检索结果-内蒙古大学图书馆

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

Inverse design of non-parametric acoustic metamaterials via transfer-learned dual variational autoencoder with latent space-based data augmentation

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 151卷

作者： Ko, Keon Cho, Min Woo Song, Kyungjun Park, Dong Yong Park, Sang Min Pusan Natl Univ Sch Mech Engn 63-2 Busan Univ Ro Busan 46241 South Korea Korea Inst Ind Technol Adv Mobil Components Grp 320 Techno sunhwan Ro Yuga South Korea

A ventilated acoustic resonator (VAR), a class of acoustic metamaterial, offers an effective noise reduction solution in urban environments, where ventilation is essential. The significant non-linearity between the VAR structure and the corresponding acoustic response poses substantial challenges to the inverse design of VAR through analytical approaches. Although deep learning has been employed to address the inverse design of such structures, conventional deep learning-based inverse design methods are constrained to parameter-defined structures, which exhibit limited design flexibility, thereby hindering the achievement of highly accurate inverse design. To address this challenge, we propose a novel inverse design framework for non-parametric VAR, composed of a dual-variational autoencoder (Dual-VAE) and iterative transfer learning method. Dual-VAE consists of structure variational autoencoder and acoustic response variational autoencoder with their latent space aligned to facilitate accurate inverse design of non-parametric VAR structures exhibiting the target acoustic response. The iterative transfer learning method is employed to enhance the inverse design performance of the Dual-VAE by progressively augmenting the initial training dataset, which consists solely of parametric VAR structures, with generated non-parametric VAR structures. The transfer-learned Dual-VAE demonstrated approximately a 32.27 % reduction in mean squared error with the target acoustic response compared to the Dual-VAE trained solely on the initial parametric VAR dataset. We present a novel approach to the inverse design of complex structures with high non-linearity by introducing the inverse design framework, demonstrating exceptional performance in generating non-parametric structures that achieve target performance.

关键词： Inverse design Latent space variational autoencoder Transfer learning Acoustic metamaterials Non-parametric structures

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

ECG Sensor Design Assessment with variational autoencoder-Based Digital Watermarking

引用

SENSORS 2025年第7期25卷 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

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

Explainable hybrid tabular variational autoencoder and feature Tokenizer Transformer for depression prediction

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 265卷

作者： Tran, Vinh Quang Byeon, Haewon Inje Univ Dept Digital Antiaging Healthcare BK21 Gimhae 50834 South Korea

Recent advancements in machine learning and deep learning have significantly improved the diagnosis, detection, prediction, and prognosis of depressive disorders. However, these methodologies have issues related to generalizability, transparency, data scarcity, privacy concerns, and class imbalance. This study develops a robust and interpretable model for predicting depression in South Korea, addressing these limitations. We employed a hybrid deep learning approach that integrates the Feature Tokenizer Transformer model, specifically designed for tabular data, to effectively tokenize and process categorical and numerical features, alongside synthetic data generated by the tabular variational autoencoder (TVAE). TVAE is an adaptation of variational autoencoders that uses a specialized loss function for tabular data. generated high-quality synthetic data from the Korea National Health and Nutrition Examination Survey (KNHANES) dataset. The efficacy of the TVAE-generated data was validated using non-parametric statistical tests, achieving 86.30% on the Kolmogorov-Smirnov test and 76.65% on the Chi-squared test. Performance evaluation metrics, such as accuracy, recall, F1-score, and AUC, demonstrated our model's effectiveness, yielding an accuracy 0.7783, a recall score of 0.5310, an F1-score of 0.4657, and an AUC of 0.6822, outperforming state-of-the-art models. Additionally, SHapley Additive exPlanations analysis was incorporated to explain feature importance, offering valuable insights for healthcare professionals. This research highlights the potential of deep learning and synthetic data generation techniques to enhance depression prediction, addressing critical challenges such as generalizability, class imbalance, data privacy, and interpretability over existing models.

关键词： variational autoencoder Feature tokenizer Transformer Depression Explainable

来源：评论

学校读者我要写书评

暂无评论

Univariate conditional variational autoencoder for morphogenic pattern design in frontal polymerization-based manufacturing

引用

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2025年 438卷

作者： Liu, Qibang Cai, Pengfei Abueidda, Diab Vyas, Sagar Koric, Seid Gomez-Bombarelli, Rafael Geubelle, Philippe Univ Illinois Natl Ctr Supercomp Applicat Urbana IL 61801 USA Univ Illinois Beckman Inst Adv Sci & Technol Urbana IL 61801 USA Univ Illinois Grainger Coll Engn Dept Aerosp Engn Urbana IL 61801 USA Univ Illinois Grainger Coll Engn Dept Mech Sci & Engn Urbana IL 61801 USA New York Univ Abu Dhabi Civil & Urban Engn Dept Abu Dhabi U Arab Emirates Kansas State Univ Dept Ind & Mfg Syst Engn Manhattan KS 66506 USA MIT Dept Mat Sci & Engn Cambridge MA 02139 USA

Under some initial and boundary conditions, the rapid reaction-thermal diffusion process taking place during frontal polymerization (FP) destabilizes the planar mode of front propagation, leading to spatially varying, complex hierarchical patterns in thermoset polymeric materials. Although modern reaction-diffusion models can predict the patterns resulting from unstable FP, the inverse design of patterns, which aims to retrieve process conditions that produce a desired pattern, remains an open challenge due to the non-unique and non-intuitive mapping between process conditions and manufactured patterns. In this work, we propose a probabilistic generative model named univariate conditional variational autoencoder (UcVAE) for the inverse design of hierarchical patterns in FP-based manufacturing. Unlike the cVAE, which encodes both the design space and the design target, the UcVAE encodes only the design space. In the encoder of the UcVAE, the number of training parameters is significantly reduced compared to the cVAE, resulting in a shorter training time while maintaining comparable performance. Given desired pattern images, the trained UcVAE can generate multiple process condition solutions that produce high-fidelity hierarchical patterns.

关键词： Frontal polymerization Manufacturing Inverse design variational autoencoder Deep learning Deep generative model

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

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

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

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：