检索结果-内蒙古大学图书馆

Improving disentanglement in variational auto-encoders via feature imbalance-informed dimension weighting

KNOWLEDGE-BASED SYSTEMS 2024年 296卷

作者： Liu, Yue Yu, Zhenyao Liu, Zitu Yu, Ziyi Yang, Xinyan Li, Xingyue Guo, Yike Liu, Qun Wang, Guoyin Shanghai Univ Sch Comp Engn & Sci Shanghai 200444 Peoples R China Shanghai Engn Res Ctr Intelligent Comp Syst Shanghai 200444 Peoples R China Imperial Coll London Dept Comp London SW7 2AZ England Chongqing Univ Posts & Telecommun Chongqing Key Lab Computat Intelligence Chongqing 400065 Peoples R China Shanghai Univ Coll Sci Shanghai 200444 Peoples R China

Using variational Auto-Encoder (VAE) to learn disentangled representation holds great promise. But there is a feature imbalance in the learning process of VAEs, and the model usually concentrates on the learning of some dimensions at the expense of others. Instead of attempting to rectify it, we exploit feature imbalance to propose a Dimension Weighting method that can boost the disentanglement effect of VAE-based models. In order to conduct disentanglement learning under a fixed size of the latent space, the intrinsic dimension of raw data is estimated by a Dimension Number Estimator and set as the latent space size. Then, leveraging the feature imbalance, a Dimension Importance Evaluator is constructed to separate each dimension in the latent variable into important, unimportant, and general dimensions. By exerting different learning pressures on specific dimensions, we further optimize the variational lower bound of model and retrain it, thus promoting the disentanglement of important dimensions. The experiments on four benchmark datasets show that the Dimension Weighting can further improve the disentangling effect without compromising model performance, and in approximately 80% of cases, the results in disentangling metric evaluation experiments achieve better disentangling scores than the original models. This reveals that not all dimensions of the latent variables are equally influential. By focusing on the crucial dimensions within the latent representation, the model can achieve better performance.

关键词： variational autoencoder Latent space Disentangled representation Dimension weighting

来源：评论

学校读者我要写书评

暂无评论

GenCoder: A Generative AI-Based Adaptive Intra-Vehicle Intrusion Detection System

引用

IEEE ACCESS 2024年 12卷 150651-150663页

作者： Smolin, Mikhail Kyrgyz State Tech Univ Dept Appl Math & Comp Sci Bishkek 720044 Kyrgyzstan

With the rapid expansion of the vehicular cybersecurity (VCS) market and the increasing sophistication of cyberthreats, developing an adaptive intra-vehicular intrusion detection system (IDS) is crucial. This paper introduces GenCoder, a generative artificial intelligence (GenAI)-based IDS that uniquely addresses the dynamic and evolving nature of vehicular cyberthreats. GenCoder combines a five-layer deep neural network (DNN) with a variational autoencoder (VAE), overseen by a novel communication layer known as the GenCoder layer. This system dynamically adapts to new intrusion patterns by generating and utilizing new training data when deviations from known patterns are detected. The generated samples have a Shannon entropy (SE) value of 1.65 bits for four classes, indicating standard variety among the synthetic data. GenCoder demonstrates exceptional adaptability, pushing the accuracy, precision, recall, and F1-score from 84.79%, 83.58%, 83.70%, and 83.64% to 92.19%, 90.12%, 90.44%, and 90.28%, respectively, after introducing 50% feature deformation to testing data. The novel concept of an adaptive intra-vehicular IDS, the innovative GenCoder layer that establishes seamless communication among the DNN, the VAE, and the dataset, as well as the unique assessment strategies of adaptability make this research exceptional with the potential to create a new dimension in automotive IDS research.

关键词： Computer crime Automobiles Principal component analysis Intrusion detection Adaptive systems Protocols NSL-KDD Vehicle dynamics Support vector machines Artificial neural networks Artificial intelligence Generative AI Encoding Adaptive intrusion detection automotive cybersecurity deep neural network GenCoder layer generative artificial intelligence variational autoencoder vehicular intrusion detection system

来源：评论

学校读者我要写书评

暂无评论

Dynamic behavior recognition in aerial deployment of multi-segmented foldable-wing drones using variational autoencoders

引用

CHINESE JOURNAL OF AERONAUTICS 2025年第6期38卷

作者： Dou, Yilin Zhou, Zhou Wang, Rui Northwestern Polytech Univ Sch Aeronaut Xian 710072 Peoples R China Natl Key Lab Aircraft Configurat Design Xian 710072 Peoples R China

