检索结果-内蒙古大学图书馆

Advancement in Computation & computer Technologies (InCACCT), International Conference on

作者： Pathik Bavadiya Purnima Upadhyaya Ajay Chandrakant Bhosle Shubham Gupta Neha Gupta Vp Production Service Application Support BNY New York USA Independent Researcher Raleigh NC USA Independent Researcher Katy TX USA Department of CSE Model Institute of Engineering & Technology Jammu India School of Computer Science and Engineering Geeta University Naultha Panipat

ISBN: (数字)9798331543891

ISBN: (纸本)9798331543907

Cyber threats are evolving rapidly, making traditional malware detection approaches insufficient in handling sophisticated attacks such as zero-day exploits, polymorphic malware, and advanced persistent threats. As a solution to these problems, this study presents a novel hybrid AI-based data analysis framework for cyber threat intelligence and anomaly detection. We specifically proposed a model that combines autoencoders, random forests, and CNN-LSTM architectures to improve anomaly detection and classification. The dataset used for training and evaluation is the Microsoft Malware Dataset, a publicly available dataset. The AE-RF module learns the normal behavior of the system to detect abnormal behavior, and the CNN-LSTM model identifies spatial and temporal properties of malware for execution patterns. This article ensures that the dataset is well-preprocessed, including feature extraction, PCA, and SMOTE for class balancing to provide optimal model performance. The experimental results show that AE-RF has an area under curve (AUC) score of 0.91 and CNN-LSTM has 0.94, which demonstrates that unsupervised and supervised techniques together have high classification accuracy. This hybrid approach not only improves malware detection accuracy but also enhances cyber threat intelligence by providing interpretable insights into attack patterns. The study concludes that integrating multiple AI techniques can significantly improve cybersecurity defenses against evolving threats, paving the way for real-time, AI-powered malware detection solutions.

关键词： Accuracy Data analysis Autoencoders Feature extraction Malware Threat assessment Real-time systems Cyber threat intelligence computer security Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Review of Nodule Mineral Image Segmentation Algorithms for Deep-Sea Mineral Resource Assessment

引用

computers, Materials & Continua 2022年第10期73卷 1649-1669页

作者： Wei Song Lihui Dong Xiaobing Zhao Jianxin Xia Tongmu Liu Yuxi Shi School of Information and Engineering Minzu University of ChinaBeijing100081China Key Laboratory of Marine Environmental Survey Technology and Application Ministry of Natural ResourceGuangzhou510300China National Language Resource Monitoring&Research Center of Minority Languages Minzu University of ChinaBeijing100081China School of Ocean Science China University of GeosciencesBeijing100191China Department of Buoy Engineering South China Sea Marine Survey and Technology Center of State Oceanic AdministrationGuangzhou510310China Department of Electrical and Computer Engineering New Jersey Institute of TechnologyNewarkNJ07102USA

A large number of nodule minerals exist in the deep *** on the factors of difficulty in shooting,high economic cost and high accuracy of resource assessment,large-scale planned commercial mining has not yet been *** experimental mining has been carried out in areas with high mineral density and obvious benefits after mineral resource *** an efficient method for deep-sea mineral resource assessment,the deep towing system is equipped with a visual system for mineral resource analysis using collected images and videos,which has become a key component of resource ***,high accuracy in deep-sea mineral image segmentation is the primary goal of the segmentation *** this paper,the existing deep-sea nodule mineral image segmentation algorithms are studied in depth and divided into traditional and deep learning-based segmentation methods,and the advantages and disadvantages of each are compared and *** deep learning methods show great advantages in deep-sea mineral image segmentation,and there is a great improvement in segmentation accuracy and efficiency compared with the traditional ***,the mineral image dataset and segmentation evaluation metrics are ***,possible future research topics and improvement measures are discussed for the reference of other researchers.

