检索结果-内蒙古大学图书馆

MemMambaAD: Memory-augmented state space model for multivariate time series anomaly detection

学校读者我要写书评

暂无评论

Engineering Applications of Artificial Intelligence 2025年 158卷

作者： Gang Li Mingchao Ge Jin Wan Delong Han Min Li Mingle Zhou Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China SHANDONG SCICOM Information and Economy Research Institute Co. Ltd. Jinan China

Multivariate time series anomaly detection focuses on recognizing abnormal patterns to reduce system failures and improve production efficiency and product quality. Accurately detecting anomalies in data remains challenging because existing reconstruction-based methods are prone to overfitting. Recently, reconstruction methods guided by memory modules have been used to address this issue. However, these methods still suffer from insufficient feature extraction of time series prototypes and inadequate storage of normal sample prototype patterns in memory modules. To address these issues, we propose a memory-augmented state space model for multivariate time series anomaly detection. Specifically, we introduce a sequence decomposition state space model-temporal convolutional encoder, which independently extracts trend and seasonal features of multivariate time series in global and local manner, capturing the intrinsic patterns of time series more comprehensively. In addition, we propose a dynamic memory update mechanism, which flexibly updates the memory item through the memory selection mechanism, to more accurately record the prototype pattern of normal samples to improve anomaly detection performance. Extensive experiments on five benchmark datasets demonstrate that our method achieves state-of-the-art performance and reduces memory usage compared with other methods.

关键词：

Double JPEG Compression Detection Based on Markov Model 18th

学校读者我要写书评

暂无评论

Double JPEG Compression Detection Based on Markov Model

18th International Workshop on Digital Forensics and Watermarking, IWDW 2019

作者： Wang, Jinwei Huang, Wei Luo, Xiangyang Shi, Yung-Qing Nanjing University of Information Science and Technology Nanjing210044 China Department of Computer and Software Nanjing University of Information Science and Technology NanjingJiangsu210044 China Shanxi Key Laboratory of Network and System Security Xidian University Xi’an710071 China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001 China State Key Laboratory of Information Security Institute Information Engineering Chinese Academy of Sciences Beijing100093 China Department of Electrical Computer Engineering New Jersey Institute of Technology NewarkNJ07102 United States

ISBN: (纸本)9783030435745

In this paper, a feature based on the Markov model in quaternion discrete cosine transform (QDCT) domain is proposed for double JPEG compression detection. Firstly, a given JPEG image is extracted from blocked images to obtain amplitude and three angles (ψ, φ, and θ). Secondly, when extracting the Markov features, we process the transition probability matrix with the corresponding refinement. Our proposed refinement method not only reduces redundant features, but also makes the acquired features more efficient for detection. Finally, a support vector machine (SVM) is employed for NA-DJPEG compression detection. It is well known that detecting NA-DJPEG compressed images with (Formula Presented) is a challenging task, and when the images with small size (i.e., 64 × 64), the detection will be more difficult. The experimental result indicates that our method can still achieve a high classification accuracy in this case. © 2020, Springer Nature Switzerland AG.

关键词： Support vector machines

Risk Modeling and Traceability of Boundary Attacks on Internet of Power Systems Based on Complex networks

学校读者我要写书评

暂无评论

Risk Modeling and Traceability of Boundary Attacks on Intern...

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Xin Li Zhaoyang Qu Tong Yu Ming Xie Fu Yu Wei Ding School of Electrical Engineering Northeast Electric Power University Jilin China People’s Bank of China Qinghai Provincial Branch Xining China China Southern Power Grid Guangxi Power Grid Co. Ltd. Research Institute Nanning China Bijie Power Supply Bureau China Guizhou Power Grid Co. Ltd. Bijie China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

With the increasing intelligence of power IoT terminal devices, the massive volume of data transmission, and the widespread adoption of shared services, traditional terminal boundary security mechanisms are unable to keep up with the rapid development of network technologies and applications. Additionally, they fail to trace and source network attacks, leading to frequent organized and purposeful malicious attack incidents. To address these issues, this paper proposes a research method for risk modeling and traceability of boundary attacks on power IoT terminals based on complex networks. First, based on the node information of power IoT terminal devices and complex network theory, a terminal boundary attack network (TBAN) is established. Next, using indicators related to complex network theory, such as degree, in-degree, and out-degree, the terminal boundary attack network is analyzed. Furthermore, a staged TBAN is proposed to analyze the attack risks at different times. Then, combining causal theory, a method for tracing and sourcing terminal boundary attacks based on a causal Bayesian network is proposed to identify and trace malicious attacks. Finally, validation and testing analysis are conducted using the actual deployment of power IoT terminal devices. The proposed analysis method transforms the spatial characteristics of the power IoT terminal boundary into a temporally sequential TBAN, which not only visually reflects attack risks but also reveals the temporal relationships of terminal boundary attacks between lines.

