检索结果-内蒙古大学图书馆

M³FuNet: An Unsupervised Multivariate Feature Fusion Network for Hyperspectral Image Classification

IEEE Transactions on Geoscience and Remote Sensing 2024年 62卷 1-15页

作者： Chen, Huayue Long, Haoyu Chen, Tao Song, Yingjie Chen, Huiling Zhou, Xiangbing Deng, Wu Key Laboratory of Optimization Theory and Applications at China West Normal University of Sichuan Province School of Computer Science China West Normal University Nanchong637002 China China West Normal University School of Geographical Science Nanchong637002 China Shandong Technology and Business University School of Computer Science and Technology Yantai264005 China Wenzhou University Computer Science Department Wenzhou325035 China Sichuan Tourism University School of Information and Engineering Chengdu610100 China Civil Aviation University of China School of Electronic Information and Automation Tianjin300300 China

Hyperspectral image (HSI) spectral-spatial joint feature (FE) extraction methods generally suffer from low feature retention and weak spatial-spectral dependence, which will lead to single-class feature confrontation (SCFC). To solve this problem, an unsupervised multivariate feature fusion network (M3FuNet) is developed in this article. In M3FuNet, multiscale supervector matrix correction (MSMC) and multiscale random convolution dispersion (MRCD) are used as the spectral and spatial feature extraction method, and the feature retention of spectral and spatial features is improved to achieve feature calibration by feature fusion and decision fusion, called 'multivariate feature fusion.' The MSMC is employed to correct the supervector matrix to reduce the intraclass variance in superpixel homogeneous regions and overcome the phenomenon of supervector block drift (SvBD). The MRCD uses random convolution and Gaussian smoothing to extract deep spatial features. Because of the similar feature representation ability of the MSMC and MRCD, the obtained spectral-spatial joint features have high feature retention and strong spectral-spatial dependence. Finally, this M3FuNet is used for realizing the classification of HSI. Three common HSI datasets are used to validate the effectiveness of the M3FuNet. The experiment results show that the M3FuNet has a superior performance compared with several state-of-the-art (SOTA) HSI classification methods. The code of the proposed M3FuNet is available at https://***/aichou233/M3FuNet. © 1980-2012 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Optimizing Stroke Diagnosis: Application of Machine Learning Algorithms for Early Detection

Optimizing Stroke Diagnosis: Application of Machine Learning...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Sharma, Chetan Anooja, A. Kishore, Jaydeep Bhardwaj, Vivek UpGrad Education Private Limited Bangalore India School of Computer Application Jecrc University Rajasthan Jaipur India School of Computer Science and Engineering Manipal University Jaipur Jaipur India

ISBN: (纸本)9798331509828

Being a top cause of mortality and serious disability, stroke demands urgent diagnosis and impactful prevention. Current innovations in machine learning (ML) show a great capacity for predicting the likelihood of a stroke. This study reports on applying ML algorithms to improve the timely and early identification of stroke, leading to more effective interventions and lowering morbidity and mortality numbers. This work employs a complete dataset that integrates demographic information, medical history, data on lifestyle, and physical measurements. engineering techniques of a high level were utilized in pre-processing the data to reduce the assumptions that lay underneath. This research applied five machine learning models for the prompt identification of stroke: Decision Tree, Support Vector Machine (SVM), Gradient Boosting, K-Nearest Neighbours (KNN), and XG Boost. The number of datasets used for training was 80%, and 20% went to testing. The accuracy of the Gradient Boosting model stood at 96%, outperforming XG Boost at 92% and Decision Tree at 91%. The model with Support Vector Machines (SVM) gave 84% accuracy, but all three models illustrated high precision and recall. These results indicate that machine learning models could significantly augment stroke prediction and enhance clinical decision processes. © 2025 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Algorithms in Mobile Edge with Real-Time Abnormal Event Detection for 5G-IoT Devices

