检索结果-内蒙古大学图书馆

Design, Automation and Test in Europe Conference and Exhibition (DATE)

作者： Chen, Zihao Yang, Fan Shang, Li Zeng, Xuan Fudan Univ Sch Microelect State Key Lab ASIC & Syst Shanghai Peoples R China Fudan Univ Sch Comp Sci China & Shanghai Key Lab Data Sci Shanghai Peoples R China

ISBN: (纸本)9798350396249

This paper presents a neural architecture search scheme for chip layout hotspot detection. In this work, hotspot detectors, in the form of neural networks, are modeled as weighted directed acyclic graphs. A variational autoencoder maps the discrete graph topological space into a continuous embedding space. Bayesian Optimization performs neural architecture search in this embedding space, where an architecture performance predictor is employed to accelerate the search process. Experimental studies on ICCAD 2012 and ICCAD 2019 Contest benchmarks demonstrate that, the proposed scheme significantly improves the agility of previous neural architecture search schemes, and generates hotspot detectors with competitive detection accuracy, false alarm rate, and inference time.

关键词： layout hotspot detection neural architecture search Bayesian Optimization variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Multivariate Time Series Anomaly Detection Method Based on mTranAD 1

引用

19th International Conference on Advanced Intelligent Computing Technology and Applications (ICIC)

作者： Zhang, Chuanlei Li, Yicong Li, Jie Li, Guixi Ma, Hui Tianjin Univ Sci & Technol Tianjin Peoples R China China Unicom Res Inst Beijing Peoples R China Yunsheng Intelligent Technol Co Ltd Tianjin Peoples R China

ISBN: (数字)9789819947522

ISBN: (纸本)9789819947515;9789819947522

Multivariate time series anomaly detection is a crucial area of research in several domains, including finance, logistics, and manufacturing. Successfully identifying abnormal behaviors or events can help prevent disruptions, but the high false positive rate in this field is a significant challenge that affects detection accuracy. In this paper, we propose a novel method, mTranAD, which improves upon the TranAD algorithm by leveraging the benefits of Transformer and variational autoencoder (VAE) in multivariate unsupervised anomaly detection. Specifically, mTranAD replaces TranAD's autoencoder structure with a VAE and trains it using the VAE's loss function. The incorporation of latent variables in the VAE model enables accurate reconstruction of data and mapping of data to a lower dimensional latent space, allowing for a more efficient description of input data complexity with fewer parameters. By utilizing these latent variables, the model can effectively handle high-dimensional, complex data and exhibit greater flexibility when generating new data. We conduct experiments on four public datasets (NAB, MBA, SMAP and WADI) and compare mTranAD's performance with 11 other state-of-the-art methods, including TranAD, MERLIN, LSTM-NDT, OmniAnomaly, USAD, and DAGMM. The experimental results demonstrate that mTranAD outperforms these methods in terms of performance, accuracy, and reliability. The primary purpose of this paper is to improve the TranAD algorithm and enhance the accuracy of multivariate time series anomaly detection by reducing the false positive rate.

关键词： Anomaly detection Transformer variational autoencoder mTranAD

来源：评论

学校读者我要写书评

暂无评论

HYPERBOLIC variational AUTO-ENCODER FOR REMOTE SENSING SCENE EMBEDDINGS

HYPERBOLIC VARIATIONAL AUTO-ENCODER FOR REMOTE SENSING SCENE...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Hamzaoui, Manal Chapel, Laetitia Pham, Minh-Tan Lefevre, Sebastien Univ Bretagne Sud IRISA UMR 6074 F-56000 Vannes France

ISBN: (纸本)9798350320107

The computer vision community is increasingly interested in exploring hyperbolic space for image representation, as hyperbolic approaches have demonstrated outstanding results in efficiently representing data with an underlying hierarchy. This interest arises from the intrinsic hierarchical nature among images. However, despite the hierarchical nature of remote sensing (RS) images, the investigation of hyperbolic spaces within the RS community has been relatively limited. The objective of this study is therefore to examine the relevance of hyperbolic embeddings of RS data, focusing on scene embedding. Using a variational Auto-Encoder, we project the data into a hyperbolic latent space while ensuring numerical stability with a feature clipping technique. Experiments conducted on the NWPU-RESISC45 image dataset demonstrate the superiority of hyperbolic embeddings over the Euclidean counterparts in a classification task. Our study highlights the potential of operating in hyperbolic space as a promising approach for embedding RS data.

