检索结果-内蒙古大学图书馆

A recover-then-discriminate framework for robust anomaly detection

science China(Information sciences) 2025年第4期68卷 300-318页

作者： Peng XING Dong ZHANG Jinhui TANG Zechao LI School of Computer Science and Engineering Nanjing University of Science and Technology Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology

Anomaly detection(AD) has been extensively studied and applied across various scenarios in recent years. However, gaps remain between the current performance and the desired recognition accuracy required for practical *** paper analyzes two fundamental failure cases in the baseline AD model and identifies key reasons that limit the recognition accuracy of existing approaches. Specifically, by Case-1, we found that the main reason detrimental to current AD methods is that the inputs to the recovery model contain a large number of detailed features to be recovered, which leads to the normal/abnormal area has not/has been recovered into its original state. By Case-2, we surprisingly found that the abnormal area that cannot be recognized in image-level representations can be easily recognized in the feature-level representation. Based on the above observations, we propose a novel recover-then-discriminate(ReDi) framework for *** takes a self-generated feature map(e.g., histogram of oriented gradients) and a selected prompted image as explicit input information to address the identified in Case-1. Additionally, a feature-level discriminative network is introduced to amplify abnormal differences between the recovered and input representations. Extensive experiments on two widely used yet challenging AD datasets demonstrate that ReDi achieves state-of-the-art recognition accuracy.

关键词： recovery network HOG prompt discriminative network self-correlation loss anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Real-time earthquake magnitude prediction using designed machine learning ensemble trained on real and CTGAN generated synthetic data

引用

Geodesy and Geodynamics 2025年第3期16卷 350-368页

作者： Anushka Joshi Balasubramanian Raman C.Krishna Mohan Department of Computer Science and Engineering Indian Institute of Technology

The earthquake early warning(EEW) system provides advance notice of potentially damaging ground shaking. In EEW, early estimation of magnitude is crucial for timely rescue operations. A set of thirty-four features is extracted using the primary wave earthquake precursor signal and site-specific *** Japan's earthquake magnitude dataset, there is a chance of a high imbalance concerning the earthquakes above strong impact. This imbalance causes a high prediction error while training advanced machine learning or deep learning models. In this work, Conditional Tabular Generative Adversarial Networks(CTGAN), a deep machine learning tool, is utilized to learn the characteristics of the first arrival of earthquake P-waves and generate a synthetic dataset based on this information. The result obtained using actual and mixed(synthetic and actual) datasets will be used for training the stacked ensemble magnitude prediction model, MagPred, designed specifically for this study. There are 13295, 3989, and1710 records designated for training, testing, and validation. The mean absolute error of the test dataset for single station magnitude detection using early three, four, and five seconds of P wave are 0.41, 0.40,and 0.38 MJMA. The study demonstrates that the Generative Adversarial Networks(GANs) can provide a good result for single-station magnitude prediction. The study can be effective where less seismic data is available. The study shows that the machine learning method yields better magnitude detection results compared with the several regression models. The multi-station magnitude prediction study has been conducted on prominent Osaka, Off Fukushima, and Kumamoto earthquakes. Furthermore, to validate the performance of the model, an inter-region study has been performed on the earthquakes of the India or Nepal region. The study demonstrates that GANs can discover effective magnitude estimation compared with non-GAN-based methods. This has a high potential for wid

关键词： Magnitude Synthetic data Machine learning Earthquake CTGAN

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving filtering, control and optimization for industrial cyber-physical systems

引用

science China(Information sciences) 2025年第4期68卷 267-283页

作者： Derui DING Qing-Long HAN Xiaohua GE Xian-Ming ZHANG Jun WANG Department of Control Science and Engineering University of Shanghai for Science and Technology School of Engineering Swinburne University of Technology Department of Computer Science City University of Hong Kong

Industrial cyber-physical systems closely integrate physical processes with cyberspace, enabling real-time exchange of various information about system dynamics, sensor outputs, and control decisions. The connection between cyberspace and physical processes results in the exposure of industrial production information to unprecedented security risks. It is imperative to develop suitable strategies to ensure cyber security while meeting basic performance *** the perspective of control engineering, this review presents the most up-to-date results for privacy-preserving filtering,control, and optimization in industrial cyber-physical systems. Fashionable privacy-preserving strategies and mainstream evaluation metrics are first presented in a systematic manner for performance evaluation and engineering *** discussion discloses the impact of typical filtering algorithms on filtering performance, specifically for privacy-preserving Kalman filtering. Then, the latest development of industrial control is systematically investigated from consensus control of multi-agent systems, platoon control of autonomous vehicles as well as hierarchical control of power systems. The focus thereafter is on the latest privacy-preserving optimization algorithms in the framework of consensus and their applications in distributed economic dispatch issues and energy management of networked power systems. In the end, several topics for potential future research are highlighted.

