检索结果-内蒙古大学图书馆

adversarial autoencoder for continuous sign language recognition

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2024年第22期36卷

作者： Kamal, Suhail Muhammad Chen, Yidong Li, Shaozi Xiamen Univ Sch Informat Xiamen Fujian Peoples R China Xiamen Univ Key Lab Digital Protect & Intelligent Proc Intangi Minist Culture & Tourism Xiamen Fujian Peoples R China Bayero Univ Kano Fac Comp Dept Informat Technol Kano Nigeria

Sign language serves as a vital communication medium for the deaf community, encompassing a diverse array of signs conveyed through distinct hand shapes along with non-manual gestures like facial expressions and body movements. Accurate recognition of sign language is crucial for bridging the communication gap between deaf and hearing individuals, yet the scarcity of large-scale datasets poses a significant challenge in developing robust recognition technologies. Existing works address this challenge by employing various strategies, such as enhancing visual modules, incorporating pretrained visual models, and leveraging multiple modalities to improve performance and mitigate overfitting. However, the exploration of the contextual module, responsible for modeling long-term dependencies, remains limited. This work introduces an adversarial autoencoder for Continuous Sign Language Recognition, AA-CSLR, to address the constraints imposed by limited data availability, leveraging the capabilities of generative models. The integration of pretrained knowledge, coupled with cross-modal alignment, enhances the representation of sign language by effectively aligning visual and textual features. Through extensive experiments on publicly available datasets (PHOENIX-2014, PHOENIX-2014T, and CSL-Daily), we demonstrate the effectiveness of our proposed method in achieving competitive performance in continuous sign language recognition.

关键词： adversarial autoencoder continuous sign language recognition vision-language

来源：评论

学校读者我要写书评

暂无评论

Missing Value Imputation Model Based on adversarial autoencoder Using Spatiotemporal Feature Extraction

引用

Intelligent Automation & Soft Computing 2023年第8期37卷 1925-1940页

作者： Dong-Hoon Shin Seo-El Lee Byeong-Uk Jeon Kyungyong Chung Department of Computer Science Kyonggi UniversitySuwon-siGyeonggi-do16227Korea Department of Public Safety Bigdata Kyonggi UniversitySuwon-siGyeonggi-do16227Korea Division of AI Computer Science and Engineering Kyonggi UniversitySuwon-siGyeonggi-do16227Korea

Recently,the importance of data analysis has increased significantly due to the rapid data *** particular,vehicle communication data,considered a significant challenge in Intelligent Transportation Systems(ITS),has spatiotemporal characteristics and many missing *** missing values in data lead to the decreased predictive performance of *** missing value imputation models ignore the topology of transportation net-works due to the structural connection of road networks,although physical distances are close in spatiotemporal image ***,the learning process of missing value imputation models requires complete data,but there are limitations in securing complete vehicle communication *** study proposes a missing value imputation model based on adversarial autoencoder using spatiotemporal feature extraction to address these *** proposed method replaces missing values by reflecting spatiotemporal characteristics of transportation data using temporal convolution and spatial *** results show that the proposed model has the lowest error rate of 5.92%,demonstrating excellent predictive *** this,it is possible to solve the data sparsity problem and improve traffic safety by showing superior predictive performance.

关键词： Missing value adversarial autoencoder spatiotemporal feature extraction

来源：评论

学校读者我要写书评

暂无评论

Purifying adversarial Images Using adversarial autoencoder With Conditional Normalizing Flows

IEEE OPEN JOURNAL OF SIGNAL PROCESSING

引用

IEEE OPEN JOURNAL OF SIGNAL PROCESSING 2023年 4卷 267-274页

作者： Ji, Yi Le, Trung-Nghia Nguyen, Huy H. H. Echizen, Isao Univ Tokyo Tokyo 1138654 Japan Natl Inst Informat Tokyo 1018430 Japan

We present a target-agnostic adversarial autoencoder with conditional normalizing flows specifically designed to, given any unlabeled image dataset, purify adversarial samples into clean images, i.e., remove adversarial noise from the images while preserving their visual quality. In our model interpretation, samples are processed by manifold projection in which the encoder brings the sample back into a posterior data distribution in latent space so that the sample is less likely to be irregular to the learned representation of any target classifier. Normalizing flows conditioned on top of our hybrid network structure and walk-back training are used to deal with common drawbacks of generative model and autoencoder-based approaches: not only the trade-off between compression loss and over-fitting on training data but also the structural model dependency on dataset classes and labels. Experiments demonstrated that our proposed model is preferable to existing target-agnostic adversarial defense methods particularly for large and unlabeled image datasets.

