检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Almaeen, Manal Alanazi, Yasir Sato, Nobuo Melnitchouk, W. Kuchera, Michelle P. Li, Yaohang Old Dominion Univ Dept Comp Sci Norfolk VA 23529 USA Jefferson Lab Theory Ctr Newport News VA 23606 USA Davidson Coll Dept Phys Davidson NC 28035 USA

ISBN: (纸本)9780738133669

Inverse problems - using measured observations to determine unknown parameters - are well motivated but challenging in many science and engineering problems. In this paper, we propose an end-to-end deep learning framework, the variational autoencoder Inverse Mapper (VAIM), as an autoencoder-based neural network architecture for inverse problems. The encoder and decoder neural networks approximate the forward and backward mapping, respectively, and a variational latent layer is incorporated into VAIM to learn the posterior parameter distributions with respect to given observables. We demonstrate the effectiveness of VAIM for several toy inverse problems, with both finite and infinite solutions, and for constructing the inverse function mapping quantum correlation functions to observables in a Quantum Chromodynamics analysis of nucleon structure.

关键词： inverse problems variational autoencoder end-to-end learning latent space analysis ill-posed

来源：评论

学校读者我要写书评

暂无评论

Efficient Side-Channel Attack through Balanced Labels Compression and variational autoencoder 19

Efficient Side-Channel Attack through Balanced Labels Compre...

引用

19th International Conference on Mobility, Sensing and Networking (MSN)

作者： Cai, Nengfu Yang, Zhigin Wang, Shuhai Jiang, Yanling Liu, Mingsheng Li, Gang Beihang Univ Sch Cyber Sci & Technol Beijing 100191 Peoples R China Shijiazhuang Railway Univ Sch Informat Sci & Technol Shijiazhuang 050043 Peoples R China Shijiazhuang Inst Railway Technol Shijiazhuang 050041 Peoples R China Zhongke Zidong Informat Technol Beijing Co Ltd Beijing Peoples R China

ISBN: (纸本)9798350358261;9798350358278

Recently, side-channel attacks based on deep learning (DLSCAs) have attracted much attention. Many works have improved the performance of DLSCAs by designing advanced neural network architectures and training strategies. There are few studies on leakage models for DLSCAs. Existing researches usually utilize the intermediate value Hamming weight (HW) and the intermediate value itself (ID) as leakage models. Training a classifier with good performance is challenging due to the many label classes in the ID leakage model. The HW leakage model can significantly reduce the number of labels, but it will cause samples imbalance. In this paper, we propose a new DLSCA leakage model, named Balanced Labels Compression (BLC). We consider dividing sensitive intermediate values with same lowest epsilon bits into same class to obtain balanced labels. Then, we train a classifier using the compressed BLC labels and profiling energy traces. At the attack phase, the probability distribution of BLC labels is extended to the probability distribution of sensitive intermediate values. We conduct extensive comparison experiments with HW, ID, and BLC leakage models under the two scenarios of sufficient and insufficient profiling energy traces. Further, we exploit VAE to improve attack performance when energy traces are insufficient. Experimental results show that VAE-based data augmentation can significantly reduce required energy traces.

关键词： Side-channel attacks Side-channel leakage model variational autoencoder Data augmentation

来源：评论

学校读者我要写书评

暂无评论

Identifying Outliers, Defective Areas and Performance Evaluation of a PV Module using EL Image Processing: A variational autoencoder Approach

Identifying Outliers, Defective Areas and Performance Evalua...

引用

2023 Innovations in Power and Advanced Computing Technologies, i-PACT 2023

作者： Soumik, Moontasir Azmi, Taium Tasneem Islam, Mohammad Aminul Department of Electrical Engineering Faculty of Engineering University of Malaya Kuala Lumpur50603 Malaysia Department of Mechanical Engineering Faculty of Engineering University of Malaya Kuala Lumpur50603 Malaysia

ISBN: (纸本)9798350325188

Enhancing the commercial viability and efficacy of PV solar cell usage necessitates a comprehensive investigation into fault identification. This study introduces the development of a defect detection system tailored for identifying solar cell defects while approximating the subsequent power and efficiency losses. The methodology proposed encompasses two primary phases: Firstly, an anomaly detection model utilizing the variational Auto Encoder identifies defects, reconstructs defect-free solar cells or modules, and generates a heatmap illustrating defect intensities. Subsequently, in the second phase, the defective area is quantified to compute total power and efficiency losses of a PV module. The method's outcomes, utilizing Electroluminescence (EL) images, machine learning, and defect simulation, demonstrate its capability to operate with minimal available data and estimate overall power and efficiency loss. This research establishes a correlation between defects and power generation loss, offering an inclusive estimation of PV module profitability, potentially mitigating the soft costs of PV systems and enhancing fault diagnosis methods. © 2023 IEEE.

