verify the effectiveness of the method proposed in this paper.
{"title":"Identification of fractional order system using Particle Swarm Optimization","authors":"Li Meng, Dongfeng Wang, P. Han","doi":"10.1109/ICMLC.2012.6359551","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359551","url":null,"abstract":"This paper presents the identification of fractional order system in frequency domain by using Particle Swarm Optimization (PSO) algorithm. PSO is extended to estimate the fractional derivative order. Meanwhile, recursive least squares algorithm is associated to calculate the denominator and numerator coefficients of transfer function. Simulation examples with noise-free and noisy data are given to verify the effectiveness of the method proposed in this paper.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"17 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":"122507903","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.2012.6359559
Ping Wang, Kaoji Xu, Y. Zhang, Huizhen Jia
Clutter suppression becomes a key point of quality control to Doppler weather radar reflectivity image, because the clutter from non-weather targets can interfere with weather targets. A novel method of suppressing clutter is proposed in this paper, which is mainly based on the Gray-level Co-occurrence Matrix(GLCM) feature. The feature possesses rotation invariability and strong ability to distinguish weather targets between clutters, which is obtained after the reflectivity image is processed by the morphological method and is segmented with the region growing method. According to statistics, there are two thresholds in different areas and Doppler velocity values in the clutters are always between -1 and 1 m/s, but precipitation clouds are always of outside this range. So the proposed feature, regional area and the Doppler velocity are combined to form a 3-layered identification method. Test result shows that the clutter clearance rate of the paper is improved from 95.7% under 2.8% loss rate to 96.5% under 1.0% loss rate.
{"title":"Doppler weather radar clutter suppression based on texture feature","authors":"Ping Wang, Kaoji Xu, Y. Zhang, Huizhen Jia","doi":"10.1109/ICMLC.2012.6359559","DOIUrl":"https://doi.org/10.1109/ICMLC.2012.6359559","url":null,"abstract":"Clutter suppression becomes a key point of quality control to Doppler weather radar reflectivity image, because the clutter from non-weather targets can interfere with weather targets. A novel method of suppressing clutter is proposed in this paper, which is mainly based on the Gray-level Co-occurrence Matrix(GLCM) feature. The feature possesses rotation invariability and strong ability to distinguish weather targets between clutters, which is obtained after the reflectivity image is processed by the morphological method and is segmented with the region growing method. According to statistics, there are two thresholds in different areas and Doppler velocity values in the clutters are always between -1 and 1 m/s, but precipitation clouds are always of outside this range. So the proposed feature, regional area and the Doppler velocity are combined to form a 3-layered identification method. Test result shows that the clutter clearance rate of the paper is improved from 95.7% under 2.8% loss rate to 96.5% under 1.0% loss rate.","PeriodicalId":128006,"journal":{"name":"2012 International Conference on Machine Learning and Cybernetics","volume":"49 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":"114480186","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：