检索结果-内蒙古大学图书馆

5th International Conference on computing Communication and Networking Technologies, ICCCNT 2014

作者： Sun, Xiao Li, Chengcheng Ye, Jiaqi Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer and Information Hefei University of Technology Hefei230009 China

ISBN: (纸本)9781479926961

Through the analysis and study of the emotional characteristics in Chinese micro-blog, this paper proposed a multidimensional sentiment classification method based micro-blog emotion classification, emoticon in micro-blog is adopted to train the support vector machine and divide micro-blog into seven types of emotions: happiness, fondness, sorrow, anger, fear, detestation and surprise. We used micro-blog emoticon to initial screen large-scale unmarked data, and automatically labeled them into seven types, then used this emotional corpus as training set to train the emotion classifier to classify micro-blog data into multiple emotion categories. The experimental results show that precision of unigram model for each type can reach 63.7%. Meanwhile, different feature selection methods for support vector machines and Naive Bayes classifier experiment have been adopted in the experiment, the precision and recall has reached more than 71%. © 2014 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Investigation of tibialis anterior muscle activation patterns during walking on different terrains

Investigation of tibialis anterior muscle activation pattern...

引用

2015 IET International Conference on Biomedical Image and Signal Processing, ICBISP 2015

作者： Zhou, Hui Wang, Yingying Ji, Ning Zhang, Haoshi Wang, Hui Chen, Shixiong Li, Guanglin Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen Guangdong518005 China

ISBN: (纸本)9781785610448

Trapezoidal stimulation profile has been used for many years in clinical applications to activate the weak tibialis anterior muscle during gait for correcting foot drop. However, this stimulation profile could not well adapt to the different types of terrain, such as level ground, upstairs and downstairs. Thus an environment aware and adaptive stimulation mode would be needed to help drop foot patients walk normally in various environments. As a part of this new stimulation system, tibialis anterior (TA) muscle activation pattern during different locomotion modes were investigated in this study. Foot pressure signals from four force sensitive resistor (FSR) and TA muscle electromyogram (EMG) signal were recorded during gait from five normal subjects. Then the averaged TA muscle activation patterns for level ground, upstairs and downstairs were calculated from the EMG signals in the study, respectively. The results of the study could provide some helpful suggestions on how to design a suitable stimulation envelope for walking over different terrains.

关键词： Muscle

来源：评论

学校读者我要写书评

暂无评论

On Simple Perturbation of the α-Universal Triple I Algorithm via Specific Interval Implication Operators 1

引用

3rd International Conference on Artificial intelligence Logic and Applications, AILA 2023

作者： Tang, Yiming Guo, Anyi Zhang, Li Gao, Jianwei Li, Shujie Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer and Information Hefei University of Technology Hefei230601 China

ISBN: (数字)9789819978694

ISBN: (纸本)9789819978687

Fuzzy reasoning aims to describe things with fuzzy and uncertain concepts and convert them into information that computers can process. Wang thought that the inference algorithm based on Compositional Rule of Inference (CRI) had certain defective nature and proposed the triple I algorithm with fully implication operator. Later, the α-universal triple I (α-UTI) algorithm was proposed. As an important part of the fuzzy inference algorithm, the implication operator directly affects the robustness of the inference algorithm, that is, affects the quality of the inference algorithm. Besides, the quality of fuzzy reasoning algorithm can be partly determined by the robustness of reasoning algorithm. In this paper, the ordinary implication operator is extended to a more general interval implication operator. And the simple perturbation of the α-UTI algorithm is studied for some specific interval implication operators under the interval-valued environment. It is observed that the α-UTI algorithm possesses good simple perturbation performance for single rule or multi-rules, in which specific interval implications are used. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Fuzzy inference

来源：评论

学校读者我要写书评

暂无评论

On-line dynamic gait generation model for wearable robot with user's motion intention

On-line dynamic gait generation model for wearable robot wit...