关键词： and module Anomaly Detection Image Processing Power Loss Estimation PV Cell variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Initial Study of Batik Generation using variational autoencoder 8

Initial Study of Batik Generation using Variational Autoenco...

引用

8th International Conference on Computer Science and Computational Intelligence, ICCSCI 2023

作者： Ihsan, Aditya Firman School of Computing Telkom University Bandung40257 Indonesia

One of the most promising architectures for generative models is the variational autoencoder (VAE). To reconstruct Batik patterns for this work, we used a deep convolutional VAE architecture. Reconstruction outcomes from various batik motifs are mapped and contrasted using some criteria. As another crucial component of the convolutional network, batch normalization's impact on the model's performance was also examined. The dataset is used to study some learned latent space features. Through these findings, we laid the framework for next research on Batik generation utilizing VAE. © 2023 The Authors. Published by Elsevier B.V.

关键词： Batik convolutional neural network generative model variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Design-Thinking-Driven variational autoencoder for Human Activity Classification 2

Design-Thinking-Driven Variational Autoencoder for Human Act...

引用

2nd International Conference on Automation, Computing and Renewable Systems, ICACRS 2023

作者： Selvakumar, N. Kalaivani, D. Vijayaraghavan, T. Department of Computer science Dr.SNS Rajalakshmi College of arts and science Coimbatore India

ISBN: (纸本)9798350340235

This study introduces a design-thinking-driven approach aimed at enhancing the accuracy and robustness of Human Activity Recognition (HAR) using sensor data from Internet of Things (IoT) devices. The proposed algorithm harnesses the synergy of a variational autoencoder-Based Dimensionality Reduction Technique with deep learning methods for human activity classification. HAR plays a pivotal role in categorizing activities, especially in domains like elder care and fitness tracking. This research work systematically assesses the model's performance across diverse datasets, including WISDM, HAPT, HAR, and KU-HAR, utilizing performance evaluation metrics such as accuracy, recall, precision, and F1-Score. The results underscore the potential of this design-thinking-infused approach to significantly enhance the precision and reliability of activity prediction in IoT-based HAR applications. The study introduces a design-thinking-driven approach by combining variational autoencoder-Based Dimensionality Reduction with deep learning techniques for enhancing Human Activity Recognition (HAR). © 2023 IEEE.

关键词： Deep Learning Design Thinking Dimensionality Reduction Human Activity Recognition Internet of Things Sensor Data variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Identifying malicious traffic under concept drift based on intraclass consistency enhanced variational autoencoder

引用

Science China(Information Sciences) 2024年第8期67卷 238-252页

作者： Xiang LUO Chang LIU Gaopeng GOU Gang XIONG Zhen LI Binxing FANG Institute of Information Engineering Chinese Academy of Sciences School of Cyber Security University of Chinese Academy of Sciences School of Computer Science and Technology Harbin Institute of Technology (Shenzhen)

Accurate identification of malicious traffic is crucial for implementing effective defense countermeasures and has led to extensive research efforts. However, the continuously evolving techniques employed by adversaries have introduced the issues of concept drift, which significantly affects the performance of existing methods. To tackle this challenge, some researchers have focused on improving the separability of malicious traffic representation and designing drift detectors to reduce the number of false ***, these methods often overlook the importance of enhancing the generalization and intraclass consistency in the representation. Additionally, the detectors are not sufficiently sensitive to the variations among different malicious traffic classes, which results in poor performance and limited robustness. In this paper, we propose intraclass consistency enhanced variational autoencoder with Class-Perception detector(ICE-CP) to identify malicious traffic under concept drift. It comprises two key modules during training:intraclass consistency enhanced(ICE) representation learning and Class-Perception(CP) detector construction. In the first module, we employ a variational autoencoder(VAE) in conjunction with Kullback-Leibler(KL)-divergence and cross-entropy loss to model the distribution of each input malicious traffic flow. This approach simultaneously enhances the generalization, interclass consistency, and intraclass differences in the learned representation. Consequently, we obtain a compact representation and a trained classifier for nondrifting malicious traffic. In the second module, we design the CP detector, which generates a centroid and threshold for each malicious traffic class separately based on the learned representation, depicting the boundaries between drifting and non-drifting malicious traffic. During testing, we utilize the trained classifier to predict malicious traffic classes for the testing samples. Then, we use the CP det

关键词： concept drift malicious traffic identification variational autoencoder intrusion detection cyberspace security

来源：评论

学校读者我要写书评

暂无评论

Interpreting rate-distortion of variational autoencoder and using model uncertainty for anomaly detection

引用

ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE 2022年第7-9期90卷 735-752页

作者： Park, Seonho Adosoglou, George Pardalos, Panos M. Univ Florida Dept Ind & Syst Engn Gainesville FL 32611 USA

Building a scalable machine learning system for unsupervised anomaly detection via representation learning is highly desirable. One of the prevalent methods is using a reconstruction error of variational autoencoder (VAE) by maximizing the evidence lower bound. We revisit VAE from the perspective of information theory to provide some theoretical foundations on using the reconstruction error and finally arrive at a simpler yet effective model for anomaly detection. In addition, to enhance the effectiveness of detecting anomalies, we incorporate a practical model uncertainty measure into the anomaly score. We show empirically the competitive performance of our approach on benchmark data sets.

