摘要
包括情感计算和情感识别在内,以人为中心的,对人的情感和认知的研究是目前人工智能领域的一个热点研究方向。对这一方向的研究将有助于推动实现人与机器之间的自然交互。虽然目前情感计算和情感识别的研究已经取得了初步的成果,但是由于缺乏坚实的心理学和认知科学的理论基础,在研究中还存在诸多待解决的关键问题。本文就人脸表情识别系统所涉及的特征选择和识别方法进行研究。这些研究工作不仅能推动计算机表情识别、计算机情感仿真等的进展,而且对于自然人机交互、远程教育、医疗看护、游戏娱乐等应用领域都有重要意义。
本文以粗糙集理论为基础,研究了粗糙集属性约简算法,并把粗糙集属性约简算法作为一种人脸表情识别系统的特征选择方法。根据人脸几何特征直观性好的优点,以人脸的几何特征作为研究对象,对人脸表情识别的重要特征进行研究。此外,本文还基于粗糙集理论,结合集成学习理论,对人脸表情识别方法进行研究。取得的主要研究成果如下：
1)提出了基于粗糙集属性约简的人脸表情识别的特征选择方法。
本文引入粗糙集理论,提出了采用粗糙集属性约简算法作为一种人脸表情识别的特征选择方法。基于经典粗糙集理论,采用基于信息熵的属性约简算法和特征选择的属性约简算法对人脸表情识别采用的特征进行了特征选择,并提出了一种RS+SVM的人脸表情识别方法。研究结果表明,相比较传统的特征选择算法,粗糙集属性约简方法不仅能有效地降低特征的维度、得到人脸表情识别的重要特征,而且基于这些重要特征,能得到较好的人脸表情识别结果。
2)提出了自主式的人脸表情特征选择算法。
本文基于粗糙集理论和面向领域的数据驱动的数据挖掘模型思想,对连续值信息系统的属性约简方法进行了研究,提出了一个自主式的属性约简算法,首先,将条件属性集对决策的可区分性作为知识的一种属性特征,并基于粗糙集理论提出一种可区分性的度量方法。然后,根据在知识获取过程中可区分性的不变性原则,提出了一个针对连续值信息系统的自主式属性约简算法(SARA),该算法可以从训练数据中自动获取控制学习过程所需要的参数。研究结果表明,该方法在不依赖于领域专家先验知识的情况下也能得到很好的结果。本文把SARA作为一种人脸表情识别的特征选择方法,把SARA挑选的表情特征应用于人脸表情识别,得到了很好的人脸表情识别结果,同时还得到了在人脸的几何特征中嘴部的特征对人脸表情识别起到最重要作用的结论。
3)基于粗糙集理论和集成学习理论,提出了一种选择性集成的人脸表情识别方法。
首先,基于经典粗糙集理论的可辨识矩阵求出信息系统的多个约简,并对得到的多个约简训练多个候选分类器。然后,基于双误的差异性度量方法,对候选分类器按差异度进行聚类。最后,采用选择性集成的策略,从每两类候选分类器中选择出差异性最大的分类器进行相对多数投票,得到集成的输出结果。仿真实验结果表明,该方法得到了良好的表情识别结果。
4)基于扩展的粗糙集理论和集成学习理论,提出了一种动态选择的人脸表情识别方法。
首先,基于面向领域的数据驱动的数据挖掘模型思想,提出了一个求核属性的算法和一个基于信息熵的求多个属性约简的算法。然后采用该方法求出信息系统的多个约简,并根据得到的多个约简训练候选分类器集合。最后,根据多分类器的本地精确性,基于动态选择的策略从候选分类器集合中挑选出最优的分类器对待识别的样本进行分类识别。该方法成功用于直接处理人脸表情特征的连续值属性,仿真实验结果表明,该方法得到了良好的表情识别结果。
5)开发了一个语音和视频的双模情感识别系统
基于本文的研究成果,开发了一个语音和视频的双模情感识别系统。该系统能实现实时的单模人脸表情识别、单模语音情感识别和双模情感识别。实际测试结果表明,该系统具有很好的实时性和识别结果。
The study of human centered emotion and cognition, including affective computing and emotion recognition, is a hot research topic in artificial intelligence. Achievements on these research topics will push the development of human-computer intelligent interaction (HCII). Although there are already some achievements of affective computing and emotion recognition in recent years, there are still some key problems unsolved due to the absence of solid theory basis of psychology and cognition. In this thesis, feature selection methods and emotion recognition methods in a facial emotion recognition system are studied. These research works can not only push the development of emotion recognition and emotion simulation, but also are important for the applications in HCII, E-learning, medical caring, game, etc.
