Neural Processing Letters最新文献_第6页

Sub-One Quasi-Norm-Based k-Means Clustering Algorithm and Analyses 基于子一准规范的 k-Means 聚类算法及分析

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-05-13 DOI: 10.1007/s11063-024-11615-y

Qi An, Shan Jiang

{"title":"Sub-One Quasi-Norm-Based k-Means Clustering Algorithm and Analyses","authors":"Qi An, Shan Jiang","doi":"10.1007/s11063-024-11615-y","DOIUrl":"https://doi.org/10.1007/s11063-024-11615-y","url":null,"abstract":"Recognizing the pivotal role of choosing an appropriate distance metric in designing the clustering algorithm, our focus is on innovating the k-means method by redefining the distance metric in its distortion. In this study, we introduce a novel k-means clustering algorithm utilizing a distance metric derived from the (ell _p) quasi-norm with (pin (0,1)). Through an illustrative example, we showcase the advantageous properties of the proposed distance metric compared to commonly used alternatives for revealing natural groupings in data. Subsequently, we present a novel k-means type heuristic by integrating this sub-one quasi-norm-based distance, offer a step-by-step iterative relocation scheme, and prove the convergence to the Kuhn-Tucker point. Finally, we empirically validate the effectiveness of our clustering method through experiments on synthetic and real-life datasets, both in their original form and with additional noise introduced. We also investigate the performance of the proposed method as a subroutine in a deep learning clustering algorithm. Our results demonstrate the efficacy of the proposed k-means algorithm in capturing distinctive patterns exhibited by certain data types.","PeriodicalId":51144,"journal":{"name":"Neural Processing Letters","volume":"46 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140938931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Time Series Classification Based on Forward Echo State Convolution Network 基于前向回波状态卷积网络的时间序列分类

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-05-11 DOI: 10.1007/s11063-024-11449-8

Lei Xia, Jianfeng Tang, Guangli Li, Jun Fu, Shukai Duan, Lidan Wang

{"title":"Time Series Classification Based on Forward Echo State Convolution Network","authors":"Lei Xia, Jianfeng Tang, Guangli Li, Jun Fu, Shukai Duan, Lidan Wang","doi":"10.1007/s11063-024-11449-8","DOIUrl":"https://doi.org/10.1007/s11063-024-11449-8","url":null,"abstract":"The Echo state network (ESN) is an efficient recurrent neural network that has achieved good results in time series prediction tasks. Still, its application in time series classification tasks has yet to develop fully. In this study, we work on the time series classification problem based on echo state networks. We propose a new framework called forward echo state convolutional network (FESCN). It consists of two parts, the encoder and the decoder, where the encoder part is composed of a forward topology echo state network (FT-ESN), and the decoder part mainly consists of a convolutional layer and a max-pooling layer. We apply the proposed network framework to the univariate time series dataset UCR and compare it with six traditional methods and four neural network models. The experimental findings demonstrate that FESCN outperforms other methods in terms of overall classification accuracy. Additionally, we investigated the impact of reservoir size on network performance and observed that the optimal classification results were obtained when the reservoir size was set to 32. Finally, we investigated the performance of the network under noise interference, and the results show that FESCN has a more stable network performance compared to EMN (echo memory network).","PeriodicalId":51144,"journal":{"name":"Neural Processing Letters","volume":"49 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2024-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140938985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Unified Asymmetric Knowledge Distillation Framework for Image Classification 图像分类的统一非对称知识提炼框架

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-05-10 DOI: 10.1007/s11063-024-11606-z

Xin Ye, Xiang Tian, Bolun Zheng, Fan Zhou, Yaowu Chen

引用次数: 0

Pinning Group Consensus of Multi-agent Systems Under DoS Attacks DoS攻击下多代理系统的钉组共识

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-05-10 DOI: 10.1007/s11063-024-11630-z

Qian Lang, Jing Xu, Huiwen Zhang, Zhengxin Wang

引用次数: 0

Use of a Modified Threshold Function in Fuzzy Cognitive Maps for Improved Failure Mode Identification 在模糊认知图中使用修正阈值函数改进故障模式识别

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-05-09 DOI: 10.1007/s11063-024-11623-y

Manu Augustine, Om Prakash Yadav, Ashish Nayyar, Dheeraj Joshi

引用次数: 0

Unsupervised Domain Adaptation Depth Estimation Based on Self-attention Mechanism and Edge Consistency Constraints 基于自我注意机制和边缘一致性约束的无监督领域自适应深度估计

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-05-09 DOI: 10.1007/s11063-024-11621-0