关键词： Complex networks Transforms Data science Data models Bayes methods Power systems Internet security Data communication Testing

MAAM:A LIGHTWEIGHT MULTI-AGENT AGGREGATION MODULE FOR EFFICIENT IMAGE CLASSIFICATION BASED ON THE MINDSPORE FRAMEWORK

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Qin, Zhenkai Zhu, Feng Zeng, Huan Nong, Xunyi School of Computing and Information Guangxi Police College Guangxi Nanning China Network Security Research Center Guangxi Police College Guangxi Nanning China Big Data and Policing Technology Laboratory Guangxi Police College Guangxi Nanning China Institute of Software Chinese Academy of Sciences Beijing China

The demand for lightweight models in image classification tasks under resource-constrained environments necessitates a balance between computational efficiency and robust feature representation. Traditional attention mechanisms, despite their strong feature modeling capability, often struggle with high computational complexity and structural rigidity, limiting their applicability in scenarios with limited computational resources (e.g., edge devices or real-time systems). To address this, we propose the Multi-Agent Aggregation Module (MAAM), a lightweight attention architecture integrated with the MindSpore framework. MAAM employs three parallel agent branches with independently parameterized operations to extract heterogeneous features, adaptively fused via learnable scalar weights, and refined through a convolutional compression layer. Leveraging MindSpore’s dynamic computational graph and operator fusion, MAAM achieves 87.0% accuracy on the CIFAR-10 dataset, significantly outperforming conventional CNN (58.3%) and MLP (49.6%) models, while improving training efficiency by 30%. Ablation studies confirm the critical role of agent attention (accuracy drops to 32.0% if removed) and compression modules (25.5% if omitted), validating their necessity for maintaining discriminative feature learning. The framework’s hardware acceleration capabilities and minimal memory footprint further demonstrate its practicality, offering a deployable solution for image classification in resource-constrained scenarios without compromising accuracy. © 2025, CC0.

关键词： Image classification

A Hybrid Routing Algorithm based on Destruction Resistance Cost and Reliability in Flying Ad-Hoc networks

学校读者我要写书评

暂无评论

A Hybrid Routing Algorithm based on Destruction Resistance C...

International Conference on Computer and Communications (ICCC)

作者： Kun Guo Dongbin Wang Hui Zhi Yibo Gao Tao Zhang Tiejun Lv Yueming Lu Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications Beijing China National Engineering Laboratory for Mobile Network Beijing University of Posts and Telecommunications Beijing China TravelSky Technology Limited Beijing China Cyberspace Security Research Center Peng Cheng Laboratory Beijing University of Posts and Telecommunications Beijing China China Academy of Launch Vehicle Technology Beijing China

ISBN: (纸本)9781665409513

Existing routing algorithms in Flying Ad-Hoc Net- works (FANETs) lack the optimization consideration of destruction resistance cost caused by routing recovery when some nodes fail suddenly. In this paper, we propose a hybrid routing algorithm based on destruction resistance cost and reliability. Based on the real-time network topology and network state, the algorithm can provide a multi-parameters-based routing path with low destruction resistance cost for communication transmission. It can ensure that the main routing path can be quickly recovered after interruption and reduce the process of discovering new routing paths. We have constructed a variety of simulation scenarios to analyze the proposed algorithm and the existing algorithms. The simulation results show that the pro- posed algorithm has good performance in reducing destruction resistance cost.

关键词： Resistance Analytical models Costs Computer network reliability Simulation Routing Real-time systems

INNOVATIVE LSGTIME MODEL FOR CRIME SPATIOTEMPORAL PREDICTION BASED ON MINDSPORE FRAMEWORK

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Qin, Zhenkai Wei, Baozhong Gao, Caifeng School of Computing and Information Guangxi Police College Nanning Guangxi China Network Security Research Center Guangxi Police College Nanning Guangxi China Big Data and Policing Technology Laboratory Guangxi Police College Nanning Guangxi China Institute of Software Chinese Academy of Sciences Beijing China

With the acceleration of urbanization, the spatiotemporal characteristics of criminal activities have become increasingly complex. Accurate prediction of crime distribution is crucial for optimizing the allocation of police resources and preventing crime. This paper proposes LGSTime, a crime spatiotemporal prediction model that integrates Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and the Multi-head Sparse Self-attention mechanism. LSTM and GRU capture long-term dependencies in crime time series, such as seasonality and periodicity, through their unique gating mechanisms. The Multi-head Sparse Self-attention mechanism, on the other hand, focuses on both temporal and spatial features of criminal events simultaneously through parallel processing and sparsification techniques, significantly improving computational efficiency and prediction accuracy. The integrated model leverages the strengths of each technique to better handle complex spatiotemporal data. Experimental findings demonstrate that the model attains optimal performance across four real - world crime datasets. In comparison to the CNN model, it exhibits performance enhancements of 2.8%, 1.9%, and 1.4% in the Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE) metrics respectively. These results offer a valuable reference for tackling the challenges in crime prediction. © 2025, CC0.