In this thesis, attribute reduction algorithms are studied based on rough set theory and used for feature selection of a facial emotion recognition system. Geometrical face features are taken as the research objects since it is intuitionistic. Important features for emotion recognition are studied based on attribute reduction algorithms. Furthermore, efficient emotion recognition methods are also studied based on rough set theory and ensemble learning. The major achievements of this thesis are as follows.
1) A feature selection method for emotion recognition based on rough set theory is proposed.
In this thesis, the attribute reduction algorithms based on rough set theory are introduced and proposed for feature selection methods for emotion recognition. Based on traditional rough set theory, the attribute reduction algorithm based on conditional entropy and the attribute reduction algorithm based on feature selection are used as feature selection methods for emotion recognition. Meanwhile, a novel emotion recognition method based on RS plus SVM is proposed. The experiment results show that the attribute reduction algorithms can reduce the feature dimension and extract the important features for emotion recognition. Based on these features, better recognition result than traditional feature selection methods can be achieved.
2) A self-learning expression feature selection algorithm is proposed.
In this thesis, based on the idea of domain-oriented data-driven data mining theory, an attribute reduction algorithm for continuously valued information systems is studied, and a self-learning attribute reduction algorithm is proposed. Discernable-ability of conditional attribute set with respect to decision attribute set is taken as an important property of knowledge, and a measurement of discernable-ability is proposed based on rough set theory. According to the criterion that discernable-ability should hold in the course of knowledge acquisition, a self-learning attribute reduction algorithm (SARA) is proposed for continuously valued information systems. Its parameter can be obtained automatically from training data set. Experiment results show that the method can get good result even if there is no prior domain knowledge. SARA is taken as a feature selection method for emotion recognition in this thesis, and good recognition result is achieved based on the features it found. Furthermore, the features which concerned mouth are found as the most important expression features.
3) A selective ensemble feature selection method for emotion recognition is proposed based on rough set theory and ensemble learning.
At first, an algorithm based on discernibility matrix is adopted and multiple reductions are generated, correspondingly multiple candidate classifiers are trained. Secondly, the double fault method is taken as the measure of the diversity of the candidate classifiers, and the candidate classifiers are clustered according to measurement of the double fault method, and the most diverse classifiers are selected from each pair of clusters. At last, the criterion of relative majority voting is adopted for the selected classifiers, and the output of the ensemble is gotten. Experiment results show that good recognition result can be achieved based on the proposed method.
4) A dynamic ensemble feature selection method for emotion recognition is proposed based on extended rough set theory and ensemble learning.
At first, an algorithm for calculating the core of a decision table is proposed based on the domain-oriented data-driven data mining theory. Secondly, an algorithm for finding multiple reductions based on conditional entropy is proposed. Accordingly, multiple candidate classifies are generated using this algorithm. At last, a dynamical selective measure is used to select the most suitable classifier for each unseen sample according to local property of the candidate classifiers, and recognition result is gotten accordingly. Experiment results show that good recognition result can be achieved based on the proposed method.
5) An audio and visual double module emotion recognition system is developed.
A double module emotion recognition system based on both audio and visual information is developed. It can recognize facial expression, emotional speech and expression of the combination of facial and speech emotions in time. Good recognition results are achieved in real testing environments.
引文
[1]Minsky M. The society of mind[M]. New York, N.Y.:Simon and Schuster, 1986:339.
[2]傅小兰.开展情感计算研究、构建和谐电子社会[J].中国科学院院刊.2008(05)：453-457.
