检索结果-内蒙古大学图书馆

Dictionary trained attention constrained low rank and sparse autoencoder for hyperspectral anomaly detection

NEURAL NETWORKS 2025年 181卷 106797页

作者： Hu, Xing Li, Zhixuan Luo, Lingkun Karimi, Hamid Reza Zhang, Dawei Univ Shanghai Sci & Technol Sch Opt Elect & Comp Engn 516 Jungong Rd Shanghai 200093 Peoples R China Shanghai Jiao Tong Univ Sch Aeronaut & Astronaut 800 Dongchuang Rd Shanghai 200240 Peoples R China Politecn Milan Dept Mech Engn I-20156 Milan Italy

Dictionary representations and deep learning autoencoder (AE) models have proven effective in hyperspectral anomaly detection. Dictionary representations offer self-explanation but struggle with complex scenarios. Conversely, autoencoders can capture details in complex scenes but lack self-explanation. Complex scenarios often involve extensive spatial information, making its utilization crucial in hyperspectral anomaly detection. To effectively combine the advantages of both methods and address the insufficient use of spatial information, we propose an attention constrained low-rank and sparse autoencoder for hyperspectral anomaly detection. This model includes two encoders: an attention constrained low-rank autoencoder (AClrAE) trained with a background dictionary and incorporating a Global Self-Attention Module (GAM) to focus on global spatial information, resulting in improved background reconstruction;and an attention constrained sparse autoencoder (ACsAE) trained with an anomaly dictionary and incorporating a Local Self-Attention Module (LAM) to focus on local spatial information, resulting in enhanced anomaly reconstruction. Finally, to merge the detection results from both encoders, a nonlinear fusion scheme is employed. Experiments on multiple real and synthetic datasets demonstrate the effectiveness and feasibility of the proposed method.

关键词： Hyperspectral Anomaly Detection Attention mechanisms autoencoder Deep learning Sparse Representation

来源：评论

学校读者我要写书评

暂无评论

DMGAE: An interpretable representation learning method for directed scale-free networks based on autoencoder and masking

引用

INFORMATION PROCESSING & MANAGEMENT 2025年第3期62卷

作者： Yang, Qin-Cheng Yang, Kai Hu, Zhao-Long Li, Minglu Zhejiang Normal Univ Sch Comp Sci & Technol Jinhua 321004 Peoples R China Yangzhou Univ Sch Informat Engn Yangzhou 225127 Peoples R China

Although existing graph self-supervised learning approaches have paid attention to the directed nature of networks, they have often overlooked the ubiquitous scale-free attributes. This oversight has resulted in a theoretical gap in understanding graph self-supervised learning from the perspective of network structure. In this paper, we study the degree distribution characteristics of source and target nodes in directed scale-free networks, encompassing node and edge dimensions. Our theoretical analysis reveals the relationship between the average degree of nodes and their average in-degree and out-degree, which is instrumental in discerning positive and negative edges, as well as edge directionality. Here positive edges are the ones that exists in the original graph, and negative edges are the ones that not exists in the original graph. Furthermore, we uncover negative edges connecting to central nodes and positive edges to peripheral nodes to be less predictable. Based on these crucial theoretical insights, we propose DMGAE (Directed Masked Graph autoencoder), a novel representation learning method for directed scale-free networks that offers interpretability. The DMGAE method employs a weighted graph based on edges to replace the original graph structure. It integrates a masking approach based on the weight of the edges. Additionally, it incorporates an adaptive negative sampling method, edge decoder and a degree decoder based on the difference between the in- degree and out-degree of the node. This enhances the model's capability to learn edges and discern their directions. Empirical studies on extensive real-world network data show that, compared to the state-of-the-art methods, DMGAE not only generally has superior learning performance on directed networks, but also performs exceedingly well on undirected networks.

