检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ragab, Mohamed Gong, Peiliang Eldele, Emadeldeen Zhang, Wenyu Wu, Min Foo, Chuan-Sheng Zhang, Daoqiang Li, Xiaoli Chen, Zhenghua Singapore The Key Laboratory of Brain-Machine Intelligence Technology Ministry of Education College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China Singapore138632 Singapore

Source-free domain adaptation (SFDA) aims to adapt a model pre-trained on a labeled source domain to an unlabeled target domain without access to source data, preserving the source domain’s privacy. While SFDA is prevalent in computer vision, it remains largely unexplored in time series analysis. Existing SFDA methods, designed for visual data, struggle to capture the inherent temporal dynamics of time series, hindering adaptation performance. This paper proposes MAsk And imPUte (MAPU), a novel and effective approach for time series SFDA. MAPU addresses the critical challenge of temporal consistency by introducing a novel temporal imputation task. This task involves randomly masking time series signals and leveraging a dedicated temporal imputer to recover the original signal within the learned embedding space, bypassing the complexities of noisy raw data. During subsequent adaptation, the imputer network guides the target model to generate target features that exhibit temporal consistency with the source features. Notably, MAPU is the first method to explicitly address temporal consistency in the context of time series SFDA. Additionally, it offers seamless integration with existing SFDA methods, providing greater flexibility. We further introduce E-MAPU, which incorporates evidential uncertainty estimation to address the overconfidence issue inherent in softmax predictions. To achieve that, we leverage evidential deep learning to obtain a better-calibrated pre-trained model and identify out-of-support target samples (those falling outside the source domain’s support) by predicting them with higher entropy than source samples. During adaptation, the target classifier remains fixed while the feature extractor is trained to minimize the evidential entropy of out-of-support target samples. This is achieved by adapting the target encoder to map these samples to a new feature representation closer to the source domain’s support. This fosters better alignment, ultimately

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Automatic Construction of Parallel Algorithm Portfolios for Multi-objective Optimization

arXiv

引用

arXiv 2022年

作者： Ma, Xiasheng Liu, Shengcai Hong, Wenjing School of Mechanical Engineering University of Science and Technology Beijing Beijing100083 China Beijing Key Laboratory of Research and Application for Robotic Intelligence of Hand-Eye-Brain Interaction Beijing100083 China Singapore Guangdong Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Guangdong Shenzhen518055 China

It has been widely observed that there exists no universal best Multi-objective Evolutionary Algorithm (MOEA) dominating all other MOEAs on all possible Multi-objective Optimization Problems (MOPs). In this work, we advocate using the Parallel Algorithm Portfolio (PAP), which runs multiple MOEAs independently in parallel and gets the best out of them, to combine the advantages of different MOEAs. Since the manual construction of PAPs is non-trivial and tedious, we propose to automatically construct high-performance PAPs for solving MOPs. Specifically, we first propose a variant of PAPs, namely MOEAs/PAP, which can better determine the output solution set for MOPs than conventional PAPs. Then, we present an automatic construction approach for MOEAs/PAP with a novel performance metric for evaluating the performance of MOEAs across multiple MOPs. Finally, we use the proposed approach to construct a MOEAs/PAP based on a training set of MOPs and an algorithm configuration space defined by several variants of NSGA-II. Experimental results show that the automatically constructed MOEAs/PAP can even rival the state-of-the-art ensemble MOEAs designed by human experts, demonstrating the huge potential of automatic construction of PAPs in multi-objective optimization. Copyright © 2022, The Authors. All rights reserved.

