检索结果-内蒙古大学图书馆

Exploration of physics-related latent vectors in hot working of Inconel 718 superalloy using autoencoder

JOURNAL OF MATERIALS RESEARCH AND TECHNOLOGY-JMR&T 2025年 35卷 6749-6762页

作者： Kim, Min Jik Yang, Seon Yeong Yang, Woo Seok Oh, Sehyeok Park, Sang Min Shin, Da Seul Korea Inst Mat Sci Mat Proc Innovat Res Div 797 Changwon Daero Chang Won 51508 Gyeongnam South Korea Korea Inst Mat Sci Mat Data & Anal Res Div 797 Changwon Daero Chang Won 51508 Gyeongnam South Korea Pusan Natl Univ Sch Mech Engn 2Busandaehak Ro 63beon Gil Busan 46241 South Korea

The thermo-mechanical processing (TMP) behavior of nickel-based superalloys during hot working exhibits highly non-linear and complex characteristics, necessitating an understanding of deformation mechanisms for industrial applications. In this study, we developed an autoencoder-prediction network (AE-PN) to model the TMP behavior of the Inconel 718 superalloy in an unsupervised way within the temperature range of 900-1200 degrees C and strain rates of 0.001-10 s-1. The AE-PN effectively reduces the dimensionality of stress-strain curves in a non-linear manner while preserving critical flow features, enabling accurate reconstruction of stressstrain curves. The AE-PN established strong correlations between processing parameters and the latent space, achieving high reconstruction accuracy for continuous flow curves (testing RMSE = 4.19). Latent features derived from stress-strain curves were linked to key characteristics of hot deformation behavior, including peak stress, strain hardening, and flow softening. Notably, one major latent component was strongly correlated with peak stress (R2 = 0.9971), highlighting its role as a physics-related variable connected to TMP behavior. For additional datasets within the processing window, the AE outperformed a conventional artificial neural network (ANN) model, achieving an RMSE of 7.98 compared to the ANN's RMSE of 60. Furthermore, hot workability characteristics, such as flow softening and dynamic recrystallization (DRX), were systematically analyzed using a processing map and microstructural analysis. This AE-PN framework provides interpretable insights beyond traditional 'black-box' systems, offering accurate stress-strain curve predictions and deeper interpretation of processing parameters through latent space exploration.

关键词： Inconel 718 Thermo-mechanical processing Hot deformation Deep learning autoencoder Hot workability

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Intrusion Detection System for Evolving IoT Threats: An autoencoder-FNN Fusion

引用

IEEE ACCESS 2025年 13卷 4201-4217页

作者： Shirley, J. Jasmine Priya, M. Vellore Inst Technol Sch Comp Sci Engn & Informat Syst Vellore 632014 India

The increasing sophistication of attacks targeting the Internet of Things environment underscores the critical need for robust intrusion detection systems. This study introduces a specialized IDS classification approach to address IoT networks' evolving and diverse threat landscape. The proposed model integrates an autoencoder for feature extraction with a Feedforward Neural Network for classification, creating a fusion that enhances the precision and efficiency of intrusion detection. The autoencoder captures and reduces the dimensionality of high-dimensional IoT network traffic data, and the FNN distinguishes between normal network behaviour and various intrusion patterns by leveraging its ability to model nonlinear relationships. This dual-stage architecture offers adaptability to dynamic network conditions, accurately identifying attack instances while minimizing false positives. Rigorous evaluations demonstrate the model's robust performance, achieving a remarkable accuracy of 99.55% in binary classification and 90.91% in multiclass classification. Key metrics such as precision, recall, F1-score, and high ROC-AUC values validate its effectiveness in detecting diverse intrusion patterns and handling various attack scenarios. Additionally, the study employs a two-stage data balancing strategy that significantly enhances the detection of minority class attacks. By addressing critical challenges in IoT network security, including imbalanced datasets and evolving threats, this research contributes a reliable and efficient IDS model optimized for real-world applications. The AE-FNN model's high accuracy, robustness, and scalability position it as a valuable tool in securing interconnected IoT ecosystems, making it an important advancement in network security.

