检索结果-内蒙古大学图书馆

An Improved Sparse Representation Classifier Based on data Augmentation for Time Series Classification 15th

学校读者我要写书评

暂无评论

An Improved Sparse Representation Classifier Based on Data A...

15th International Conference on Green, Pervasive, and Cloud computing, GPC 2020

作者： Lu, Juhong Huang, Fangwan Yu, Zhiyong College of Mathematics and Computer Science Fuzhou University Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Key Laboratory of Spatial Data Mining & Information Sharing Ministry of Education Fuzhou China

ISBN: (纸本)9783030642426

Sparse Representation-based Classification (SRC), which has achieved good performance in face recognition and other image classification, has been successfully extended to time series classification in recent years. As a generalization of the nearest subspace classifier, the performance of SRC depends on a rich set of training samples for each class, which can span as many variations of each class as possible under testing conditions. However, due to the difficulty of sample collection, many important applications can only provide a few or even a single sample for each class, which inevitably affects the performance of SRC. To address the problem of insufficient training samples, ESRC (Extended SRC) was proposed to put some samples that reflect the variations within the class into the dictionary, to obtain better generalization ability than SRC for under-sampled face recognition. In this paper, a new approach IESRC (Improved extend sparse representation based classification) is developed by splitting the dictionary into an original dictionary and auxiliary dictionary. The proposed model was first evaluated in 30 baseline data sets in the University of California, Riverside time series classification archive and then applied to classify the effects of aerobic exercise intervention in 24 young hypertensive patients based on the time series of the cardiopulmonary exercise test. Experimental results show that the proposed model can achieve better performance than SRC and ESRC in time series classification. © 2020, Springer Nature Switzerland AG.

关键词： Face recognition

Brain Image Parcellation Using Fully Convolutional Network with Adaptively Selected Features from Brain Atlases 9

学校读者我要写书评

暂无评论

Brain Image Parcellation Using Fully Convolutional Network w...

9th International Conference on Bioinformatics and Biomedical Science, ICBBS 2020

作者： Zhang, Xiao Zhao, Haifeng Tang, Zhenyu Zhang, Shaojie Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University China

ISBN: (纸本)9781450388658

Brain image parcellation is an important data processing step in neuroscience. Since multi-atlas based parcellation (MAP) uses prior information from brain atlases (i.e., manually labeled brainregions), it can provide accurate brain parcellation and has been widely adopted. Recently, some deep learning based brain image parcellation (DLP) methods using fully convolutional network (FCN) have been proposed. Compared with MAP, DLP has high computational efficiency, making it more applicable in practice. However, existing DLP methods either neglect or partially utilize brain atlases, making it difficult to get comparable parcellation accuracy as MAP. In this paper, we propose a new DLP method which is able to use brain atlases in an effective way. The network is based on FCN and non-local block based channel attention module (NL module). The input of our network is the target brain image to be parcellated as well as available brain atlases, and the parcellation result is produced through the FCN guided by the features of brain atlases selected by NL modules at different scales. In the experiments using two public MR brain image datasets (LPBA40 and NIREP-NA0), our method outperforms MAP and the state-of-the-art DLP methods due to the effective usage of brain atlases. © 2020 ACM.

关键词： Computational efficiency

MOAL: Multi-view Out-of-distribution Awareness Learning

学校读者我要写书评

暂无评论

Neural Networks 2025年 190卷 107581页

作者： Xuzheng Wang Zihan Fang Shide Du Wenzhong Guo Shiping Wang College of Computer and Data Science Fuzhou University Fuzhou 350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou 350108 China

Multi-view learning integrates data from multiple sources to enhance task performance by improving data quality. However, existing approaches primarily focus on intra-distribution data learning and consequently fail to identify out-of-distribution instances effectively. This paper introduces a method to improve the perception of out-of-distribution data in multi-view situations. First, we employ multi-view consistency and complementarity principles to develop sub-view complementarity representation learning and multi-view consistency fusion layers, thereby enhancing the model’s perception ability to typical intra-distribution features. Additionally, we introduce a specialized multi-view training loss and an agent mechanism tailored for out-of-distribution scenarios, facilitating the ability to differentiate between known and new or anomalous instances effectively. The proposed approach enhances the recognition of out-of-distribution data by improving intra-distribution feature representations and minimizing the entropy associated with out-of-distribution instances. Experimental results on multiple multi-view datasets simulating out-of-distribution scenarios confirm the effectiveness of MOLA, which consistently outperforms all baselines with average accuracy improvements of over 5%.

