检索结果-内蒙古大学图书馆

unsupervised representation learning for Large-Scale Wafer Maps in Micro-Electronic Manufacturing

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 2024年第1期70卷 1226-1235页

作者： Xu, Qiao Yu, Naigong Yu, Hejie Beijing Univ ofTechnol Fac Informat Technol Beijing 100124 Peoples R China Beijing Univ Technol Beijing Key Lab Comp Intelligence & Intelligent Sy Beijing Municipal Commiss Sci & Technol Beijing 100124 Peoples R China

Recognition of wafer map defect patterns is essential for evaluating the reliability of micro-electronic manufacturing. Due to the difficulty of labeling, the available large-scale wafer maps are raw data without labeling. The scarcity of labeled samples reduces the defect pattern recognition accuracy of popular deep convolutional neural networks. To overcome this problem, we propose a wafer map deep clustering (WMDC) model. It learns generic representations from unlabeled datasets in an unsupervised manner. A prototype metric loss during training helps to learn the semantic features of the categories. We improve the recognition accuracy of the model when trained using scarce labeled data by transferring the weights of unsupervised pretraining. Experiments on WM811K and MixedWM38 wafer datasets demonstrate that the WMDC model is capable of obtaining robust prior representations from the unlabeled wafer maps. Accuracies of 97.43% and 98.74% are obtained when fine-tuning using scarce labeled data from both datasets, respectively.

关键词： Semiconductor device modeling Pattern recognition Training Task analysis Data models Labeling Manuals Wafer map defect pattern recognition convolutional neural network unsupervised representation learning deep clustering scarce labeled data

来源：评论

学校读者我要写书评

暂无评论

unsupervised representation learning-based Doppler Ultrasound Signal Quality Assessment

Unsupervised Representation Learning-based Doppler Ultrasoun...

引用

IEEE Global Communications Conference (GLOBECOM)

作者： Shi, Xintong Yamamoto, Kohei Ohtsuki, Tomoaki Matsui, Yutaka Owada, Kazunari Keio Univ Dept Informat & Comp Sci Yokohama Kanagawa 2238522 Japan Atom Med Co Ltd Tech Dept Res & Dev Grp Tokyo 1130021 Japan

ISBN: (纸本)9781665435406

The Doppler ultrasound (DUS) transducer has been widely used for fetal heart rate (FHR) monitoring. However, the fetal DUS signals from the transducers can be corrupted by several interference sources such as maternal and fetal movements, which makes FHR estimation using fetal DUS signals challenging. Fetal DUS signal quality assessment (SQA) can help to remove or interpolate unreliable FHRs estimated from noisy signals to improve the accuracy of FHR estimation. There are some existing approaches for fetal DUS SQA, and most of these approaches with high accuracy are based on supervised learningbased algorithms and human-defined properties. Nonetheless, the fetal DUS datasets with quality-level annotations are limited, and human-defined properties place a limitation on mining more deep information related to signal quality in fetal DUS signals. In this paper, we propose an unsupervised representation learning-based fetal DUS SQA for the improvement of FHR estimation performance. We firstly learn representations of preprocessed fetal DUS data from variational autoencoder (VAE) and then combine these representations as one signal quality index (SQI) using a self-organizing map (SOM). Finally, we apply the combined SQI and a Kalman filter (KF) to estimate fetal RR intervals (FRRI) for reducing the errors of FHR estimation. The experimental results showed that our proposed method could reduce the averaged root mean squared error (RMSE) of FRRI and averaged absolute error (AAE) of FHR.

关键词： unsupervised representation learning Fetal doppler ultrasound signal Signal quality assessment Variational autoencoder Kalman filter

来源：评论

学校读者我要写书评

暂无评论

Semantic Relationship-Based unsupervised representation learning of Multivariate Time Series