[3]Fragopanagos N, Taylor J G. Emotion recognition in human-computer interaction[J]. Neural Networks.2005,18(4):389-405.
[4]Picard R W. Affective computing:challenges [J]. International Journal of Human-Computer Studies.2003,59(1):55-64.
[5]Brave S, Nass C. Emotion in human-computer interaction[M]. The human-computer interaction handbook:fundamentals, evolving technologies and emerging applications, Hillsdale, NJ, USA:Lawrence Erlbaum Associates Inc., 2002.
[6]王志良.人工心理[M].北京：机械工业出版社,2006.
[7]Mehrabian A. Silent messages:Implicit communication of emotions and attitudes[M]. Belmont, California.:Wadsworth Pub Co.,1981.
[8]Picard R W. Affective Computing[M]. Londan, England:MIT Press,1997.
[9]Picard R W, Vyzas E, Healey J. Toward machine emotional intelligence: analysis of affective physiological state[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2001,23(10):1175-1191.
[10]王志良.人工心理与人工情感[J].智能系统学报.2006,1(1)：38-43.
[11]Fujita M. Digital creatures for future entertainment robotics[C].2000 IEEE International Conference on Robotics and Automation, San Francisco, CA, USA, 2000:801-806.
[12]Nee. Personal Robot PaPeRo. http://www.incx.nec.co.jp/robot/english/robotcenter_e.html.
[13]王志良.人工心理学：关于更接近人脑工作模式的科学[J].北京科技大学学报.2000,22(5)：478-481.
[14]张雪元.基于人工心理的服务机器人交互平台相关技术研究[D].博士.北京科技大学,2007.
[15]王玉洁.基于人工心理的情感建模及人工情感交互技术研究[D].博士.北京科技大学,2007.
[16]杨国亮.人工心理相关技术研究—面部表情识别与情感建模[D].博士.北京科技大学,2006.
[17]腾少冬.应用于个人机器人的人工心理模型的研究[D].博士.北京科技大学,2006.
[18]金辉,高文.人脸面部混合表情识别系统[J].计算机学报.2000,23(6)：602-608.
[19]金辉,高文.基于HMM的面部表情图像序列的分析与识别[J].自动化学报.2002,28(4)：646-650.
[20]高文,金辉.面部表情图像的分析与1识别[J].计算机学报.1997,20(9)：782-790.
[21]焦峰,高文,等.基于局部特征分析的人脸识别方法[J].计算机辅助设计与图形学学报.2003,15(1)：53-58.
[22]山世光,高文,唱轶钲.人脸识别中的“误配准灾难”问题研究[J].计算机学报.2005,28(5)：782-791.
[23]Ekman P, Friesen W V. Constants across cultures in the face and emotion[J]. Journal of Personality Scoial Psychol.1971,17(2):124-129.
[24]Suwa M, Sugie N, Fujimora K. A preliminary note on pattern recognition of human emotional expression[C]. The Fourth International Joint Conference on Pattern Recognition, Kyoto, Japan,1978:408-410.
[25]Fasel B, Luettin J. Automatic facial expression analysis:a survey [J]. Pattern Recognition.2003,36(1):259-275.
[26]Pantic M, Sebe N, Cohn J F. Affective Multimodal Human-Computer Interaction[C].13th annual ACM international conference on Multimedia, Singapore,2005:669-675.
[27]Pantic M, Rothkrantz L J M. Facial action recognition for facial expression analysis from static face images[J]. IEEE Transactions on Systems, Man, and Cybernetics.2004,34(3):1449-1461.
[28]Bourel F, Chibelushi C C, Low A A. Robust facial expression recognition using a state-based model ofspatially-localised facial dynamics[C]. Fifth IEEE International Conference on Automatic Face and Gesture Recognition,2002: 106-111.
[29]Chibelushi C C, Bourel F. Hierarchical multistream recognition of facial expressions[J]. IEE Proceedings on Vision, Image and Signal Processing.2004, 151(4):307-313.
[30]Kotsia I, Pitas I. Facial Expression Recognition in Image Sequences Using Geometric Deformation Features and Support Vector Machines[J]. IEEE Transactions on Image Processing.2007,16(1):172-187.
