{"title":"Face Recognition Based on Two-Dimension Kernel Principal Component Analysis and Fuzzy Maximum Scatter Difference","authors":"J. Zeng, Wei Wang, Jinge Tian","doi":"10.1109/ISKE.2015.18","DOIUrl":"https://doi.org/10.1109/ISKE.2015.18","url":null,"abstract":"Considering the \"nonlinear\",\"outer classes\" and \"hard classifier\" problem in two-direction maximum scatter difference discriminant analysis method, a new method(2DKFMSD) of face recognition based on two-dimension kernel principal component(K2DPCA) and fuzzy maximum scatter difference (FMSD) is developed in this paper. Firstly, the K2DPCA overcomes the limitations of the traditional PCA method and can extract the nonlinear structures features in faces efficiently. Secondly, selecting the eigenvectors that between-class scatter is greater than within-class scatter after projection as optimal projection axis. and the distribution information of samples is represented with fuzzy membership degree in the FMSD. Finally, it uses the nearest neighbor classifier for face recognition. The experiment results on ORL and YALE face databases show that the 2DKFMSD is better than other methods.","PeriodicalId":312629,"journal":{"name":"2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121505822","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":"Study on Temporal Patterns of Medical Emergency Call","authors":"Kuiyu Ma, Wenjun Wang, Ning Yuan, Xiaotong Chi","doi":"10.1109/ISKE.2015.96","DOIUrl":"https://doi.org/10.1109/ISKE.2015.96","url":null,"abstract":"The quantitative analysis of human behavior is an effective way to understand human communication behavior, and some relevant empirical researches have revealed that human communication behavior would follow power-law distribution rather than Poisson distribution in temporal characteristics. As to the sudden emergency call behavior, the analysis of temporal patterns is crucial to hospitals and patients. Based on the quantitative analysis of interval time distribution, burstiness and memory of medical emergency call data of a metropolitan city in China, we find that the maximum call happen at 9:00 and the least in the night 4:00. While to the regional statistics, District A has the maximum call in the aspect of area, population and call amount. On the other hand, different individuals' emergency call at the group level shows a power-law distribution on temporal patterns, and in about two hours, the position slightly bulges, while in five or seven days, the position fluctuates slightly. Individuals who take more medical emergency calls have more obvious burstiness character, in terms of burstiness and memory, and all individuals show weak memory character. In this paper, we do the quantitative analysis of temporal patterns of medical emergency call based on the medical emergency call data, which could provide data basis for scientific rational allocation of aid resources and effective emergency measures, in order to further adjust and improve aid resources, and help to improve the efficiency of pre-hospital care.","PeriodicalId":312629,"journal":{"name":"2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121585783","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}
Yang Xu, Jun Liu, Xingxing He, Xiaomei Zhong, Shuwei Chen
{"title":"Non-clausal Multi-ary alpha-Generalized Resolution Principle for a Lattice-Valued First-Order Logic","authors":"Yang Xu, Jun Liu, Xingxing He, Xiaomei Zhong, Shuwei Chen","doi":"10.1109/ISKE.2015.88","DOIUrl":"https://doi.org/10.1109/ISKE.2015.88","url":null,"abstract":"The present paper focuses on a resolution-based automated reasoning theory in a lattice-valued logic system with truth-values defined in a lattice-valued algebraic structure - lattice implication algebras (LIA) in order to handle automated deduction under an uncertain environment. Particularly, as a continuation and extension of the established work on binary resolution at a certain truth-value level α (called α-resolution), a non-clausal multi-ary α-generalized resolution principle and deduction are introduced in this paper for a lattice-valued first-order logic LF(X) based on LIA, which is essentially non-clausal generalized resolution avoiding the reduction to normal clausal form. Non-clausal multi-ary α-generalized resolution deduction in LF(X) is then proved to be sound and complete. The present work is expected to provide a theoretical foundation of more efficient resolution based automated reasoning in lattice-valued logic.","PeriodicalId":312629,"journal":{"name":"2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114969336","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":"Reverse Triple I Algorithms Based on Schweizer-Sklar Interval-Valued t-Norms","authors":"M. Luo, Xiaoling Zhou","doi":"10.1109/ISKE.2015.10","DOIUrl":"https://doi.org/10.1109/ISKE.2015.10","url":null,"abstract":"In this paper, full implication reverse triple I algorithms based on Schweizer-Sklar interval-valued t-norms are proposed, and the corresponding interval-valued Rm-type reverse triple I solutions are given. Moreover, robustness of the new algorithms are discussed.","PeriodicalId":312629,"journal":{"name":"2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129731497","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":"A Matrix-Based Incremental Attribute Reduction Approach under Knowledge Granularity on the Variation of Attribute Set","authors":"Yunge Jing, Tianrui Li","doi":"10.1109/ISKE.2015.40","DOIUrl":"https://doi.org/10.1109/ISKE.2015.40","url":null,"abstract":"Attribute reduction in rough sets is a key step to discover interesting patterns in decision systems with numbers of attributes available. Moreover, data processing tools have been developed rapidly in recent years, and then the information system may increase quickly in attributes with time in real-life applications. How to update attribute reduction efficiently becomes an important task in knowledge discovery related tasks. The attribute reduction of information systems may alter with the attributes increasing. This paper aims for investigation of incremental attribute reduction algorithm based on knowledge granularity in information systems on the variation of attribute set. Matrix-based incremental mechanisms to calculate the new knowledge granularity are first introduced. Then, the corresponding incremental algorithm is presented for attribute reduction based on the calculated knowledge granularity when multiple attributes are added to a decision table. Finally, experiments performed on UCI data sets and the complexity analysis show