关键词： adversarial autoencoder adversarial purification normalizing flow representation learning

来源：评论

学校读者我要写书评

暂无评论

An Optimized Self-representation Subspace Clustering Model Based on adversarial autoencoder 20th

An Optimized Self-representation Subspace Clustering Model B...

引用

20th International Conference on Intelligent Computing (ICIC)

作者： Sun, Deyan Chen, Dufeng Liu, Hai Chen, Wei Liu, Jueting Yang, Yuancan Wang, Zehua Zhu, Pengcheng China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221116 Jiangsu Peoples R China Beijing Geotech & Invest Engn Inst Beijing 100080 Peoples R China China Univ Min & Technol Sch Comp Sci & Technol Xuzhou 221116 Jiangsu Peoples R China Minist Emergency Management Big Data Ctr Beijing 100010 Peoples R China

ISBN: (纸本)9789819756742;9789819756759

Subspace clustering, as a high-dimensional data clustering method has been widely applied in multiple fields such as data mining and computer vision. The existing deep subspace clustering methods only consider the distribution characteristics of low dimensional representations of data, and do not effectively utilize the implicit spatial distribution of data categories to improve clustering performance. This paper proposes a self-representation subspace clustering model based on adversarial autoencoder (AAESC). In this model, the low dimension representation of data is subject to Normal distribution, and the class representation is subject to polynomial distribution by antagonizing the low dimension representation and class representation of self codec learning data, and using two antagonizing generation networks respectively. Then, by introducing from the presentation layer, the data similarity matrix is constructed based on the low dimensional representation of the data, and the spectral clustering algorithm is used to obtain the clustering results. Experiments have shown that the self-representation subspace clustering model based on adversarial self-coding can better learn the low dimensional representation of data and construct a good data similarity matrix based on it, with better clustering performance than other methods.

关键词： Subspace Clustering adversarial autoencoder Self-representation Neural Network

来源：评论

学校读者我要写书评

暂无评论

AAE-Dpeak-SC: A novel unsupervised clustering method for space target ISAR images based on adversarial autoencoder and density peak-spectral clustering

引用

ADVANCES IN SPACE RESEARCH 2022年第5期70卷 1472-1495页

作者： Yang, Hong Ding, Wenzhe Yin, Canbin Beijing Inst Tracking & Telecommun Technol Beijing 100096 Peoples R China Space Engn Univ Beijing 101416 Peoples R China

Aiming at the problem of unlabeled ISAR image clustering of space targets, the paper proposes a new unsupervised clustering method based on adversarial autoencoder (AAE) and density peak-spectral clustering (Dpeak-SC). This method introduces the AAE into the unsupervised clustering problem of radar images for the first time and realizes the automatic extraction of the features of unlabeled space target ISAR image data. And on this basis, by combining the density peak algorithm with the spectral clustering algorithm, the ISAR image data is classified into multiple clusters with good clustering accuracy, clustering coincidence, and clustering similarity without providing any prior information. This method first implements the self-supervised training of the AAE model through the adversarial and reconstruction process. Then, it uses the trained encoder to extract the latent features of the ISAR image of the space target in the lowdimensional space. Next, a decision graph is constructed by calculating the local density and relative distance of the proposed features to determine the number of clusters in the hidden feature vector set. Finally, the spectral clustering algorithm is used to transform the problem into the graph's optimal partition problem. The clustering is realized by constructing and segmenting the undirected weight graph of the hidden feature vector set. The simulation test on the unlabeled space target ISAR image data verifies the method's effectiveness in this paper. (c) 2022 COSPAR. Published by Elsevier B.V. All rights reserved.