关键词： Remote sensing scene embedding underlying hierarchy hyperbolic space variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Towards Multi-User Activity Recognition through Facilitated Training Data and Deep Learning for Human-Robot Collaboration Applications

Towards Multi-User Activity Recognition through Facilitated ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Semeraro, Francesco Carberry, Jon Cangelosi, Angelo Univ Manchester Manchester Ctr Robot & Manchester Lancs England BAE Syst Plc BAE Syst Operat Ltd Warton England

ISBN: (纸本)9781665488679

Human-robot interaction (HRI) research is progressively addressing multi-party scenarios, where a robot interacts with more than one human user at the same time. Conversely, research is still at an early stage for human-robot collaboration. The use of machine learning techniques to handle such type of collaboration requires data that are less feasible to produce than in a typical HRC setup. This work outlines scenarios of concurrent tasks for non-dyadic HRC applications. Based upon these concepts, this study also proposes an alternative way of gathering data regarding multi-user activity, by collecting data related to single users and merging them in post-processing, to reduce the effort involved in producing recordings of pair settings. To validate this statement, 3D skeleton poses of activity of single users were collected and merged in pairs. After this, such datapoints were used to separately train a long shortterm memory (LSTM) network and a variational autoencoder (VAE) composed of spatio-temporal graph convolutional networks (STGCN) to recognise the joint activities of the pairs of people. The results showed that it is possible to make use of data collected in this way for pair HRC settings and get similar performances compared to using training data regarding groups of users recorded under the same settings, relieving from the technical difficulties involved in producing these data. The related code and collected data are publicly available(1).

关键词： multi-user activity recognition single-user training data concurrent tasks multi-party human-robot collaboration non-dyadic human-robot collaboration deep learning long short-term memory variational autoencoder spatio-temporal graph convolutional network transfer learning

来源：评论

学校读者我要写书评

暂无评论

Vehicular Trajectory Classification and Traffic Anomaly Detection in Videos Using a Hybrid CNN-VAE Architecture

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第8期23卷 11891-11902页

作者： Santhosh, Kelathodi Kumaran Dogra, Debi Prosad Roy, Partha Pratim Mitra, Adway Indian Inst Technol Bhubaneswar Sch Elect Sci Bhubaneswar 752050 Odisha India Indian Inst Technol Dept Comp Sci & Engn Roorkee 247667 Uttar Pradesh India Indian Inst Technol Kharagpur Ctr Excellence Artificial Intelligence AI Kharagpur 721302 W Bengal India

Visual surveillance has become indispensable in the evolution of Intelligent Transportation Systems (ITS). Video object trajectories are key to many of the visual surveillance applications. Classifying varying length time series data such as video object trajectories using conventional neural networks, can be challenging. In this paper, we propose trajectory classification and anomaly detection using a hybrid Convolutional Neural Network (CNN) and variational autoencoder (VAE) architecture. First, we introduce a high level features for varying length object trajectories using color gradient representation. In the next stage, a semi-supervised way to annotate moving object trajectories extracted using Temporally Incremental Gravitational Model (TIGM) is used for class labeling. For training, anomalous trajectories are identified using t-Distributed Stochastic Neighbor Embedding (t-SNE). Finally, a hybrid CNN-VAE architecture has been proposed for trajectory classification and anomaly detection. The results obtained using publicly available surveillance video datasets reveal that the proposed method can successfully identify traffic anomalies such as violations in lane driving, sudden speed variations, abrupt termination of vehicle during movement, and vehicles moving in wrong directions. The accuracy of trajectory classification improves by a margin of 1-6% against popular neural networks-based classifiers across various datasets using the proposed high-level features. The gradient representation also improves the anomaly detection accuracy significantly (30-35%). Code and dataset can be found at https://***/santhoshkelathodi/CNN-VAE.

