{"title":"A New SVR Incremental Algorithm Based on Boundary Vector","authors":"Hongmin Xu, Ruopeng Wang, Kaiyi Wang","doi":"10.1109/CISE.2010.5676955","DOIUrl":"https://doi.org/10.1109/CISE.2010.5676955","url":null,"abstract":"In dealing with a large number of train samples, Support Vector Regression (SVR) algorithm is slow. In particular, while new sample is added, all the training samples must be re-trained. In this paper, a new SVR incremental algorithm is presented, which is based on boundary vector. The algorithm takes full advantages of the geometric information of training sample sets. The observed data of China's GDP is used as a case study for the new algorithm. The computing results show that the new algorithm not only can guarantee the accuracy of machine learning and good generalization ability, but also can increase the learning speed of the algorithm than the classical SVR algorithm, and can be used rapid incremental learning.","PeriodicalId":232832,"journal":{"name":"2010 International Conference on Computational Intelligence and Software Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129564002","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":"The Impact of Explanation Facilities on Decision Support Systems Includes Multiple Knowledge Domains","authors":"Zhi Chen, Hongbin Dong","doi":"10.1109/CISE.2010.5677053","DOIUrl":"https://doi.org/10.1109/CISE.2010.5677053","url":null,"abstract":"DSS depends not only on the accuracy of the results, but also on acceptance of these results by its users. Research in the field of DSS has shown that providing explanations may improve the acceptance. Decision making process includes the procedures of decision and the support of different knowledge, to reveal such process will help people understand and audit the results of DSS. This paper attempts to provide an explanation mechanism for decision making process which includes different knowledge domains. First, a process of cognitive is described to show how decisions are made. Second, the trace of knowledge domains is used to establish the pattern of decision making process. Finally, a framework of comparison between decisions is provided.","PeriodicalId":232832,"journal":{"name":"2010 International Conference on Computational Intelligence and Software Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128754446","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":"Automated Verification of Goal Net Models","authors":"M. Ngo, Zhiqi Shen, C. Miao","doi":"10.1109/CISE.2010.5676884","DOIUrl":"https://doi.org/10.1109/CISE.2010.5676884","url":null,"abstract":"Multi-agent systems are increasingly complex and the problem of their verification is acquiring increasing importance. Most of the existing approaches are based on model checking techniques which require system specification in a formal language. This is an error-prone task and can only be performed by experts who have considerable experiences in logic reasoning. We proposed in this paper an easy-to-use approach to the verification of multi-agent systems based on the Goal Net modeling methodology. Goal Net is a goal-oriented framework which aspires to simplify the process of designing and implementing multi-agent systems. In our approach, a multi-agent system is modeled as a goal net. The goal net and its properties will be automatically converted into FSP (Finite State Processes) specification, which can be automatically verified by the model checker LTSA (Labeled Transition System Analyzer).","PeriodicalId":232832,"journal":{"name":"2010 International Conference on Computational Intelligence and Software Engineering","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128671936","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}
Yihua Lan, H. Ren, Cunhua Li, Xuefeng Zhao, Zhifang Min
{"title":"Feature Based Sequence Image Stitching Method","authors":"Yihua Lan, H. Ren, Cunhua Li, Xuefeng Zhao, Zhifang Min","doi":"10.1109/CISE.2010.5677208","DOIUrl":"https://doi.org/10.1109/CISE.2010.5677208","url":null,"abstract":"Image mosaic is useful for the traditional image process. We proposed a novel feature based sequence image stitching method for the image mosaic system. In this method, the whole image registration process has five steps, which includes feature point detection, feature descriptor extraction, feature points matching, estimation of the motion model parameters and stitching process. In these steps, difference of Gaussian image is used to get the extreme points as the feature points, then the SIFT descriptor operator is used to describe the feature, finally random sample consensus method is used for estimating the motion parameters. We test our method on two kinds of sequence images, the artificial images and the real images. The results show the stitching method is robust.","PeriodicalId":232832,"journal":{"name":"2010 International Conference on Computational Intelligence and Software Engineering","volume":"292 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129269501","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}
X. Yu, Yanchen Yang, Hong-ye Liu, Xuan Li, Xu Zhang
