检索结果-内蒙古大学图书馆

EEG-to-EEG: Scalp-to-Intracranial EEG Translation Using a Combination of variational autoencoder and Generative Adversarial Networks

引用

SENSORS 2025年第2期25卷 494-494页

作者： Abdi-Sargezeh, Bahman Shirani, Sepehr Valentin, Antonio Alarcon, Gonzalo Sanei, Saeid Univ Oxford Nuffield Dept Clin Neurosci Oxford OX1 2JD England Kings Coll London Dept Clin Neurosci London WC2R 2LS England UNIV MANCHESTER Sch Med Sci MANCHESTER M13 9PL England Imperial Coll London Dept Elect & Elect Engn London SW7 2AZ England

A generative adversarial network (GAN) makes it possible to map a data sample from one domain to another one. It has extensively been employed in image-to-image and text-to image translation. We propose an EEG-to-EEG translation model to map the scalp-mounted EEG (scEEG) sensor signals to intracranial EEG (iEEG) sensor signals recorded by foramen ovale sensors inserted into the brain. The model is based on a GAN structure in which a conditional GAN (cGAN) is combined with a variational autoencoder (VAE), named as VAE-cGAN. scEEG sensors are plagued by noise and suffer from low resolution. On the other hand, iEEG sensor recordings enjoy high resolution. Here, we consider the task of mapping the scEEG sensor information to iEEG sensors to enhance the scEEG resolution. In this study, our EEG data contain epileptic interictal epileptiform discharges (IEDs). The identification of IEDs is crucial in clinical practice. Here, the proposed VAE-cGAN is firstly employed to map the scEEG to iEEG. Then, the IEDs are detected from the resulting iEEG. Our model achieves a classification accuracy of 76%, an increase of, respectively, 11%, 8%, and 3% over the previously proposed least-square regression, asymmetric autoencoder, and asymmetric-symmetric autoencoder mapping models.

关键词： generative adversarial networks IED detection interictal epileptiform discharge scalp-to-intracranial EEG translation variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

G-VAE: variational autoencoder-based adversarial attacks and defenses in industrial control systems

引用

COMPUTERS & ELECTRICAL ENGINEERING 2025年 124卷

作者： Xu, Lijuan Yang, Zhi Zhao, Dawei Yu, Fuqiang Zhou, Yang Zhang, Hu Qilu Univ Technol Jinan Peoples R China Qilu Univ Technol Shandong Acad Sci Natl Supercomp Ctr Jinan Key Lab Comp Power Network & Informat SecurMinist Jinan 250014 Shandong Peoples R China Shandong Fundamental Res Ctr Comp Sci Shandong Prov Key Lab Ind Network & Informat Syst Jinan 250014 Peoples R China

The industrial control domain is increasingly focused on addressing the cybersecurity challenges posed by adversarial sample attacks. A key difficulty in such attacks on industrial control systems (ICS) is the failure to account for the complex dependencies among various features, making it challenging to learn the relationships between multiple sensors and establish constraints for representing multidimensional data in this domain. Additionally, defending against adversarial samples is hindered by the existence of multiple detection methods and the challenge of creating a defense model without being aware of adversarial samples beforehand. To tackle these challenges, this paper proposes a gated recurrent unit (GRU)-based variational autoencoder (VAE) method for both attacking and defending against adversarial samples. Our approach involves training a GRU model to understand the intrinsic interactions among sensors and then adding perturbations to generate adversarial samples that adhere to feature constraints. On the defense side, we introduce a VAE Feature Weight (VAE-FW) method, which operates without explicit information about the adversarial samples. To make sure that characteristics with the worst prediction outcomes do not dominate anomaly scores in VAE-FW, we equalize the prediction errors across various features. Experiments conducted on three real-world sensor datasets demonstrate that our adversarial attack method significantly enhances attack efficiency while confirming its effectiveness. Furthermore, our defense method, VAEFW, detects anomalies with greater accuracy than current baseline anomaly detection methods, achieving an average increase of 28.8% in AUC values.