引用

2018 IEEE International Conference on Information and Automation, ICIA 2018

作者： Ren, Hao Liu, Du-Xin Li, Niannian He, Yong Yan, Zefeng Wu, Xinyu CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518000 China

ISBN: (纸本)9781538680698

In this paper, an on-line dynamic gait generation model is proposed, which makes it possible to plan real-time gait trajectories in continuous motion process online. The model enables wearers to perform complex movements in different scenes with the help of an exoskeleton robot. Meanwhile, based on multi-sensor fusion, a method is designed to detect the wearers' movement intention. The gait trajectories generated by the proposed algorithm are applied to the lightweight lower-limb exoskeleton robot (LLEX). The experimental results show that the algorithm can accurately and effectively plan wearers' movement trajectories of lower limbs, and freely perform various gait patterns, indicating the described algorithm is credible enough to generate dynamic gait patterns for wearable exoskeleton robots. © 2018 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Towards privacy-preserving and efficient word vector learning for lightweight IoT devices

引用

Digital Communications and Networks 2024年第4期10卷 895-903页

作者： Nan Jia Shaojing Fu Guangquan Xu Kai Huang Ming Xu National University of Defense Technology ChangshaChina Big Data School Qingdao Huanghai UniversityQingdaoChina Tianjin Key Laboratory of Advanced Networking College of Intelligence and ComputingTianjin UniversityTianjinChina College of Joint Operations National Defense UniversityShijiazhuangChina

Nowadays,Internet of Things(IoT)is widely deployed and brings great opportunities to change people's daily *** realize more effective human-computer interaction in the IoT applications,the Question Answering(QA)systems implanted in the IoT services are supposed to improve the ability to understand natural ***,the distributed representation of words,which contains more semantic or syntactic information,has been playing a more and more important role in the QA ***,learning high-quality distributed word vectors requires lots of storage and computing resources,hence it cannot be deployed on the resource-constrained IoT *** is a good choice to outsource the data and computation to the cloud ***,it could cause privacy risks to directly upload private data to the untrusted ***,realizing the word vector learning process over untrusted cloud servers without privacy leakage is an urgent and challenging *** this paper,we present a novel efficient word vector learning scheme over encrypted *** first design a series of arithmetic computation *** we use two non-colluding cloud servers to implement high-quality word vectors learning over encrypted *** proposed scheme allows us to perform training word vectors on the remote cloud servers while protecting *** analysis and experiments over real data sets demonstrate that our scheme is more secure and efficient than existing privacy-preserving word vector learning schemes.

关键词： Privacy-preserving Word vector learning Secret sharing Internet of things

来源：评论

学校读者我要写书评

暂无评论

Amplitude Consistent Enhancement for Speech Dereverberation 20

Amplitude Consistent Enhancement for Speech Dereverberation

引用

6th International Conference on computing and Artificial intelligence, ICCAI 2020

作者： Liu, Chunlei Wang, Longbiao Dang, Jianwu Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin300350 China Japan Advanced Institute of Science and Technology Ishikawa9231292 Japan

ISBN: (纸本)9781450377089

The mapping and masking methods based on deep learning are both essential methods for speech dereverberation at present, which typically enhance the amplitude of the reverberant speech while letting the reverberant phase unprocessed. The reverberant phase and enhanced amplitude are used to synthesize the target speech. However, because the overlapping frames interfere with each other during the superposition process (overlap-and-add), the final synthesized speech signal will deviate from the ideal value. In this paper, we propose an amplitude consistent enhancement method (ACE) to solve this problem. With ACE to train the deep neural networks (DNNs), we use the difference between amplitudes of the synthesized and clean speech as the loss function. Also, we propose a method of adding an adjustment layer to improve the regression accuracy of DNN. The speech dereverberation experiments show that the proposed method has improved the PESQ and SNR by 5% and 15% compared with the traditional signal approximation method. © 2020 ACM.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

machine translation approach for Chinese whole-sentence Pinyin-to-character conversion

Machine translation approach for Chinese whole-sentence Piny...

引用

26th Pacific Asia Conference on Language, Information and Computation, PACLIC 2012

作者： Yang, Shaohua Zhao, Hai Lu, Bao-Liang MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Center for Brain-Like Computing and Machine Intelligence Shanghai Jiao Tong University 800 Dongchuan Road Shanghai 200240 China

ISBN: (纸本)9789791421171

This paper introduces a new approach to solve the Chinese Pinyin-to-character (PTC) conversion problem. The conversion from Chinese Pinyin to Chinese character can be regarded as a transformation between two different languages (from the Latin writing system of Chinese Pinyin to the character form of Chinese,Hanzi), which can be naturally solved by machine translation framework. PTC problem is usually regarded as a sequence labeling problem, however, it is more difficult than any other general sequence labeling problems, since it requires a large label set of all Chinese characters for the labeling task. The essential difficulty of the task lies in the high degree of ambiguities of Chinese characters corresponding to Pinyins. Our approach is novel in that it effectively combines the features of continuous source sequence and target sequence. The experimental results show that the proposed approach is much faster, besides, we got a better result and outperformed the existing sequence labeling approaches. © 2012 The PACLIC.