引用

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 2024年第2期E107卷 191-200页

作者： Ye, Chengyang Ma, Qiang Kyoto Univ Grad Sch Informat Kyoto 6068303 Japan

representation learning is a crucial and complex task for multivariate time series data analysis, with a wide range of applications including trend analysis, time series data search, and forecasting. In practice, unsupervised learning is strongly preferred owing to sparse labeling. However, most existing studies focus on the representation of individual subseries without considering relationships between different subseries. In certain scenarios, this may lead to downstream task failures. Here, an unsupervised representation learning model is proposed for multivariate time series that considers the semantic relationship among subseries of time series. Specifically, the covariance calculated by the Gaussian process (GP) is introduced to the self -attention mechanism, capturing relationship features of the subseries. Additionally, a novel unsupervised method is designed to learn the representation of multivariate time series. To address the challenges of variable lengths of input subseries, a temporal pyramid pooling (TPP) method is applied to construct input vectors with equal length. The experimental results show that our model has substantial advantages compared with other representation learning models. We conducted experiments on the proposed algorithm and baseline algorithms in two downstream tasks: classification and retrieval. In classification task, the proposed model demonstrated the best performance on seven of ten datasets, achieving an average accuracy of 76%. In retrieval task, the proposed algorithm achieved the best performance under different datasets and hidden sizes. The result of ablation study also demonstrates significance of semantic relationship in multivariate time series representation learning.

关键词： unsupervised representation learning semantic relationship gaussian process covariance multivariate time series

来源：评论

学校读者我要写书评

暂无评论

View sequence prediction GAN: unsupervised representation learning for 3D shapes by decomposing view content and viewpoint variance

引用

MULTIMEDIA SYSTEMS 2024年第4期30卷 231-231页

作者： Zhou, Heyu Li, Jiayu Liu, Xianzhu Lyu, Yingda Chen, Haipeng Liu, An-An Yichang Testing Tech R&D Inst Yichang 443003 Peoples R China Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Changchun Univ Sci & Technol Natl & Local Joint Engn Res Ctr Space Optoelect Te Changchun 130022 Peoples R China Changchun Univ Sci & Technol Coll Optoelect Engn Changchun 130022 Peoples R China Jilin Univ Coll Comp Sci & Technol Changchun 130012 Peoples R China Jilin Univ Key Lab Symbol Computat & Knowledge Engn Minist Ed Changchun 130012 Peoples R China

unsupervised representation learning for 3D shapes has become a critical problem for large-scale 3D shape management. Recent model-based methods for this task require additional information for training, while popular view-based methods often overlook viewpoint variance in view prediction, leading to uninformative 3D features that limit their practical applications. To address these issues, we propose an unsupervised 3D shape representation learning method called View Sequence Prediction GAN (VSP-GAN), which decomposes view content and viewpoint variance. VSP-GAN takes several adjacent views of a 3D shape as input and outputs the subsequent views. The key idea is to split the multi-view sequence into two available perceptible parts, view content and viewpoint variance, and independently encode them with separate encoders. With the information, we design a decoder implemented by the mirrored architecture of the content encoder to predict the view sequence by multi-steps. Besides, to improve the quality of the reconstructed views, we propose a novel hierarchical view prediction loss to enhance view realism, semantic consistency, and details retainment. We evaluate the proposed VSP-GAN on two popular 3D CAD datasets, ModelNet10 and ModelNet40, for 3D shape classification and retrieval. The experimental results demonstrate that our VSP-GAN can learn more discriminative features than the state-of-the-art methods.

关键词： 3D Shape Classification & Retrieval Multi-View learning unsupervised representation learning

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Self-Organizing Clustering Network: A Novel unsupervised representation learning Method

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND learning SYSTEMS 2024年第2期35卷 1857-1871页

作者： Li, Shuo Liu, Fang Jiao, Licheng Chen, Puhua Li, Lingling Xidian Univ Joint Int Res Lab Intelligent Percept & Computat Key Lab Intelligent Percept & Image Understanding Int Res Ctr Intelligent Percept & ComputatMinist Xian 710071 Shaanxi Peoples R China

Deep learning-based clustering methods usually regard feature extraction and feature clustering as two independent steps. In this way, the features of all images need to be extracted before feature clustering, which consumes a lot of calculation. Inspired by the self-organizing map network, a self-supervised self-organizing clustering network (S(3)OCNet) is proposed to jointly learn feature extraction and feature clustering, thus realizing a single-stage clustering method. In order to achieve joint learning, we propose a self-organizing clustering header (SOCH), which takes the weight of the self-organizing layer as the cluster centers, and the output of the self-organizing layer as the similarities between the feature and the cluster centers. In order to optimize our network, we first convert the similarities into probabilities which represents a soft cluster assignment, and then we obtain a target for self-supervised learning by transforming the soft cluster assignment into a hard cluster assignment, and finally we jointly optimize backbone and SOCH. By setting different feature dimensions, a Multilayer SOCHs strategy is further proposed by cascading SOCHs. This strategy achieves clustering features in multiple clustering spaces. S(3)OCNet is evaluated on widely used image classification benchmarks such as Canadian Institute For Advanced Research (CIFAR)-10, CIFAR-100, Self-Taught learning (STL)-10, and Tiny ImageNet. Experimental results show that our method significant improvement over other related methods. The visualization of features and images shows that our method can achieve good clustering results.