关键词： Complex networks Representation learning Directed graph Scale-free networks Masking autoencoder

来源：评论

学校读者我要写书评

暂无评论

Supervised autoencoder denoiser for non-stationarity in multi-session EEG-based BCI

引用

JOURNAL OF NEURAL ENGINEERING 2025年第2期22卷 026043-026043页

作者： Ofer, Avin Ophir, Almagor Yoav, Noah Roman, Rosipal Oren, Shriki Ben Gurion Univ Negev Dept Cognit & Brain Sci Beer Sheva Israel Slovak Acad Sci Inst Measurement Sci Bratislava Slovakia

Objective. Non-stationarity in electroencephalogram (EEG) signals poses significant challenges for the performance and implementation of brain-computer interfaces (BCIs). Approach. In this study, we propose a novel method for cross-session BCI tasks that employs a supervised autoencoder to reduce session-specific information while preserving task-related signals. Our approach compresses high-dimensional EEG inputs and reconstructs them, thereby mitigating non-stationary variability in the data. In addition to unsupervised minimization of the reconstruction error, the objective function of the network includes two supervised terms to ensure that the latent representations exclude session identity information and are optimized for subsequent classification. Main results. Evaluation across three different motor imagery datasets demonstrates that our approach effectively addresses domain adaptation challenges, outperforming both na & iuml;ve cross-session and within-session methods. Significance. Our method eliminates the need for data from new sessions, making it fully unsupervised concerning new session data and reducing the necessity for recalibration with each session. Furthermore, the reduction of session-specific information in the reconstructed signals indicates that our approach effectively denoises non-stationary signals, thereby enhancing the accuracy of BCI models. Future applications could extend this model to a broader range of BCI tasks and explore the residual signals to investigate sources of non-stationary brain components and other cognitive processes.

关键词： motor-imagery BCI EEG non-stationarity autoencoder denoising

来源：评论

学校读者我要写书评

暂无评论

Leveraging Mask autoencoder and Crossover Binary Sand Cat Algorithm for Early Detection of Glaucoma

引用

MICROSCOPY RESEARCH AND TECHNIQUE 2025年第6期88卷 1816-1834页

作者： Rekha, C. Jayashree, K. Panimalar Engn Coll Dept Informat Technol Chennai India Panimalar Engn Coll Dept Artificial Intelligence & Data Sci Chennai India

Glaucoma, a leading cause of irreversible blindness worldwide, can be effectively managed if detected early. Glaucoma is directly associated with aging as it commonly occurs in people over the age of 40 and in elderly people. Glaucoma detection in retinal fundus images typically involves utilizing image processing and machine learning techniques. By leveraging advancements in computer vision, a robust and automated system is developed to assist ophthalmologists in screening and diagnosing glaucoma from retinal fundus images. Furthermore, fundus images can vary significantly in quality due to factors like illumination variations, focus, and artifacts. Ensuring consistent image quality across different datasets and acquisition devices is essential for reliable detection. Addressing these challenges requires interdisciplinary collaboration between ophthalmologists to develop robust and reliable solutions for the detection of glaucoma. Hence a novel mask autoencoder-based crossover binary sand cat (MA-CBSC) algorithm is proposed to detect glaucoma. In this algorithm, the mask autoencoder recognizes the features indicating the presence of glaucoma in the input images and the crossover binary sand cat algorithm is used to fine tune the overall performance of the algorithm by selecting the most appropriate features escaped due to overfitting issues. Preprocessing steps such as image enhancement, filtering, and data cleaning are applied to the extracted ROI for the purpose of increasing the image quality and enhancing the visibility of features relevant to glaucoma detection. ROI extraction attributes namely optic disc, cup-to-disc ratio, bean-pot cupping, and vertical enlargement are derived from the ROI along with some other relevant features. In this work, the crossover-based binary sand cat optimization algorithm is utilized for hyperparameter tuning to enhance the efficiency of the MA-CBSC method. Extensive experimental assessments are conducted, comparing the effectiv

关键词： autoencoder binary sand cat optimization crossover strategy filters fundus image glaucoma image enhancement mask RCNN

来源：评论

学校读者我要写书评

暂无评论

Improved network anomaly detection system using optimized autoencoder - LSTM

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 273卷

作者： Narmadha, S. Balaji, N. V. Karpagam Acad Higher Educ Dept Comp Sci Coimbatore 641021 India