关键词： Space target unlabeled ISAR image Unsupervised clustering adversarial autoencoder Density peak clustering Spectral clustering

来源：评论

学校读者我要写书评

暂无评论

AFExNet: An adversarial autoencoder for Differentiating Breast Cancer Sub-Types and Extracting Biologically Relevant Genes

引用

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2022年第4期19卷 2060-2070页

作者： Mondol, Raktim Kumar Nhan Duy Truong Reza, Mohammad Ippolito, Samuel Ebrahimie, Esmaeil Kavehei, Omid RMIT Univ Dept Elect & Biomed Engn Melbourne Vic 3000 Australia Univ Queensland Ctr Adv Imaging St Lucia Qld 4072 Australia La Trobe Univ Coll Sci Hlth & Engn Sch Life Sci Genom Res Platform Melbourne Vic 3086 Australia Univ Adelaide Sch Anim & Vet Sci Adelaide SA 5371 Australia Univ Melbourne Sch BioSci Parkville Vic 3010 Australia Univ Sydney Sch Biomed Engn Camperdown NSW 2006 Australia

Technological advancements in high-throughput genomics enable the generation of complex and large data sets that can be used for classification, clustering, and bio-marker identification. Modern deep learning algorithms provide us with the opportunity of finding most significant features in such huge dataset to characterize diseases (e.g., cancer) and their sub-types. Thus, developing such deep learning method, which can successfully extract meaningful features from various breast cancer sub-types, is of current research interest. In this paper, we develop dual stage (unsupervised pre-training and supervised fine-tuning) neural network architecture termed AFExNet based on adversarial auto-encoder (AAE) to extract features from high dimensional genetic data. We evaluated the performance of our model through twelve different supervised classifiers to verify the usefulness of the new features using public RNA-Seq dataset of breast cancer. AFExNet provides consistent results in all performance metrics across twelve different classifiers which makes our model classifier independent. We also develop a method named 'TopGene' to find highly weighted genes from the latent space which could be useful for finding cancer bio-markers. Put together, AFExNet has great potential for biological data to accurately and effectively extract features. Our work is fully reproducible and source code can be downloaded from Github: https://***/NeuroSyd/breast-cancer-sub-types.

关键词： Feature extraction Breast cancer Gene expression Genomics Deep learning Biological information theory Bioinformatics Neural network deep learning genetic data feature extraction adversarial autoencoder

来源：评论

学校读者我要写书评

暂无评论

Damage Detection and Localization for Indirect Bridge Monitoring Exploiting adversarial autoencoder and Wavelet Transform 10th

Damage Detection and Localization for Indirect Bridge Monito...

引用

10th European Workshop on Structural Health Monitoring (EWSHM)

作者： Kaur, Kirandeep Alamdari, Mehri Makki Chang, Kai Chun Kim, Chul Woo Atroshchenko, Elena Univ New South Wales Sch Civil & Environm Engn Ctr Infrastruct Engn & Safety Sydney NSW 2052 Australia Kyoto Univ Grad Sch Engn Dept Civil & Earth Resources Engn Kyoto 6158540 Japan

ISBN: (纸本)9783031072543;9783031072536

Indirect bridge monitoring provides an economical procedure to ensure reliable operation of the bridges by utilizing the vehicle responses passing over the bridge. The present work proposes a unified framework for damage detection, assessment, and localization using adversarial autoencoder and wavelet transform in an unsupervised manner. Vehicle acceleration signals from healthy bridge state only are considered for adversarial autoencoder model training. Estimated reconstruction error is used as a damage detection index. Pre-processing techniques of spectrum filtering, and signal averaging are adopted to improve the model performance. Further, the locations of the detected damages are estimated by employing wavelet transform along with signal pre-processing techniques. The approach is tested on numerically simulated vehicle acceleration signals which are obtained by considering a half-car model on a simply supported bridge using finite element analysis. Different damage scenarios with varying severity at different bridge locations have been considered. It has been investigated that the proposed approach is successful in detecting damages with varying damage severity alongside locating their respective locations. The proposed approach also outperforms other unsupervised learning techniques by detecting and isolating different damages effectively.

关键词： adversarial autoencoder Indirect monitoring Moving load Deep learning Wavelet transform

来源：评论

学校读者我要写书评

暂无评论

adversarial autoencoder for trajectory generation and maneuver classification 25

Adversarial Autoencoder for trajectory generation and maneuv...