关键词： Deep learning-based clustering self-organizing map self-supervised learning unsupervised clustering algorithm unsupervised representation learning

来源：评论

学校读者我要写书评

暂无评论

Lung-GANs: unsupervised representation learning for Lung Disease Classification Using Chest CT and X-Ray Images

引用

IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT 2023年第8期70卷 2774-2786页

作者： Yadav, Pooja Menon, Neeraj Ravi, Vinayakumar Vishvanathan, Sowmya VMware Bangalore 560076 Karnataka India Prince Mohammad Bin Fand Univ Ctr Artificial Intelligence Khobar 34754 Saudi Arabia Amrita Vishwa Vidyapeetham Amrita Sch Engn Ctr Computat Engn & Networking CEN Coimbatore 641112 Tamil Nadu India

Lung diseases are a tremendous challenge to the health and life of people globally, accounting for 5 out of 30 most common causes of death. Early diagnosis is crucial to help in faster recovery and improve long-term survival rates. Deep learning techniques offer a great promise for automated, fast, and reliable detection of lung diseases from medical images. Specifically, convolutional neural networks have accomplished encouraging results in disease detection. In spite of that, the performance of such supervised models depends heavily on the availability of large labeled data, the collection of which is an expensive and tedious task, specially for a novel disease. Therefore, in this article, we propose a deep unsupervised framework to classify lung diseases from chest CT and X-ray images. Our framework introduces multiple-layer generative adversarial networks called Lung-GANs that learn interpretable representations of lung disease images using only unlabeled data. We use the lung features learned by the model to train a support vector machine and a stacking classifier. We demonstrate through experiments that the proposed method outperforms the current state-of-the-art unsupervised models in lung disease classification. Our model obtained an accuracy of 94%-99.5% on all the six large-scale publicly available lung disease datasets used in this study. Hence, the proposed framework will simplify lung disease detection by reducing the time for diagnosis and increasing the convenience of diagnostics.

关键词： Pulmonary diseases X-ray imaging Computed tomography Generators Feature extraction COVID-19 Training COVID-19 CT scan generative adversarial networks lung disease pediatric pneumonia pneumonia tuberculosis unsupervised representation learning X-ray

来源：评论

学校读者我要写书评

暂无评论

LBP4MTS: Local Binary Pattern-Based unsupervised representation learning of Multivariate Time Series

引用

IEEE ACCESS 2023年 11卷 118595-118605页

作者： Ye, Chengyang Ma, Qiang Kyoto Univ Grad Sch Informat Yoshida Tachibana ChoSakyo Ku Kyoto 6068303 Japan Kyoto Inst Technol Dept Informat Sci Matsugasaki Hashigami ChoSakyo Ku Kyoto 6068585 Japan

representation learning of multivariate time series is a crucial and complex task that offers valuable insights for numerous applications, including time series classification, trend analysis, and regression. unsupervised learning approaches are often favored in practical scenarios due to the limited availability of labeled data. However, most existing studies focus more on the global information of time series and ignore the local information, especially the representation learning based on the self-attention mechanism. This affects representation performance and may lead to the failure of downstream tasks. This study proposed an unsupervised representation learning model for multivariate time series by comprehensively considering multivariate time series data's global and local information. Specifically, a specially designed local binary pattern (LBP) method for multivariate time series (multivariate LBP) is introduced to the self-attention mechanism to improve the representation performance of modeling in terms of local information. Additionally, we propose a novel unsupervised approach for learning multivariate time series representations. The experimental results demonstrate significant advantages of our model over other representation learning methods and can be well applied in various downstream tasks.

关键词： unsupervised representation learning local binary pattern global and local features multivariate time series

来源：评论

学校读者我要写书评

暂无评论

unsupervised representation learning for Speech Activity Detection in the Fearless Steps Challenge 2021 22

Unsupervised Representation Learning for Speech Activity Det...