Intrusion detection (ID) gives security in network traffic or system activities monitors to detect suspicious activities, behavior, potential attacks, or unauthorized access. IDs are crucial in cybersecurity, as organizations identify and respond to threats before they cause harm. The anomaly-based detection method is a popular and challenging research area in identifying new threats. So, this study focuses on developing an efficient network anomaly-based detection approach. It can establish a baseline for normal behavior and flag deviations from this baseline as potential threats. So, it can detect new or unknown attacks that deviate from standard traffic patterns. The study's main objective is to reduce the false positive rate and improve the class imbalance issues in the data. So, an optimized Deep Learning (DL) model is developed to detect new threats and reduce the false positive rate in the present ID systems. The DL model combines the Long Short-Term Memory (LSTM) with the autoencoder model, where the auto-encoder learns normal patterns, while LSTM handles sequential dependencies in the data. Moreover, the LSTM model performance is optimized using Particle Swarm Optimization (PSO). The performance of the DL model is evaluated with existing IDS methods and the results shows that the proposed model achieves maximum detection accuracy rate of 0.9989.

关键词： Anomaly detection autoencoder Deep learning Intrusion detection system Long short-term memory Particle swarm optimization

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

XAInomaly: Explainable and interpretable Deep Contractive autoencoder for O-RAN traffic anomaly detection

引用

COMPUTER NETWORKS 2025年 261卷

作者： Basaran, Osman Tugay Dressler, Falko TU Berlin Sch Elect Engn & Comp Sci Berlin Germany

Generative Artificial Intelligence (AI) techniques have become integral part in advancing next generation wireless communication systems by enabling sophisticated data modeling and feature extraction for enhanced network performance. In the realm of open radio access networks (O-RAN), characterized by their gregated architecture and heterogeneous components from multiple vendors, the deployment of generative models offers significant advantages for network management such as traffic analysis, traffic forecasting anomaly detection. However, the complex and dynamic nature of O-RAN introduces challenges that necessitate not only accurate detection mechanisms but also reduced complexity, scalability, and most importantly interpretability to facilitate effective network management. In this study, we introduce the XAInomaly framework, an explainable and interpretable Semi-supervised (SS) Deep Contractive autoencoder (DeepCAE) design for anomaly detection in O-RAN. Our approach leverages the generative modeling capabilities SS-DeepCAE model to learn compressed, robust representations of normal network behavior, which captures essential features, enabling the identification of deviations indicative of anomalies. To address the black nature of deep learning models, we propose reactive Explainable AI (XAI) technique called fastshap-C, is providing transparency into the model's decision-making process and highlighting the features contributing to anomaly detection.

关键词： Explainable and trustworthy AI Generative AI O-RAN autoencoder Anomaly detection Network management

来源：评论

学校读者我要写书评

暂无评论

Epileptic Seizure Recognition Using Improved Modes Decomposition and Online Sequential autoencoder Multi-Kernel Broad Learning System

引用

IEEE SENSORS JOURNAL 2025年第6期25卷 10454-10465页

作者： Swain, Bhanja Kishor Rout, Susanta Kumar Sahani, Mrutyunjaya Dash, Pradipta Kishore Panda, Sanjib Kumar Siksha O Anusandhan Deemed Be Univ Ctr Internet Things Bhubaneswar 751030 Odisha India JSPM Univ Sch Elect & Commun Sci Pune 412207 Maharashtra India Natl Univ Singapore Dept Elect & Comp Engn Queenstown 751030 Singapore Siksha O Anusandhan Deemed be Univ Multidisciplinary Res Cell Bhubaneswar 751030 India

In this article, improved variational mode decomposition (IVMD) and the online sequential autoencoder multi-kernel broad learning system (OSAEMKBLS) are integrated to recognize epileptic seizure (ES) epochs from both multichannel and single-channel electroencephalogram (EEG) recordings. The proposed IVMD extracts the optimum number of efficient band-limited intrinsic mode functions (BLIMFs) and the data fidelity factor ( alpha ) using the irregularity index-based Tsallis entropy as a cost function. The designed autoencoder in the proposed OSAEMKBLS architecture is utilized to extract the most elucidative unsupervised signatures from selected informative BLIMFs, chunk by chunk sequentially. These signatures are then fed into the novel supervised kernel trick-based broad learning system for the efficacious recognition of seizure epochs, based on the root mean square error (RMSE) optimal cost function. The efficacy of the proposed IVMD-OSAEMKBLS algorithm is evaluated using benchmark multichannel scalp EEG (sEEG) and single-channel EEG datasets. The proposed method demonstrates higher learning speed, lower computational complexity, better model generalization, and a lower false positive rate per hour (FPR/h) at 0.019. It achieves outstanding recognition accuracy at 99.98% and a short-event recognition time of 42 ms, compared to the IVMD-BLS, IVMD-OSBLS, and IVMD-OSMKBLS methods. Finally, reconfigurable field-programmable gate array (FPGA) hardware is employed to implement the novel IVMD-OSAEMKBLS, developing a computer-aided diagnosis (CAD) system for the automated diagnosis of ES patients. The integrity and expediency of the proposed algorithm endorse secure and admirable accomplishments in seizure detection and recognition.