关键词： industrial cyber-physical systems privacy preservation distributed control distributed optimization power systems

来源：评论

学校读者我要写书评

暂无评论

An Analytical Review of Large Language Models Leveraging KDGI Fine-Tuning,Quantum Embedding’s,and Multimodal Architectures

引用

computers, Materials & Continua 2025年第6期83卷 4031-4059页

作者： Uddagiri Sirisha Chanumolu Kiran Kumar Revathi Durgam Poluru Eswaraiah G Muni Nagamani Department of Computer Science and Engineering Prasad V Potluri Siddhartha Institute of TechnologyVijayawada520007India Department of Computer Science and Engineering Koneru Lakshmaiah Education FoundationVaddeswaram522302India Department of Computer Science and Engineering(Data Science) AVN Institute of Engineering and TechnologyHyderabad501510India Department of Computer Science and Engineering(Data Science) Vignan’s Institute of Management and Technology forWomenHyderabad501301India Department of Computer Science and Engineering Andhra Loyola Institute of Engineering and TechnologyVijayawada520008India

A complete examination of Large Language Models’strengths,problems,and applications is needed due to their rising use across *** studies frequently focus on single-use situations and lack a comprehensive understanding of LLM architectural performance,strengths,and *** gap precludes finding the appropriate models for task-specific applications and limits awareness of emerging LLM optimization and deployment *** this research,50 studies on 25+LLMs,including GPT-3,GPT-4,Claude 3.5,DeepKet,and hybrid multimodal frameworks like ContextDET and GeoRSCLIP,are thoroughly *** propose LLM application taxonomy by grouping techniques by task focus—healthcare,chemistry,sentiment analysis,agent-based simulations,and multimodal *** methods like parameter-efficient tuning(LoRA),quantumenhanced embeddings(DeepKet),retrieval-augmented generation(RAG),and safety-focused models(GalaxyGPT)are evaluated for dataset requirements,computational efficiency,and performance *** for ethical issues,data limited hallucinations,and KDGI-enhanced fine-tuning like Woodpecker’s post-remedy corrections are *** investigation’s scope,mad,and methods are described,but the primary results are *** work reveals that domain-specialized fine-tuned LLMs employing RAG and quantum-enhanced embeddings performbetter for context-heavy *** medical text normalization,ChatGPT-4 outperforms previous models,while two multimodal frameworks,GeoRSCLIP,increase remote ***-efficient tuning technologies like LoRA have minimal computing cost and similar performance,demonstrating the necessity for adaptive models in multiple *** discover the optimum domain-specific models,explain domain-specific fine-tuning,and present quantum andmultimodal LLMs to address scalability and cross-domain *** framework helps academics and practitioners identify,adapt,and innovate LLMs for different *** work

关键词： Large languagemodels quantum embeddings fine-tuning techniques multimodal architectures ethical AI scenarios

来源：评论

学校读者我要写书评

暂无评论

Enhanced Acceleration for Generalized Nonconvex Low-Rank Matrix Learning

引用

Chinese Journal of Electronics 2025年第1期34卷 98-113页

作者： Hengmin Zhang Jian Yang Wenli Du Bob Zhang Zhiyuan Zha Bihan Wen School of Electrical and Electronic Engineering Nanyang Technological University School of Computer Science and Engineering Nanjing University of Science and Technology School of Information Science and Engineering East China University of Science and Technology Department of Electrical and Computer Engineering University of Macau

Matrix minimization techniques that employ the nuclear norm have gained recognition for their applicability in tasks like image inpainting, clustering, classification, and reconstruction. However, they come with inherent biases and computational burdens, especially when used to relax the rank function, making them less effective and efficient in real-world scenarios. To address these challenges, our research focuses on generalized nonconvex rank regularization problems in robust matrix completion, low-rank representation, and robust matrix regression. We introduce innovative approaches for effective and efficient low-rank matrix learning, grounded in generalized nonconvex rank relaxations inspired by various substitutes for the ?0-norm relaxed functions. These relaxations allow us to more accurately capture low-rank structures. Our optimization strategy employs a nonconvex and multi-variable alternating direction method of multipliers, backed by rigorous theoretical analysis for complexity and *** algorithm iteratively updates blocks of variables, ensuring efficient convergence. Additionally, we incorporate the randomized singular value decomposition technique and/or other acceleration strategies to enhance the computational efficiency of our approach, particularly for large-scale constrained minimization problems. In conclusion, our experimental results across a variety of image vision-related application tasks unequivocally demonstrate the superiority of our proposed methodologies in terms of both efficacy and efficiency when compared to most other related learning methods.