关键词： Adversarial sample attack and defense Gated recurrent unit Industrial control system variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Virtual sample generation for soft-sensing in small sample scenarios using glow-embedded variational autoencoder

引用

COMPUTERS & CHEMICAL ENGINEERING 2025年 193卷

作者： Xu, Yan Zhu, Qun-Xiong Ke, Wei He, Yan-Lin Zhang, Ming-Qing Xu, Yuan Beijing Univ Chem Technol Coll Informat Sci & Technol Beijing 100029 Peoples R China Minist Educ China Engn Res Ctr Intelligent PSE Beijing 100029 Peoples R China Macao Polytech Univ Fac Appl Sci Macau 999078 Peoples R China

In industrial processes, limitations of the physical environment, sensors drop-out, and repetitive sampling often lead to insufficient and unevenly distributed representative instances, which greatly hinders the accuracy of soft-sensing models. This paper presents a novel virtual sample generation method based on Glow-embedded variational autoencoder (GVAE-VSG), aimed at enhancing data richness and diversity to improve the modeling performance. Specifically, GVAE-VSG embeds the Glow model from flow transformations into the variational autoencoder. This allows for the derivation of amore generalized posterior distribution without reducing sample dimensionality, thereby ensuring the generation of higher-quality virtual input samples. Subsequently, a nonlinear iterative partial least squares regression framework, incorporating a sparse constrained error matrix, is employed to generate virtual output samples that more closely resemble actual data. Finally, by a synthetic nonlinear function and an actual purification terephthalic acid (PTA) solvent system, the generative and modeling performance of the proposed method are comprehensively assessed.

关键词： Virtual sample generation Glow model variational autoencoder Soft-sensing PTA solvent system

来源：评论

学校读者我要写书评

暂无评论

Lab-ver: an LSTM attention based on variational autoencoder representation learning of remaining useful life estimation

ENGINEERING RESEARCH EXPRESS

引用

ENGINEERING RESEARCH EXPRESS 2025年第1期7卷

作者： Zhang, Chenxu Guo, Yu Zhang, Yanjun North Univ China State Key Lab Extreme Environm Optoelect Dynam Mea Taiyuan 030051 Shanxi Peoples R China Beijing Electromech Engn Inst Beijing 100074 Peoples R China

A representation learning model based on a variational autoencoder(LAB-VER) was introduced for the remaining useful life (RUL) prediction task. Deep learning methods are effective in learning the features within the data and leveraging these features to conduct tests and evaluations on the equipment. However, existing methods often lack the ability to represent data features effectively. To address this limitation, a novel representation learning model based on a variational autoencoder was proposed. The model consists of an encoder and a regression: the encoder learns to decouple the input data into the feature space, while the regression maps the decoupled data features to obtain the prediction results. Within the encoder of the VAE, a parallel information fusion and enhancement approach has been developed, ingeniously integrating the distinct modules of LSTM, multi-head attention, and nonlinear transfer mapping. Within the architecture, a compact fusion sub-module is employed. This approach leverages the processing results of each layer, thereby effectively enhancing the decoupling capability of the encoder component. On the C-MAPSS simulated dataset, the model outperforms most state-of-the-art methods, achieving root mean square errors of 10.10, 10.36, 8.73, and 9.85 on the four sub-datasets, with RUL prediction scores of 231.10, 755.01, 202.62, and 800.79, respectively.

关键词： remaining useful life prediction prognostics and health management representation learning long short-term memory variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

A Guided variational autoencoder for Targeted Molecule Optimization in Drug Discovery

引用

JOURNAL OF HEALTHCARE INFORMATICS RESEARCH 2025年 1-21页

作者： Tan, Da Henry, Christopher J. Leung, Carson K. Univ Manitoba Dept Comp Sci Winnipeg MB Canada

In drug discovery, optimizing molecules to enhance target properties is a crucial step. Recent advances in generative machine learning have facilitated this by exploring molecular structures within a latent representation space. Those studies typically employ encoder-decoder architectures to convert molecules into latent vectors and then reconstruct them. This process often requires complex subsequent editing to produce valid molecules. In this research article, we propose a framework that eliminates this final editing step by directly mapping input molecules to a latent subspace preferred by a binary classifier aimed at the target property. Based on a variational autoencoder (VAE), we integrate an auxiliary classifier in the latent space to steer the training process toward generating molecular fragments that better align with binary labels. We test our model on three benchmark drug optimization tasks, achieving positive outcomes for various molecular properties, including improvement of the target property. This study presents a molecule optimization method particularly effective in settings with limited data and offers insights into molecule substructures that could enhance drug lead properties.

关键词： Healthcare informatics Drug discovery Molecule optimization Generative models variational autoencoder Latent subspace

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graphs (KG) Assisted variational autoencoder (VAE) for Large-Scale Anomaly and Event Detection 16th

Knowledge Graphs (KG) Assisted Variational Autoencoder (VAE)...