关键词： Parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Tuning In to Neural Encoding: Linking Human brain and Artificial Supervised Representations of Language

arXiv

引用

arXiv 2023年

作者： Sun, Jingyuan Zhang, Xiaohan Moens, Marie-Francine Department of Computer Science KU Leuven Belgium Institute of Neuroscience Key Laboratory of Primate Neurobiology CAS Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences China

To understand the algorithm that supports the human brain’s language representation, previous research has attempted to predict neural responses to linguistic stimuli using embeddings generated by artificial neural networks (ANNs), a process known as neural encoding. However, most of these studies have focused on probing neural representations of Germanic languages, such as English, with unsupervised ANNs. In this paper, we propose to bridge the gap between human brain and supervised ANN representations of the Chinese language. Specifically, we investigate how task tuning influences a pretained Transformer for neural encoding and which tasks lead to the best encoding performances. We generate supervised representations on eight Natural Language Understanding (NLU) tasks using prompt-tuning, a technique that is seldom explored in neural encoding for language. We demonstrate that prompt-tuning yields representations that better predict neural responses to Chinese stimuli than traditional fine-tuning on four tasks. Furthermore, we discover that tasks that require a fine-grained processing of concepts and entities lead to representations that are most predictive of brain activation patterns. Additionally, we reveal that the proportion of tuned parameters highly influences the neural encoding performance of fine-tuned models. Overall, our experimental findings could help us better understand the relationship between supervised artificial and brain language representations. Copyright © 2023, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

GaitSet: Cross-view gait recognition through utilizing gait as a deep set

arXiv

引用

arXiv 2021年

作者： Chao, Hanqing Wang, Kun He, Yiwei Zhang, Junping Feng, Jianfeng The Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200438 China The Institute of Science and Technology for Brain-inspired Intelligence Fudan University China

Gait is a unique biometric feature that can be recognized at a distance;thus, it has broad applications in crime prevention, forensic identification, and social security. To portray a gait, existing gait recognition methods utilize either a gait template which makes it difficult to preserve temporal information, or a gait sequence that maintains unnecessary sequential constraints and thus loses the flexibility of gait recognition. In this paper, we present a novel perspective that utilizes gait as a deep set, which means that a set of gait frames are integrated by a global-local fused deep network inspired by the way our left- and right-hemisphere processes information to learn information that can be used in identification. Based on this deep set perspective, our method is immune to frame permutations, and can naturally integrate frames from different videos that have been acquired under different scenarios, such as diverse viewing angles, different clothes, or different item-carrying conditions. Experiments show that under normal walking conditions, our single-model method achieves an average rank-1 accuracy of 96.1% on the CASIA-B gait dataset and an accuracy of 87.9% on the OU-MVLP gait dataset. Under various complex scenarios, our model also exhibits a high level of robustness. It achieves accuracies of 90.8% and 70.3% on CASIA-B under bag-carrying and coat-wearing walking conditions respectively, significantly outperforming the best existing methods. Moreover, the proposed method maintains a satisfactory accuracy even when only small numbers of frames are available in the test samples;for example, it achieves 85.0% on CASIA-B even when using only 7 frames. The source code has been released at https://***/AbnerHqC/GaitSet. Copyright © 2021, The Authors. All rights reserved.

关键词： Gait analysis

来源：评论

学校读者我要写书评

暂无评论

SMALL-FOOTPRINT CONVOLUTIONAL NEURAL NETWORK FOR SPOOFING DETECTION

SMALL-FOOTPRINT CONVOLUTIONAL NEURAL NETWORK FOR SPOOFING DE...

引用

International Joint Conference on Neural Networks

作者： Heinrich Dinkel Yanmin Qian Kai Yu Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University

ISBN: (纸本)9781509061839

Albeit recent progress in speaker verification engendered powerful models, malicious attacks in the form of spoofed speech, are generally not coped with. In previous attempts, deep neural networks were used to extract high dimensional features which were later classified using an independent classifier. Even though the results of this approach are promising, this architecture's disadvantage is it's complexity of optimizing both, neural network and back-end classifier. In this paper we present a simplified neural network approach to address this problem based on the convolutional neural network architecture. Our model concatenates the output of all abstract convolutional representations within the network into a single high-dimensional vector. By preserving all the information within the network, the networks generalization capabilities are greatly enhanced, resulting in an favorable error rate of 5.4% on the S10 condition. Scores are frame wise obtained by directly extracting the posteriors from the output neurons and further reduced to an utterance score by the use of variance reduction. We show that by using variance posterior score reduction, large performance gains can be achieved. This model outperforms standard feature extracting neural network approaches, in addition on being more versatile, robust and faster to train. Our best model achieves an error rate of 0.7% on the ASVspoof corpus, utilizing common PLP features. It significantly outperforms conventional feature extraction neural networks, while only having 100k parameters.

