Data prediction and classification is a critical method in medical nutrition data analysis area. As for the characteristics of being intuitive, efficient and easy to understand, the decision tree algorithm is widely used in this field. However, the classification rules extracted from the decision tree are not the most simple and efficient. The paper analyzes the classical decision tree algorithm CART, and proposes a new improved algorithm R2-CART. The core idea of the advanced algorithm is, in order to simplify the classification rules and tree, combining CART algorithm with rough set theory to conduct the attribute and rule reduction on the classification rules of decision tree. The experiment, which compares the Original CART algorithm with the improved algorithm, shows that the improved algorithm has much better classification efficiency with achieving a simple and efficient classification rule set at the same time. This improved algorithm has a potential practical value for large-scale medical nutrition data of classification and predictive analysis.
{"title":"An Improved Algorithm for CART Based on the Rough Set Theory","authors":"Weiguang Wang, Cong Wang, W. Gao, Jinbin Li","doi":"10.1109/GCIS.2013.7","DOIUrl":"https://doi.org/10.1109/GCIS.2013.7","url":null,"abstract":"Data prediction and classification is a critical method in medical nutrition data analysis area. As for the characteristics of being intuitive, efficient and easy to understand, the decision tree algorithm is widely used in this field. However, the classification rules extracted from the decision tree are not the most simple and efficient. The paper analyzes the classical decision tree algorithm CART, and proposes a new improved algorithm R2-CART. The core idea of the advanced algorithm is, in order to simplify the classification rules and tree, combining CART algorithm with rough set theory to conduct the attribute and rule reduction on the classification rules of decision tree. The experiment, which compares the Original CART algorithm with the improved algorithm, shows that the improved algorithm has much better classification efficiency with achieving a simple and efficient classification rule set at the same time. This improved algorithm has a potential practical value for large-scale medical nutrition data of classification and predictive analysis.","PeriodicalId":366262,"journal":{"name":"2013 Fourth Global Congress on Intelligent Systems","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126400785","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}
Asset quality is the foundation of enterprise survival and development we choose one-class support vector machine (OCSVM) is chosen to deal with asset quality abnormal detection for it pays great roles to acquire the abnormal data. As well as flexible to be constructed, Biorthogonal wavelet consists linear-phase nature and high vanishing moment, therefore, corresponding wavelet kernel functions are respectively constructed relying on Bior (2, 2) and Bior (3, 9) wavelet. On the basis of which new hybrid kernel is proposed and then introduced to OCSVM to innovate the model. In addition, it is applied into kernel principal component analysis (KPCA) method to realize a high dimension space mapping and enforce dimension reduction. Empirical research on A-share listed manufacturing enterprises at last is conducted and the result tells that the model we come up with is greatly improved on the recognition rate of abnormal samples when compared with other method.
{"title":"Research on Asset Quality Detection Based on Hybrid Biorthogonal Wavelet OCSVM Model","authors":"Huang Chao, Jiang Hongyan, Han Tingting","doi":"10.1109/GCIS.2013.27","DOIUrl":"https://doi.org/10.1109/GCIS.2013.27","url":null,"abstract":"Asset quality is the foundation of enterprise survival and development we choose one-class support vector machine (OCSVM) is chosen to deal with asset quality abnormal detection for it pays great roles to acquire the abnormal data. As well as flexible to be constructed, Biorthogonal wavelet consists linear-phase nature and high vanishing moment, therefore, corresponding wavelet kernel functions are respectively constructed relying on Bior (2, 2) and Bior (3, 9) wavelet. On the basis of which new hybrid kernel is proposed and then introduced to OCSVM to innovate the model. In addition, it is applied into kernel principal component analysis (KPCA) method to realize a high dimension space mapping and enforce dimension reduction. Empirical research on A-share listed manufacturing enterprises at last is conducted and the result tells that the model we come up with is greatly improved on the recognition rate of abnormal samples when compared with other method.","PeriodicalId":366262,"journal":{"name":"2013 Fourth Global Congress on Intelligent Systems","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121096512","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}
Gong Guoliang, Lu Huaxiang, Chen Gang, Jin Min, Chen Xu
Noise is the key to cause phase measurement error of sine signals. Although there have been many attempts to suppress noise interference, high accuracy is still hard to meet in terrible noise environment. In order to improve reliability and accuracy of the measurement system, a robust method is proposed. In this paper, independent component analysis (ICA) is used to separate sine signal from noises. Firstly, an ICA model, which compensate the number of observed signals and its components is established. Then, the relationship of separation order of the independent components with measurement error is revealed, and a sorting algorithm based on priori knowledge is proposed to improve separation accuracy. Experimental results indicate the method is robust and accurate.