关键词： autoencoder deep learning Intrusion detection IoT environments network traffic neural networks autoencoder deep learning intrusion detection IoT environments network traffic neural networks

来源：评论

学校读者我要写书评

暂无评论

XAI-DSCSA: explainable-AI-based deep semi-supervised convolutional sparse autoencoder for facial expression recognition

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2025年第5期19卷 1-18页

作者： Mohana, M. Subashini, P. Ghinea, George Avinashilingam Inst Ctr Machine Learning & Intelligence Dept Comp Sci Coimbatore India Brunel Univ Dept Comp Sci London England

Facial expression recognition (FER) continues to be a vibrant research field, driven by the increasing need for its practical applications in areas such as e-learning, healthcare, candidate interview analysis, and more. Most deep learning approaches in supervised FER systems heavily rely on large, labeled datasets. Implementing FER in Convolutional Neural Networks (CNNs) often requires many layers, leading to extended training times and difficulties in finding optimal parameters. This can result in challenges in creating distinct facial expression patterns for classification, leading to poor real-time emotion classification In this paper, we propose a novel approach known as the Deep Semi-supervised Convolutional Sparse autoencoder to address the aforementioned issues and enhance FER performance and prediction accuracy. This approach comprises two parts: (i) Initially, a deep convolutional sparse autoencoder is trained with unlabeled samples of facial expressions. Here, sparsity is introduced in the convolutional block to enforce penalties, focusing on more relevant features for feature representation in the latent space. (ii) A trained encoder with a feature map is connected to a fully connected layer with softmax for final fine-tuning with learned weights and labeled facial expression samples in a semi-supervised approach for emotion classification. This approach was experimented with two benchmark datasets, namely CK + and JAFFE, and achieved significant results of 98.98% and 93.10% accuracy, respectively. The results were analyzed using established state-of-the-art techniques. Additionally, eXplainable AI (XAI) methods like Grad-CAM and image-LIME were employed to interpret the performance and prediction outcomes of the DSCSA model.

关键词： autoencoder Convolutional sparse autoencoder Facial expression recognition Feature representation Unsupervised learning Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

All-Optical autoencoder Machine Learning Framework Using Linear Diffractive Processors

引用

LASER & PHOTONICS REVIEWS 2025年

作者： Feng, Peijie Tan, Yong Chong, Mingzhe Li, Lintao Zhang, Zongkun Liu, Fubei Wen, Yongzheng Tan, Yunhua Peking Univ Sch Elect Beijing 100871 Peoples R China Tsinghua Univ Sch Mat Sci & Engn State Key Lab New Ceram & Fine Proc Beijing 100084 Peoples R China Wuzhen Lab Res Ctr Metamat Jiaxing 314500 Peoples R China

Diffractive deep neural network (D2NN), known for its high speed and strong parallelism, is applied across various fields, including pattern recognition, image processing, and image transmission. However, existing network architectures primarily focus on data representation within the original domain, with limited exploration of the latent space, thereby restricting the information mining capabilities and multifunctional integration of D2NNs. Here, an all-optical autoencoder (OAE) framework is proposed that linearly encodes the input wavefield into a prior shape distribution in the diffractive latent space (DLS) and decodes the encoded pattern back to the original wavefield. By leveraging the bidirectional multiplexing property of D2NN, the OAE modelsfunction as encoders in one direction and as decoders in the opposite direction. The models are applied to three areas: image denoising, noise-resistant reconfigurable image classification, and image generation. Proof-of-concept experiments are conducted to validate numerical simulations. The OAE framework exploits the potential of latent representations, enabling single set of diffractive processors to simultaneously achieve image reconstruction, representation, and generation. This work not only offers fresh insights into the design of optical generative models but also paves the way for developing multifunctional, highly integrated, and general optical intelligent systems.