The aerial deployment method enables Unmanned Aerial Vehicles (UAVs) to be directly positioned at the required altitude for their mission. This method typically employs folding technology to improve loading efficiency, with applications such as the gravity-only aerial deployment of high-aspect-ratio solar-powered UAVs, and aerial takeoff of fixed-wing drones in Mars research. However, the significant morphological changes during deployment are accompanied by strong nonlinear dynamic aerodynamic forces, which result in multiple degrees of freedom and an unstable character. This hinders the description and analysis of unknown dynamic behaviors, further leading to difficulties in the design of deployment strategies and flight control. To address this issue, this paper proposes an analysis method for dynamic behaviors during aerial deployment based on the variational autoencoder (VAE). Focusing on the gravity-only deployment problem of highaspect-ratio foldable-wing UAVs, the method encodes the multi-degree-of-freedom unstable motion signals into a low-dimensional feature space through a data-driven approach. By clustering in the feature space, this paper identifies and studies several dynamic behaviors during aerial deployment. The research presented in this paper offers a new method and perspective for feature extraction and analysis of complex and difficult-to-describe extreme flight dynamics, guiding the research on aerial deployment drones' design and control strategies. (c) 2025 Published by Elsevier Ltd on behalf of Chinese Society of Aeronautics and Astronautics. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Dynamic behavior recogni tion Aerial deployment technol ogy variational autoencoder Pattern recognition Multi-rigid-body dynamics

来源：评论

学校读者我要写书评

暂无评论

A deep representation learning speech enhancement method using β-VAE 30

A deep representation learning speech enhancement method usi...

引用

30th European Signal Processing Conference (EUSIPCO)

作者： Xiang, Yang Hojvang, Jesper Lisby Rasmussen, Morten Hojfeldt Christensen, Mads Graesboll Aalborg Univ Audio Anal Lab CREATE Aalbory Denmark Capturi AS Aarhus Denmark

ISBN: (纸本)9789082797091

In previous work, we proposed a variational autoencoder-based (VAE) Bayesian permutation training speech enhancement (SE) method (PVAE) which indicated that the SE performance of the traditional deep neural network-based (DNN) method could be improved by deep representation learning (DRL). Based on our previous work, we in this paper propose to use beta-VAE to further improve PVAE's ability of representation learning. More specifically, our beta-VAE can improve PVAE's capacity of disentangling different latent variables from the observed signal without the trade-off problem between disentanglement and signal reconstruction. This trade-off problem widely exists in previous beta-VAE algorithms. Unlike the previous beta-VAE algorithms, the proposed beta-VAE strategy can also be used to optimize the DNN's structure. This means that the proposed method can not only improve PVAE's SE performance but also reduce the number of PVAE training parameters. The experimental results show that the proposed method can acquire better speech and noise latent representation than PVAE. Meanwhile, it also obtains a higher scale-invariant signal-to-distortion ratio, speech quality, and speech intelligibility.

关键词： deep representation learning speech enhancement variational autoencoder beta-VAE

来源：评论

学校读者我要写书评

暂无评论

User Activity Detection for mmWave Grant-free IoT Networks 27

User Activity Detection for mmWave Grant-free IoT Networks

引用

27th Asia-Pacific Conference on Communications (APCC) - Creating Innovative Communication Technologies for Post-Pandemic Era

作者： Wu, Shanai Shin, Yoan Soongsil Univ Sch Elect Engn Seoul South Korea

ISBN: (数字)9781665499279

ISBN: (纸本)9781665499279

Considering sporadic traffic in IoT networks, grantfree random access is inevitable. In a grant-free random access system, channel estimation and activity detection are crucial to enable data transmission. In this paper, we propose a deep learning-based activity detection scheme for mmWave grant-free IoT networks, and the detection accuracy is validated by the simulation result.

关键词： grant-free IoT mmWave channel virtual representation activity detection variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

3D MRI Brain Tumour Segmentation with autoencoder Regularization and Hausdorff Distance Loss Function 7th

3D MRI Brain Tumour Segmentation with Autoencoder Regulariza...

引用

7th International Brain Lesion Workshop (BrainLes)

作者： Fonov, Vladimir S. Rosa-Neto, Pedro Collins, D. Louis McGill Univ McConnell Brain Imaging Ctr Montreal Neurol Inst Montreal PQ Canada McGill Univ Translat Neuroimaging Lab McGill Univ Res Ctr Studies Aging Douglas Hosp Montreal PQ Canada

ISBN: (纸本)9783031089992;9783031089985

Manual segmentation of the Glioblastoma is a challenging task for the radiologists, essential for treatment planning. In recent years deep convolutional neural networks have been shown to perform exceptionally well, in particular the winner of the BraTS challenge 2019 uses 3D U-net architecture in combination with variational autoencoder, using Dice overlap measure as a cost function. In this work we are proposing a loss function that approximates Hausdorff Distance metric that is used to evaluate performance of different segmentation in the hopes that it will allow achieving better performance of the segmentation on new data.

关键词： Brain tumor U-Net variational autoencoder Hausdorff distance

来源：评论

学校读者我要写书评

暂无评论

Pilot Decontamination Scheme for mmWave Grant-free IoT Networks

Pilot Decontamination Scheme for mmWave Grant-free IoT Netwo...

