检索结果-内蒙古大学图书馆

Inverse design of ventilated acoustic resonators using a sound transmission loss-encoded variational autoencoder

JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY 2025年第2期39卷 509-518页

作者： Song, Jin Yeong Hwang, Seok Hyeon Cho, Min Woo Ko, Keon Kim, Baekgyu Song, Kyungjun Park, Sang Min Pusan Natl Univ Sch Mech Engn Busan 46241 South Korea

Ventilated acoustic resonators (VARs) for simultaneous sound attenuation and ventilation have presented a unique challenge in acoustics. Traditional methods for designing VARs are limited by their reliance on human intuition and extensive computational resources. This study proposes a novel sound transmission loss-encoded variational autoencoder (STL-VAE) for the inverse design of ventilated acoustic resonators (VARs). The STL-VAE model overcomes these limitations by encoding the target sound transmission loss (STL) into a latent space, enabling the generation of VAR designs that achieve broadband sound attenuation. STL-VAE significantly reduces the mean squared error (MSE) between the target STL and the generated VAR designs, outperforming the best designs from the training dataset by over 100fold. The proposed method offers a highly efficient and accurate approach for designing complex acoustic metamaterials with applications in urban and industrial noise mitigation.

关键词： Deep generative model Inverse design Acoustic resonator Acoustic metamaterial variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Runner system geometry prediction using variational autoencoder deep learning model

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 150卷

作者： Kurkin, Evgenii Pioquinto, Jose Gabriel Quijada Chertykovtseva, Vladislava Minaev, Evgenii Samara Natl Res Univ Dept Aircraft Construct & Design Samara 443086 Russia

The novelty of this article is the choice of the architecture of neural networks for fluid channel topology optimization and its application in the design of multi-cavity injection molds. A generative deep learning model was developed to extract characteristics representing the inverse field of the permeability of a fluid in a porous medium, which in turn represents the runner system geometry of a thermoplastic injection mold. The model comprises a variational autoencoder network and multilayer perceptron. The characteristics extracted from the variational autoencoder are used as a set of multilayer perceptron output vectors, whereas the input data are determined by the positions of the input and outputs of the injection channels. The field of the inverse permeability in each case was obtained by topology optimization using a heuristic algorithm. The trained model displayed statistical metrics indicating good performance and task generalizability. The mean absolute error was 0.0106 for the entire dataset. Speed up compared to traditional computational fluid dynamics software was 625 times faster in one case. For 150 cases, it was 76907 times faster. The purpose of generating a deep learning model in this area is to reduce the design time of injection molds and the computational requirements. The developed neural network reduces the runner system volume by 16% or its hydraulic resistance by 25%.

关键词： Multilayer perceptron variational autoencoder Principal component analysis Deep learning Runner system geometry

来源：评论

学校读者我要写书评

暂无评论

XIDINTFL-VAE: XGBoost-based intrusion detection of imbalance network traffic via class-wise focal loss variational autoencoder

引用

JOURNAL OF SUPERCOMPUTING 2025年第1期81卷 1-38页

作者： Abdulganiyu, Oluwadamilare Harazeem Tchakoucht, Taha Ait Saheed, Yakub Kayode Ahmed, Hilali Alaoui Euro Mediterranean Univ Fes Euromed Res Ctr Sch Digital Engn & Artificial Intelligence UEMF Fes Morocco Amer Univ Nigeria Sch IT & Comp Yola Nigeria

Intrusion Detection Systems (IDS) face significant challenges in detecting minority class attacks within imbalanced network traffic, where traditional methods often struggle to maintain high accuracy without sacrificing key performance metrics like precision and recall. This study introduces the XIDINTFL-VAE framework, which leverages Class-Wise Focal Loss (CWFL) and variational autoencoder (VAE) integrated with XGBoost to effectively address this imbalance. Our approach is designed to enhance the detection of minority class intrusions while maintaining robust overall performance. Current techniques, such as SMOTE and its variants, often fail to balance precision and recall adequately in highly imbalanced datasets, resulting in either high false positives or missed detections. The proposed method directly addresses this gap by generating synthetic data tailored to the most challenging cases within the minority class, thereby improving the classifier's ability to detect these rare but critical instances. A comparative analysis of the proposed XIDINTFL-VAE method was conducted against various oversampling techniques, including SMOTE, Borderline-SMOTE, and Adaptive Synthetic Sampling (ADASYN), as well as traditional classifiers like Logistic Regression, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Decision Tree. While existing techniques focus on balancing datasets or generating realistic data, the CWFL-VAE method takes a more targeted approach by generating synthetic data that specifically enhances the classifier's ability to handle challenging minority class instances. Experimental evaluations using the NSL-KDD and CSE-CIC-IDS2018 datasets demonstrate that the XIDINTFL-VAE model outperforms traditional methods, achieving a precision of 99.67% and an F1 score of 94.74%, with a slight trade-off in recall at 89.41%. These results underscore the model's capability to reduce false positives while maintaining high detection rates, which is crucial for real-

