检索结果-内蒙古大学图书馆

EXTENDING THE LEE-CARTER MODEL WITH variational autoencoder: A FUSION OF NEURAL NETWORK AND BAYESIAN APPROACH

ASTIN BULLETIN-THE JOURNAL OF THE INTERNATIONAL ACTUARIAL ASSOCIATION 2022年第3期52卷 789-812页

作者： Miyata, Akihiro Matsuyama, Naoki Meiji Univ AMS Tokyo Japan Meiji Univ Grad Sch Adv Math Sci AMS Tokyo Japan

In this study, we propose a nonlinear Bayesian extension of the Lee-Carter (LC) model using a single-stage procedure with a dimensionality reduction neural network (NN). LC is originally estimated using a two-stage procedure: dimensionality reduction of data by singular value decomposition followed by a time series model fitting. To address the limitations of LC, which are attributed to the two-stage estimation and insufficient model fitness to data, single-stage procedures using the Bayesian state-space (BSS) approaches and extensions of flexibility in modeling by NNs have been proposed. As a fusion of these two approaches, we propose a NN extension of LC with a variational autoencoder that performs the variational Bayesian estimation of a state-space model and dimensionality reduction by autoencoding. Despite being a NN model that performs single-stage estimation of parameters, our model has excellent interpretability and the ability to forecast with confidence intervals, as with the BSS models, without using Markov chain Monte Carlo methods.

关键词： Lee-Carter model state-space model variational autoencoder variational Bayesian inference

来源：评论

学校读者我要写书评

暂无评论

variational autoencoder FOR SPEECH ENHANCEMENT WITH A NOISE-AWARE ENCODER

VARIATIONAL AUTOENCODER FOR SPEECH ENHANCEMENT WITH A NOISE-...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Fang, Huajian Carbajal, Guillaume Wermter, Stefan Gerkmann, Timo Univ Hamburg Signal Proc SP Hamburg Germany Univ Hamburg Knowledge Technol WTM Hamburg Germany

ISBN: (纸本)9781728176055

Recently, a generative variational autoencoder (VAE) has been proposed for speech enhancement to model speech statistics. However, this approach only uses clean speech in the training phase, making the estimation particularly sensitive to noise presence, especially in low signal-to-noise ratios (SNRs). To increase the robustness of the VAE, we propose to include noise information in the training phase by using a noise-aware encoder trained on noisy-clean speech pairs. We evaluate our approach on real recordings of different noisy environments and acoustic conditions using two different noise datasets. We show that our proposed noise-aware VAE outperforms the standard VAE in terms of overall distortion without increasing the number of model parameters. At the same time, we demonstrate that our model is capable of generalizing to unseen noise conditions better than a supervised feedforward deep neural network (DNN). Furthermore, we demonstrate the robustness of the model performance to a reduction of the noisy-clean speech training data size.

关键词： speech enhancement generative model variational autoencoder semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptation via variational autoencoder with Explicit and Implicit Feature Alignment for Cardiac Segmentation 8

Unsupervised Domain Adaptation via Variational Autoencoder w...

引用

8th International Conference on Cloud Computing and Big Data Analytics (ICCCBDA)

作者： Li, Yan Wang, Yifan Zheng, Fan Cheng, Linkai Xu, Di Cui, Hengfei Northwestern Polytech Univ Sch Comp Sci Xian Peoples R China Huawei Cloud Media Innovat Lab Xian Peoples R China Northwestern Polytech Univ Shenzhen Inst Res & Dev Shenzhen Peoples R China

ISBN: (纸本)9781665455336

Late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) is of vital importance in the diagnosis of myocardial infarction (MI). However, the LGE image annotations are limited, it is urgently needed to transfer the learned knowledge in other modalities. We propose an unsupervised domain adaptation (UDA) algorithm based on variational autoencoder (VAE) with a Combination of Explicit and Implicit Alignment of feature distributions (VCEIA). First, we re-derive the Kullback-Leibler (KL) divergence of the features extracted in the source and target domains as a measure of distribution discrepancy. Secondly, for explicit category-level distribution alignment, we use contrast learning to reduce the distance between prototypes of the same category in the source and target domains. Finally, we add a domain discriminator to the output space to implicitly align the feature distributions. Extensive experiments were conducted to validate the effectiveness of VCEIA on the MS-CMRSeg 2019 dataset, which showed competitive results.

关键词： cardiac segmentation domain adaptation distribution alignment variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

variational autoencoder for Anomaly Detection in Event Data in Online Process Mining 23

Variational Autoencoder for Anomaly Detection in Event Data ...

引用

23rd International Conference on Enterprise Information Systems (ICEIS)

作者： Krajsic, Philippe Franczyk, Bogdan Univ Leipzig Business Informat Syst Inst Grimmaische Str 12 Leipzig Germany Wroclaw Univ Econ Business Informat Syst Inst Ul Komandorska 118-120 Wroclaw Poland

ISBN: (纸本)9789897585098

The analysis of event data recorded by information systems is becoming increasingly relevant. An increasing data-centric analysis of processes by using process mining techniques has a direct impact on the management of business processes. To achieve a positive impact on business process management, a high quality data basis is important. This paper presents an approach for the application of variational autoencoder for the filtering of anomalous event data in an online process mining environment, which help to improve the results of process mining techniques and thus positively influence business process management. For anomaly detection in an unsupervised environment, mass-volume and excess-mass scores are used as metrics. The results are compared on the basis of established algorithms such as one-class support vector machine, isolation forest and local outlier factor. These insights are used to highlight the benefits of this approach for process mining and business process management.

关键词： Anomaly Detection Business Process Management Deep Generative Model Process Mining variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

variational autoencoder Inverse Mapper: An End-to-End Deep Learning Framework for Inverse Problems

Variational Autoencoder Inverse Mapper: An End-to-End Deep L...

引用

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

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：