2011 International Conference on Machine Learning and Cybernetics最新文献

{"title":"Theoretical assessment of immunogenicity variation on the HA protein of H2N2 influenza virus by using fuzzy integral and SVM classifier","authors":"Po-Fon Chen, Ya-Li Hsiao, Hsiang-Chuan Liu, Pei-Chun Chang","doi":"10.1109/ICMLC.2011.6016797","DOIUrl":"https://doi.org/10.1109/ICMLC.2011.6016797","url":null,"abstract":"Hemagglutinin (HA) is the surface protein of influenza viruses, which is known to play important role in the infection process. It is the antigen that inducing immune responses and currently be used as the influenza vaccine potency marker. Epitope are some segments in the antigen which could be recognized by the immune system specifically and induce immune response. The T-cell epitopes of protein antigens are some peptides that presented on the cell surface by MHC molecules via the MHC class I pathway or the MHC class II pathway. The antigen presentation mechanisms are different in these two pathways. The MHC class I pathway is used to present endogeneous antigens to cytotoxic T cell, while the MHC class II pathway is used to present the extracellular antigens to helper T cell. The epitope with strong immune response is good target for vaccine design. Recently, the type of H2N2 influenza has a tendency towards popular again. To understand the immunogenicity variation among the HA proteins of H2N2 influenza for the past decade is important for deciphering the infection tendency. It is also a clue to design effective vaccine in advance. Fuzzy measure considers a series of special classes of measures and defined by a special property, respectively. The concept of fuzzy measure theory was introduced by Choquet in 1953 and independently defined by Sugeno in 1974 in the context of fuzzy integrals. The Choquet integral is a fuzzy integral based on any fuzzy measure that provides a computational scheme for information aggregation. In this study, we proposed a novel algorithm with high accuracy in immunogenicity prediction based on fuzzy measure and SVM classifier. Accordingly, we applied this prediction method to assess the immunogenicity variation on the HA protein of H2N2 influenza virus for the past three decades. The results show that the immunogenicity strength decreased for MHC class II response that implied the increasing tendency of influenza outbreak by H2N2 virus.","PeriodicalId":228516,"journal":{"name":"2011 International Conference on Machine Learning and Cybernetics","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115166592","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 optimal stopping problem on the finite-step simple random walk with absorbent boundaries","authors":"Jun-Li Fu, Wen-Xing Han, Bo Zhang","doi":"10.1109/ICMLC.2011.6016827","DOIUrl":"https://doi.org/10.1109/ICMLC.2011.6016827","url":null,"abstract":"This paper proposes a model of finite-step simple random walk with absorbent boundaries. We address a problem of optimal stop for this model, which is defined as the absorbent boundary value with maximum profit. Compared with many existing optimal stopping investigations in the random process, the optimal stopping time is given based on the classical probability computation within finite steps which is more easier to comprehend. The result obtained in this paper may provide some useful guidelines for real applications associated with the finite-step simple random walk such as stock market and gambling game.","PeriodicalId":228516,"journal":{"name":"2011 International Conference on Machine Learning and Cybernetics","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124463749","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":"Semi-supervised training for conditional random fields with pseudo auxiliary task","authors":"Jie Liu, Yalou Huang","doi":"10.1109/ICMLC.2011.6016764","DOIUrl":"https://doi.org/10.1109/ICMLC.2011.6016764","url":null,"abstract":"Conditional random fields (CRFs) have been successful in many sequence labeling tasks, which conventionally rely on a hand-craft feature representation of input data. However, a powerful data representation could be another determining factor of the performance, which has not attracted enough attention yet. We describe a novel sequence labeling framework that builds a supervised CRF and an unsuper-vised dynamic model on a shared nonlinear feature transformation neural network. The model could be used for transfer learning by jointly optimizing two learning tasks together. We demonstrate the effectiveness of the proposed modeling framework using synthetic data. We also show that this model yields a significant improvement of recognition accuracy over conventional CRFs on gesture recognition tasks.","PeriodicalId":228516,"journal":{"name":"2011 International Conference on Machine Learning and