Peng Guo, Shuguo Pan, Peng Hu, Ling Pei, Baoguo Yu

{"title":"Unsupervised Domain Adaptation Depth Estimation Based on Self-attention Mechanism and Edge Consistency Constraints","authors":"Peng Guo, Shuguo Pan, Peng Hu, Ling Pei, Baoguo Yu","doi":"10.1007/s11063-024-11621-0","DOIUrl":"https://doi.org/10.1007/s11063-024-11621-0","url":null,"abstract":"In the unsupervised domain adaptation (UDA) (Akada et al. Self-supervised learning of domain invariant features for depth estimation, in: 2022 IEEE/CVF winter conference on applications of computer vision (WACV), pp 3377–3387 (2022). 10.1109/WACV51458.2022.00107) depth estimation task, a new adaptive approach is to use the bidirectional transformation network to transfer the style between the target and source domain inputs, and then train the depth estimation network in their respective domains. However, the domain adaptation process and the style transfer may result in defects and biases, often leading to depth holes and instance edge depth missing in the target domain’s depth output. To address these issues, We propose a training network that has been improved in terms of model structure and supervision constraints. First, we introduce a edge-guided self-attention mechanism in the task network of each domain to enhance the network’s attention to high-frequency edge features, maintain clear boundaries and fill in missing areas of depth. Furthermore, we utilize an edge detection algorithm to extract edge features from the input of the target domain. Then we establish edge consistency constraints between inter-domain entities in order to narrow the gap between domains and make domain-to-domain transfers easier. Our experimental demonstrate that our proposed method effectively solve the aforementioned problem, resulting in a higher quality depth map and outperforming existing state-of-the-art methods.","PeriodicalId":51144,"journal":{"name":"Neural Processing Letters","volume":"2 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2024-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140938928","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Prototype-Based Neural Network for Image Anomaly Detection and Localization 基于原型的图像异常检测和定位神经网络

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-05-08 DOI: 10.1007/s11063-024-11466-7

Chao Huang, Zhao Kang, Hong Wu

{"title":"A Prototype-Based Neural Network for Image Anomaly Detection and Localization","authors":"Chao Huang, Zhao Kang, Hong Wu","doi":"10.1007/s11063-024-11466-7","DOIUrl":"https://doi.org/10.1007/s11063-024-11466-7","url":null,"abstract":"Image anomaly detection and localization perform not only image-level anomaly classification but also locate pixel-level anomaly regions. Recently, it has received much research attention due to its wide application in various fields. This paper proposes ProtoAD, a prototype-based neural network for image anomaly detection and localization. First, the patch features of normal images are extracted by a deep network pre-trained on nature images. Then, the prototypes of the normal patch features are learned by non-parametric clustering. Finally, we construct an image anomaly localization network (ProtoAD) by appending the feature extraction network with L2 feature normalization, a (1times 1) convolutional layer, a channel max-pooling, and a subtraction operation. We use the prototypes as the kernels of the (1times 1) convolutional layer; therefore, our neural network does not need a training phase and can conduct anomaly detection and localization in an end-to-end manner. Extensive experiments on two challenging industrial anomaly detection datasets, MVTec AD and BTAD, demonstrate that ProtoAD achieves competitive performance compared to the state-of-the-art methods with a higher inference speed. The code and pre-trained models are publicly available at https://github.com/98chao/ProtoAD.","PeriodicalId":51144,"journal":{"name":"Neural Processing Letters","volume":"45 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2024-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140938881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

WaveVC: Speech and Fundamental Frequency Consistent Raw Audio Voice Conversion WaveVC：语音和基频一致的原始音频语音转换

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-05-08 DOI: 10.1007/s11063-024-11613-0

Kyungdeuk Ko, Donghyeon Kim, Kyungseok Oh, Hanseok Ko

{"title":"WaveVC: Speech and Fundamental Frequency Consistent Raw Audio Voice Conversion","authors":"Kyungdeuk Ko, Donghyeon Kim, Kyungseok Oh, Hanseok Ko","doi":"10.1007/s11063-024-11613-0","DOIUrl":"https://doi.org/10.1007/s11063-024-11613-0","url":null,"abstract":"Voice conversion (VC) is a task for changing the speech of a source speaker to the target voice while preserving linguistic information of the source speech. The existing VC methods typically use mel-spectrogram as both input and output, so a separate vocoder is required to transform mel-spectrogram into waveform. Therefore, the VC performance varies depending on the vocoder performance, and noisy speech can be generated due to problems such as train-test mismatch. In this paper, we propose a speech and fundamental frequency consistent raw audio voice conversion method called WaveVC. Unlike other methods, WaveVC does not require a separate vocoder and can perform VC directly on raw audio waveform using 1D convolution. This eliminates the issue of performance degradation caused by the train-test mismatch of the vocoder. In the training phase, WaveVC employs speech loss and F0 loss to preserve the content of the source speech and generate F0 consistent speech using the pre-trained networks. WaveVC is capable of converting voices while maintaining consistency in speech and fundamental frequency. In the test phase, the F0 feature of the source speech is concatenated with a content embedding vector to ensure the converted speech follows the fundamental frequency flow of the source speech. WaveVC achieves higher performances than baseline methods in both many-to-many VC and any-to-any VC. The converted samples are available online.","PeriodicalId":51144,"journal":{"name":"Neural Processing Letters","volume":"37 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2024-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140887887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-view Self-supervised Learning and Multi-scale Feature Fusion for Automatic Speech Recognition 多视角自监督学习和多尺度特征融合用于自动语音识别

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-05-08 DOI: 10.1007/s11063-024-11614-z

Jingyu Zhao, Ruwei Li, Maocun Tian, Weidong An

引用次数: 0

TLCE: Transfer-Learning Based Classifier Ensembles for Few-Shot Class-Incremental Learning TLCE：基于迁移学习的分类器集合，用于少镜头分类增量学习

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-05-08 DOI: 10.1007/s11063-024-11605-0

Shuangmei Wang, Yang Cao, Tieru Wu

引用次数: 0