{"title":"Phase Difference Measurement Method for Sine Signals Based on Fast ICA","authors":"Gong Guoliang, Lu Huaxiang, Chen Gang, Jin Min, Chen Xu","doi":"10.1109/GCIS.2013.46","DOIUrl":"https://doi.org/10.1109/GCIS.2013.46","url":null,"abstract":"Noise is the key to cause phase measurement error of sine signals. Although there have been many attempts to suppress noise interference, high accuracy is still hard to meet in terrible noise environment. In order to improve reliability and accuracy of the measurement system, a robust method is proposed. In this paper, independent component analysis (ICA) is used to separate sine signal from noises. Firstly, an ICA model, which compensate the number of observed signals and its components is established. Then, the relationship of separation order of the independent components with measurement error is revealed, and a sorting algorithm based on priori knowledge is proposed to improve separation accuracy. Experimental results indicate the method is robust and accurate.","PeriodicalId":366262,"journal":{"name":"2013 Fourth Global Congress on Intelligent Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121030707","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}
It is impossible for severely disabled people to browse or learn through the Internet due to the mere lack of independent control of the mouse. This paper proposes a brain computer interface (BCI) to aid severely disabled individuals, such as people disabled by amyotrophic lateral sclerosis (ALS), in browsing or learning on the Internet. By analyzing specific components of event-related potentials (ERPs), cursor control can be achieved. The cursor can be controlled by brain waves in a user-friendly manner to move or click on the web page. The major contributions of this research include: (1) designing a BCI for disabled people, (2) embedding the BCI's cursor controller into a web page, (3) conducting clinical experiments, (4) analysing the experimental results, system accuracy, and effectiveness, and (5) evaluating the system's practicability and giving suggestions for future work. There are two innovative technologies proposed in this research: (1) a specific component of ERPs located at O1, the N2P3 (the difference between the peak and trough of N200 and P300), was used to differentiate targeted from non-targeted (non-selected) signals, (2) instead of a fixed position style BCI, a movable watermark style BCI which follows the cursor was designed. The novel technique supported by a user-friendly interface helps the disabled have contact with the outside world resulting in positive emotions.
{"title":"Brainwave Technology Gives Internet Access to the Physically Disabled","authors":"Y. Tai, Y. J. Tian, T. W. Huang, K. Sun","doi":"10.1109/GCIS.2013.59","DOIUrl":"https://doi.org/10.1109/GCIS.2013.59","url":null,"abstract":"It is impossible for severely disabled people to browse or learn through the Internet due to the mere lack of independent control of the mouse. This paper proposes a brain computer interface (BCI) to aid severely disabled individuals, such as people disabled by amyotrophic lateral sclerosis (ALS), in browsing or learning on the Internet. By analyzing specific components of event-related potentials (ERPs), cursor control can be achieved. The cursor can be controlled by brain waves in a user-friendly manner to move or click on the web page. The major contributions of this research include: (1) designing a BCI for disabled people, (2) embedding the BCI's cursor controller into a web page, (3) conducting clinical experiments, (4) analysing the experimental results, system accuracy, and effectiveness, and (5) evaluating the system's practicability and giving suggestions for future work. There are two innovative technologies proposed in this research: (1) a specific component of ERPs located at O1, the N2P3 (the difference between the peak and trough of N200 and P300), was used to differentiate targeted from non-targeted (non-selected) signals, (2) instead of a fixed position style BCI, a movable watermark style BCI which follows the cursor was designed. The novel technique supported by a user-friendly interface helps the disabled have contact with the outside world resulting in positive emotions.","PeriodicalId":366262,"journal":{"name":"2013 Fourth Global Congress on Intelligent Systems","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132672012","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 image segmentation of corn diseases is one of the critical technical aspects of digital image processing technology for disease recognition. Currently, aiming at solving the loss of colure texture of corn disease image segmentation, this paper proposes a modified bionic pulse coupled neural network. This proposed algorithm combined from pulse coupled neural network and a modified artificial bee colony algorithm. A revenue function is defined based on linear weighted function with maximum Shannon entropy and minimum cross-entropy. Through adaptive strategy of searching solutions, we optimized the parameters of pulse coupled neural network based on the modified ABC. The modified network is used to segment the color images of different kinds of corn disease in RGB color subspaces. Then combined with the results by color image merger strategy, we can get the terminal results of target area. The experimental results show that the proposed method could segment the disease regions better and set complexity parameters simplier.