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2023年第17期17卷 59-71页

作者： Praveenchandar, J. Kumar, S. Vinoth Paul, A. Christopher Mukunthan, M.A. Maharajan, K. Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Tamil Nadu Coimbatore India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamil Nadu Avadi India Department of Information Technology Karpagam Institute of Technology Tamil Nadu Coimbatore India Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Tamil Nadu Krishnankoil India

IoT is becoming increasingly popular due to its quick expansion and variety of applications. In addition, 5G technology helps with communication and network connectivity. This work integrates C-RAN with IoT networks to provide an experimental 5G testbed. In a 5G IoT environment, this experience is utilized to enhance both perpendicular and flat localization (3D localization). DRCaG, an acronym for the proposed model, stands for a deep, complicated network with a gated layer on top. The performance of the proposed model has been demonstrated through extensive simulations in terms of learning reduction, accuracy, and matrix disorientation, with a variable signal-to-noise ratio (SNR) spanning from 20 dB to + 20 dB, which illustrates the superiority of DRCaG compared to others. An online, end-to-end solution based on deep learning techniques is presented in this study for the fast, precise, reliable, and automatic detection of diverse petty crime types. By detecting tiny crimes like hostility, bag snatching, and vandalism, the suggested system may not only identify unusual passenger behavior like vandalism and accidents but also improve passenger security. The solution performs admirably in a variety of use cases and environmental settings. © 2023 by the authors of this article. Published under CC-BY.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Reset-Free Reinforcement Learning via Multi-State Recovery and Failure Prevention for Autonomous Robots

引用

Tsinghua science and Technology 2024年第5期29卷 1481-1494页

作者： Xu Zhou Benlian Xu Zhengqiang Jiang Jun Li Brett Nener School of Mechanical Engineering Changshu Institute of TechnologyChangshu 215500China School of Automation Nanjing University of Science and TechnologyNanjing 210094China School of Electronic and Information Engineering Suzhou University of Science and TechnologySuzhou 215009China Faculty of Medicine and Health The University of SydneySydney 2006Australia Department of Electrical Electronic and Computer EngineeringThe University of Western AustraliaPerth 6009Australia

Reinforcement learning holds promise in enabling robotic tasks as it can learn optimal policies via trial and ***,the practical deployment of reinforcement learning usually requires human intervention to provide episodic resets when a failure *** manual resets are generally unavailable in autonomous robots,we propose a reset-free reinforcement learning algorithm based on multi-state recovery and failure prevention to avoid failure-induced *** multi-state recovery provides robots with the capability of recovering from failures by self-correcting its behavior in the problematic state and,more importantly,deciding which previous state is the best to return to for efficient *** failure prevention reduces potential failures by predicting and excluding possible unsafe actions in specific *** simulations and real-world experiments are used to validate our algorithm with the results showing a significant reduction in the number of resets and failures during the learning.

关键词： reinforcement learning manual reset multi-state recovery failure prediction

来源：评论

学校读者我要写书评

暂无评论

Augmented Data Protection: Fortifying Confidentiality through CBBPH approach 15

Augmented Data Protection: Fortifying Confidentiality throug...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Tripathy, Aayushi Jeeban Tiwari, Utkarsh Anirudh, S. Ashwani, Siddhant Kavitha, C.R. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798350370249

The foundation of contemporary data security, guaranteeing integrity and confidentiality in digital communications, is referred to as cryptography. On the other side, image steganography strengthens data security by providing a stealthy way to hide information within seemingly same images. A new level of data camouflage is added by the tactile writing system Braille, whose small representation makes effective use of pixel components for storage. Columnar transposition is also applied to improve security by further obscuring the contained data. To improve data security, this paper presents the Columnar Binary Braille Pixel Hiding (CBBPH) approach, a revolutionary technology that combines Braille encoding, image steganography, encryption, and columnar transposition synergistically. The proposed method involves encoding plaintext messages into Braille, transposing them using columnar transposition, and then embedding them into the pixels in the least important portions of the image. The CBBPH strategy represents a significant breakthrough in data security techniques as experimental results show that it generates higher values in Peak Signal-to-Noise Ratio (PSNR) metric computations, indicating superior visual fidelity. ©2024 IEEE.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Auto-Scaling Anomaly Detection in Cloud Computing Models using MAPE-K Loop 15