关键词： machine translation

来源：评论

学校读者我要写书评

暂无评论

Flatten hierarchies for large-scale hierarchical text categorization

Flatten hierarchies for large-scale hierarchical text catego...

引用

International Conference on Digital Information Management

作者： Wang, Xiao-Lin Lu, Bao-Liang Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University China

ISBN: (纸本)9781424475728

Hierarchies are very popular in organizing documents and web pages, hence automated hierarchical classification techniques are desired. However, the current dominant hierarchical approach of top-down method suffers accuracy decrease compared with flat classification approaches, because of error propagation and bottom nodes' data sparsity. In this paper we flatten hierarchies to relieve such accuracy decrease in top-down method, which aims to make hierarchies both effective enough to make large-scale classification tasks feasible, and simple enough to ensure high classification accuracy. We propose two flattening strategies based on these two causes of the accuracy decrease, and experimental results show that the flattening strategy designed for error propagation is more effective, which suggests that hierarchies with lots of branches at top layers can provide high classification accuracy. Besides, we analyze the computational complexity before and after flattening, which approximately agree with the experimental results. ©2010 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Attention-Guided Siamese Network for Clothes-Changing Person Re-identification 11th

Attention-Guided Siamese Network for Clothes-Changing Person...

引用

11th International Conference on Image and Graphics, ICIG 2021

作者： Feng, Zhanxiang Huang, Sien Lai, Jianhuang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangzhou Xinhua University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China

ISBN: (纸本)9783030873578

Person re-identification (re-id) has achieved significant progresses in recent years. However, the existing methods generally assume that the clothes of pedestrians remain unchanged throughout the surveillance periods, which is contradict to realistic environment where pedestrians may change their clothes. Current re-id techniques may encounter a dramatic performance degradation when the pedestrians change the clothes. In this paper, we propose a novel attention-guided siamese network (AGS-Net) to solve the cross-clothes re-id challenge. The AGS-Net integrates the visual and contour information together by developing a dual-branch structure, among which one extracts powerful features from raw inputs while the other learns robust features from the sketch image. Moreover, we exploit the attention modules to emphasize reliable identity-related features considering changing clothes and avoid generating features sensitive to clothes. Specifically, we propose a clothes-change invariant constraint to learn clothes-invariant features. Experimental results verify the effectiveness of our approach. © 2021, Springer Nature Switzerland AG.

关键词： Computers

来源：评论

学校读者我要写书评

暂无评论

Memory-Guided Contrastive and Triplet Separation for Weakly-Supervised Disease Detection

Memory-Guided Contrastive and Triplet Separation for Weakly-...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： She, Jinwen Li, Qiong Ma, Andy J. Sun Yat-sen University Cancer Center Guangzhou China Sun Yat-sen University School of Computer Science and Engineering Guangzhou China Ministry of Education Guangdong Province Key Laboratory of Information Security Technology Key Laboratory of Machine Intelligence and Advanced Computing China

ISBN: (纸本)9798350386226

Weakly-supervised disease detection has the great potential to alleviate the time-consuming and labor-intensive burden of manual annotations in instance level. While existing methods extract normality prototypes encoding normal patterns to improve the detection performance, they may fail to detect subtle anomalies without considering the diverse abnormal patterns. In this paper, we propose to recognize both normal and abnormal patterns for feature representation learning in disease detection based on a dual memory network. To learn discriminative memory banks and classifiers, dual memory loss is incorporated with a feature magnitude separation loss for model training. With the proposed contrastive feature separation loss and triplet feature separation loss, feature discriminability is further improved to obtain a more separable decision boundary. Additionally, we collect a large-scale CT dataset to evaluate lung tumor detection. Extensive experiments on the publicly available PANDA-MIL dataset and the collected LUNG-MIL dataset demonstrate the superiority of our proposed method compared to the state-of-the-art approaches for weakly-supervised disease detection. © 2024 IEEE.

关键词： Contrastive Learning

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：