[31]金辉,高文.基于特征流的面部表情运动分析及应用[J].软件学报.2003,14(12)：2098-2105.
[32]刘晓旻,谭华春,章毓晋.人脸表情识别研究的新进展[J].中国图象图形学报.2006,11(10)：1359-1368.
[33]赵力庄,高文.Eigenface的变维分类方法及其在表情识别中的应用[J].计算机学报.1999,22(6)：627-632.
[34]何良华,邹采荣,包永强.人脸面部表情识别的研究进展[J].电路与系统学报.2005(01)：70-75.
[35]Donato G, Bartlett M S, Hager J C. Classifying facial actions[J]. IEEE transactions on pattern analysis and machine intelligence.1999,21(10):974-989.
[36]Wen Z, Huang T S. Capturing subtle facial motions in 3d face tracking[C]. Ninth IEEE International Conference on Computer Vision, Nice, France,2003: 1343-1350.
[37]Ye J, Zhan Y, Song S. Facial Expression Features Extraction Based On Gabor Wavelet Transformation[C].2004 IEEE International Conference on Systems, Man and Cybernetics,2004:2215-2219.
[38]He K, Wang G, Yang Y. Optical flow-based facial feature tracking using prior measurement[C].7th IEEE International Conference on Cognitive Informatics,2008:324-331.
[39]Cootes T F, Edwards G J, Taylor C J. Active Appearance Models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2001,23(6): 681-685.
[40]Bouchra A, Franck D, Mo D. Facial expression recognition and synthesis based on an appearance model[J]. Signal Processing:Image Communication. 2004,19(8):723-740.
[41]何良华.人脸表情识别中若干关键技术的研究[D].博士.东南大学,2005.
[42]Ma L, Khorasani K. Facial Expression Recognition Using Constructive Feedforward Neural Networks[J]. IEEE Transactions on Systems, Man, and Cybernetics.2004,34(3):1588-1595.
[43]Ioannou S V, Raouzaiou A T, Tzouvaras V A. Emotion recognition through facial expression analysis based on a neurofuzzy network [J]. Neural Networks. 2005,18(4):423-435.
[44]Cohen I, Sebe N, Garg A. Facial expression recognition from video sequences:temporal and static modeling[J]. Computer Vision and Image Understanding.2003, Special Issue on Face Recognition:160-187.
[45]Zhang Y, Ji Q. Active and dynamic information fusion for facial expression understanding from image sequences[J]. IEEE Transactions on Pattern Analysis an d Machine Intelligence.2005,27(5):699-714.
[46]Vapnik V. Statistical Learning Theory[M]. New York:Wiley-Interscience, 1998.
[47]Bartlett M S, Littlewort G C, Frank M G. Automatic Recognition of Facial Actions in Spontaneous Expressions[J]. Journal of Multimedia.2006,1(6): 22-36.
[48]Katsis C D, Katertsidis N, Ganiatsas G. Toward Emotion Recognition in Car-Racing Drivers:A Biosignal Processing Approach[J]. IEEE Transactions on Systems, Man and Cybernetics.2008,38(3):502-512.
[49]Hong H, Neven H, Von Der Malsburg C. Online facial expression recognition based on personalized galleries[C]. Third IEEE International Conference on Automatic Face and Gesture Recognition, Nara, Japan,1998: 354-359.
[50]The Cohn-Kanade AU-Coded Facial Expression Database. http://vasc.ri.cmu.edu/idb/html/face/facial_expression/index.html.
[51]The Japanese Female Facial Expression (JAFFE) Database.http://www.kasrl.org/jaffe.html.
[52]汪亚珉,傅小兰.区分度在面部表情与面孔身份识别交互中的作用[J].心理学报.2007(02)：191-200.
[53]谭华春,章毓晋.基于人脸相似度加权距离的非特定人表情识别[J].电子与信息学报.2007,29(02)：455-459.
[54]隋雪,任延涛.面部表情识别的即时加工过程[J].心理学报.2007,39(1)：64-70.