Auto-Scaling Anomaly Detection in Cloud Computing Models usi...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Mahesh, Nikhil Supriya, M. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350370249

Computing paradigms are changing at a faster pace leading to highly complex and dynamic environments, thereby demanding resource management acumen. Pivoting in these paradigms, auto scaling ensures optimal resource allocation, sufficient to accommodate variable demands. However, the dynamic nature of such settings poses challenges in maintaining reliability and efficiency in auto-scaling methodologies. This paper proposal solves this challenge through a dependable anomaly detection system intended for auto-scaling in cloud computing frameworks. This work tries to design, develop, and validate the framework of anomaly detection for resource consumption and workload patterns using a MAPE-K loop. The envisioned framework is meant to use machine learning techniques and methodologies of data analysis to track in real time system parameters for the early identification of potential scalability issues. In terms of scores for all metrics, it has performed better with the MAPE-K loop, and the R2 score for all metrics came out to be 1. © 2024 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

How does the digitalization of the SCOR model contribute to the efficiency of supply chain operations?

引用

Logistique et Management 2024年第4期32卷 194-214页

作者： Hrouga, Mustapha Said, Dhaou Department of Finance Operations and Marketing Brest Business School Brest France School of Electrical Engineering and Computer Science University of Ottawa Canada

Résumé: Les outils digitaux tels que la blockchain, l’Internet des objets (IoT) et le big data (BD) ont été largement utilisés pour digitaliser la logistique et la gestion de la chaîne d’approvisionnement (CA). En fait, la technologie blockchain peut offrir divers avantages tels que la confiance, la traçabilité et la transparence qui permettent d’améliorer les performances de la chaîne d’approvisionnement. En plus, l’IoT est considéré comme la technologie la plus encourageante pour suivre et partager des informations en temps réel entre tous les acteurs de la CA. Enfin, le BD est considéré comme un outil très puissant et efficace pour optimiser la CA et permet à plusieurs entreprises de contrôler et de traiter une énorme quantité de données. C’est pour ces raisons que dans cet article, nous proposons d’utiliser ces technologies numériques pour développer un modèle SCOR digital pour une CA efficace, intelligente et performante. Afin de mettre en lumière les performances de cette étude, un modèle SCOR est initialement présenté pour mettre en évidence les avantages et les impacts de ces trois technologies sur les principales activités de la CA, notamment plan, source, make, deliver et return. Ensuite, les trois technologies sont combinées où le cloud est utilisé comme PaaS (platform as service) afin de les connecter. Enfin, pour valider le modèle SCOR 4.0 proposé, nous avons présenté un exemple didactique avec une CA multi-échelons et demande déterministe. Les résultats ont montré que le modèle proposé a permis d’améliorer la visibilité de la CA et d’augmenter le niveau de satisfaction des clients. © 2024 KEDGE Business school.

关键词： Supply chain 4.0 Digitalisation Modèle SCOR Blockchain internet des objets Big data Supply chain 4.0 digitalization SCOR model blockchain Internet of Things big data

来源：评论

学校读者我要写书评

暂无评论

Robust Device-Free Mmwave Sensing with Specular Reflection Interference Mitigation

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 5749-5764页

作者： Liu, Yulin Wang, Jie Gao, Qinghua Pan, Miao Fang, Yuguang Dalian Maritime University School of Information Science and Technology Dalian116026 China Dalian University of Technology Faculty of Electronic Information and Electrical Engineering Dalian China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States City University of Hong Kong Department of Computer Science Hong Kong Hong Kong