{"title":"An Image Segmentation Algorithm of Corn Disease Based on the Modified Bionic Pulse Coupled Neural Network","authors":"Wen Changji, Yu Helong, He Shanshan","doi":"10.1109/GCIS.2013.21","DOIUrl":"https://doi.org/10.1109/GCIS.2013.21","url":null,"abstract":"The image segmentation of corn diseases is one of the critical technical aspects of digital image processing technology for disease recognition. Currently, aiming at solving the loss of colure texture of corn disease image segmentation, this paper proposes a modified bionic pulse coupled neural network. This proposed algorithm combined from pulse coupled neural network and a modified artificial bee colony algorithm. A revenue function is defined based on linear weighted function with maximum Shannon entropy and minimum cross-entropy. Through adaptive strategy of searching solutions, we optimized the parameters of pulse coupled neural network based on the modified ABC. The modified network is used to segment the color images of different kinds of corn disease in RGB color subspaces. Then combined with the results by color image merger strategy, we can get the terminal results of target area. The experimental results show that the proposed method could segment the disease regions better and set complexity parameters simplier.","PeriodicalId":366262,"journal":{"name":"2013 Fourth Global Congress on Intelligent Systems","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116298469","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}
Digital Living Network Alliance (DLNA) has developed guidelines for interoperability among home devices for media content sharing. However, the sharing of the content is limited inside local area networks. On the Internet, users can share the media resources through the Social Network Service (SNS) websites. In order that users in DLNA networks can easily access resources shared by friends in SNS such as photos, video clips and music, we propose SNS website Media Agent (SMA) in this paper. The SMA introduces the media resources shared by friends in SNS into home networks through OpenAPIs of SNS website. Users can browse shared resources conveniently at home on any devices according to Universal Plug and Play (UPnP).
{"title":"Extending SNS Media to DLNA Content Sharing Systems","authors":"Xiao Guo, Jianzeng Li","doi":"10.1109/GCIS.2013.41","DOIUrl":"https://doi.org/10.1109/GCIS.2013.41","url":null,"abstract":"Digital Living Network Alliance (DLNA) has developed guidelines for interoperability among home devices for media content sharing. However, the sharing of the content is limited inside local area networks. On the Internet, users can share the media resources through the Social Network Service (SNS) websites. In order that users in DLNA networks can easily access resources shared by friends in SNS such as photos, video clips and music, we propose SNS website Media Agent (SMA) in this paper. The SMA introduces the media resources shared by friends in SNS into home networks through OpenAPIs of SNS website. Users can browse shared resources conveniently at home on any devices according to Universal Plug and Play (UPnP).","PeriodicalId":366262,"journal":{"name":"2013 Fourth Global Congress on Intelligent Systems","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124674224","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}
This paper presents a BCI (brain-computer interface) system called, "fast Phonics-to-Chinese-Character system", for individuals to write Chinese Characters using his or her brain waves. This research proposes a novel timing coding method to collocate the order of stimuli presentation. Previously, we had developed a Phonics-to-Chinese-Character system that used both the components of the P300 and the N200 of ERPs (event-related potentials) to detect the targets of a user's intention. Although the previously proposed system achieved good performance, we still tried to reduce the time spent on selecting an item. Based on experiences from previous studies, we propose four rules to collocate the timing of stimuli presentation for brain-computer interface, and then introduce a faster system. The results of the clinical experiments show that the proposed method elicits potentials of brain waves effectively for determining a target that was his/her intention. The accuracy of the system is above 95%. The proposed system is also the fastest BCI for writing Chinese characters via brain waves known today. The proposed system was verified as having high academic value and practicability.
{"title":"The Fastest BCI for Writing Chinese Characters Using Brain Waves","authors":"T. W. Huang, Y. Tai, Y. J. Tian, K. Sun","doi":"10.1109/GCIS.2013.62","DOIUrl":"https://doi.org/10.1109/GCIS.2013.62","url":null,"abstract":"This paper presents a BCI (brain-computer interface) system called, \"fast Phonics-to-Chinese-Character system\", for individuals to write Chinese Characters using his or her brain waves. This research proposes a novel timing coding method to collocate the order of stimuli presentation. Previously, we had developed a Phonics-to-Chinese-Character system that used both the components of the P300 and the N200 of ERPs (event-related potentials) to detect the targets of a user's intention. Although the previously proposed system achieved good performance, we still tried to reduce the time spent on selecting an item. Based on experiences from previous studies, we propose four rules to collocate the timing of stimuli presentation for brain-computer interface, and then introduce a faster system. The results of the clinical experiments show that the proposed method elicits potentials of brain waves effectively for determining a target that was his/her intention. The accuracy of the system is above 95%. The proposed system is also the fastest BCI for writing Chinese characters via brain waves known today. The proposed system was verified as having high academic value and practicability.","PeriodicalId":366262,"journal":{"name":"2013 Fourth Global Congress on Intelligent Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130286111","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}
Power Line Communication (PLC) is a kind of communication technology which uses low-voltage power line as the signal transmission medium to realize the data transmission and exchange of information. In this paper, three characteristics of the low-voltage power line signal including impedance, noise and attenuation were analyzed, while with the basic model of the channel built, the advantages of BPSK modulation technology were demonstrated.