关键词： Intrusion detection system Imbalance network traffic Focal loss variational autoencoder Extreme gradient boosting

来源：评论

学校读者我要写书评

暂无评论

Nonlinear interpolated variational autoencoder for generalized fluid content estimation

GEOENERGY SCIENCE AND ENGINEERING

引用

GEOENERGY SCIENCE AND ENGINEERING 2025年 244卷

作者： Arief, Hasan Asyari Thomas, Peter James Li, Weichang Brekken, Christian Hjelstuen, Magnus Smith, Ivar Eskerud Kragset, Steinar Katsaggelos, Aggelos NORCE Norwegian Res Ctr AS N-5008 Bergen Norway SINTEF AS N-7034 Trondheim Norway Northwestern Univ Elect & Comp Evanston IL 60208 USA Aramco Res Ctr Houston TX 77084 USA

Generalizing machine learning models for petroleum applications, especially in scenarios with limited and less varied training data compared to real-world conditions, remains a persistent challenge. This study introduces a novel method combining interpolation mixup with a variational autoencoder (VAE) and adaptable interpolation loss for downstream regression tasks. By implementing this approach, we generate high-quality interpolated samples, yielding accurate estimations. Experimental validation on a real-world industrial dataset focused on fluid content measurement demonstrates the superior performance of our method compared to other interpolation and regularization techniques. Our approach achieves over a 15% improvement on generalized out-of-distribution datasets, offering crucial insights for fluid content estimation and practical implications for industrial applications.

关键词： Distributed acoustic sensor variational autoencoder Out-of-distribution regression Fluid content estimation

来源：评论

学校读者我要写书评

暂无评论

Graph convolutional network based on self-attention variational autoencoder and capsule contrastive learning for aspect-based sentiment analysis

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 279卷

作者： Wang, Xinyue Liu, Long Chen, Zhuo Wang, Haiyan Yu, Bin Qingdao Univ Sci & Technol Sch Data Sci Qingdao 266061 Peoples R China Qingdao Univ Sci & Technol Sch Foreign Languages Qingdao 266061 Peoples R China Univ Sci & Technol China Sch Artificial Intelligence & Data Sci Hefei 230026 Peoples R China

Aspect-based sentiment analysis (ABSA) predicts sentiment polarity by aligning aspect words with their matching sentiment words in sentences at a fine-grained level. Previous methods have limitations, such as over-reliance on syntactic trees ignoring semantic and global information, and difficulty in solving long-distance dependency problems. In response to these issues, this article puts forward a hybrid graph convolutional network (GCN) called SVCCL-GCN, which combines an improved variational autoencoder (VAE) and a contrastive learning module. First, construct dependency graph structures using syntactic dependency trees to obtain explicit syntactic dependency information. Then, a VAE module based on the self-attention mechanism is devised to acquire both global and local information of the data, and it is beneficial for capturing the explicit associations between aspect terms and relevant contexts to solve the long-distance dependency problems. Finally, so as to stimulate the model's capacity to flexibly learn comprehensive semantic information and emotional feature information between different words, a contrastive learning loss based on the capsule network is constructed by taking the output of the capsule network as the contrastive feature for unsupervised contrastive learning. The extensive experimental findings on five benchmark datasets demonstrate that SVCCL-GCN productively improves the accuracy in distinguishing sentiment polarity. The source codes and datasets are available at https://github. com/YuBinLab-QUST/SVCCL-GCN/.