关键词： Learning systems Image recognition Minimization Computational efficiency Complexity theory Matrix decomposition Optimization Image reconstruction Singular value decomposition Convergence

来源：评论

学校读者我要写书评

暂无评论

The superalignment of superhuman intelligence with large language models

引用

science China(Information sciences) 2025年第6期68卷 101-111页

作者： Minlie HUANG Yingkang WANG Shiyao CUI Pei KE Jie TANG The CoAI Group Department of Computer Science and Technology Tsinghua University Laboratory of Intelligent Collaborative Computing University of Electronic Science and Technology of China Knowledge Engineering Group Department of Computer Science and Technology Tsinghua University

We have witnessed the emergence of superhuman intelligence thanks to the fast development of large language models(LLMs) and multimodal language models. As the application of such superhuman models becomes increasingly popular, a critical question arises: how can we ensure they still remain safe, reliable, and aligned well with human values encompassing moral values, Schwartz's Values, ethics, and many more? In this position paper, we discuss the concept of superalignment from a learning perspective to answer this question by outlining the learning paradigm shift from large-scale pretraining and supervised fine-tuning, to alignment training. We define superalignment as designing effective and efficient alignment algorithms to learn from noisy-labeled data(point-wise samples or pair-wise preference data) in a scalable way when the task is very complex for human experts to annotate and when the model is stronger than human experts. We highlight some key research problems in superalignment, namely, weak-to-strong generalization, scalable oversight, and evaluation. We then present a conceptual framework for superalignment, which comprises three modules: an attacker which generates the adversary queries trying to expose the weaknesses of a learner model, a learner which refines itself by learning from scalable feedbacks generated by a critic model with minimal human experts, and a critic which generates critics or explanations for a given query-response pair, with a target of improving the learner by criticizing. We discuss some important research problems in each component of this framework and highlight some interesting research ideas that are closely related to our proposed framework, for instance, self-alignment, self-play, self-refinement, and more. Last, we highlight some future research directions for superalignment, including the identification of new emergent risks and multi-dimensional alignment.

关键词： superalignment superhuman intelligence large language models scalable feedback weak-to-strong generalization

来源：评论

学校读者我要写书评

暂无评论

MLRT-UNet:An Efficient Multi-Level Relation Transformer Based U-Net for Thyroid Nodule Segmentation

引用

computer Modeling in engineering & sciences 2025年第4期143卷 413-448页

作者： Kaku Haribabu Prasath R Praveen Joe IR Department of Computer Science and Engineering RMK College of Engineering and TechnologyTiruvallur601206India School of Computer Science and Engineering Vellore Institute of TechnologyChennai600127India

Thyroid nodules,a common disorder in the endocrine system,require accurate segmentation in ultrasound images for effective diagnosis and ***,achieving precise segmentation remains a challenge due to various factors,including scattering noise,low contrast,and limited resolution in ultrasound *** existing segmentation models have made progress,they still suffer from several limitations,such as high error rates,low generalizability,overfitting,limited feature learning capability,*** address these challenges,this paper proposes a Multi-level Relation Transformer-based U-Net(MLRT-UNet)to improve thyroid nodule *** MLRTUNet leverages a novel Relation Transformer,which processes images at multiple scales,overcoming the limitations of traditional encoding *** transformer integrates both local and global features effectively through selfattention and cross-attention units,capturing intricate relationships within the *** approach also introduces a Co-operative Transformer Fusion(CTF)module to combine multi-scale features from different encoding layers,enhancing the model’s ability to capture complex patterns in the ***,the Relation Transformer block enhances long-distance dependencies during the decoding process,improving segmentation *** results showthat the MLRT-UNet achieves high segmentation accuracy,reaching 98.2% on the Digital Database Thyroid Image(DDT)dataset,97.8% on the Thyroid Nodule 3493(TG3K)dataset,and 98.2% on the Thyroid Nodule3K(TN3K)*** findings demonstrate that the proposed method significantly enhances the accuracy of thyroid nodule segmentation,addressing the limitations of existing models.

关键词： Thyroid nodules endocrine system multi-level relation transformer U-Net self-attention external attention co-operative transformer fusion thyroid nodules segmentation

来源：评论

学校读者我要写书评

暂无评论

DeepGAN: Utilizing generative adversarial networks for improved deep learning

引用

International Journal of Knowledge-Based and Intelligent engineering Systems 2024年第4期28卷 732-748页

作者： V, Edward Naveen A, Jenefa T.M, Thiyagu A, Lincy Taurshia, Antony Department of Computer Science and Engineering Sri Shakthi Institute of Engineering and Technology India Department of Computer Science and Engineering Karunya Institute of Technology and Sciences India Division of Computer Science and Engineering Karunya Institute of Technology and Sciences India Department of Computer Science and Engineering National Engineering College India