关键词： Anomaly detection Deep learning Multi-view learning Out-of-distribution learning

Balanced Multi-view Clustering

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Zhenglai Wang, Jun Tang, Chang Zhu, Xinzhong Zhang, Wei Liu, Xinwang Faculty of data science City University of Macau 999078 China School of computer National University of Defense Technology Changsha410073 China School of computer China University of Geosciences Wuhan430074 China College of Mathematics Physics and Information Engineering Zhejiang Normal University Jinhua China Research Institute of Ningbo Cixing Co. Ltd Ningbo China Qilu University of Technology Shandong Academy of Sciences China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan250000 China

Multi-view clustering (MvC) aims to integrate information from different views to enhance the capability of the model in capturing the underlying data structures. The widely used joint training paradigm in MvC is potentially not fully leverage the multi-view information, since the imbalanced and under-optimized view-specific features caused by the uniform learning objective for all views. For instance, particular views with more discriminative information could dominate the learning process in the joint training paradigm, leading to other views being under-optimized. To alleviate this issue, we first analyze the imbalanced phenomenon in the joint-training paradigm of multi-view clustering from the perspective of gradient descent for each view-specific feature extractor. Then, we propose a novel balanced multi-view clustering (BMvC) method, which introduces a view-specific contrastive regularization (VCR) to modulate the optimization of each view. Concretely, VCR preserves the sample similarities captured from the joint features and view-specific ones into the clustering distributions corresponding to view-specific features to enhance the learning process of view-specific feature extractors. Additionally, a theoretical analysis is provided to illustrate that VCR adaptively modulates the magnitudes of gradients for updating the parameters of view-specific feature extractors to achieve a balanced multi-view learning procedure. In such a manner, BMvC achieves a better trade-off between the exploitation of view-specific patterns and the exploration of view-invariance patterns to fully learn the multi-view information for the clustering task. Finally, a set of experiments are conducted to verify the superiority of the proposed method compared with state-of-the-art approaches on eight benchmark MvC datasets. The demo code of this work is publicly available at https://***/guanyuezhen/BMvC. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

Learnable Graph Convolutional Network and Feature Fusion for Multi-view Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Zhaoliang Fu, Lele Yao, Jie Guo, Wenzhong Plant, Claudia Wang, Shiping College of Computer and Data Science Fuzhou University Fuzhou350116 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China Faculty of Computer Science University of Vienna Vienna1090 Austria Research Network Data Science @ Uni Vienna University of Vienna Vienna1090 Austria

In practical applications, multi-view data depicting objectives from assorted perspectives can facilitate the accuracy increase of learning algorithms. However, given multi-view data, there is limited work for learning discriminative node relationships and graph information simultaneously via graph convolutional network that has drawn the attention from considerable researchers in recent years. Most of existing methods only consider the weighted sum of adjacency matrices, yet a joint neural network of both feature and graph fusion is still under-explored. To cope with these issues, this paper proposes a joint deep learning framework called Learnable Graph Convolutional Network and Feature Fusion (LGCN-FF), consisting of two stages: feature fusion network and learnable graph convolutional network. The former aims to learn an underlying feature representation from heterogeneous views, while the latter explores a more discriminative graph fusion via learnable weights and a parametric activation function dubbed Differentiable Shrinkage Activation (DSA) function. The proposed LGCN-FF is validated to be superior to various state-of-the-art methods in multi-view semi-supervised classification. Copyright © 2022, The Authors. All rights reserved.

关键词： Learning algorithms

Decentralized Linear MMSE Equalizer Under Colored Noise for Massive MIMO Systems

学校读者我要写书评

暂无评论

Decentralized Linear MMSE Equalizer Under Colored Noise for ...

2021 IEEE Global Communications Conference (GLOBECOM)

作者： Xiaotong Zhao Xin Guan Mian Li Qingjiang Shi School of Software Engineering Tongji University Shanghai China Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data Shenzhen China

ISBN: (纸本)9781728181059

Conventional uplink equalization in massive MIMO systems relies on a centralized baseband processing architecture. However, as the number of base station antenna increases, centralized baseband processing architectures encounter two bot-tlenecks, i.e., the tremendous data interconnection and the high-dimensional computation. To tackle these obstacles, decentralized baseband processing was proposed for uplink equalization, but only applicable to the scenarios with unpractical white Gaussian noise assumption. This paper presents an uplink linear mini-mum mean-square error (L-MMSE) equalization method in the daisy chain decentralized baseband processing architecture under colored noise assumption. The optimized L-MMSE equalizer is derived by exploiting the block coordinate descent method, which shows near-optimal performance both in theoretical and simulation while significantly mitigating the bottlenecks.