[55]汪亚珉,傅小兰.负性面部表情影响面孔身份识别的实验研究[J].人类工效学.2007(03)：1-3.
[56]Murray W. Effect of photographic negation on matching the expressions and identities of faces[J]. Perception.2001,30(8):969-981.
[57]Murray W. Different spatial-relational information is used to recognise faces and emotional expressions[J]. Perception.2002,31(6):675-682.
[58]Bluma A L, Langley P. Selection of relevant features and examples in machine learning[J]. Artificial Intelligence.1997,97(1):245-271.
[59]Saeys Y, Inza I, Larranaga P. A review of feature selection techniques in bioinformatics[J]. Bioinformatics.2007,23(19):2507-2517.
[60]Inza I, Larranaga P, Blanco R. Filter versus wrapper gene selection approaches in DNA microarray domains[J]. Artificial Intelligence in Medicine. 2004,31(2):91-103.
[61]Kohavia R, John G H. Wrappers for feature subset selection[J]. Artificial Intelligence.1997,97(1):273-324.
[62]Swiniarski R W, Skowron A. Rough set methods in feature selection and recognition[J]. Pattern Recognition Letters.2003,24(6):833-849.
[63]Banerjee M, Mitra S, Banka H. Evolutionary rough feature selection in gene expression data[J]. IEEE Transactions on Systems, Man, and Cybernetics. 2001,37(4):622-632.
[64]Zhong N, Dong J, Ohsuga S. Using Rough Sets with Heuristics for Feature Selection[J]. Journal of Intelligent Information Systems.2001,16(3):199-214.
[65]Weston J, Mukherjee S, Chapelle O. Feature selection for SVMs[M]. Advances in Neural Information Processing Systems, MIT Press,2000, 6674-6678.
[66]Setiono R, Liu H. Neural Network Feature Selector[J]. IEEE Transaction on Neural Networks.1997,8(3):654-662.
[67]Lee H, Chen C, Chen J. An efficient fuzzy classifier with feature selection based on fuzzyentropy[J]. IEEE Transactions on Systems, Man, and Cybernetics. 2001,31(3):426-432.
[68]Mitra P, Murthy C A, Pal S K. Unsupervised feature selection using feature similarity[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2002,24(3):301-312.
[69]Dy J G, Brodley C E. Feature Selection for Unsupervised Learning[J]. Journal of Machine Learning Research.2004,5(1):845-889.
[70]张丽新.高维数据的特征选择及基于特征选择的集成学习研究[D].博士.清华大学,2004.
[71]刘天羽.基于特征选择技术的集成学习方法及其应用研究[D].博士上海大学,2006.
[72]Liu H, Yu L. Toward Integrating Feature Selection Algorithms for Classification and Clustering[J]. IEEE Transaction on Knowledge and Data Engineering.2005,17(4):491-502.
[73]Zhou X J, Dillon T S. A statistical-heuristic feature selection criterion for decisiontree induction[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1991,13(8):834-841.
[74]Viola P, Jones M. Rapid object detection using a boosted cascade of simple features[C].2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2001:511-518.
[75]Silapachote P, Karuppiah D R, Hanson A R. Feature Selection using AdaBoost for Face Expression Recognition[C]. Fourth IASTED International Conference On Visualization, Imaging, And Image Processing, Marbella, Spain, 2004:273-279.
[76]Schapire R E. A Brief Introduction to Boosting[C]. Sixteenth International Joint Conference on Artificial Intelligence, Stockholm, Sweden,1999: 1401-1406.
[77]柴秀娟,山世光,高文.基于样例学习的面部特征自动标定算法[J].软件学报.2005,16(5)：716-718.
[78]Shi J, Tomasi C. Good features to track[C].1994 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 1994:593-600.
[79]Pandzic I S, Forchheimer R. MPEG-4 Facial Animation:The Standard, Implementation and Applications [M]. New York, NY, USA:ohn Wiley & Sons, Inc.,2003.
[80]Yang Y, Wang G, Chen P. Feature Selection in Audiovisual Emotional Recognition Based on Rough Set Theory[J]. Transactions on Rough Sets VII. 2007:283-294.
