检索结果-内蒙古大学图书馆

IEEE International Conference on Cloud computing and Intelligence Systems (CCIS)

作者： Min Hu Yaona Zheng Fuji Ren He Jiang School of Computer and Information Hefei University of Technology Anhui China Affective Computing and Advanced Intelligent Machines Anhui Key Laboratory The University of Tokushima Japan

ISBN: (纸本)9781467369541

In order to improve shortage of Local Binary Pattern (LBP) algorithm in the field of facial feature extraction, this paper uses Local Directional Pattern (LDP) algorithm to extract the facial features about age estimation and gender classification. Because gradient information is more stable than gray information, LDP algorithm is not affected easily by noise. After preprocessing images, we use block strategy to represent facial features more fully. And then, we extract features of each block with LDP algorithm, storing the LDP histogram. Finally, we obtain age and gender identification results by Support Vector machine (SVM). Experimental results on FG-NET face database show that this method has a good effect on age estimation and gender classification.

关键词： Face Feature extraction Estimation Interference Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Chinese Microblog Sentiment Classification Based on Deep Belief Nets with Extended Multi-Modality Features

Chinese Microblog Sentiment Classification Based on Deep Bel...

引用

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

FACE RECOGNITION BASED ON ADAPTIVE WEIGHTING AND FUZZY FUSION WITH SINGLE TRAINING SAMPLE

FACE RECOGNITION BASED ON ADAPTIVE WEIGHTING AND FUZZY FUSIO...

引用

2014 IEEE 3rd International Conference on Cloud computing and Intelligence Systems

作者： Xiaohua Wang Chao Jin Wei Liu Min Hu Fuji Ren Affective Computing and Advanced Intelligent Machines Anhui Key Laboratory School of Computer and Information Hefei University of Technology The University of Tokushima 770-8506Japan

In order to solve the robustness issues for single training sample face recognition under occlusion conditions,this paper presents a recognition method based on adaptive weighting and fuzzy *** our method,the information entropy expansion mode is introduced in sub-mode method and via adaptively assigning the weights corresponding to each sub-model can reduce the impact of occluded *** addition,through summing the similar blocks in face images can make up for the defect of the sub-model which ignores the integrity of ***,the method based on fuzzy comprehensive evaluation is utilized for decision-level fusion to the outputs by these two ways of *** results on AR face database show that this method has state-of-the-art classification accuracy and also robustness to occlusion.

关键词： Face recognition Single training sample Adaptive weighting Fuzzy comprehensive evaluation Sub-model

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE FACIAL EXPRESSION RECOGNITION METHOD BASED ON MBP AND HMOG FEATURE

ADAPTIVE FACIAL EXPRESSION RECOGNITION METHOD BASED ON MBP A...

引用

2014 IEEE 3rd International Conference on Cloud computing and Intelligence Systems

作者： Min Hu Xiaoyin Huang Xiaohua Wang Kun Li Fuji Ren Liangfeng Xu Affective Computing and Advanced Intelligent Machines Anhui Key Laboratory School of Computer and Information Hefei University of Technology The University of Tokushima 770-8506Japan

Because of the limitation of Monogenic waves’ extraction from expression texture,this thesis proposes an adaptive facial expression feature fusion method based on MBP（monogenic binary pattern） and Histogram of HMOG（monogenic orientated gradients）.To begin with our method,we get information of orientation,phase and magnitude component from filtered image by monogenic waves,besides,extract and fuse texture information from orientation and magnitude component to recognize facial *** single texture feature have some inadequacies for facial expression *** of all,this paper describes a new kind of HMOG feature inspired by thoughts of HOG（histogram of oriented gradients） to indicate shape information of facial ***,acquiring best adaptive weights of expression block through information ***,we classify the expression image using Nearest Neighbor to get the final result of effect of proposed *** order to verify the efficiency of the methods above,we do a large number of experiments and it turns out our methods have great ability to explain expression feature.

关键词： Monogenic signal Histogram of Monogenic Oriented Gradients Adaptive weights by information entropy Nearest Neighbor

来源：评论

学校读者我要写书评

暂无评论

AGE ESTIMATION AND GENDER CLASSIFICATION OF FACIAL IMAGES BASED ON LOCAL DIRECTIONAL PATTERN

AGE ESTIMATION AND GENDER CLASSIFICATION OF FACIAL IMAGES BA...

引用

2014 IEEE 3rd International Conference on Cloud computing and Intelligence Systems

作者： Min Hu Yaona Zheng Fuji Ren He Jiang Affective Computing and Advanced Intelligent Machines Anhui Key Laboratory School of Computer and Information Hefei University of Technology The University of Tokushima 770-8506Japan

In order to improve shortage of Lxical Binary Pattern(LBP) algorithm in the field of facial feature extraction,this paper uses Lxical Directional Pattern(LDP) algorithm to extract the facial features about age estimation and gender *** gradient information is more stable than gray information,LDP algorithm is not affected easily by *** preprocessing images,we use block strategy to represent facial features more *** then,we extract features of each block with LDP algorithm,storing the LDP histogram Finally,we obtain age and gender identification results by Support Vector machine(SVM).Experimental results on FG-NET face database show that this method has a good effect on age estimation and gender classification.

关键词： feature extraction,LDP,age estimation,gender classification

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

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

FACE RECOGNITION BASED ON DOUBLE COMPLEMENTARY SPACE AND MULTI-DECISION CLASSIFICATION

FACE RECOGNITION BASED ON DOUBLE COMPLEMENTARY SPACE AND MUL...

引用

2014 IEEE 3rd International Conference on Cloud computing and Intelligence Systems

作者： Fuji Ren Yanqiu Li Liangfeng Xu Min Hu Xiaohua Wang Affective Computing and Advanced Intelligent Machines Anhui Key Laboratory School of Computer and Information Hefei University of Technology Faculty of Engineering The University of Tokushima770-8506TokushimaJapan

In order to overcome the one-sidedness and limitations of a single subspace in feature extraction and classification,we propose a face recognition method that extracts features in double complementary space and utilize multi-decision for *** the feature extraction stage,we use ICA and LPE algorithm as the first layer in complementary space to extract global and local features of the face ***,for the purpose of solving the problem that features extracted by ICA are lack of classification information,we further extract classification information from the independent features extracted by ICA on the condition that the FLDA and DCV algorithm are used as the second layer in the complementary *** the classification stage,the test samples are firstly projected to the independent *** that,projected the samples which are difficult to identify to the LPE space and reclassified ***,the results are been determined *** results on ORL database show that the proposed method can effectively improve the recognition rate.

关键词： algorithms complementary space multi-decision classification face recognition

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：