{"title":"Research on Modulation Technology of Low-Voltage Power Line Carrier Communication","authors":"Yilin Zhou, Yilin Wang","doi":"10.1109/GCIS.2013.54","DOIUrl":"https://doi.org/10.1109/GCIS.2013.54","url":null,"abstract":"Power Line Communication (PLC) is a kind of communication technology which uses low-voltage power line as the signal transmission medium to realize the data transmission and exchange of information. In this paper, three characteristics of the low-voltage power line signal including impedance, noise and attenuation were analyzed, while with the basic model of the channel built, the advantages of BPSK modulation technology were demonstrated.","PeriodicalId":366262,"journal":{"name":"2013 Fourth Global Congress on Intelligent Systems","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130789157","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}
In the product usage life cycle, the problems found by customers can be considered separately to the market, procurement, manufacturing and channel departments to generate the product related attributes. This has meant that do not consider other process multi-attributes simultaneously, and do not capture enough structured and relational feedback information through product usage life cycle. This paper design the intelligent agent-based tracing system based on IOT(internet of things) architecture using FCM (fuzzy cognitive maps) and fuzzy rule method for product usage life cycle. It aimed at simulate complex system with imprecise relationships while quantifying the performance impact of backward design process efficiency using the total effects algorithm.
{"title":"Intelligent IOT-Based Tracing System for Backward Design Using FCM and Fuzzy Rule","authors":"Rui-Yang Chen","doi":"10.1109/GCIS.2013.43","DOIUrl":"https://doi.org/10.1109/GCIS.2013.43","url":null,"abstract":"In the product usage life cycle, the problems found by customers can be considered separately to the market, procurement, manufacturing and channel departments to generate the product related attributes. This has meant that do not consider other process multi-attributes simultaneously, and do not capture enough structured and relational feedback information through product usage life cycle. This paper design the intelligent agent-based tracing system based on IOT(internet of things) architecture using FCM (fuzzy cognitive maps) and fuzzy rule method for product usage life cycle. It aimed at simulate complex system with imprecise relationships while quantifying the performance impact of backward design process efficiency using the total effects algorithm.","PeriodicalId":366262,"journal":{"name":"2013 Fourth Global Congress on Intelligent Systems","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126604891","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 purpose of this research is to analyze the event-related potentials (ERPs) of brain waves while engaged in reading in English. The brain wave responses of participants in choosing correct and incorrect answers on English reading tests were studied. Three English reading tests at differing levels of difficulty were used in the experiment and twelve participants (non-native English learners), six males and six females whose ages ranged from 20 to 24, voluntarily participated in the experiment. Experimental results were analyzed by independent t-tests on the EEG potentials of participants having different levels of English proficiency. A significant difference was observed at the frontal lobe under differing conditions. Subjects who chose incorrect answers on the tests elicited a higher N600, a finding similar to that of previous literature. In addition, an interesting result was found: for males, the significant area was located in the right hemisphere, whereas for females, it was in the left hemisphere. This seems to imply that males and females employ different areas of the brain to comprehend the meaning of difficult statements.
{"title":"Reactions of Brain in English Reading Tests","authors":"Y. J. Tian, Y. Tai, T. Kuo, K. Sun","doi":"10.1109/GCIS.2013.56","DOIUrl":"https://doi.org/10.1109/GCIS.2013.56","url":null,"abstract":"The purpose of this research is to analyze the event-related potentials (ERPs) of brain waves while engaged in reading in English. The brain wave responses of participants in choosing correct and incorrect answers on English reading tests were studied. Three English reading tests at differing levels of difficulty were used in the experiment and twelve participants (non-native English learners), six males and six females whose ages ranged from 20 to 24, voluntarily participated in the experiment. Experimental results were analyzed by independent t-tests on the EEG potentials of participants having different levels of English proficiency. A significant difference was observed at the frontal lobe under differing conditions. Subjects who chose incorrect answers on the tests elicited a higher N600, a finding similar to that of previous literature. In addition, an interesting result was found: for males, the significant area was located in the right hemisphere, whereas for females, it was in the left hemisphere. This seems to imply that males and females employ different areas of the brain to comprehend the meaning of difficult statements.","PeriodicalId":366262,"journal":{"name":"2013 Fourth Global Congress on Intelligent Systems","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114545032","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：