引用

16th International Conference on Social Networks Analysis and Mining

作者： Zhao, Ying Naval Postgrad Sch Monterey CA 93943 USA

ISBN: (纸本)9783031785535;9783031785542

This work focuses on general ML/AI assisted analytic processes for monitoring, detection, and classification of anomaly signals from multi-modality sensor data. Specifically, I will show series of variational autoencoders (VAE) including unsupervised AI transformers and related workflow pipelines applied to maritime surveillance in the different time scales of hours, minutes, and seconds. I show these developments using the distributed acoustic sensing (DAS) data set. The DAS data set is from the Sandia National Laboratories. DAS is a special type of fiber optic seafloor communications cables to interrogate the submarine environment at Arctic Alaska. Acoustic heatmaps can be generated to detect waves, ships, marine mammals, and other events. There are 18000 channels and sampled at 1kHZ for the data in 2022. The data set is used to demonstrate the VAE methodology for detecting anomaly, event, and classify objects. The results can enable processing and data analytical capabilities critical to actionable intelligence for mission planning and emerging behavior detection.

关键词： anomaly detection event detection machine learning ML artificial intelligence AI generative AI AI transformer variational autoencoder VAE distributed acoustic sensing DAS heatmap latent variables knowledge graph KG

来源：评论

学校读者我要写书评

暂无评论

Copula entropy regularization transformer with C2 variational autoencoder and fine-tuned hybrid DL model for network intrusion detection

引用

TELEMATICS AND INFORMATICS REPORTS 2025年 17卷

作者： Akkepalli, Srinivas Sagar, K. Osmania Univ Hyderabad 500007 Telagana India JNTUH Sreyas Inst Engn & Technol Hyderabad Telangana India

In cyber security, Intrusion Detection Systems (IDS) act as a network security tool, in which computational complexity and dynamic IDS detection issues are observed by conventional studies. In this paper, a novel Copula Entropy Regularization Transformer with C2 variational autoencoder and Fine-tuned Hybrid Deep Learning (DL) model is introduced for Network Intrusion Detection. In previous IDSs studies, flow-based feature extraction techniques are concentrated, which is ineffective for detecting high-dimensional anomaly data. This work proposes a novel Copula Entropy Regularization Transformer with C2 variational autoencoder for regularizing the feature extraction and feature selection, using a self-paced regularization mechanism. Recently, the pull towards IDS with Zero-Day (ZD) attacks gets increased, and the existing studies over it, possess high False-Negative Rates (FNR), leading to limited practical usage. For reducing the FNR and to improve the identification of ZD, a Finetuned Hybrid DL attack prediction model with deep Transudative Federated Transfer Learning (TFTL) is proposed. This gives out a map connection between known and zero-day attacks, data points for different dynamic network traffic, and classification of known and unknown network attacks. To investigate the ZD attack detection with the proposed model, it is validated in Python platform with Network Intrusion Detection dataset and the performance results show that the work gives better accuracy (98.54%), F1-score (97.5%), recall (97.302%), precision (98.2%) and detection rate of about 0.975%, while the comparative results show that this approach achieves a comparatively low false positive rate of 0.1, yielding high detection rate, and high accuracy in predicting attacks.

关键词： variational autoencoder Euclidian convolutional neural network Copula entropy Self-paced regularization and intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Engineering Dehalogenase Enzymes Using variational autoencoder-Generated Latent Spaces and Microfluidics

引用

JACS AU 2025年第2期5卷 838-850页

作者： Kohout, Pavel Vasina, Michal Majerova, Marika Novakova, Veronika Damborsky, Jiri Bednar, David Marek, Martin Prokop, Zbynek Mazurenko, Stanislav Masaryk Univ Fac Sci Dept Expt Biol Loschmidt Labs Brno 61137 Czech Republic Masaryk Univ Fac Sci RECETOX Brno 61137 Czech Republic St Annes Univ Hosp Int Clin Res Ctr Brno 65691 Czech Republic

Enzymes play a crucial role in sustainable industrial applications, with their optimization posing a formidable challenge due to the intricate interplay among residues. Computational methodologies predominantly rely on evolutionary insights of homologous sequences. However, deciphering the evolutionary variability and complex dependencies among residues presents substantial hurdles. Here, we present a new machine-learning method based on variational autoencoders and evolutionary sampling strategy to address those limitations. We customized our method to generate novel sequences of model enzymes, haloalkane dehalogenases. Three design-build-test cycles improved the solubility of variants from 11% to 75%. Thorough experimental validation including the microfluidic device MicroPEX resulted in 20 multiple-point variants. Nine of them, sharing as little as 67% sequence similarity with the template, showed a melting temperature increase of up to 9 degrees C and an average improvement of 3 degrees C. The most stable variant demonstrated a 3.5-fold increase in activity compared to the template. High-quality experimental data collected with 20 variants represent a valuable data set for the critical validation of novel protein design approaches. Python scripts, jupyter notebooks, and data sets are available on GitHub (https://***/loschmidt/vae-dehalogenases), and interactive calculations will be possible via https://***/fireprotasr/.