{"title":"A Distributed Spatial Data Sharing and Management System for Forest Farms","authors":"X. Yu, Yanchen Yang, Hong-ye Liu, Xuan Li, Xu Zhang","doi":"10.1109/CISE.2010.5677028","DOIUrl":"https://doi.org/10.1109/CISE.2010.5677028","url":null,"abstract":"Spatial data has been extensively used in forest resource management and decision making in China. But research on spatial data sharing and interoperability in forest farm level is unavailable. This paper proposed an approach to address problems of distributed spatial data management, sharing, integration and interoperability for forest farms using OGC Web Feature Services (WFS), Web Map Service (WMS) and Geography Markup Language (GML). The System composed of a service aggregation and management component and service node component. Service aggregation and management component provides service management and chaining functionalities. Service node provides WMS, WFS, GML conversion service, and management mechanism for local spatial data. Service nodes can be deployed in different forest farms.","PeriodicalId":232832,"journal":{"name":"2010 International Conference on Computational Intelligence and Software Engineering","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123865332","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":"Praat Software and Its Application to Analyze Sound Acquisition in Mandarin Chinese","authors":"Xinlu Yang, Jie Liang","doi":"10.1109/CISE.2010.5677148","DOIUrl":"https://doi.org/10.1109/CISE.2010.5677148","url":null,"abstract":"Praat is a free scientific software program for the analysis of speech in phonetics with which phoneticians can analyze, synthesize, and manipulate speech. In the present study, the acquisition of Mandarin Chinese stop consonants by native speakers of Uygur are analyzed by the software Praat. The results of the analysis indicate that Mandarin Chinese voiceless aspirated and unaspirated stop consonants as two phonemic categories can be distinguished by native speakers of Uygur. They can produce voiceless unaspirated stop consonants as authentically as Han Chinese speakers. However, they can not produce voiceless aspirated stops as Han Chinese speakers from the analysis of voice onset time. Moreover, the production of voiceless aspirated stop consonants by Uygur and Han Chinese speakers have not been affected by the speaking rate. The results of the experiment support the Speech Learning Model. In addition, it shows that the second language speech acquisition is restricted by the first language phonological system.","PeriodicalId":232832,"journal":{"name":"2010 International Conference on Computational Intelligence and Software Engineering","volume":"8 Suppl 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124208408","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":"Noise Performance Analysis of Chaotic Coherent CSK Communication System","authors":"Chunyan Han, Fengquan Man","doi":"10.1109/CISE.2010.5676923","DOIUrl":"https://doi.org/10.1109/CISE.2010.5676923","url":null,"abstract":"To provide a quantitative description for noisy multiuser performance of chaos-based communications, this paper presents an simple and effective approach for analyzing the noisy multiuser performance of coherent CSK (chaos-shift-keying) system with two basis functions under a noisy multiuser environment. Using a Logistic map as the chaotic signal and assuming ideal synchronization at receiver, the bit-error rate (BER) of CSK is derived in terms of the noisy intensity, the number of users and the length of bit sequence. The calculated BERs are consistent with those found from numerical simulations. In addition, the BER and it's upon bound for single-user systems are the special results of this paper.","PeriodicalId":232832,"journal":{"name":"2010 International Conference on Computational Intelligence and Software Engineering","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123659998","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":"Bitmap Edge Detection Method and Improvement","authors":"Huaqing Mao, Li Zhu","doi":"10.1109/CISE.2010.5677189","DOIUrl":"https://doi.org/10.1109/CISE.2010.5677189","url":null,"abstract":"Edge detection is very important in image process. According the three standards in edge detection: optimal detection result, optimal location and low repeat response, optimal linear filter is deduced. Base on the standards, a simple BMP edge Detection algorithm is proposed, improved algorithm and color scope D algorithm are given. Experiments prove that running speed of algorithms is satisfied and more efficient than the regular algorithm.","PeriodicalId":232832,"journal":{"name":"2010 International Conference on Computational Intelligence and Software Engineering","volume":"16 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114109596","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":"E-Learning and E-Portfolio for In-Service Secondary Technology Teacher Education on the Chinese Mainland and in Hong Kong","authors":"Wei Feng, K. Siu","doi":"10.1109/CISE.2010.5676737","DOIUrl":"https://doi.org/10.1109/CISE.2010.5676737","url":null,"abstract":"Secondary technology education on the Chinese mainland and in Hong Kong is confronted with the big rebuilt and challenge. Many teachers in these two regions received teacher education such a long time ago that their knowledge of the subject is not up to date and especially on the Chinese mainland most of them are from other disciplines. Moreover, due to the lack of a formal system of technology teacher education, in-service teacher education has become more necessary and urgent. This paper aims to identify and analyze the advantages of and potential development of e- learning for in-service secondary technology teacher education. Furthermore, this paper puts forward the utilization of e-portfolio for secondary teacher education as the learning and assessment tool.","PeriodicalId":232832,"journal":{"name":"2010 International Conference on Computational Intelligence and Software Engineering","volume":"186 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116179136","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":"p-Quasi Martingale Transforms","authors":"F. Zhai","doi":"10.1109/CISE.2010.5677234","DOIUrl":"https://doi.org/10.1109/CISE.2010.5677234","url":null,"abstract":"In this paper, we give the equivalent conditions on the boundedness of p- quasi-martingale transforms, the result we obtained extend the corresponding result in some literate.","PeriodicalId":232832,"journal":{"name":"2010 International Conference on Computational Intelligence and Software Engineering","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116213061","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}