关键词： Trajectory Image color analysis Videos Anomaly detection Convolutional neural networks Feature extraction Training data Convolutional neural network deep learning variational autoencoder Dirichlet process mixture model visual surveillance trajectory classification traffic anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Learning to Disentangle Inter-Subject Anatomical Variations in Electrocardiographic Data

引用

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 2022年第2期69卷 860-870页

作者： Gyawali, Prashnna K. Murkute, Jaideep Vitthal Toloubidokhti, Maryam Jiang, Xiajun Horacek, B. Milan Sapp, John L. Wang, Linwei Rochester Inst Technol Stanford CA 94305 USA Stanford Univ Stanford CA 94305 USA Dalhousie Univ Sch Biomed Engn Halifax NS Canada

Objective: This work investigates the possibility of disentangled representation learning of inter-subject anatomical variations within electrocardiographic (ECG) data. Methods: Since ground truth anatomical factors are generally not known in clinical ECG for assessing the disentangling ability of the models, the presented work first proposes the SimECG data set, a 12-lead ECG data set procedurally generated with a controlled set of anatomical generative factors. Second, to perform such disentanglement, the presented method evaluates and compares deep generative models with latent density modeled by nonparametric Indian Buffet Process to account for the complex generative process of ECG data. Results: In the simulated data, the experiments demonstrate, for the first time, concrete evidence of the possibility to disentangle key generative anatomical factors within ECG data in separation from task-relevant generative factors. We achieve a disentanglement score of 92.1% while disentangling five anatomical generative factors and the task-relevant generative factor. In both simulated and real-data experiments, this work further provides quantitative evidence for the benefit of disentanglement learning on the downstream clinical task of localizing the origin of ventricular activation. Overall, the presented method achieves an improvement of around 18.5%, and 11.3% for the simulated dataset, and around 7.2%, and 3.6% for the real dataset, over baseline CNN, and standard generative model, respectively. Conclusion: These results demonstrate the importance as well as the feasibility of the disentangled representation learning of inter-subject anatomical variations within ECG data. Significance: This work suggests the important research direction to deal with the well-known challenge posed by the presence of significant inter-subject variations during an automated analysis of ECG data.

关键词： Disentangled representation learning generative models variational autoencoder India Buffet process electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Detecting Out-of-Distribution Data in Wireless Communications Applications of Deep Learning

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2022年第4期21卷 2476-2487页

作者： Liu, Jinshan Oyedare, Taiwo Park, Jung-Min Virginia Tech Dept Elect & Comp Engn Arlington VA 22203 USA

Deep learning-based classification algorithms offer no performance guarantees when deployed on testing data not generated by the same process as the training data. Such out-of-distribution (OOD) data often cause classification errors that are hard to detect since they do not generate explicit errors in the model. In real-world applications, there is no way to ensure that the testing data and the training data are drawn from the same or sufficiently similar distributions. This problem is especially challenging in wireless communications applications. Because the radio propagation channel is highly dynamic, it is very difficult to ensure that a deep learning model is not tested on OOD data. In this paper, we propose a novel deep learning model called FOOD (Feature representation for detecting OOD data) to detect OOD data in wireless communications applications. FOOD incorporates a new model architecture to detect OOD data accurately and minimizes the instances of normal data being recognized as OOD. We evaluated the performance of FOOD extensively using transmitter classification and modulation recognition tasks, with both experimental datasets and simulation-generated datasets. As far as we know, this is the first systematic study on the impact and detection of OOD data in deep learning-based wireless communications applications.

关键词： Wireless communication Data models Training data Training Deep learning Testing Feature extraction Deep learning out-of-distribution variational autoencoder transmitter classification modulation recognition

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Retargeting From Human to Avatar Made Easy

引用

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 2022年第2期28卷 1274-1287页

作者： Zhang, Juyong Chen, Keyu Zheng, Jianmin Univ Sci & Technol China Sch Math Sci Hefei 230052 Anhui Peoples R China Nanyang Technol Univ Sch Comp Sci & Engn Singapore 639798 Singapore

Facial expression retargeting from humans to virtual characters is a useful technique in computer graphics and animation. Traditional methods use markers or blendshapes to construct a mapping between the human and avatar faces. However, these approaches require a tedious 3D modeling process, and the performance relies on the modelers' experience. In this article, we propose a brand-new solution to this cross-domain expression transfer problem via nonlinear expression embedding and expression domain translation. We first build low-dimensional latent spaces for the human and avatar facial expressions with variational autoencoder. Then we construct correspondences between the two latent spaces guided by geometric and perceptual constraints. Specifically, we design geometric correspondences to reflect geometric matching and utilize a triplet data structure to express users' perceptual preference of avatar expressions. A user-friendly method is proposed to automatically generate triplets for a system allowing users to easily and efficiently annotate the correspondences. Using both geometric and perceptual correspondences, we trained a network for expression domain translation from human to avatar. Extensive experimental results and user studies demonstrate that even nonprofessional users can apply our method to generate high-quality facial expression retargeting results with less time and effort.