引用

IEEE VTS Asia Pacific Wireless Communications Symposium (APWCS)

作者： Wu, Shanai Shin, Yoan Soongsil Univ Sch Elect Engn Seoul South Korea

ISBN: (数字)9781665471213

ISBN: (纸本)9781665471213

In this paper, we propose a deep learning-based pilot decontamination scheme for mmWave grant-free IoT networks. Considering sporadic traffic in IoT networks, grant-free random access is inevitable and enables massive machine connections in IoT networks. Despite its great potential, grant-free random access is vulnerable to pilot contamination. To tackle the pilot contamination problem, we utilize the channel virtual representation to emphasize the characteristics of a mmWave channel. We utilize a variational autoencoder to reconstruct a decontaminated channel, and the simulation results validate the decontamination performance of the proposed scheme.

关键词： grant-free IoT mmWave channel virtual representation pilot decontamination variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

COIL: Constrained Optimization in Learned Latent Space

COIL: Constrained Optimization in Learned Latent Space

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Bentley, Peter J. Lim, Soo Ling Gaier, Adam Tran, Linh UCL Dept Comp Sci Autodesk Res London England UCL Dept Comp Sci London England Autodesk Res London England

ISBN: (纸本)9781450392686

Constrained optimization problems can be difficult because their search spaces have properties not conducive to search, e.g., multimodality, discontinuities, or deception. To address such difficulties, considerable research has been performed on creating novel evolutionary algorithms or specialized genetic operators. However, if the representation that defined the search space could be altered such that it only permitted valid solutions that satisfied the constraints, the task of finding the optimal would be made more feasible without any need for specialized optimization algorithms. We propose Constrained Optimization in Latent Space (COIL), which uses a VAE to generate a learned latent representation from a dataset comprising samples from the valid region of the search space according to a constraint, thus enabling the optimizer to find the objective in the new space defined by the learned representation. Preliminary experiments show promise: compared to an identical GA using a standard representation that cannot meet the constraints or find fit solutions, COIL with its learned latent representation can perfectly satisfy different types of constraints while finding high-fitness solutions.

关键词： variational autoencoder Learning latent representations Genetic algorithm Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

CSI CLUSTERING WITH variational AUTOENCODING 47

CSI CLUSTERING WITH VARIATIONAL AUTOENCODING

引用

47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Baur, Michael Wuerth, Michael Koller, Michael Andrei, Vlad-Costin Utschick, Wolfgang Tech Univ Munich Dept Elect & Comp Engn Munich Germany

ISBN: (纸本)9781665405409

The model order of a wireless channel plays an important role for a variety of applications in communications engineering, e.g., it represents the number of resolvable incident wave-fronts with non-negligible power incident from a transmitter to a receiver. Areas such as direction of arrival estimation leverage the model order to analyze the multipath components of channel state information. In this work, we propose to use a variational autoencoder to group unlabeled channel state information with respect to the model order in the variational autoencoder latent space in an unsupervised manner. We validate our approach with simulated 3GPP channel data. Our results suggest that, in order to learn an appropriate clustering, it is crucial to use a more flexible likelihood model for the variational autoencoder decoder than it is usually the case in standard applications.

关键词： variational autoencoder generative modeling latent space vector channels clustering

来源：评论

学校读者我要写书评

暂无评论

Neural Topic Modeling with Gaussian Mixture Model and Householder Flow 26th

Neural Topic Modeling with Gaussian Mixture Model and Househ...

引用

26th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)

作者： Zhou, Cangqi Xu, Sunyue Ban, Hao Zhang, Jing Nanjing Univ Sci & Technol Nanjing Peoples R China SenseDeal Intelligent Technol Co Ltd Beijing Peoples R China Southeast Univ Nanjing Peoples R China

ISBN: (纸本)9783031059360;9783031059353

To overcome high computational cost suffered by statistical inference algorithms used in traditional topic models, recently, variational autoencoder (VAE) frameworks have been proposed for topic modeling. However, the vanilla VAE model is originally introduced for unsupervised learning, which cannot meet more precise and customized requirements. In addition, the approximate posterior distribution in VAE is often selected as a Gaussian with a diagonal covariance matrix. This unimodal choice may hinder the ability of representation of latent space. In view of these limitations, in this paper, we propose to use Gaussian mixture model and Householder Flows for topic modeling under semi-supervised settings. We assume a document is associated with a mixture of classes, and a class is modeled as a multivariate Gaussian over latent topics. Specifically, an input document is encoded by a network into a discrete distribution, which not only serves the classifier for prediction, but also acts as mixing weights of Gaussian components. Another network is adopted to learn the parameters of Gaussian components. Additionally, Gaussian mixture is transformed by a Householder Flow to produce a more general posterior distribution. The effectiveness of the proposed model has been validated by the experiments performed on several standard datasets.

关键词： Topic model variational autoencoder Semi-supervised learning Gaussian mixture model Householder flow

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：