that the proposed matrix-based incremental method is effective and efficient to update attribute reduction with the increase of attributes.","PeriodicalId":312629,"journal":{"name":"2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130099042","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 Endocrine System Inspired Behavior Selecting Algorithm for Moving Robot System","authors":"Fang Li, L. Ren, Yongsheng Ding, K. Hao","doi":"10.1109/ISKE.2015.67","DOIUrl":"https://doi.org/10.1109/ISKE.2015.67","url":null,"abstract":"The robots that operate in real environment are often limited to many different problems. One of the main problems comes from the fact that outdoor real-world environments are dynamic and full of interventions, and the reactive behaviors may be sometimes conflicting to each other correspondingly. Artificial endocrine system can be the key to solve the problem. This paper proposes an algorithm for the coordination of multiple and possible conflicting behaviors selecting algorithm, devoted to reach the goal while collecting collectable objectives. The proposed endocrine based behavior selecting algorithm is composed of an artificial endocrine system, including two hormones, and three behaviors. The experiments are performed in simulation conditions. The results show that the algorithm proposed is able to coordinate a multiple and conflicting behaviors task, with less time and being more efficient.","PeriodicalId":312629,"journal":{"name":"2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125437696","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":"A Hybrid Sentiment Analysis Framework for Large Email Data","authors":"Sisi Liu, Ickjai Lee","doi":"10.1109/ISKE.2015.91","DOIUrl":"https://doi.org/10.1109/ISKE.2015.91","url":null,"abstract":"Sentiment analysis for online text documents has been a burgeoning field of text mining among researchers and scholars for the past few decades. Nevertheless, sentiment analysis on large Email data, a ubiquity means of social networking and communication, has not been studied thoroughly. This paper proposes a framework for Email sentiment analysis using a hybrid scheme of algorithms combined with Kmeans clustering and support vector machine classifier. The evaluation for the framework is conducted through the comparison among three labeling methods, including SentiWordNet labeling, Kmeans labeling, and Polarity labeling, and five classifiers, including Support Vector Machine, Naïve Bayes, Logistic Regression, Decision Tree and OneR. Empirical results indicate a relatively high classification accuracy with proposed framework in comparison with other approaches.","PeriodicalId":312629,"journal":{"name":"2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124721122","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":"Design Successive Approximation Register Analog-to-Digital Converter with Vcm-Based Method for M-PAM Receiver and Computational Intelligence Application","authors":"W. Lai","doi":"10.1109/ISKE.2015.102","DOIUrl":"https://doi.org/10.1109/ISKE.2015.102","url":null,"abstract":"In this paper proposed successive approximation register (SAR) analog-to-digital converter (ADC) implemented for M-PAM receiver and computational intelligence application is presented. By applying Vcm-based switching method that reduces switching power of the DAC, the proposed SAR ADC uses less capacitor in the DAC array. Also, asynchronous control logic is used which an external high frequency doesn't need clock to drive ADC. This design provide on the automatic gain control (AGC) scheme for pulse amplitude modulation (PAM) with analog-to-digital converters (ADCs).","PeriodicalId":312629,"journal":{"name":"2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117048656","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":"A New Approach to Multi-objective Programming Based on Satisfied Degree under Fuzzy Environment","authors":"Jing-Duo Jie, Fachao Li, Chenxia Jin","doi":"10.1109/ISKE.2015.23","DOIUrl":"https://doi.org/10.1109/ISKE.2015.23","url":null,"abstract":"Fuzziness is a common uncertainty who exists widespread in decision process and how to process fuzziness is a widespread context in academic and application fields. For the multi-objective programming under fuzzy environment, this paper firstly analyze the essential characteristics of fuzzy objectives. Then fuzzy objectives are divided into three kinds and represent by fuzzy number by introducing deviation parameter α . Then, regarding membership of fuzzy number as the satisfied degree, we establish the multi-objective programming based on satisfied degree (denotes as MP-SD) and a new solving strategy based on MP-SD is further given. Finally, we illustrate the validity of MPSD through a case. The analytical results show that the proposed approach is effective in fuzzy decision environment and provide rich decision theories for integrated multi-objective programming problems in artificial intelligence and resource management and so on.","PeriodicalId":312629,"journal":{"name":"2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116316660","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":"A Framework of Hybrid Recommender System for Personalized Clinical Prescription","authors":"Qian Zhang, Guangquan Zhang, Jie Lu, D. Wu","doi":"10.1109/ISKE.2015.98","DOIUrl":"https://doi.org/10.1109/ISKE.2015.98","url":null,"abstract":"General practitioners are faced with a great challenge of clinical prescription owing to the increase of new drugs and their complex functions to different diseases. A personalized recommender system can help practitioners discover mass of medical knowledge hidden in history medical records to deal with information overload problem in prescription. To support practitioner's decision making in prescription, this paper proposes a framework of a hybrid recommender system which integrates artificial neural network and case-based reasoning. Three issues are considered in this system framework: (1) to define a patient's need by giving his/her symptom, (2) to mine features from free text in medical records and (3) to analyze temporal efficiency of drugs. The proposed recommender system is expected to help general practitioners to improve their efficiency and reduce risks of making errors in daily clinical consultation with patients.","PeriodicalId":312629,"journal":{"name":"2015 10th International Conference on Intelligent Systems and Knowledge Engineering (ISKE)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133339044","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}