关键词： Electroencephalography Recording Feature extraction Accuracy Sensors Learning systems Support vector machines Kernel Databases autoencoder broad learning system electroencephalogram (EEG) epileptic seizure (ES) recognition field program gate array improved variational mode decomposition (IVMD) kernel trick kernel trick

来源：评论

学校读者我要写书评

暂无评论

Abstractive text summarization from Amazon food review dataset using modified attention based Bi-LSTM autoencoder model

引用

JOURNAL OF THE CHINESE INSTITUTE OF ENGINEERS 2025年第3期48卷 268-282页

作者： Prabha, P. L. Parvathy, M. Sethu Inst Technol Dept Comp Sci & Engn Kariapatti 626115 India

Automatic Text Summarization (ATS) is extensively performed to obtain insights from long texts or documents through Natural Language Processing (NLP). Even though various DL and ML-based algorithms have been used to perform text summarization, there is a lack of extensive studies on abstractive text summarization. The attention mechanisms used in traditional text summarization methods generate a fixed length vector irrespective of input sequence length. Hence, this study enhances the summarization efficiency through the implementation of a modified attention mechanism to generate dynamic weights for the input sequence. The proposed Modified Attention-based Bi-directional LSTM with Auto Encoder (Matt BiLSTM-AE) model is implemented for abstractive text summarization. The Amazon food review dataset is loaded as an input dataset, which is pre-processed to remove stop words, punctuation, and special characters. The optimized weight adjustment is obtained through the dynamic attention mechanism in the proposed model. The performance of the proposed MAtt-Bi-LSTM-AE text summarization is evaluated through ROUGE, accuracy, and loss metrics. From performance analysis, the accuracy rate was found to be 74.6%, while the loss rate was found to be 1.1751.

关键词： Abstractive text summarization dynamic attention natural language processing automatic text summarization autoencoder Bi-LSTM ROUGE

来源：评论

学校读者我要写书评

暂无评论

Enhanced autoencoder and deep neural network (AE&DNN) method for ddos attack recognition

引用

WIRELESS NETWORKS 2025年第4期31卷 3277-3295页

作者： Pajila, P. J. Beslin Robinson, Y. Harold Allimuthu, Udayakumar Julie, E. Golden Jaffrin, Lijetha. C. Sheena, B. Gracelin Vel Tech Rangarajan Dr Sagunthala R&D Inst Sci & T Dept Comp Sci & Engn Chennai Tamil Nadu India Francis Xavier Engn Coll Dept Comp Sci & Engn Tirunelveli Tamil Nadu India Anna Univ Reg Campus Dept Comp Sci & Engn Tirunelveli 627007 Tamil Nadu India Vel Tech Rangarajan Dr Sagunthala R&D Inst Sci & T Dept IT Chennai Tamil Nadu India Sathyabama Inst Sci & Technol Dept Comp Sci & Engn Chennai Tamil Nadu India

For the purpose of identifying attacks on the network systems, a monitoring method is essential. Identification of DDOS attacks is one of the most important concerns now a days in wireless networks. This paper proposed a security mechanism to identify DDoS attacks using enhanced autoencoder and Deep Neural Network (AE & DNN). In traditional methods, it is very difficult to classify the normal traffic in the network from the malicious one. Therefore some attacks will exist for a long time. So that the network will get affected by various attacks. To overcome these problems autoencoder is combined with Deep Neural Network, where autoencoder is mainly utilized for feature extraction and Deep Neural Network is used for classification. For validation, experiments have been done on the WSN-DS, CICIDS2017, and NSL-KDD standard datasets. From the experiments made, the proposed method outperformed than the CICIDS2017, and NSL-KDD datasets.

关键词： autoencoder DeepLearning Datasets Wireless sensor networks Classification WSN-DS Datasets

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：