关键词： Aspect-based sentiment analysis Graph convolutional network variational autoencoder Capsule contrastive learning

来源：评论

学校读者我要写书评

暂无评论

One-step variation included compact modeling with conditional variational autoencoder

引用

SOLID-STATE ELECTRONICS 2025年 227卷

作者： Wang, Shuhan Zhou, Zheng Tang, Zili Xu, Jinghan Liu, Xiaoyan Zhang, Xing Peking Univ Sch Integrated Circuits Beijing 100871 Peoples R China Beijing Adv Innovat Ctr Integrated Circuits Beijing 100871 Peoples R China

Efficient and accurate variation modeling serves as a critical part in circuit evaluation, which can reproduce actual electrical behavior of semiconductor devices. Conventional variation modeling usually consists of two steps: compact modeling the basic electrical properties and sub-modeling the variation sources introduced in MOSFET manufacturing process, mostly structural and doping parameters. This lengthy process results in a gap between device production and rapid circuit analysis. In order to improve modeling efficiency, in this work, we propose a one-step variation-included compact modeling approach leveraging machine learning. Utilizing conditional variational autoencoder (cVAE), currents with variation are directly constructed without the submodeling step, as variation sources of the cVAE model are automatically extracted. Benchmark against prior distribution of dataset generated by Monte Carlo simulation of BSIM-CMG, normalized variation in figure of merits (FoMs) of cVAE generated I-V curves are all above 0.9. After implementing the model in SPICE, high accuracy in circuit-level variation modeling also indicates the potential of the proposed model.

关键词： Compact model Machine learning variational autoencoder Variation modeling

来源：评论

学校读者我要写书评

暂无评论

ECG Sensor Design Assessment with variational autoencoder-Based Digital Watermarking

引用

SENSORS 2025年第7期25卷 2321-2321页

作者： Hsu, Chih-Yu Chang, Chih-Yin Chen, Yin-Chi Wu, Jasper Chen, Shuo-Tsung Fujian Univ Technol Sch Transportat Fuzhou 350118 Peoples R China Chung Shan Med Univ Dept Med Informat Taichung 40201 Taiwan Kang Chiao Int Sch Linkou Campus New Taipei 23153 Taiwan Natl Kaohsiung Univ Sci & Technol Dept Elect Engn Kaohsiung 807618 Taiwan

Designing an ECG sensor circuit requires a comprehensive approach to detect, amplify, filter, and condition the weak electrical signals produced by the heart. To evaluate sensor performance under realistic conditions, diverse ECG signals with embedded watermarks are generated, enabling an assessment of how effectively the sensor and its signal-conditioning circuitry handle these modified signals. A variational autoencoder (VAE) framework is employed to generate the watermarked ECG signals, addressing critical concerns in the digital era, such as data security, authenticity, and copyright protection. Three watermarking strategies are examined in this study: embedding watermarks in the mean (mu) of the VAE's latent space, embedding them through the latent variable (z), and using post-reconstruction watermarking in the frequency domain. Experimental results demonstrate that watermarking applied through the mean (mu) and in the frequency domain achieves a low Mean Squared Error (MSE) while maintaining stable signal fidelity across varying watermark strengths (alpha), latent space dimensions, and noise levels. These findings indicate that the mean (mu) and frequency domain methods offer robust performance and are minimally affected by changes in these parameters, making them particularly suitable for preserving ECG signal quality. By contrasting these methods, this study provides insights into selecting the most appropriate watermarking technique for ECG sensor applications. Incorporating watermarking into sensor design not only strengthens data security and authenticity but also supports reliable signal acquisition in modern healthcare environments. Overall, the results underscore the effectiveness of combining VAEs with watermarking strategies to produce high-fidelity, resilient ECG signals for both sensor performance evaluation and the protection of digital content.

关键词： variational autoencoder Fourier-simulated ECG dataset latent variable space watermarking technology

来源：评论

学校读者我要写书评

暂无评论

An extended variational autoencoder for cross-subject electromyograph gesture recognition

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2025年 99卷

作者： Zhang, Zhen Ming, Yuewei Shen, Quming Wang, Yanyu Zhang, Yuhui Shanghai Univ Sch Mechatron Engn & Automat Shanghai 200444 Peoples R China Shanghai Jiao Tong Univ Renji Hosp Dept Spine Surg Sch Med Shanghai 200127 Peoples R China

Surface electromyographic hand gesture recognition has gained significant attention in recent years, especially within the field of human-computer interfaces. However, cross-subject tasks remain challenging due to inherent individual differences. To address this, a novel approach for hand gesture recognition is proposed that leverages a subject-generalized variational autoencoder. This approach involves an extended variational autoencoder designed to disentangle input data into three distinct feature-specific representations. The primary classifier within the variational autoencoder focuses on gesture recognition, while two auxiliary classifiers work together to extract subject-specific and gesture-specific features. The gesture-specific features capture generalized characteristics applicable across all subjects, enabling direct application to new subjects. To enhance accuracy and stability, a competitive voting strategy is implemented. The effectiveness of the proposed method was evaluated using a dataset comprising six representative gestures performed by eight subjects. Comparative analysis with baseline models shows that our approach outperforms others, demonstrating superior generalization with an average accuracy of 90.52% in cross-subject validation.

关键词： Surface electromyographic Gesture recognition Cross-subject Feature disentanglement variational autoencoder Competitive voting

来源：评论

学校读者我要写书评

暂无评论

Generative autoencoder to prevent overregularization of variational autoencoder

引用

ETRI JOURNAL 2025年第1期47卷 80-89页

作者： Ko, YoungMin Ko, SunWoo Kim, YoungSoo Jeonju Univ Dept Artificial Intelligence Jeonju South Korea Jeonbuk Univ Artificial Intelligence Res Lab Jeonju South Korea

In machine learning, data scarcity is a common problem, and generative models have the potential to solve it. The variational autoencoder is a generative model that performs variational inference to estimate a low-dimensional posterior distribution given high-dimensional data. Specifically, it optimizes the evidence lower bound from regularization and reconstruction terms, but the two terms are imbalanced in general. If the reconstruction error is not sufficiently small to belong to the population, the generative model performance cannot be guaranteed. We propose a generative autoencoder (GAE) that uses an autoencoder to first minimize the reconstruction error and then estimate the distribution using latent vectors mapped onto a lower dimension through the encoder. We compare the Frechet inception distances scores of the proposed GAE and nine other variational autoencoders on the MNIST, Fashion MNIST, CIFAR10, and SVHN datasets. The proposed GAE consistently outperforms the other methods on the MNIST (44.30), Fashion MNIST (196.34), and SVHN (77.53) datasets.

关键词： autoencoder data augmentation dimensionality reduction generative model variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

An explainable variational autoencoder model for three-dimensional acoustic emission source localization in hollow cylindrical structures

引用

STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL 2025年第3期24卷 1601-1618页

作者： Lee, Guan-Wei Livadiotis, Stylianos Salamone, Salvatore Univ Texas Austin Dept Civil Architectural & Environm Engn 301 DeanKeeton C1748 Room ECJ 4-710 Austin TX 78758 USA

We introduce an explainable variational autoencoder for three-dimensional (3D) localization of acoustic emission sources in hollow cylindrical structures, with an unsupervised approach. This research capitalizes on multi-arrival waveforms generated by helical path propagation in cylindrical geometries to enable efficient two-receiver localization. By integrating the modal characteristics of Lamb modes under multi-path conditions, we demonstrate that two sets of time-of-arrival differences and peak amplitudes extracted from one receiver can serve as effective localization features. This initial approach identifies four potential source locations, highlighting the feasibility of two-receiver source localization using traditional feature extraction methods. However, direct extraction can be challenging when mode overlaps occur, complicating the localization process. To address this, our work proposes a novel waveform-based method. This method leverages the consistent dispersion characteristics within isotropic materials, where each unique combination of mode arrival times and peak amplitudes constructs a distinct waveform. This distinctiveness overcomes the ambiguities associated with mode overlaps, significantly enhancing the method's precision and robustness. Our approach adopts a data-driven strategy for waveform-based localization using variational autoencoder (VAE). VAE discerns waveform patterns for localization, while also addressing data uncertainties. The VAE's encoder and decoder networks capture the localization process and the source's influence on waveform generation, respectively, guiding latent variables to segregate waveforms by source in the latent space. The design of the learning process focuses on specific localization characteristics to enhance result explainability. Localization predictions are generated by projecting test waveforms, not included in the training set, onto a trained latent space. The prediction is determined using a nearest-neighbo

关键词： Acoustic emission source localization Lamb waves variational autoencoder cylindrical structures explainable deep 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：