关键词： Avatars Three-dimensional displays Strain Animation Shape Solid modeling Machine learning Facial expression retargeting variational autoencoder deformation transfer cross domain translation triplet

来源：评论

学校读者我要写书评

暂无评论

Adversarial Separation Network for Text Style Transfer

引用

ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING 2022年第2期21卷 1–14页

作者： Yang, Haitong Zhou, Guangyou He, Tingting Cent China Normal Univ Hubei Prov Key Lab Artificial Intelligence & Smar Wuhan Peoples R China Cent China Normal Univ Natl Language Resources Monitoring Wuhan Peoples R China Cent China Normal Univ Res Ctr Network Media Wuhan Peoples R China Cent China Normal Univ Sch Comp Luo Yu Rd Wuhan Hubei Peoples R China

This article considers the task of text style transfer: transforming a specific style of sentence into another while preserving its style-independent content. A dominate approach to text style transfer is to learn a good content factor of text, define a fixed vector for every style and recombine them to generate text in the required style. In fact, there are a large number of different words to convey the same style from different aspects. Thus, using a fixed vector to represent one style is very inefficient, which causes the weak representation power of the style vector and limits text diversity of the same style. To address this problem, we propose a novel neural generative model called Adversarial Separation Network (ASN), which can learn the content and style vector jointly and the learnt vectors have strong representation power and good interpretabilities. In our method, adversarial learning is implemented to enhance our model's capability of disentangling the two factors. To evaluate our method, we conduct experiments on two benchmark datasets. Experimental results show our method can perform style transfer better than strong comparison systems. We also demonstrate the strong interpretability of the learnt latent vectors.

关键词： Adversarial learning adversarial separation network latent factor mapping neural generative model text style transfer variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Unseen Speaker Anonymization via Voice Conversion

引用

IEEE ACCESS 2022年 10卷 130190-130199页

作者： Chang, Hyung-Pil Yoo, In-Chul Jeong, Changhyeon Yook, Dongsuk Korea Univ Dept Comp Sci & Engn Artificial Intelligence Lab Seoul South Korea

Speech-based interfaces provide convenient methods for controlling various smart devices. For these interfaces to work reliably, considerable speech data with various noise and speaker characteristics must be collected to train the associated speech-processing models. Gathering spoken commands from actual users of devices can improve those devices' performance by familiarizing each device with the individual acoustic characteristic of its particular user's speech. However, the direct acquisition of spoken commands could threaten the privacy of users, as the spoken data would contain sensitive speaker-specific information. Speaker anonymization algorithms can be applied to suppress such sensitive information, while preserving the linguistic content of a user's speech. Previous speaker anonymization algorithms could handle only the voice of speakers who contributed to the training datasets. As speaker anonymization algorithms are typically applied to new speakers (who are absent from the training datasets), a method of handling such speakers (commonly referred to as unseen speakers) should be developed. In this paper, we propose a novel method that can effectively suppress the individual characteristics in an unseen speaker's voice, while retaining the linguistic content of the speech. It adopts zero-shot voice conversion methods for the unseen speaker anonymization. Since the proposed method utilizes speaker identity vectors commonly used in many-to-many voice conversion algorithms and does not modify the conversion algorithm itself, it can be easily combined with many other voice conversion algorithms. The proposed method is evaluated using the VCC2018 and VCTK corpora. Speaker identification rate and speech recognition rate are used for quantitative analysis. The experimental results showed that the average speaker identification accuracy was decreased by 92.3% point absolutely and the average speech recognition accuracy was decreased by 17.7% point absolutely afte

关键词： Data privacy speaker anonymization unseen speakers variational autoencoder voice conversion zero-shot learning

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：