[81]Pawlak Z. Rough sets[J]. International journal of computer & information sciences.1982,11(5):341-356.
[82]Pawlak Z. Rough Classification[J]. International Journal of Man-Machine Studies.1984,20(5):469-483.
[83]Pawlak Z. Rough Set Theory and Its applications to Data Analysis[J]. Cybernetics and Systems.1998,29(7):661-688.
[84]于洪.Rough Set理论及其在数据挖掘中的应用研究[D].博士.重庆大学,2003.
[85]王国胤.Rough集理论与知识获取[M].西安：西安交通大学出版社,2001.
[86]王国胤,于洪,杨大春.基于条件信息熵的决策表约简[J].计算机学报.2002,25(7)：759-766.
[87]苗夺谦,胡桂荣.知识约简的一种启发式算法[J].计算机研究与发展.1999(06)：42-45.
[88]Hu X, Cercone N. Learning maximal generalized decision rules via discretization, generalization and rough set feature selection[C]. Ninth IEEE International Conference on Tools with Artificial Intelligence, Newport Beach, CA,USA,1997:548-556.
[89]Kullback S. Information Theory and Statistics[M]. New York:Dover Publications,1968.
[90]Ziarko W. Variable Precision Rough Set Model[J]. Journal of Computer and Systems Sciences.1993,46(1):39-59.
[91]Guo G, Li S Z, Chan K L. Support vector machines for face recognition[J]. Image and Vision Computing.2001,19(9):631-638.
[92]Tong S, Koller D. Support vector machine active learning with applications to text classification[J]. The Journal of Machine Learning Research.2002,2(1): 45-66.
[93]梁路宏,艾海舟.基于模板匹配与支持矢量机的人脸检测[J].计算机学报.2002,25(1)：22-29.
[94]Cristianini N, Shawe-Taylor J.支持向量机导论[M].北京： 电子工业出版社,2004.
[95]张建明,曾建武,谢磊.基于粗糙集的支持向量机故障诊断[J].清华大学学报(自然科学版).2007,47(S2)：1774-1777.
[96]肖云,韩崇昭,郑庆华.基于粗糙集-支持向量机理论的过滤误报警方法[J].电子与信息学报.2007,29(12)：3011-3014.
[97]Zhang B, Yin J, Tang W. Unknown Malicious Codes Detection Based on Rough Set Theory and Support Vector Machine[C].2006 International Joint Conference on Neural Networks, Vancouver, BC,2006:2583-2587.
[98]Jia Z, Gong L, Han J. Application of Support Vector Machine Based on Rough Sets to Project Risk Assessment (RS-SVM)[C].2008 International Conference on Computer Science and Software Engineering, Wuhan, China, 2008:508-511.
[99]Li Y, Cai Y, Li Y. Rough sets method for SVM data preprocessing[C]. 2004 IEEE Conference on Cybernetics and Intelligent Systems, Singapore,2004: 1039-1042.
[100]Zhang G, Cao Z, Gu Y. A Hybrid Classifier Based on Rough Set Theory and Support Vector Machines [C].2005 International conference on Fuzzy systems adn knowledge discovery., Changsha, China,2005:1287-1296.
[101]Vapnik V N.统计学习理论[M].北京：电子工业出版社,2006.
[102]Chongqing University of Posts and Telecommunications Emotional Database (CQUPTE). http://cs.cqupt.edu.cn/users/904/docs/9317-1.rar.
[103]Goldberg D E. Genetic algorithms in search, optimization and machine learning[M]. Boston, MA, USA:Addison-Wesley Longman Publishing Co., Inc., 1989.
[104]Wang G, Zheng Z, Zhang Y. RIDAS-A Rough Set Based Intelligent Data Analysis System[C]. International Conference on Machine Learrung and Cybernetics, Beijin,2002:646-649.
[105]Nguyen S H, Andrzej S. Quantization of real values attributes, rough set and boolean reasoning approaches[C]. Second Joint Annual Conference on Information Sciences, Wrightsville Beach, North Carolina,1995:34-37.
[106]Holmes G, Donkin A, Witten I H. WEKA:a machine learning workbench[C]. Second Australian and New Zealand Conference on Intelligent Information Systems, Qld., Australia,1994:357-361.
[107]Weka 3:Data Mining Software in Java. http://www.cs.waikato.ac.nz/ml/weka/.
[108]Hall M A. Correlation-based Feature Selection for Machine Learning[D]. Doctoral dissertation. Hamilton, NewZealand:Univ. of Waikato,1998.
[109]John G H, Langley P. Estimating Continuous Distributions in Bayesian Classifiers[C]. Eleventh Conference on Uncertainty in Artificial Intelligence, San Mateo,1995:338-345.
[110]Wang G. Introduction to 3DM:Domain-Oriented Data-Driven Data Mining[C]. The Third International Conference on Rough Set and Knowledge Technology, Chengdu, China,2008:25-26.
[111]Wang G, Wang Y.3DM:Domain-oriented Data-driven Data Mining[J]. Fundamenta Informaticae.2009,90(4):395-426.
[112]肖迪,胡寿松.实域粗糙集理论及属性约简[J].自动化学报.2007,33(3)：253-258.
[113]刘文军,谷云东,李洪兴.一种基于t相似分类的连续值域决策表的决策算法[J].模式识别与人工智能.2005,18(6)：652-656.
[114]商琳,万琼,姚望舒.一种连续值属性约简方法ReCA[J].计算机研究与发展.2005,42(7)：1217-1224.
[115]Jensen R, Shen Q. Tolerance-based and fuzzy-rough feature selection[C]. 2007 IEEE International Fuzzy Systems Conference, London,2007:1-6.
[116]Tsumoto S. Knowledge Discovery as Translation[M]. Foundations of Data Mining and Knowledge Discovery, Tsau Young Lin S O C L, Birkhauser,2005, 3-42.
[117]UCI Machine Learning Repository. http://archive.ics.uci.edu/ml/.
[118]Dietterich T G. Ensemble Methods in Machine Learning[C]. The First International Workshop on Multiple Classifier Systems,2000:1-15.
[119]Dietterich T G, Bakiri G. Solving multiclass learning problems via error-correcting output codes[J]. Journal of Artificial Intelligence Research.1995, 2(1995):263-286.
[120]Breiman L. Bagging predictors[J]. Machine Learning.1996,24(2): 123-140.
[121]Freund Y. Boosting a weak learning algorithm by majority[J]. Information and Computatio.1995,121(2):256-285.
[122]Freund Y, Schapire R E. A decision-theoretic generalization of on-line learning and an application to boosting[J]. Journal of Computer and System Sciences.1997,55(1):119-139.
[123]Opitz D W. Feature selection for ensembles[C]. The sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence, Orlando, Florida, United States,1999:379-384.
[124]Ho T K. The Random Subspace Method for Constructing Decision Forests[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1998,20(8):832-844.
[125]Guerra-Salcedo C, Whitley D. Genetic Approach to Feature Selection for Ensemble Creation[C]. The Genetic and Evolutionary Computation Conference, Orlando, Florida, USA,1999:236-243.
[126]Cunningham P, Carney J. Diversity versus quality in classification ensembles based on feature selection[C].11th European Conference on Machine Learning, Barcelona, Catalonia, Spain,2000:249-264.
[127]Oza N C, Turner K. Input Decimation Ensembles:Decorrelation through Dimensionality Reduction[C]. Second International Workshop on Multiple Classifier Systems, London, UK,2001:238-247.
[128]Bryll R, Gutierrez-Osuna R, Quek F. Attribute bagging:improving accuracy of classifier ensembles by using random feature subsets[J]. Pattern Recognition.2003,36(6):1291-1302.
[129]Kuncheva L I, Whitaker C J. Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy[J]. Machine Learning.2003, 51(2):181-207.
[130]Yule G U. On the Association of Attributes in Statistics[J]. Philosophical Transactions of the Royal Society of London.1900,194:257-319.
[131]Sneath P H A, Sokal R R. Numerical Taxonomy[J]. Nature.1962, 193(4818):855-860.
[132]Dietterich T G. An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees:Bagging, Boosting, and Randomization [J]. Machine Learning.2000,40(2):139-157.
[133]Giacinto G, Roli F. Design of Effective Neural Network Ensembles for Image Classification Purposes[J]. Image and Vision Computing.2001,19(9): 699-707.
[134]Hansen L K, Salamon P. Neural network ensembles[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.1990,12(10):993-1001.
[135]Tsymbal A, Pechenizkiy M, Cunningham P. Diversity in search strategies for ensemble feature selection[J]. Information Fusion.2005,6(1):83-98.
[136]Brown G, Wyatt J, Harris R. Diversity creation methods:a survey and categorisation[J]. Information Fusion.2005,6(1):5-20.
[137]Hu X. Using rough sets theory and database operations to construct a good ensemble of classifiers for data mining applications[C].2001 IEEE International Conference on Data Mining, San Jose, CA, USA,2001:233-240.
[138]Mei S Y, Liu Y, Wu G F. Rough reducts based SVM ensemble[C].2005 IEEE International Conference on Granular Computing, Beijing, China,2005: 571-574.
[139]Hu Q, Yua D, Xie Z. EROS:Ensemble rough subspaces[J]. Pattern Recognition.2007,40(12):3728-3739.
[140]Suraj Z, Gayar N E, Delimata P. A Rough Set Approach to Multiple Classifier Systems[J]. Fundamenta Informaticae.2006,72(1):393-406.
[141]Saha S, Murthy C A, Pal S K. Rough set Based Ensemble Classifier for Web Page Classification[J]. Fundamenta Informaticae.2007,76(1):171-187.
[142]Hu X. Ensembles of classifiers based on rough sets theory and set-oriented database operations[C].2006 IEEE International Conference on Granular Computing, Atlanta, USA,2006:67-73.
[143]Sun L, Han C, Lei M. Knowledge discovery-based multiple classifier fusion:a generalized rough set method[C].2006 9th International Conference on Information Fusion, Florence,2006:1-8.
[144]Dietterich T G. Machine Learning Research:Four Current Directions [J]. The AI Magazine.1997,18(4):97-136.
[145]常犁云,王国胤.一种基于Rough Set理论的属性约简及规则提取方法[J].软件学报.1999,10(11)：1206-1211.
[146]王国胤.决策表核属性的计算方法[J].计算机学报.2003,26(5)：611-615.
[147]Zhou Z, Wu J, Tang W. Ensembling neural networks:Many could be better than all[J]. Artificial Intelligence.2002,137(1):239-263.
[148]Shipp C A, Kuncheva L I. Relationships between combination methods and measures of diversity in combining classifiers [J]. Information Fusion.2002,3(2): 135-148.
[149]Zhou Z. Ensemle[M]. Encyclopedia of Database Systems,2009.
[150]Kevin Woods, W. Philip Kegelmeyer Jr., Bowyer K. Combination of multiple classifiers using local accuracy estimates[J]. IEEE transactions on pattern analysis and machine intelligence.1997,19(4):405-410.
[151]Giacinto G, Roli F. A Theoretical Framework for Dynamic Classifier Selection[C].15th International Conference on Pattern Recognition,2000:8-11.
[152]Giacinto G, Roli F. Dynamic Classifier Selection based on Multiple Classifier Behaviour[J]. Pattern Recognition.2001,34:1879-1881.
[153]征荆,丁晓青,吴佑寿.基于最小代价的多分类器动态集成[J].计算机学报.1999,22(2)：182-187.
[154]Zhou J, Wang G, Yang Y. Speech Emotion Recognition Based on Rough Set and SVM[C]. Fifth IEEE International Conference on Cognitive Informatics, 2006:53-61.
[155]周健.基于粗糙集和SVM的语音情感识别[D].硕士.西南交通大学,2007.
[156]韩一.情感识别中的语音信号处理研究[D].硕士.重庆邮电大学,2008.
[157]罗飞,王国胤,杨勇.一种基于Gabor小波特征的人脸表情识别新方法[J].计算机科学.2009,36(1)：181-183.