关键词： Anomaly detection Rate-Distortion theory Information theory Model uncertainty MC dropout variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

variational autoencoder-based topological optimization of an anechoic coating: An efficient- and neural network-based design

引用

MATERIALS TODAY COMMUNICATIONS 2022年 32卷

作者： Sun, Yiping Li, Zhaoyu Chen, Jiadui Zhao, Xuefeng Tao, Meng Guizhou Univ Sch Mech Engn Guiyang 550025 Peoples R China Guizhou Open Univ Coll Aeronaut Guiyang 550023 Peoples R China Guizhou Univ Key Lab Adv Mfg Technol Minist Educ Guiyang 550025 Peoples R China

An anechoic coating is an artificial heterogeneous composite material composed of periodic cells with cavities. Using the local resonance of cavities to reduce their sound absorption frequencies and widen their frequency bands has been a research hotspot in recent years. One of the main challenges involves optimizing the cavity structure of an anechoic coating to obtain low-frequency, broadband, and strong sound absorption properties. In this paper, a variational autoencoder (VAE) model-based topology optimization method was investigated. First, the finite-element method (FEM) was used to calculate the sound absorption coefficient, and a dataset was constructed with samples whose average sound absorption coefficients ranged from 200 to 6000 Hz and were greater than 0.75. Then, the VAE model was trained to learn the key features of an anechoic coating. Finally, the data were reconstructed with Gaussian distributions. The decoder network of the trained VAE model was used to design a new anechoic coating. It took only approximately 3 s to generate 100 new topologies, and the average absorption coefficients were all greater than 0.754. This efficient neural network-based method can be further generalized to optimize the designs of various mechanical structural materials with specific functions.

关键词： Anechoic coating Topology optimization variational autoencoder Neural network

来源：评论

学校读者我要写书评

暂无评论

Federated Learning with variational autoencoder for Popularity Profile Prediction 14

Federated Learning with Variational Autoencoder for Populari...

引用

14th International Conference on Information and Communication Technology Convergence, ICTC 2023

作者： Ahn, Minkyun Choi, Minseok Kyung Hee University Department of Electronic Engineering Yongin Korea Republic of

ISBN: (纸本)9798350313277

Motivated by increasingly exploding data traffic of online video services, the prediction of the popularity profile of video contents becomes very important for network traffic prediction, recommendation systems, and wireless caching. This paper proposes a federated learning-based popularity prediction scheme using a variational autoencoder (VAE), which copes with the situation where users are moving and/or their data privacy should be protected. Users are participants of federated learning, and the VAE model is trained by user's own request history;afterwards, randomly generated samples from the pretrained decoder of VAE can mimic the original popularity profile. We adopt the MovieLens dataset to validate the proposed model, and experimental results show that our scheme predicts the popularity profile almost perfectly. © 2023 IEEE.

关键词： Federated learning Popularity prediction variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

CNC Machining Quality Prediction Using variational autoencoder: A Novel Industrial 2 TB Dataset

CNC Machining Quality Prediction Using Variational Autoencod...

引用

Prognostics and Health Management Conference (PHM-2022 London)

作者： Proteau, Antoine Zemouri, Ryad Tahan, Antoine Thomas, Marc Bounouara, Wafa Agnard, Stephane Ecole Technol Super Dept Mech Engn Montreal PQ Canada Conservatoire Natl Arts & Metiers CNAM CEDRIC Lab Paris France APN Inc Quebec City PQ Canada

ISBN: (纸本)9781665479547

The purpose of this paper is to present and to describe a novel dataset acquired entirely in an industrial environment during multiple regular scheduled production runs. In the monitoring, prognostic and fault detection literature, researchers are often faced with work based on the same popular datasets;for instance, the milling dataset, the Pronostia Bearing Dataset, the IMS Bearing Dataset or the Turbofan Engine Degradation Simulation Dataset. On the one hand, these datasets are the results of either simulations or acquired in a laboratory under controlled environment. On the other hand, a real industrial context might not be adequately represented within these datasets due to less controlled parameters or increased complexity. Consequently, it becomes critical to have access to a way to test and validate research work on both experimental and industrial data. In that mindset, to accelerate the technological transfer to the industry and to ensure that it can quickly profit from the benefits that the monitoring, diagnostic and prognostic research area can provide them, a new dataset acquired at an industrial partner: a machining company located in Quebec City (Qc, Canada) is presented.

关键词： Dataset Machining GD&T Prognostic variational autoencoder

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：