关键词： Polymetallic nodule deep-sea mining image segmentation deep learning

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Techniques for IoT Data Sharing

Privacy-Preserving Techniques for IoT Data Sharing

引用

International Conference on science Technology engineering and Management (ICONSTEM)

作者： P Karthikeyan Shashiraj Teotia Toralkar Pawan B Ardly Melba Reena Chirag Vibhakar Kalai Priya V Department of Electronics and Communication Engineering Velammal College of Engineering and Technology Madurai Tamil Nadu Department of Computer Application Swami Vivekanand Subharti University Meerut Department of Artificial Intelligence Madanapalle Institute of Technology & Science Madanapalle Andhra Pradesh India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Saveetha University Chennai Tamil Nadu India Department of Electrical Engineering Gujarat Power Engineering &. Research Institute Mevad Mehsana Gujarat Technological University Ahmedabad Gujarat India Department of Computer Science and Engineering RMK College of Engineering and Technology Puduvoyal Tamil Nadu India

ISBN: (数字)9798350365092

ISBN: (纸本)9798350365108

In aperiod dominated by the Internet of Effects (IoT), the sharing of data has become an integral aspect of technological advancements. still, the ubiquitous nature of IoT raises significant enterprises regarding stonerse questration. Thisexploration paper delves into innovatives equestration conservingwaysacclimatized for securing the sharing of IoT-generated data. The explores cryptographic protocols, anonymisation strategies, and decentralized fabrics toguard sensitive information while easing meaningful data exchange. Addressing the contradiction between datamileage and individuals equestration, the paper proposes new methodologies that intricately balance the need for dataparticipation with the imperative tocoverstoner confidentiality. By introducing a comprehensive analysis of sequestration-conserving mechanisms with in the IoT eco system, this exploration contribute sprecious perceptivity to the ongoingconverse on securing the digitalgeography. The findings offer a foundation for developing robustfabrics that harmonize the imperatives of dataparticipating with the consummatesignificance of securing stoner sequestration in the expanding realm of Io'Toperations.

关键词： Mathematics Fabrics Internet of Things STEM Cryptographic protocols

来源：评论

学校读者我要写书评

暂无评论

Vision-Amplified Semantic Entropy for Hallucination Detection in Medical Visual Question Answering

arXiv

引用

arXiv 2025年

作者： Liao, Zehui Hu, Shishuai Zou, Ke Fu, Huazhu Zhen, Liangli Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China Institute of High Performance Computing Agency for Science Technology and Research Singapore138632 Singapore National University of Singapore Singapore119077 Singapore

Multimodal large language models (MLLMs) have demonstrated significant potential in medical Visual Question Answering (VQA). Yet, they remain prone to hallucinations—incorrect responses that contradict input images, posing substantial risks in clinical decision-making. Detecting these hallucinations is essential for establishing trust in MLLMs among clinicians and patients, thereby enabling their real-world adoption. Current hallucination detection methods, especially semantic entropy (SE), have demonstrated promising hallucination detection capacity for LLMs. However, adapting SE to medical MLLMs by incorporating visual perturbations presents a dilemma. Weak perturbations preserve image content and ensure clinical validity, but may be overlooked by medical MLLMs, which tend to over rely on language priors. In contrast, strong perturbations can distort essential diagnostic features, compromising clinical interpretation. To address this issue, we propose Vision Amplified Semantic Entropy (VASE), which incorporates weak image transformations and amplifies the impact of visual input, to improve hallucination detection in medical VQA. We first estimate the semantic predictive distribution under weak visual transformations to preserve clinical validity, and then amplify visual influence by contrasting this distribution with that derived from a distorted image. The entropy of the resulting distribution is estimated as VASE. Experiments on two medical open-ended VQA datasets demonstrate that VASE consistently outperforms existing hallucination detection methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Sustainable Self-evolution Adversarial Training

arXiv

引用

arXiv 2024年

作者： Wang, Wenxuan Wang, Chenglei Qi, Huihui Ye, Menghao Qian, Xuelin Wang, Peng Zhang, Yanning School of Computer Science Northwestern Polytechnical University National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi’an China School of Automation Northwestern Polytechnical University The BRain and Artificial INtelligence Lab Shaanxi Xi’an China

With the wide application of deep neural network models in various computer vision tasks, there has been a proliferation of adversarial example generation strategies aimed at deeply exploring model security. However, existing adversarial training defense models, which rely on single or limited types of attacks under a one-time learning process, struggle to adapt to the dynamic and evolving nature of attack methods. Therefore, to achieve defense performance improvements for models in long-term applications, we propose a novel Sustainable Self-Evolution Adversarial Training (SSEAT) framework. Specifically, we introduce a continual adversarial defense pipeline to realize learning from various kinds of adversarial examples across multiple stages. Additionally, to address the issue of model catastrophic forgetting caused by continual learning from ongoing novel attacks, we propose an adversarial data replay module to better select more diverse and key relearning data. Furthermore, we design a consistency regularization strategy to encourage current defense models to learn more from previously trained ones, guiding them to retain more past knowledge and maintain accuracy on clean samples. Extensive experiments have been conducted to verify the efficacy of the proposed SSEAT defense method, which demonstrates superior defense performance and classification accuracy compared to competitors. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Identifying Flight Trajectory Patterns via a Density-Aided Hierarchical Clustering Algorithm 5th

Identifying Flight Trajectory Patterns via a Density-Aided H...