关键词： Neural network Error analysis Feature extraction speaker recognition Classifiers Information Network neural net architecture

来源：评论

学校读者我要写书评

暂无评论

GLEU-guided Multi-Resolution Network for Short Text Conversation

GLEU-guided Multi-Resolution Network for Short Text Conversa...

引用

第十四届全国人机语音通讯学术会议

作者： Xuan Liu Kai Yu Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University

With the recent development of sequence-to-sequence framework,generation approach for short text conversation becomes *** sequence-to-sequence method for short text conversation often suffers from dull response ***-resolution generation approach has been introduced to address this problem by dividing the generation process into two steps:keywords-sequence generation and response ***,this method still tends to generate short and common *** this work,a new multi-resolution generation framework is *** of using the word-level maximum likelihood criterion,we optimize the sequence-level GLEU score of the entire generated keywords-sequence using a policy gradient approach in reinforcement *** show that the proposed approach can generate longer and more diverse ***,it achieves better score in human evaluation.

关键词： short text conversation sequence-to-sequence policy gradient

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition Using Support Vector Machine and Deep Neural Network

Emotion Recognition Using Support Vector Machine and Deep Ne...

引用

第十四届全国人机语音通讯学术会议

作者： Chen Ruinian Zhou Ying Qian Yanmin Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering SpeechLab Department of Computer Science and Engineering Brain Science and Technology Research Center Shanghai Jiao Tong University

We propose a classification system which is a combination of three subsystem to solve the speech emotion recognition *** first subsystem utilizes support vector machines(SVMs) to classify the features *** second subsystem utilizes deep neural networks(DNNs) to classify the features *** the third subsystem,we utilize DNNs to extract high level features from raw data and show that they are effective for speech emotion *** first produce an emotion state probability distribution for each speech segment using DNNs,then we construct utterance-level features from segment-level probability *** utterance level features are fed into an SVM to identify utterance-level *** experimental results show that all the subsystems are outperform the HMM baseline system,and the combined system get the best result on F-score.

关键词： Emotion recognition Deep neural networks Support vector machine

来源：评论

学校读者我要写书评

暂无评论

Superpixelwise Low-rank Approximation based Partial Label Learning for Hyperspectral Image Classification

arXiv

引用

arXiv 2024年

作者： Yang, Shujun Zhang, Yu Ding, Yao Hong, Danfeng Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Peng Cheng Laboratory Shenzhen518055 China School of Optical Engineering Xi'an Research Institute of High Technology Xi’an710025 China Key Laboratory of Digital Earth Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China

Insufficient prior knowledge of a captured hyperspectral image (HSI) scene may lead the experts or the automatic labeling systems to offer incorrect labels or ambiguous labels (i.e., assigning each training sample to a group of candidate labels, among which only one of them is valid;this is also known as partial label learning) during the labeling process. Accordingly, how to learn from such data with ambiguous labels is a problem of great practical importance. In this paper, we propose a novel superpixelwise low-rank approximation (LRA)- based partial label learning method, namely SLAP, which is the first to take into account partial label learning in HSI classification. SLAP is mainly composed of two phases: disambiguating the training labels and acquiring the predictive model. Specifically, in the first phase, we propose a superpixelwise LRA-based model, preparing the affinity graph for the subsequent label propagation process while extracting the discriminative representation to enhance the following classification task of the second phase. Then to disambiguate the training labels, label propagation propagates the labeling information via the affinity graph of training pixels. In the second phase, we take advantage of the resulting disambiguated training labels and the discriminative representations to enhance the classification performance. The extensive experiments validate the advantage of the proposed SLAP method over state-of-the-art methods. © 2024, CC BY.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Research on EEG Signal Classification Method Based on brain-computer interface Control of Rehabilitation Robot

Research on EEG Signal Classification Method Based on Brain-...