In the realm of deep learning, Generative Adversarial Networks (GANs) have emerged as a topic of significant interest for their potential to enhance model performance and enable effective data augmentation. This paper addresses the existing challenges in synthesizing high-quality data and harnessing the capabilities of GANs for improved deep learning outcomes. Unlike traditional approaches that heavily rely on manually engineered data augmentation techniques, our work introduces a novel framework that leverages DeepGANs to autonomously generate diverse and high-fidelity data. Our experiments encompass a diverse spectrum of datasets, including images, text, and time series data. In the context of image classification tasks, we conduct experiments on the widely recognized CIFAR-10 dataset, which consists of 50,000 image samples. Our results demonstrate the remarkable efficacy of DeepGANs in enhancing model performance across various data domains. Notably, in image classification using the CIFAR-10 dataset, our innovative approach achieves an impressive accuracy of 97.2%. This represents a substantial advancement beyond conventional CNN models, underscoring the profound impact of DeepGANs in the realm of deep learning. In summary, this research sheds light on DeepGANs as a fundamental component in the pursuit of enhanced deep learning performance. Our framework not only overcomes existing limitations but also heralds a new era of data augmentation, with generative adversarial networks leading the way. The attainment of an accuracy rate of 97.2% on CIFAR-10 serves as a compelling testament to the transformative potential of DeepGANs, solidifying their pivotal role in the future of deep learning. This promises the development of more robust, adaptive, and accurate models across a myriad of applications, marking a significant contribution to the field. © 2024 – IOS Press. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Using DTL-MD with GANs and ResNet for Malicious Code Detection

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第14期49卷 63-78页

作者： Li, Yiming Xie, Tao Mei, Dongdong Department of Computer Science and Technology School of Computer Science and Engineering Ningxia Institute of Science and Technology Shizuishan753000 China

This study proposes a malicious code detection model DTL-MD based on deep transfer learning, which aims to improve the detection accuracy of existing methods in complex malicious code and data scarcity. In the feature extraction process, the weighted sum method of GIST and LBP features is used to combine the advantages of the two features. Online transfer learning is used to reduce the data distribution difference between the target domain and the source domain. The model uses ResNet50V2 as the backbone network and combines SimAM to enhance the feature extraction and representation capabilities. In addition, in order to further improve the robustness of detection, GAN is used to generate malicious code variants and expand the training data set. In the experiment, the public CICIDS 2017 data set is used for model training and testing. The performance test results show that when the threshold is 0.7, the accuracy of DTL-MD is 95.8% and the F1 score is 0.93. In a performance test involving 30,000 samples, the throughput of the DTL-MD model under Trojans, viruses, worms, and adware is 11, 12, 11, and 12 tasks/s, respectively, and the inference time is 211, 225, 239, and 234 samples/s, respectively. Compared with GAN, DTL-MD increases the throughput by about 10% and the inference speed by about 15%. The research aims to provide new ideas for improving the intelligence and automation level of malicious code detection technology, which has certain application value and practical significance. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

IDLRN-DBN: SEGMENTATION-BASED EARLY DIAGNOSIS OF RICE PLANT DISEASE DETECTION USING DEEP BELIEF NETWORK

引用

KSII Transactions on Internet and Information Systems 2025年第5期19卷 1539-1563页

作者： Raji, N. Manohar, S. Department of Computer Science and Engineering SRM Institute of Science and Technology Vadapalani Chennai India Department of Computer Science and Engineering SRM Institute of Science and Technology Vadapalani Chennai India

Agriculture remains the basis of the Indian economy, with rice being a pivotal crop. However, rice cultivation faces significant challenges from various plant diseases, leading to substantial agricultural losses. The advanced segmentation-based Deep Belief Network (DBN) model iDLRN-DBN is proposed to meet the need for early and precise diagnosis of rice plant diseases and addresses the critical challenge of agricultural losses caused by plant diseases in India. The methodology is further improved upon as compared with the traditional methods by the addition of deep learning (DL), along with being supported by machine learning (ML) techniques. The six critical phases are comprised of the iDLRN-DBN model: image acquisition from a Kaggle dataset, pre-processing using adaptive filters, image segmentation through an enhanced DeepLabV3+ model, feature extraction through Efficient Grey Level Co-occurrence Matrix and Haralick Texture Features, a hybrid optimization model known as the Lyrebat Algorithm for optimal feature selection, and the classification of disease through a DBN. The iDLRN-DBN model reduced the false negative rate to 0.0257, the false positive rate to 0.0245, precision was boosted by 0.0050, and the negative predictive value increased by 0.0926. This model showed high accuracy at 0.9762, F1 score at 0.9860, low FNR at 0.0250, and a high NPV at 0.8676, which implies it is useful in conducting timely interventions and efficient crop management in smart farming. This research contributes to the progress of agricultural technology and food security due to the integration of techniques in ML and DL into the diagnostics of rice plant diseases. Copyright © 2025 KSII.

关键词： Image segmentation

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：