关键词： Deep learning

Segment Anything Model is a Good Teacher for Local Feature Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Jingqian Xu, Rongtao Wood-Doughty, Zach Wang, Changwei Xu, Shibiao Lam, Edmund Y. The University of Hong Kong Pokfulam Hong Kong The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100190 China Northwestern University EvanstonIL60201 United States The Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Qilu University of Technology Shandong Academy of Sciences Jinan250013 China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China The School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China

Local feature detection and description play an important role in many computer vision tasks, which are designed to detect and describe keypoints in any scene and any downstream task. Data-driven local feature learning methods need to rely on pixel-level correspondence for training. However, a vast number of existing approaches ignored the semantic information on which humans rely to describe image pixels. In addition, it is not feasible to enhance generic scene keypoints detection and description simply by using traditional common semantic segmentation models because they can only recognize a limited number of coarse-grained object classes. In this paper, we propose SAMFeat to introduce SAM (segment anything model), a foundation model trained on 11 million images, as a teacher to guide local feature learning. SAMFeat learns additional semantic information brought by SAM and thus is inspired by higher performance even with limited training samples. To do so, first, we construct an auxiliary task of Attention-weighted Semantic Relation Distillation (ASRD), which adaptively distillates feature relations with category-agnostic semantic information learned by the SAM encoder into a local feature learning network, to improve local feature description using semantic discrimination. Second, we develop a technique called Weakly Supervised Contrastive Learning Based on Semantic Grouping (WSC), which utilizes semantic groupings derived from SAM as weakly supervised signals, to optimize the metric space of local descriptors. Third, we design an Edge Attention Guidance (EAG) to further improve the accuracy of local feature detection and description by prompting the network to pay more attention to the edge region guided by SAM. SAMFeat’s performance on various tasks such as image matching on HPatches, and long-term visual localization on Aachen Day-Night showcases its superiority over previous local features. The release code is available at https://***/vignywang/SAMFeat

关键词： Computer vision

Research on Text Classification Based on BERT-BiGRU Model

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2021年第1期1746卷

作者： Qing Yu Ziyin Wang Kaiwen Jiang Tianjin Key Laboratory of Intelligence Computing and Network Security Tianjin University of Technology Tianjin China

Text classification is a typical application of natural language processing. At present, the most commonly used text classification method is deep learning. Meanwhile there are many difficulties in natural language processing, such as metaphor expression, semantic diversity and grammatical specificity. To solve these problems, this paper proposes the structure of BERT-BiGRU model. First, use the BERT model instead of the traditional word2vec model to represent the word vector, the word representation is calculated according to the context information, and it can be adjusted according to the meaning of word while the context information is fused. Secondly BiGRU model is attached to the BERT model, BiGRU model can extract the text information features from both directions at the same time. Multiple sets of experiments were set up and compared with the model proposed in this paper, according to the final experimental results, using the proposed BERT-BiGRU model for text classification, the final accuracy, recall and F1 score were all above 0.9. It shows that BERT-BiGRU model has good performance in the Chinese text classification task.

关键词：

Federated Semantic Learning for Privacy-preserving Cross-domain Recommendation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Lu, Ziang Guo, Lei Yu, Xu Cheng, Zhiyong Han, Xiaohui Zhu, Lei Shandong Normal University Shandong Jinan250358 China Shandong Qingdao266580 China Hefei University of Technology Anhui Hefei230009 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology Shandong Academy of Sciences Shandong Jinan250014 China Tongji University Shanghai Jinan200092 China

In the evolving landscape of recommender systems, the challenge of effectively conducting privacy-preserving Cross-Domain Recommendation (CDR), especially under strict non-overlapping constraints, has emerged as a key focus. Despite extensive research has made significant progress, several limitations still exist: 1) Previous semantic-based methods fail to deeply exploit rich textual information, since they quantize the text into codes, losing its original rich semantics. 2) The current solution solely relies on the text-modality, while the synergistic effects with the ID-modality are ignored. 3) Existing studies do not consider the impact of irrelevant semantic features, leading to inaccurate semantic representation. To address these challenges, we introduce federated semantic learning and devise FFMSR as our solution. For Limitation 1, we locally learn items’ semantic encodings from their original texts by a multi-layer semantic encoder, and then cluster them on the server to facilitate the transfer of semantic knowledge between domains. To tackle Limitation 2, we integrate both ID and Text modalities on the clients, and utilize them to learn different aspects of items. To handle Limitation 3, a Fast Fourier Transform (FFT)-based filter and a gating mechanism are developed to alleviate the impact of irrelevant semantic information in the local model. We conduct extensive experiments on two real-world datasets, and the results demonstrate the superiority of our FFMSR method over other SOTA methods. Our source codes are publicly available at: https://***/Sapphire-star/FFMSR. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning