检索结果-内蒙古大学图书馆

IEEE International Conference on Data Mining Workshops (ICDM Workshops)

作者： Xiao Sun Chengcheng Li Wanyi Xu Fuji Ren Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei China School of Information Science and Engineering Southeast University Shanghai China Faculty of Engineering University of Tokushima Tokushima Japan

ISBN: (纸本)9781479942732

This paper presents a DBN (deep belief nets) model and a multi-modality feature extraction method to extend features' dimensionalities of short text for Chinese micro blogging sentiment classification. Besides traditional features sets for document classification, comments for certain posts are also extracted as part of the micro blogging features according to the relationship between commenters and posters though constructing micro blogging social network as input information. Then, the integration of the above modality features is combined and represented as input vector for DBN. In this paper, a DBN model, which is stacked with several layers of RBM (Restricted Boltzmann Machine), is implemented to initialize the structure of neural network. The RBM layers can take probability distribution samples of original data to learn hidden structures for better feature representation. A Class RBM (Classification RBM) layer, which is stacked on top of several RBM layers, is adapted to achieve the final sentiment classification. The results demonstrate that, with proper structure and parameter, the performance of the proposed deep learning method on sentiment classification is better than state of the art surface learning models such as SVM or NB, which proves that DBN is suitable for short-length document classification with the proposed feature dimensionality extension method.

关键词： Feature extraction Semantics Visualization Training Social network services Blogs Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Finding Emotional Focus for Emotion Recognition at Sentence Level

引用

电子学报(英文版) 2013年第1期22卷 99-103页

作者： QUAN Changqin REN Fuji Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei 230009 China Faculty of Engineering The University of Tokushima Tokushima Japan

Emotion recognition at sentence level is one of the fundamental problems of textual emotion un- derstanding. Based on the observation that sentence emo- tional focus can be expressed by some clauses in this sen- tence, this paper proposes to find the emotional focus for sentence emotion recognition. For the sake of breaking through the problems brought about by depending on emo- tion lexicons, we first recognize word emotions in a sen- tence based on Maximum entropy model. And then homo- geneous Markov model is built for clause emotion recogni- tion; After that, a strategy based on emotion selection is proposed for a sentence with multiple clauses, and genetic algorithm is used for clause selection by textual feature weighting. The experimental results show that, comparing with the baseline, there are 9.1% and 3.6% improvement respectively for two different evaluations. It is demon- strated that finding emotional focus by clause selection is able to improve the performance of sentence emotion recognition significantly.

关键词：情感识别句子层面聚焦马尔可夫模型最大熵模型特征加权遗传算法

来源：评论

学校读者我要写书评

暂无评论

On the α-universal multiple I restriction method for general fuzzy reasoning

On the α-universal multiple I restriction method for genera...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： Yiming Tang Xiaomei Li Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei P. R. China School of Computer and Information Hefei University of Technology Hefei P. R. China

Based on the differently implicational idea, the a-universal multiple I restriction method is put forward for general fuzzy reasoning, which contains the a-multiple I restriction method as its specific case. First of all, we give the a-universal multiple I restriction principle, which improves the previous restriction principle, and then provide the existing condition of the solutions of the new method. Furthermore, we obtain the optimal solution of the new method for the fuzzy implications with residual pair, the R-implications, as well as some particular fuzzy implications. Finally, it is found that the new method is more reasonable by contrast with the a-multiple I restriction method.

关键词： Fuzzy reasoning Fuzzy systems Educational institutions Bismuth Conferences Abstracts Laboratories

来源：评论

学校读者我要写书评

暂无评论

Facial expression recognition based on adaptive weighted fusion histograms

引用

9th International Conference on intelligent computing, ICIC 2013

作者： Hu, Min Xu, Yanxia Xu, Liangfeng Wang, Xiaohua College of Computer and Information Hefei University of Technology Hefei 230009 China Affective Computing and Advanced Intelligent Machines AnHui Key Laboratory Hefei 230009 China

ISBN: (纸本)9783642394812

In order to improve the performance of expression recognition, this paper proposes a facial expression recognition method based on adaptive weighted fusion histograms. Firstly, the method obtains expression sub-regions by pretreatment, and calculates the contribution maps (CM) of each expression sub-region. Secondly, this method extracts Histograms of Oriented Gradient by the Kirsch operator and extracts histograms of intensity by centralized binary pattern (CBP), then the paper fuses the Histograms by parallel manner and the fused histograms are weighted by CMs. At last, the weighted fused histograms are used to classify by the Euclidean Distance and the nearest neighbor method. Experimental results which are obtained by applying the proposed algorithm and the Gabor wavelet, LBP, LBP+LPP, Local Gabor and AAM on JAFFE face expression dataset show that the proposed method achieves better performance for the face expression recognition. © 2013 Springer-Verlag.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Multi-Modality Emotion Analysis of Chinese Microblogging

Multi-Modality Emotion Analysis of Chinese Microblogging

引用

2014 International Conference on Artificial,Intelligence and Software Engineering(AISE 2014)

作者： Xiao SUN Cheng-cheng LI Yong-an YU Xiao-li NAN Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer and Information Hefei University of Technology Dalian Informedia Electronic Co. Ltd. Dalian University of Technology AAVIC Jiangxi Hongdu Aviation Industry Group Corporation Limited

This paper presents a multi-modality feature extraction method based sentiment classification for Chinese microblogging. Human sentiment in microblogging is divided into three categories(positive, neutral, negative). Compared with traditional Chinese microblogging sentiment classification approaches, the method adopts the characteristics of microblogging social environment modality(including microblogging comments and relationships between commentators and micro-bloggers), while it extracts the microblogging text feature. The paper integrates the above two modality features and improve the performance of sentiment classification. At last, we model the feature sets by adopting fuzzy SVM model. The experimental results demonstrate the performance of the method on sentiment classification.

关键词： Emotion analysis Sentiment classification Multi-modality Sentiment fuzzy SVM

来源：评论

学校读者我要写书评

暂无评论

Speech emotion recognition using a novel feature set

引用

Journal of Computational Information Systems 2013年第15期9卷 6097-6104页

作者： Wang, Kunxia Li, Lian Yang, Jing Ren, Fuji Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei 230000 China School of Electricity and Information Engineering Anhui University of Architecture Hefei 230000 China

Speech emotion recognition has attracted attentions from increased number of researchers in Psychology, Computer science, Phonetics and related disciplines. This paper discusses combining multiple features for speech emotion recognition to yield improved performance. It proposes using combination of multiple features to improve recognition performance. Using ChineseLDC emotional database, the experiment results show that a novel feature set of MFCC, fundamental frequency, Δ MFCC, Δ Δ MFCC, energy, zero-crossing ratio and amplitude can get the best performance as 95% and 84% for emotional speech recognition of four emotional state and six emotional state. © 2013 Binary Information Press.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Mining Semantic Orientation of Multiword Expression from Chinese Microblogging with Discriminative Latent Model

Mining Semantic Orientation of Multiword Expression from Chi...

引用

International Conference on Asian Language Processing (IALP)

作者： Xiao Sun Chengcheng Li Chenyi Tang Fuji Ren Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei China

Extracting semantic orientation of Multiword Expression, especially some newly generated Multiword Expression from internet, is an important task for sentiment analysis of web texts or other real word text as some Multiword Expressions can express more integrative sentiments than words units. This paper proposes a method contains a novel latent discriminative algorithm, which attempts to attack this problem by integrating discriminative model and latent value model. Although Chinese Multiword Expressions consist of multiple words, the semantic orientation of the Multiword Expression is not just simple integration of orientations of the component words, as some words can invert the affective orientation so the Multiword Expressions can have totally opposite semantic orientation. In order to capture the property of such Multiword Expressions, hidden semi-CRF which includes a latent valuable layer, which can be used to address dual-sequence labeling tasks synchronously, is adopted. The method is tested experimentally by adopting a manually labeled set of positive and negative Multiword Expressions from microblog or other internet resources, and the experiments have shown very promising results, which is comparable to the best value ever reported.