Cybernetics","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121260675","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":"Practical implementation of EPLAS: An Epistemic Programming Language for all scientists","authors":"W. Fang, Isao Takahashi, Y. Goto, Jingde Cheng","doi":"10.1109/ICMLC.2011.6016780","DOIUrl":"https://doi.org/10.1109/ICMLC.2011.6016780","url":null,"abstract":"Epistemic Programming was proposed as a new programming paradigm for scientists to program their epistemic processes in scientific discovery. To provide such epistemic programming environment, the concept and some fundamental ideas of EPLAS, an Epistemic Programming Language for All Scientists, were proposed. As a programming language, EPLAS must have a practical implementation. However there does not exist such implementation. This paper describes the requirements of both EPLAS language specification and its implementation. Based on those requirements, the paper presents an interpreter of EPLAS which is the first epistemic programming environment. Our implementation can be used to program the epistemic processes of some scientific thinking methods.","PeriodicalId":228516,"journal":{"name":"2011 International Conference on Machine Learning and Cybernetics","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127184060","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":"Combination of manual and non-manual features for sign language recognition based on conditional random field and active appearance model","authors":"Hee-Deok Yang, Seong-Whan Lee","doi":"10.1109/ICMLC.2011.6016973","DOIUrl":"https://doi.org/10.1109/ICMLC.2011.6016973","url":null,"abstract":"Sign language recognition is the task of detection and recognition of manual signals (MSs) and non-manual signals (NMSs) in a signed utterance. In this paper, a novel method for recognizing MS and facial expressions as a NMS is proposed. This is achieved through a framework consisting of three components: (1) Candidate segments of MSs are discriminated using an hierarchical conditional random field (CRF) and Boost-Map embedding. It can distinguish signs, fingerspellings and non-sign patterns, and is robust to the various sizes, scales and rotations of the signer's hand. (2) Facial expressions as a NMS are recognized with support vector machine (SVM) and active appearance model (AAM), AAM is used to extract facial feature points. From these facial feature points, several measurements are computed to distinguish each facial component into defined facial expressions with SVM. (3) Finally, the recognition results of MSs and NMSs are fused in order to recognize signed sentences. Experiments demonstrate that the proposed method can successfully combine MSs and NMSs features for recognizing signed sentences from utterance data.","PeriodicalId":228516,"journal":{"name":"2011 International Conference on Machine Learning and Cybernetics","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127377368","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":"Implementation and analysis of IEEE 802.11 PSM in NS-2","authors":"Xijian Chen, Yi Xie, Chengyan Wang","doi":"10.1109/ICMLC.2011.6016894","DOIUrl":"https://doi.org/10.1109/ICMLC.2011.6016894","url":null,"abstract":"Energy management in a wireless LAN is an important problem, as the viability of wireless devices depends very much on their battery life. In order to achieve energy efficiency of wireless devices, IEEE 802.11 protocol has designed an important scheme, Power Save Mode (PSM). This paper implements the PSM in NS-2 which is a popular discrete event simulator for analyzing the performance of network protocols. Firstly, the NS-2 patch of PSM is implemented in the WLAN with infrastructure mode. After validating the PSM implementation, we show that PSM can save wireless devices' energy while influencing bandwidth slightly. We analyze how the protocol parameters and network conditions affect the performance of PSM in terms of clients' energy consumption and energy efficiency metric. The experiment results show that the parameter configuration has a great impact on the performance of PSM. Especially, according to network conditions, a good configuration of protocol parameters is helpful to increase the energy efficiency of wireless clients.","PeriodicalId":228516,"journal":{"name":"2011 International Conference on Machine Learning and Cybernetics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127497861","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 method for fuzzy interpolative reasoning based on the slopes of fuzzy sets","authors":"Shyi-Ming Chen, Wen-Chyuan Hsin, Yu-Chuan Chang","doi":"10.1109/ICMLC.2011.6016696","DOIUrl":"https://doi.org/10.1109/ICMLC.2011.6016696","url":null,"abstract":"In this paper, we present a new fuzzy interpolative reasoning method for sparse fuzzy rule-based systems based on the slopes of fuzzy sets. We also make an experiment to deal with the computer activity prediction problem to compare the fuzzy interpolative reasoning results of the proposed method with the ones of the existing methods. The experimental results show that the proposed fuzzy interpolative reasoning method outperforms the existing methods to deal with the computer activity prediction problem.","PeriodicalId":228516,"journal":{"name":"2011 International Conference on Machine Learning and Cybernetics","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124954509","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":"Traffic in cooperative consensus behavior of swarm robots","authors":"Cheng-Feng Li, Zong-Chun Liu, Yantao Tian","doi":"10.1109/ICMLC.2011.6016857","DOIUrl":"https://doi.org/10.1109/ICMLC.2011.6016857","url":null,"abstract":"The problem of traffic redundancy in the cooperative and consistent behavior of swarm robots system is studied in this paper. Based on the existing flocking model and distributed controller with local interaction, the optimum communication frequency of swarm system is obtained by using particle swarm optimization. To further reduce the traffic among individuals two different methods to design evaluation value of the swarm's state are adopted, and then the communication frequencies are different with varying evaluation value. Simulation results show that the reduction of redundant communications system does not affect the cooperative consensus of swarm and the proposed communication strategies are effective.","PeriodicalId":228516,"journal":{"name":"2011 International Conference on Machine Learning and Cybernetics","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124979888","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 trend of high tech and exquisite DSC","authors":"Wei-Ming Yeh","doi":"10.1109/ICMLC.2011.6016880","DOIUrl":"https://doi.org/10.1109/ICMLC.2011.6016880","url":null,"abstract":"Just a couple of years, many camera manufactures in Japan, have promoted a new system: MILC/EVIL which sets a new format between DSLR and DSLR-like, and offers some marvelous wonders: dwindle size in shape, brilliant colors in appearance, and high tech digital image in quality. In fact, based on the data from Japan, this exquisite new camera may attraction female photo fans a lot, and set a new selling record in camera market, no wonder the president of Nikon, Makoto Kimura, declared that the EVIL system may “Redefinition of photography” (Chris chessman, July, 2010) [2], and will announce its first “counter-back weapon” before the end of 2010 or early in 2011. In our research, we collect more than 300 cases from the telephone survey during Jan., 2011 and March, 2011. Total of 202 cases comply with the conditions. To probe mainly into the relationship between EVIL camera Confidence level and 3 different potential customers: Amateur Photographer (AP), Senior Photographer (SP), and photo fans (PF). The profiles of contingency table were used to explore the potential preference for the camera with EVIL device. That is the reason what we are probe into this highly competitively market with brilliant creative design, and hope to offer an objective suggestion for both industry and education administers.","PeriodicalId":228516,"journal":{"name":"2011 International Conference on Machine Learning and Cybernetics","volume":"273 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123294003","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":"Caricaturation for human face pictures","authors":"I. Chang, Ruei-Min Cheng","doi":"10.1109/ICMLC.2011.6017011","DOIUrl":"https://doi.org/10.1109/ICMLC.2011.6017011","url":null,"abstract":"Being one of the attractive art forms, comic appears on many different media and is able to represent the subjects well with only a few strokes. The paper proposes a caricaturation system in which a face picture can be transformed into a caricatured output in accordance with the specific painter's style. A facial feature rendering process and a hair rendering process are included in the system. We build a database in advance that stores the extracted information of the face pictures and caricatured face of a painting style. According to the input face picture, the proposed rendering processes compute the correspondence to the database so that it can select the appropriate caricatured facial features and hairs from the database, and adjust them to fit the input face. The proposed system can keep the characteristics of the input face as well as preserve the painter's style. To increase the flexibility, an additional portrayal rendering process is used to add the shadows on the caricatured faces and feminize a male face.","PeriodicalId":228516,"journal":{"name":"2011 International Conference on Machine Learning and Cybernetics","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123475129","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}