关键词： dehalogenase protein engineering machinelearning microfluidics protein stability variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Unlearning of Multiple Protected User Attributes From variational autoencoder Recommenders Using Adversarial Training 5th

Simultaneous Unlearning of Multiple Protected User Attribute...

引用

5th International Workshop on Algorithmic Bias in Search and Recommendation

作者： Escobedo, Gustavo Ganhoer, Christian Brandl, Stefan Augstein, Mirjam Schedl, Markus Johannes Kepler Univ Linz Linz Austria Linz Inst Technol Linz Austria Univ Appl Sci Upper Austria Hagenberg Austria

ISBN: (纸本)9783031719745;9783031719752

In widely used neural network-based collaborative filtering models, users' history logs are encoded into latent embeddings that represent the users' preferences. In this setting, the models are capable of mapping users' protected attributes (e.g., gender or ethnicity) from these user embeddings even without explicit access to them, resulting in models that may treat specific demographic user groups unfairly and raise privacy issues. While prior work has approached the removal of a single protected attribute of a user at a time, multiple attributes might come into play in real-world scenarios. In the work at hand, we present ADVXMULTVAE which aims to unlearn multiple protected attributes (exemplified by gender and age) simultaneously to improve fairness across demographic user groups. For this purpose, we couple a variational autoencoder (VAE) architecture with adversarial training (ADVMULTVAE) to support simultaneous removal of the users' protected attributes with continuous and/or categorical values. Our experiments on two datasets, LFM-2B-100K and ML-1M, from the music and movie domains, respectively, show that our approach can yield better results than its singular removal counterparts (based on ADVMULTVAE) in effectively mitigating demographic biases whilst improving the anonymity of latent embeddings.

关键词： Recommender Systems Collaborative Filtering variational autoencoder Privacy Debiasing

来源：评论

学校读者我要写书评

暂无评论

SC-VAE: Sparse coding-based variational autoencoder with learned ISTA

引用

PATTERN RECOGNITION 2025年 161卷

作者： Xiao, Pan Qiu, Peijie Ha, Sung Min Bani, Abdalla Zhou, Shuang Sotiras, Aristeidis Washington Univ Sch Med St Louis Dept Radiol St Louis MO 63110 USA Washington Univ Sch Med St Louis Dept Radiat Oncol St Louis MO 63110 USA Washington Univ Inst Informat Data Sci & Biostat Sch Med St Louis St Louis MO 63110 USA

Learning rich data representations from unlabeled data is a key challenge towards applying deep learning algorithms in downstream tasks. Several variants of variational autoencoders (VAEs) have been proposed to learn compact data representations by encoding high-dimensional data in a lower dimensional space. Two main classes of VAEs methods may be distinguished depending on the characteristics of the meta-priors that are enforced in the representation learning step. The first class of methods derives a continuous encoding by assuming a static prior distribution in the latent space. The second class of methods learns instead a discrete latent representation using vector quantization (VQ) along with a codebook. However, both classes of methods suffer from certain challenges, which may lead to suboptimal image reconstruction results. The first class suffers from posterior collapse, whereas the second class suffers from codebook collapse. To address these challenges, we introduce a new VAE variant, termed sparse coding-based VAE with learned ISTA (SCVAE), which integrates sparse coding within variational autoencoder framework. The proposed method learns sparse data representations that consist of a linear combination of a small number of predetermined orthogonal atoms. The sparse coding problem is solved using a learnable version of the iterative shrinkage thresholding algorithm (ISTA). Experiments on two image datasets demonstrate that our model achieves improved image reconstruction results compared to state-of-the-art methods. Moreover, we demonstrate that the use of learned sparse code vectors allows us to perform downstream tasks like image generation and unsupervised image segmentation through clustering image patches. The code is available at https://***/sotiraslab/SC-VAE.

关键词： Sparse coding variational autoencoder Learned iterative shrinkage thresholding algorithm

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：