关键词： autoencoder diffractive neural network image classification image denoising image generation

来源：评论

学校读者我要写书评

暂无评论

Unsupervised temperature-compensated damage localization method based on damage to baseline autoencoder and delay-based probabilistic imaging

引用

MECHANICAL SYSTEMS AND SIGNAL PROCESSING 2025年 230卷

作者： Song, Ruijie Sun, Lingyu Gao, Yumeng Wei, Juntao Peng, Chang Fan, Longqing Jiang, Mingshun Shandong Univ Sch Control Sci & Engn Jinan 250061 Peoples R China CRRC Qingdao Sifang Rolling Stock Res Inst Co Ltd Qingdao 26611 Peoples R China Natl Innovat Ctr High Speed Train Qingdao Qingdao 266111 Peoples R China Shandong Res Inst Ind Technol Jinan 250098 Peoples R China

Ultrasonic guided wave-based structural health monitoring (UGW-SHM) technology has a highly efficient damage detection capability. However, changes in environmental factors such as temperature can lead to changes in the signal waveform, which greatly affects the damage detection performance. In this paper, a novel unsupervised temperature compensated damage localization method called damage to baseline autoencoder - delay-based probabilistic imaging (DBAE-DPI) method is proposed. Firstly, based on the propagation mechanism of Lamb waves and the unsupervised learning method, the temperature-compensated unsupervised model DBAE is designed. This model does not require any damage samples during the training stage and consists of a path fusion module, an encoder, and a decoder, which fully extract and utilize environmental feature information from all paths to achieve baseline signal reconstruction for the detected environments. Secondly, unlike the existing unsupervised learning models in the field of SHM, the output of DBAE is the reconstructed baseline signal of all paths;based on the output signal and input damage signal, the scattering signal can be computed to extract richer damage information. Thirdly, a temperature-compensated DPI damage imaging method is designed, which is based on the temperature-compensated reconstructed signal of DBAE and combines the time delay principle with the probabilistic imaging algorithm to achieve more accurate damage localization effect under temperature-varying environments. Finally, experiments were conducted on the Open Guided Waves (OGW) temperature compensation benchmark dataset to evaluate the temperature compensation and damage localization performance of the DBAE-DPI method on carbon fiber composite plates. The results show that the method has a better temperature compensation effect and damage localization accuracy than other damage localization methods validated using the OGW dataset (In the temperature range of 20 degrees

关键词： Ultrasonic guided wave Temperature compensation Damage localization Unsupervised learning autoencoder Damage imaging

来源：评论

学校读者我要写书评

暂无评论

MTCR-AE: A Multiscale Temporal Convolutional Recurrent autoencoder for unsupervised malicious network traffic detection

引用

COMPUTER NETWORKS 2025年 261卷

作者： Ahmed, Mukhtar Chen, Jinfu Akpaku, Ernest Sosu, Rexford Nii Ayitey Jiangsu Univ Sch Comp Sci & Commun Engn 301 Xuefu Rd Zhenjiang 212013 Jiangsu Peoples R China Jiangsu Univ Jiangsu Key Lab Secur Technol Ind Cyberspace 301 Xuefu Rd Zhenjiang 212013 Jiangsu Peoples R China Lasbela Univ Agr Water & Marine Sci Qual Enhancement Cell Uthal Pakistan Ghana Commun Technol Univ Fac Comp & Informat Syst Accra Ghana

The increasing sophistication of network attacks, particularly zero-day threats, underscores the need for robust, unsupervised detection methods. These attacks can flood networks with malicious traffic, overwhelm resources, or render services unavailable to legitimate users. Existing machine learning methods for zero-day attack detection typically rely on statistical features of network traffic, such as packet sizes and inter-arrival times. However, traditional approaches that depend on manually labeled data and linear structures often struggle to capture the intricate spatiotemporal correlations crucial for detecting unknown attacks. This paper introduces the Multiscale Temporal Convolutional Recurrent autoencoder (MTCR-AE), an innovative framework designed to detect malicious network traffic by leveraging Multiscale Temporal Convolutional Networks (TCN) and Gated Recurrent Units (GRU). The MTCR-AE model captures both short- and long-range spatiotemporal dependencies while incorporating a temporal attention mechanism to dynamically prioritize critical features. The MTCR-AE operates in an unsupervised manner, eliminating the need for manual data labeling and enhancing its scalability for real-world applications. Experimental evaluations conducted on four benchmark datasets - ISCX-IDS-2012, USTC-TFC-2016, CIRA-CIC-DoHBrw2020, and CICIoT2023 - demonstrate the model's superior performance, achieving an accuracy of 99.69%, precision of 99.63%, recall of 99.69%, and an F1-score of 99.66%. The results highlight the model's capability to deliver state-of-the-art detection performance while maintaining low false positive and false negative rates, offering a scalable and reliable solution for dynamic network environments.