引用

5th China Aviation science and Technology Conference, 2021

作者： Zhang, Zhuxi Chen, Yichong Fang, Jing Zhou, Xueyang An, Yuhang Zhu, Xi National Engineering Laboratory for Comprehensive Transportation Big Data Application Technology Beihang University Beijing100191 China Unit 32751 Beijing China School of Electronics and Information Engineering Beihang University Beijing100191 China Aviation Data Communication Corporation Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China Research Institute for Frontier Science Beihang University Beijing100191 China

ISBN: (纸本)9789811674228

Identifying flight trajectory patterns is a vital task that helps controllers better understand the flight operation mechanism, so as to effectively recognize flight anomalies and manage traffic flow, etc. However, flight operation is sensitively affected by the weather and instant airspace regulation, making the flight trajectory pattern too intertwined to be easily distinguished. In this work, we propose a trajectory pattern identification method based on a density-aided hierarchical clustering algorithm. This method employs a weighted trajectory clustering mechanism to keep the minor trajectory patterns from being improperly "swallowed" by other large trajectory patterns. Experimental results show that the proposed method can explicitly distinguish different trajectory patterns and achieve more accurate results than existing approaches. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

A Game-Theoretic Incentive Mechanism for Multi-Distributor Multi-Agent Federated Learning

A Game-Theoretic Incentive Mechanism for Multi-Distributor M...

引用

IEEE Conference on Wireless Communications and Networking

作者： Jian Yang Mingkai Zhu Yan Zhou Qingrui Zhang Yiyang Ni School of Computer NUPT-JSTZ Carbon Peaking & Carbon Neutrality Application Technology R&D Institute Nanjing University of Posts and Telecommunications Nanjing China College of Telecommunications and Information Engineering Nanjing University of Posts and Telecommunications Nanjing China School of Computer Nanjing University of Posts and Telecommunications Nanjing China School of Philosophy Religion and History of Science University of Leeds Leeds UK

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

In a multi-distributor multi-agent federated learning architecture, it is desired to maximize the overall system benefits by optimizing the association relationship between the base station and users. To address this issue, a novel incentive mechanism based on Stackelberg game is proposed. Firstly, each mobile device determines its own strategy based on the utility function. Then, each base station adjusts its own strategy based on the optimal solution of the mobile devive to maximize its own utiltiy function. By relaxing the binary variables that represent the correlation relationship into continuous variables, the 0–1 optimization problem for base stations and mobile devices is transformed into a linear problem and solved. The simulation results show that the proposed algorithm is better than random algorithm in terms of training loss and testing accuracy.

关键词： Training Base stations Correlation Accuracy Federated learning Simulation Games

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Multi-Granular Decision Networks for Hierarchical Classification

SSRN

引用

SSRN 2024年

作者： Liu, Haoyang Hu, Xue gang Bai, Shengxing Lin, Yaojin Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education China School of Computer Science and Information Engineering Hefei University of Technology Anhui Hefei230009 China Anhui Province Key Laboratory of Industry Safety and Emergency Technology Anhui Hefei230009 China School of Computer Science Minnan Normal University Fujian Zhangzhou363000 China Key Laboratory of Data Science and Intelligence Application Minnan Normal University Fujian Zhangzhou363000 China