引用

Interspeech Conference

作者： Gimeno, Pablo Ortega, Alfonso Miguel, Antonio Lleida, Eduardo Univ Zaragoza Aragon Inst Engn Res I3A ViVoLab Zaragoza Spain

ISBN: (纸本)9781713836902

In this paper, we describe the ViVoLab speech activity detection (SAD) system submitted to the Fearless steps Challenge phase III. This series of challenges have proposed a number of speech processing task dealing with audio from Apollo space missions over the last few years. The focus in this edition is set on the generalisation capabilities of the systems, with new evaluation data from different channels. Our proposed submission is based on the use of the unsupervised representation learning paradigm, seeking to obtain a new and more discriminative audio representation than traditional perceptual features such as log Mel-filterbank energies. These new features are used to train different variations of a convolutional recurrent neural network (CRNN). Experimental results show that features learned via unsupervised learning provide a much more robust representation, significantly reducing the mismatch observed between development and evaluation partition results. Obtained results largely outperform the organisation baseline, achieving a DCF metric of 2.98% on the evaluation set and ranking third among all the participant teams.

关键词： unsupervised representation learning speech activity detection fearless steps challenge

来源：评论

学校读者我要写书评

暂无评论

unsupervised representation learning Meets Pseudo-Label Supervised Self-Distillation: A New Approach to Rare Disease Classification 24th

Unsupervised Representation Learning Meets Pseudo-Label Supe...

引用

International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)

作者： Sun, Jinghan Wei, Dong Ma, Kai Wang, Liansheng Zheng, Yefeng Xiamen Univ Xiamen Peoples R China Tencent Jarvis Lab Shenzhen Peoples R China

ISBN: (纸本)9783030872403;9783030872397

Rare diseases are characterized by low prevalence and are often chronically debilitating or life-threatening. Imaging-based classification of rare diseases is challenging due to the severe shortage in training examples. Few-shot learning (FSL) methods tackle this challenge by extracting generalizable prior knowledge from a large base dataset of common diseases and normal controls, and transferring the knowledge to rare diseases. Yet, most existing methods require the base dataset to be labeled and do not make full use of the precious examples of the rare diseases. To this end, we propose in this work a novel hybrid approach to rare disease classification, featuring two key novelties targeted at the above drawbacks. First, we adopt the unsupervised representation learning (URL) based on self-supervising contrastive loss, whereby to eliminate the overhead in labeling the base dataset. Second, we integrate the URL with pseudo-label supervised classification for effective self-distillation of the knowledge about the rare diseases, composing a hybrid approach taking advantages of both unsupervised and (pseudo-) supervised learning on the base dataset. Experimental results on classification of rare skin lesions show that our hybrid approach substantially outperforms existing FSL methods (including those using fully supervised base dataset) for rare disease classification via effective integration of the URL and pseudo-label driven self-distillation, thus establishing a new state of the art.

关键词： Rare disease classification unsupervised representation learning Pseudo-label supervised self-distillation

来源：评论

学校读者我要写书评

暂无评论

Deep boundary-aware clustering by jointly optimizing unsupervised representation learning

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2022年第24期81卷 34309-34324页

作者： Wang, Ru Li, Lin Wang, Peipei Tao, Xiaohui Liu, Peiyu Shandong Normal Univ Sch Informat Sci & Engn Jinan Peoples R China Wuhan Univ Technol Sch Comp Sci & Technol Wuhan Peoples R China Univ Southern Queensland Sch Sci Toowoomba Qld Australia

Deep clustering obtains feature representation generally and then performs clustering for high dimension real-world data. However, conventional solutions are two-stage embedding learning-based methods and these two processes are separate and independent, which often leads to clustering results cannot feedback to optimize the representation learning and reduces the performance of deep clustering. In this paper, we aim to propose a deep boundary-aware clustering by jointly optimizing unsupervised representation learning. More specifically, we joint boundary-aware variational auto-encoder and deep regularized clustering for deep regularized clustering for unsupervised learning, named Boundary-aware DEep Clustering (BaDEC). BaDEC is able to learn feature representation and clustering simultaneously, and it introduces deep regularized clustering to reduce the unreliability of the similarity measures. In particular, we present a boundary-aware variational auto-encoder that tunes variable evidence lower bounds flexibly to assist feature representation learning better for more accurate clustering. Extensive experiments on various datasets from multiple domains demonstrate that the proposed method outperforms several popular comparison baseline methods.

关键词： unsupervised representation learning Deep clustering Variational bounds

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：