关键词： Semantics Dictionaries Feature extraction Computational modeling Labeling Tagging Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Facial expression recognition algorithm based on feature fusion adaptive weighted HLAC

Facial expression recognition algorithm based on feature fus...

引用

IEEE/SICE International Symposium on System Integration

作者： Rui Li Zhuguo Yu Min Hu Zhong Huang Fuji Ren Institute of Intelligent Machines(IIM) Chinese Academy of Sciences School of Computer and Information Affective Computing and Advanced Intelligent Machines AnHui Key Laboratory Hefei China Japan Federation of Engineering Societies University of Tokushima Shinkura-cho Tokushima Japan

In this paper, a novel method of facial expression recognition based on adaptive weighted higher-order local autocorrelation coefficient (WHLAC) is presented. Firstly, The method gets whole face region and sub-regions of eyebrows, eyes, nose and mouth. Secondly, the global features of the face regions and local features of the sub-regions are extracted by HLAC, the weights of sub-regions are calculated by fisher linear discriminant (FLD), and then these two parts features are fused together by the weights. Finally, the fused features are classified by FLD. The experimental results show that the proposed method has higher recognition rate and lower computational cost than Gabor, WLBP, HLAC for facial expression recognition.

关键词： Feature extraction Face recognition Eyebrows Nose Mouth Educational institutions Correlation

来源：评论

学校读者我要写书评

暂无评论

Facial expression recognition based on multi-scale vector triangle

Facial expression recognition based on multi-scale vector tr...

引用

IEEE/SICE International Symposium on System Integration

作者： He Jiang Min Hu Hongbo Chen Kun Li Xiaohua Wang Fuji Ren School of Computer and Information Affective Computing and Advanced Intelligent Machines AnHui Key Laboratory Hefei China Fellow of the Japan Federation of Engineering Societies University of Tokushima Shinkura-cho Tokushima Japan

Image description is not sufficient in traditional facial expression recognition (FER) methods, therefore this paper proposes a FER method based on multi-scale vector triangle. It combines vector triangle pattern with image pyramid to extract facial expression features. Firstly, construct a facial image pyramid to produce images in different scales. Secondly, divide each image into blocks, and extract vector triangle features of each sub-image. Then, use histogram to statistical characteristics, and calculate Euclidean distance between the histograms. Finally, fusion weighted eigenvalues and come to the recognition results. Multi-scale vector triangle pattern can not only avoid the loss of information in image asymmetric regions, but also reflect image features in different scales. It can describe images more adequately. In order to verify the effectiveness of the algorithm, this paper uses the Japanese Female Facial Expression (JAFFE) database to do the experiments and compare the results with Complete Local Binary Patterns (CLBP), Gabor wavelet, Active Appearance Models (AAM) and so on. Experimental results indicate that this method has higher recognition rate and better real-time effect.

关键词： Vectors Feature extraction Face recognition Conferences Databases Histograms affective computing

来源：评论

学校读者我要写书评

暂无评论

Reduce the dimensions of emotional features by principal component analysis for speech emotion recognition

Reduce the dimensions of emotional features by principal com...

引用

IEEE/SICE International Symposium on System Integration

作者： Changqin Quan Dongyu Wan Bin Zhang Fuji Ren AnHui Province Key laboratory of Affective Computing and Advanced Intelligent Machine HeFei University of Technology HeFei China The School of Computer and Information HeFei University of Technology HeFei China

In this paper, the principal component analysis (PCA) is applied to speech emotion recognition for improving the accuracy of the system. The traditional prosodic features like pitch-related features and formant-related features are extracted from the Berlin speech database [7] and a Chinese database. These collected feature data is processed by PCA to remove the irrelevant information. After that, three kinds of features including the processed features by PCA, unprocessed features and other speech-related features are used to train a SVM classifier. And six emotions are tested in the experiment. The classification accuracy of the processed features by PCA is about 3.1% higher than the unprocessed features and about 17.6% higher than the MFCC features when using 240 utterances. The recognition accuracies among different emotions in both databases are also presented in the study.

关键词： Speech Speech recognition Principal component analysis Emotion recognition Feature extraction Accuracy Databases

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：