关键词： Malicious network traffic Network security Zero-day Spatiotemporal feature Multiscale temporal convolutional network Gated recurrent units autoencoder

来源：评论

学校读者我要写书评

暂无评论

An ECG Signal Encryption and Classification Using Sparse autoencoder and Optimized Neural Network Techniques

引用

TRAITEMENT DU SIGNAL 2025年第1期42卷 557-568页

作者： Shanmugasundaram, Sumathi Chinnasamy, Murukesh Annaman, Lakshmi Sangeetha Velammal Engn Coll Dept ECE Chennai 600066 India

Secure transmission of patient diagnostic information is crucial in healthcare monitoring due to the inclusion of private user details. Electrocardiogram (ECG) signal is one of the most important medical signals that represents the vital signs of patients and immediate medications are provided by physicians based on the observation of ECG signals. Altering or tampering with such data leads to serious issues so it is essential to introduce proper security measures to enhance the data security. Encryption is one of the efficient approaches which is widely used for data security in various domains. However, the features of encryption methodologies are less explored in raw medical data applications. This research work introduces a novel method for encrypting and decrypting ECG signals by utilizing a sparse autoencoder combined with Chaotic Logistic Mapping to enhance data security. The classification module in this research employs a convolutional neural network to efficiently extract features and an optimized artificial neural network to classify the data. Experimental verification of proposed approach attains better classification accuracy of 96.6% which is much better than the existing classification techniques.

关键词： healthcare data security encryption classification deep learning CNN autoencoder optimization

来源：评论

学校读者我要写书评

暂无评论

Enhanced Colon Cancer Prediction Using Capsule Networks and autoencoder-Based Feature Selection in Histopathological Images

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2025年第2期16卷 817-829页

作者： Ramesh, Janjhyam Venkata Naga Mary, F. Sheeja Balaji, S. Nimma, Divya Muniyandy, Elangovan Kranthi, A. Smitha El-Ebiary, Yousef A. Baker Koneru Lakshmaiah Educ Fdn Dept CSE Vaddeswaram Andhra Pradesh India Graph Era Hill Univ Dept CSE Dehra Dun 248002 India Graph Era Deemed Be Univ Dept CSE Dehra Dun 248002 Uttarakhand India Vel Tech Rangarajan Dr Sagunthala R&D Inst Sci & T Dept CSE Chennai India Panimalar Engn Coll Dept CSE Chennai India Univ Southern Mississippi Computat Sci Hattiesburg MS USA Saveetha Inst Med & Tech Sci Saveetha Sch Engn Dept Biosci Chennai India Appl Sci Private Univ Appl Sci Res Ctr Amman Jordan Koneru Lakshmaiah Educ Fdn Dept Comp Sci & Engn Vaddeswaram 522302 AP India UniSZA Univ Fac Informat & Comp Kuala Terengganu Malaysia

The malignant development of cells in the colon or rectum is known as colon cancer, and because of its high incidence and possibility for death, it is a serious health problem. Because the disease frequently advances without symptoms in its early stages, early identification is essential. Improved survival rates and more successful therapy depend on an early and accurate diagnosis. The reliability of early detection can be impacted by problems with traditional diagnostic procedures, such as high false-positive rates, insufficient sensitivity, and inconsistent outcomes. This unique approach to colon cancer diagnosis uses autoencoder-based feature selection, capsule networks (CapsNets), and histopathology images to overcome these problems. CapsNets capture spatial hierarchies in visual input, improving pattern identification and classification accuracy. When employed for feature extraction, autoencoders reduce dimensionality, highlight important features, and eliminate noise, all of which enhance model performance. The suggested approach produced remarkable outcomes, with a 99.2% accuracy rate. The model's strong capacity to detect cancerous lesions with few mistakes is demonstrated by its high accuracy in differentiating between malignant and non-malignant tissues. This study represents a substantial development in cancer detection technology by merging autoencoders with Capsule Networks, so overcoming the shortcomings of existing approaches and offering a more dependable tool for early diagnosis. This method may improve patient outcomes, provide more individualized treatment regimens, and boost diagnostic accuracy.