引用

25th IEEE International Conference on Intelligent Engineering Systems (INES)

作者： Rakos, Oliver Becsi, Tamas Aradi, Szilard Budapest Univ Technol & Econ Dept Control Transportat & Vehicle Syst Budapest Hungary

ISBN: (纸本)9781665444996

For the development of self-driving cars, it is essential to perceive the environment as accurately as possible and to interpret the movement of the surrounding vehicles. It makes sense to draw conclusions based on the past trajectories of these vehicles, whether it is maneuver detection or, in more complex cases, maneuver or trajectory prediction. Trajectories are time series data, so it is obvious to deploy recurrent neural networks for their analysis, or 1-dimensional convolutional networks that can capture temporal patterns. The concept is presented that trajectories starting from the origin can be compressed efficiently so that the reconstructed trajectory is quite similar to the original, and the latent space code obtained by compression can be used for maneuver detection. Using a variational autoencoder, assuming a normal distribution, the latent spatial distribution can be approximated. However, in this article, the goal was to test this concept with adversarial training, so the so-called adversarial autoencoder is trained. It has been shown that this method is suitable for twelve-fold compression of trajectories, and the latent code is suitable for maneuver detection. This proves that the encoder has learned useful features about the distribution that generates trajectories.

关键词： adversarial autoencoder NGSIM maneuver deteciton trajectory compression

来源：评论

学校读者我要写书评

暂无评论

Generating spectral samples with analyte concentration values using the adversarial autoencoder

引用

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS 2024年 252卷

作者： Huang, Guangzao Zhao, Xinyu Chen, Xiao Ali, Shujat Shi, Wen Xie, Zhonghao Chen, Xiaojing Wenzhou Univ Coll Elect & Elect Engn Wenzhou 325035 Peoples R China Wenzhou Inst Ind & Sci Wenzhou 325035 Peoples R China

The prediction of analyte concentration by spectral responses using a calibration model is a commonly used method in chemical analysis. However, insufficient modeling samples will limit the performance of the calibration model. Artificial generation of spectral samples with analyte concentration values is an effective way to address the shortage of modeling samples. However, traditional methods for generating spectral samples with concentration values still have problems in terms of diversity and accuracy. We proposed a method for generating spectral samples with analyte concentration values based on an adversarial autoencoder (AAE). The proposed method combined spectral responses and analyte concentration as the inputs and fitted the extracted latent variables into a prior distribution. By decoding the random sampling points of the prior distribution, the spectral samples with analyte concentration values were generated. Four spectral datasets were used to validate the effectiveness of the proposed method. Two traditional spectral generation methods were used to evaluate the performance of the proposed methods. It was found that the proposed method performed significantly better than traditional ones. The spectral responses generated by the proposed method had good diversity and similarity to the real ones. In addition, the generated spectral samples could also accurately simulate the actual relationship between spectral responses and analyte properties. The proposed method is an effective solution to the problem of insufficient modeling samples in the quantitative analysis of spectral technology.

关键词： Analyte concentration Spectral responses Calibration model Artificial generation adversarial autoencoder

来源：评论

学校读者我要写书评

暂无评论

Unsupervised anomalous sound detection method based on Gammatone spectrogram and adversarial autoencoder with attention mechanism

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART E-JOURNAL OF PROCESS MECHANICAL ENGINEERING 2024年

作者： Yan, Hao Zhan, Xianbiao Wu, Zhenghao Cheng, Junkai Wen, Liang Jia, Xisheng Army Engn Univ PLA Shijiazhuang Campus Shijiazhuang 050003 Peoples R China Northwestern Polytech Univ Sch Automat Xian Peoples R China

Anomalous sound detection (ASD) is an important technology in the fourth industrial revolution, which can monitor the abnormal state of machine by identifying whether the sound of the machine is normal or not. However, in practical applications where there are few anomalous sound samples from machines, achieving effective ASD is still a challenge. In this paper, an unsupervised ASD algorithm based on adversarial autoencoder with attention mechanism is proposed. Different from the traditional reconstruction-based ASD model, in order to make the features learned by the model more representative, complex sound timing signals are converted into Gammatone spectrogram with richer features through filtering. Then the spectrogram is used as the input of the convolutional autoencoder. At the same time, the attention mechanism is introduced in the encoder to enhance adaptive learning of the normal patterns. Then the discriminator is used in the generative adversarial network to perform adversarial learning with the improved convolutional autoencoder to improve the reconstruction ability of the model for normal samples. Experimental results demonstrate that the proposed algorithm significantly outperforms commonly used industry methods for anomaly detection and exhibits advantages over other deep learning approaches in terms of system complexity.

关键词： Anomalous sound detection unsupervised learning adversarial autoencoder attention mechanism Gammatone spectrogram

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：