Hierarchical classification learning is an effective means of solving large-scale classification problems, which models classification problems at different levels of granularity according to a hierarchical structure. In hierarchical classification tasks, classification results at different levels of granularity are mutually beneficial, where coarse-grained results can reduce the number of fine-grained candidate categories, and fine-grained results can provide a basis for coarse-grained classification. However, for the final decision, the contribution of the granularity levels in the different hierarchies is different and unknown. Feedback from different granularity levels should be flexibly integrated. In addition, errors in hierarchical classification are not equivalent, and some errors can have serious results for practical applications. In order to address the above challenges, we propose a new hierarchical network to integrate multi-granularity knowledge for decision making. On the one hand, the network computes the decision scores of instances at each granularity level and learns a set of weights to combine all scores. Based on the learnable weights, the model can effectively utilize the multi-granularity classification results to obtain the final decision. On the other hand, we design local and global classification losses to guide model optimization, which allows the model to gain a hierarchical perspective and the ability to understand the degree of hierarchical misclassification. As a result, the extent to which the method results in misclassification consequences is limited. Experimental results on five benchmark datasets show that our method arises as a state-of-the-art hierarchical classification method. © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Complementary Advantages: Exploiting Cross-Field Frequency Correlation for NIR-Assisted Image Denoising

arXiv

引用

arXiv 2024年

作者： Wang, Yuchen Wang, Hongyuan Wang, Lizhi Wang, Xin Zhu, Lin Lu, Wanxuan Huang, Hua School of Computer Science and Technology Beijing Institute of Technology China School of Artificial Intelligence Beijing Normal University China Engineering Research Center of Intelligent Technology and Educational Application Ministry of Education China Aerospace Information Research Institute Chinese Academy of Sciences China

Existing single-image denoising algorithms often struggle to restore details when dealing with complex noisy images. The introduction of near-infrared (NIR) images offers new possibilities for RGB image denoising. However, due to the inconsistency between NIR and RGB images, the existing works still struggle to balance the contributions of two fields in the process of image fusion. In response to this, in this paper, we develop a cross-field Frequency Correlation Exploiting Network (FCENet) for NIR-assisted image denoising. We first propose the frequency correlation prior based on an in-depth statistical frequency analysis of NIR-RGB image pairs. The prior reveals the complementary correlation of NIR and RGB images in the frequency domain. Leveraging frequency correlation prior, we then establish a frequency learning framework composed of Frequency Dynamic Selection Mechanism (FDSM) and Frequency Exhaustive Fusion Mechanism (FEFM). FDSM dynamically selects complementary information from NIR and RGB images in the frequency domain, and FEFM strengthens the control of common and differential features during the fusion process of NIR and RGB features. Extensive experiments on simulated and real data validate that the proposed method outperforms other state-of-the-art methods. The code will be released at https://***/yuchenwang815/FCENet. Copyright © 2024, The Authors. All rights reserved.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Neural Network Implementation for Battery Failure Detection in Electric Vehicles

Neural Network Implementation for Battery Failure Detection ...

引用

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： S. Vijitha Dheeraj Hebri Sangeeta Singh M. Manohara Mohammad Ishrat D Raja Joseph Department of Computer Science and Engineering Vels Institute of Science Technology & Advanced Studies Chennai Tamil Nadu India Department of Master of Computer Application Srinivas Institute of Technology Mangaluru Karnataka India Department of Electrical Engineering JSS Academy of Technical Education Noida Uttar Pradesh India School of Engineering Mohan Babu University Tirupati Andhra Pradesh India Department of Computer Science and Engineering KoneruLakshmaiah Education Foundation Vaddeswaram Guntur Andhra Pradesh India School of Aeronautical Sciences Hindustan Institute of Technology and Science Chennai Tamil Nadu India

Soil destruction and global warming have recently come to the forefront of discussion in industrialised nations as governments strive to accommodate the rising demands of their citizens. The demand for zero-emission electric cars has increased as a result of international competitiveness and technological advancements (EVs). Concerns about the high voltage of increasing numbers of electric cars are shared by an increasing number of individuals. Since the system of batteries may be at responsible for over 30% of EV accidents, it is vital to investigate how problems with LIBs are recognized. Many different kinds of problems make it hard to fix EV's LIB. Fast and precise diagnosis of battery pack problems is crucial for the immediate and ongoing safety of EV operation. Utilizing models of neural networks like multiple hidden layers (MLP) or nonlinear activation functions, this research provides a mechanism for identifying and fixing problems with electric vehicle batteries (RBF). To generate information for the BFD system, battery simulations are done in MATLAB. Accuracy may be improved by performing pre-processing steps on the information once it has been generated. After training, the two models are put to the test to see how well they perform. There are both positive and negative measures that may be used to determine which model is the best.

关键词：

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：