关键词： Colon cancer prediction capsule network autoencoder histopathological images early cancer detection

来源：评论

学校读者我要写书评

暂无评论

Few-shot traffic classification based on autoencoder and deep graph convolutional networks

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-16页

作者： Xu, Shengwei Han, Jijie Liu, Yilong Liu, Haoran Bai, Yijie Beijing Elect Sci & Technol Inst Informat Secur Res Inst Beijing 100070 Peoples R China Beijing Elect Sci & Technol Inst Dept Cryptog Sci & Technol Beijing 100070 Peoples R China Beijing Univ Posts & Telecommun Sch Cyberspace Secur Beijing 100876 Peoples R China

Traffic classification is a crucial technique in network management that aims to identify and manage data packets to optimize network efficiency, ensure quality of service, enhance network security, and implement policy management. As graph convolutional networks (GCNs) take into account not only the features of the data itself, but also the relationships among sets of data during classification. Many researchers have proposed their own traffic classification methods based on GCN in recent years. However, most of the current approaches use two-layer GCN primarily due to the over-smoothing problem associated with deeper GCN. In scenarios with small samples, a two-layer GCN may not adequately capture relationships among traffic data, leading to limited classification performance. Additionally, during graph construction, traffic usually needs to be trimmed to a uniform length, and for traffic with insufficient length, zero-padding is typically applied to extension. This zero-padding strategy poses significant challenges in traffic classification with small samples. In this paper, we propose a method based on autoencoder (AE) and deep graph convolutional networks (ADGCN) for traffic classification for few-shot datasets. ADGCN first utilizes an AE to reconstruct the traffic. AE enables shorter traffic to learn abstract feature representations from longer traffic of the same class to replace zeros, mitigating the adverse effects of zero-padding. The reconstructed traffic is then classified using GCNII, a deep GCN model that addresses the challenge of insufficient data samples. ADGCN is an end-to-end traffic classification method applicable to various scenarios. According to experimental results, ADGCN can achieve a classification accuracy improvement of 3.5 to 24% compared to existing state-of-the-art methods. The code is available at https://***/han20011019/ADGCN.

关键词： Traffic classification autoencoder Graph convolutional networks Few-shot

来源：评论

学校读者我要写书评

暂无评论

FactorVQVAE: Discrete latent factor model via Vector Quantized Variational autoencoder

引用

KNOWLEDGE-BASED SYSTEMS 2025年 318卷

作者： Kim, Namhyoung Ock, Seung Eun Song, Jae Wook Hanyang Univ Dept Ind Engn Seoul 04763 South Korea

This study introduces FactorVQVAE, the first integration of the Vector Quantized Variational autoencoder (VQVAE) into factor modeling, providing a novel framework for predicting cross-sectional stock returns and constructing systematic investment portfolios. The model employs a two-stage architecture to improve the extraction and utilization of latent financial factors. In the first stage, an encoder-decoder-quantizer compresses high-dimensional input data into discrete latent factors through vector quantization, addressing posterior collapse and ensuring distinct representations. In the second stage, an autoregressive Transformer captures sequential dependencies among these latent factors, enabling precise return predictions. Empirical results in the CSI300 and S&P500 markets demonstrate FactorVQVAE's superior performance. The model achieves the best Rank IC and Rank ICIR scores, surpassing the state-of-the-art latent factor models in varying market conditions. In portfolio evaluations, FactorVQVAE consistently excels in both Top-k Drop-n and Long-Short strategies, translating predictive accuracy into robust investment performance. In particular, it delivers the highest risk-adjusted returns, highlighting its ability to balance returns and risks effectively. These findings position FactorVQVAE as a significant advancement in integrating modern deep learning methodologies with financial factor modeling. Its adaptability, robustness, and exceptional performance in portfolio investment establish it as a promising tool for systematic investing and financial analytics.

关键词： Dynamic latent factor model Vector quantization autoencoder Transformer Portfolio investment

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：