关键词： Baseband Equalizers Computer architecture Massive MIMO Mean square error methods Interference Large-scale systems

Wasserstein Archetypal Analysis

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Craig, Katy Osting, Braxton Wang, Dong Xu, Yiming Department of Mathematics University of California Santa Barbara Department of Mathematics University of Utah Salt Lake City School of Science and Engineering & Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong Shenzhen Guangdong China Corporate Model Risk Wells Fargo

Archetypal analysis is an unsupervised machine learning method that summarizes data using a convex polytope. In its original formulation, for fixed k, the method finds a convex polytope with k vertices, called archetype points, such that the polytope is contained in the convex hull of the data and the mean squared Euclidean distance between the data and the polytope is minimal. In the present work, we consider an alternative formulation of archetypal analysis based on the Wasserstein metric, which we call Wasserstein archetypal analysis (WAA). In one dimension, there exists a unique solution of WAA [7] and, in two dimensions, we prove existence of a solution, as long as the data distribution is absolutely continuous with respect to Lebesgue measure. We discuss obstacles to extending our result to higher dimensions and general data distributions. We then introduce an appropriate regularization of the problem, via a Rényi entropy, which allows us to obtain existence of solutions of the regularized problem for general data distributions, in arbitrary dimensions. We prove a consistency result for the regularized problem, ensuring that if the data are iid samples from a probability measure, then as the number of samples is increased, a subsequence of the archetype points converges to the archetype points for the limiting data distribution, almost surely. Finally, we develop and implement a gradient-based computational approach for the two-dimensional problem, based on the semi-discrete formulation of the Wasserstein metric. Our analysis is supported by detailed computational *** Codes 62H12, 62H30, 65K10, 49Q22 Copyright © 2022, The Authors. All rights reserved.

关键词： Multivariant analysis

Speaker Extraction with Co-Speech Gestures Cue

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Pan, Zexu Qian, Xinyuan Li, Haizhou The Integrative Sciences and Engineering Programme The Institute of Data Science National University of Singapore 119077 Singapore The Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore The Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong Shenzhen518172 China The School of Data Science The Chinese University of Hong Kong Shenzhen518172 China The University of Bremen 28359 Germany

Speaker extraction seeks to extract the clean speech of a target speaker from a multi-talker mixture speech. There have been studies to use a pre-recorded speech sample or face image of the target speaker as the speaker cue. In human communication, co-speech gestures that are naturally timed with speech also contribute to speech perception. In this work, we explore the use of co-speech gestures sequence, e.g. hand and body movements, as the speaker cue for speaker extraction, which could be easily obtained from low-resolution video recordings, thus more available than face recordings. We propose two networks using the co-speech gestures cue to perform attentive listening on the target speaker, one that implicitly fuses the co-speech gestures cue in the speaker extraction process, the other performs speech separation first, followed by explicitly using the co-speech gestures cue to associate a separated speech to the target speaker. The experimental results show that the co-speech gestures cue is informative in associating with the target speaker. Copyright © 2022, The Authors. All rights reserved.

关键词： Extraction

A residual attention-based privacy-preserving biometrics model of transcriptome prediction from genome

学校读者我要写书评

暂无评论

A residual attention-based privacy-preserving biometrics mod...

IEEE International Conference on Trust, Security and Privacy in computing and Communications (TrustCom)

作者： Cheng Tian Song Liu Jinbao Li Guangchen Wang Luyue Kong Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Department of Medicine Shandong Medical College Jinan China

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

Transcriptome prediction from genetic variation data is an important task in the privacy-preserving and biometrics field, which can better protect genomic data and achieve biometric recognition through transcriptome. Many transcriptome prediction methods have achieved good accuracy from genetic variation data. However, these traditional transcriptome prediction methods have the problems of linear assumption, overfitting, expose personal privacy, and extensive manual optimization. To solve these shortcomings, we propose an attention-based transcriptome prediction model from genetic variation named RATPM that improves the accuracy of transcriptome prediction and protects participant genomic data. In RATPM, we introduce and improve the deep learning model with multi-head self-attention into the transcriptome prediction stage of Predixcan, which uncovers the non-linear relationship between genetic variation and transcriptome. Moreover, we introduce a residual attention module to generate attention-aware features and extract more accurate features at different levels from genetic variation. Furthermore, we introduce the BERT pre-training module to encode genetic variation fully utilizing their contextual information. Our research enables scientific institutions to publish only predicted transcriptomic data for biometric purposes, thus protecting the genomic information of the subjects. Finally, we evaluated our model on the 1000 Genomes and Geuvadis projects datasets to compare with other baseline models.

关键词： Privacy Biometrics (access control) Biological system modeling Genomics Predictive models Feature extraction Gene expression