引用

Rehabilitation Engineering and Assistive technology (i-CREATe), International Convention on

作者： Yiwen Zhang Wenzhi Wang Gan Liu Yi Qiao Ruochuan Shi Yahan Duan Ying Du Sining Li Fengrui Guo Thomas John McHugh Feng Duan Tianjin key Laboratory of Interventional Brain-Computer Interface and Intelligent Rehabilitation Nankai University Tianjin P. R. China Laboratory for Circuit and Behavioral Physiology RIKEN Center for Brain Science Wakoshi Saitama Japan Department of Life Sciences Graduate School of Arts and Sciences The University of Tokyo Tokyo Japan

ISBN: (数字)9798350355154

ISBN: (纸本)9798350355161

brain-computer interface (BCI) control of multiple rehabilitation robots provides a novel type of human-robot interaction and an important research direction in the field of intelligent rehabilitation. However, most current EEG signal classification algorithms for controlling rehabilitation robots exhibit several drawbacks, including a lack of novelty, insufficient classification accuracy and poor adaptability to different experimental paradigms. Therefore, we designed a new deep-learning method to classify EEG signals to enhance the effectiveness of BCI control of rehabilitation robots. Here we apply this method to classify EEG signals and control the rehabilitation robot to accomplish a target task. In addition, we compare our algorithm with several different EEG signal classification algorithms in two experimental paradigms: motor imagery and motor execution. Our deep learning method has the highest offline accuracy of 72.7% and an average accuracy of 72.4% under the motor imagery experimental paradigm, and the highest offline accuracy of 97.5% and an average accuracy of 90.4% under the motor execution experimental paradigm. These results show that our EEG signal classification algorithms is more effective compared to other EEG signal classification algorithms and can effectively be used to control a rehabilitation robot across a wider range of applications.

关键词： Deep learning Accuracy Robot control Pattern classification Human-robot interaction Assistive robots Motors Electroencephalography brain-computer interfaces Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Face recognition using skin color segmentation and template matching algorithms

引用

Information technology Journal 2011年第12期10卷 2308-2314页

作者： Wang, Zhiwen Li, Shaozi Department of Computer and Engineering Guangxi University of Technology Liuzhou China Department of Cognitive Science Xiamen University Xiamen China Key Laboratory of the Brain-Like Intelligent Systems Xiamen University Xiamen China

Currently, relatively popular and representative face recognition algorithms are algorithm based on template matching and algorithms based on skin-color segmentation. The computation of recognition algorithm based on template matching is very high and the recognition rate of recognition algorithms based on skin color segmentation is low and is vulnerable to the impact of background which is similar with skin color, In order to overcome these deficiencies, face recognition using skin color segmentation and template matching algorithm is presented in this study. According to the clustering properties that the skin-color of human faces emerge in the YCbCr color space, the regions closing to facial skin color are separated from the image by using Gaussian mixture model in order to achieve the purpose of rapidly detecting the external face of human face. Adaptive template matching is used to overcome the affect of the backgrounds which are similar with skin color on face detection and recognition. Computation in the matching process is reduced by using the second matching algorithm. Extraction of face images by using singular value features is used to identify faces and to reduce the dimensions of the eigenvalue matrix in the process of facial feature extraction. Experimental results show that proposed method can rapidly detect and recongnise human faces and improve the accuracy of face detection and recognition. © 2011 Asian Network for Scientific Information.

关键词： Template matching

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：