Device-Free mmWave Sensing (DFWS) could sense target state by analyzing how target activities influence the surrounding mmWave signals. It has emerged as a promising sensing technology. However, when employing DFWS indoors, specular reflection interference arises due to the specular reflectors. This interference often induces ghost targets, impacting the accurate estimation of the number and position of targets, resulting in degradation in sensing performance. To tackle this issue, we delve into the generation mechanism of specular reflection interference and analyze its multi-domain characteristics. Through exploration, we discern its temporal sparsity, spatial symmetry or collinearity, and frequency correlation characteristics, and propose four metrics to measure them, accordingly. Specifically, we propose a temporal characteristic quantitative evaluation metric based on identity matching, spatial symmetry and collinearity quantitative evaluation metrics based on geometric analysis, and a frequency correlation quantitative evaluation metric based on Doppler velocity correction, respectively. Based on these metrics, we design a novel Specular Reflection Interference Mitigation (SRIM) method and develop a robust SRIM-DFWS prototype system based on a 60 GHz mmWave radar to validate our proposed method. Experimental results demonstrate that our proposed method could achieve accurate and effective mitigation of specular reflection interference in device-free target tracking. © 2002-2012 IEEE.

关键词： Radar interference

来源：评论

学校读者我要写书评

暂无评论

TRS Scheduling for Improved QoS Performance in Cloud System

引用

computers, Materials & Continua 2023年第4期75卷 1547-1559页

作者： G.John Samuel Babu M.Baskar Department of Computer Science and Engineering School of ComputingCollege of Engineering and TechnologySRM Institute of Science and TechnologyKattankulathurChengalpattuTamilnadu603203India Department of Computing Technologies School of ComputingCollege of Engineering andTechnologySRM Institute of Science and TechnologyKattankulathurChengalpattuTamilnadu603203India

Numerous methods are analysed in detail to improve task schedulingand data security performance in the cloud environment. The methodsinvolve scheduling according to the factors like makespan, waiting time,cost, deadline, and popularity. However, the methods are inappropriate forachieving higher scheduling performance. Regarding data security, existingmethods use various encryption schemes but introduce significant serviceinterruption. This article sketches a practical Real-time Application CentricTRS (Throughput-Resource utilization–Success) Scheduling with Data Security(RATRSDS) model by considering all these issues in task scheduling anddata security. The method identifies the required resource and their claim timeby receiving the service requests. Further, for the list of resources as services,the method computes throughput support (Thrs) according to the number ofstatements executed and the complete statements of the service. Similarly, themethod computes Resource utilization support (Ruts) according to the idletime on any duty cycle and total servicing time. Also, the method computesthe value of Success support (Sus) according to the number of completions forthe number of allocations. The method estimates the TRS score (ThroughputResource utilization Success) for different resources using all these supportmeasures. According to the value of the TRS score, the services are rankedand scheduled. On the other side, based on the requirement of service requests,the method computes Requirement Support (RS). The selection of service isperformed and allocated. Similarly, choosing the route according to the RouteSupport Measure (RSM) enforced route security. Finally, data security hasgets implemented with a service-based encryption technique. The RATRSDSscheme has claimed higher performance in data security and scheduling.

关键词： Cloud task scheduling TRS quality of service RSM route security data security SDE RATRSDS

来源：评论

学校读者我要写书评

暂无评论

An Exploration of Object Detection and Vehicular Communication for Autonomous Vehicles 7th

An Exploration of Object Detection and Vehicular Communicati...

引用

7th IFIP TC 12 International Conference on Computational Intelligence in Data science, ICCIDS 2024

作者： Padmavathi, A. Pullela, Dheeraj Reddy Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India

ISBN: (纸本)9783031699818

Autonomous vehicles represent a transformative technology with the best implications for transportation systems. The key component of their success is their capability to detect and respond to their surroundings. For the benefits to be realized, the fusion of advanced computer vision techniques, such as object detection and vehicular communication, is essential. This paper explains the techniques in object detection and vehicular communication in autonomous vehicle applications for future advancements based on related works. The research highlights the need for creative solutions in integrating communication and computer vision tasks and presents idea of work flow for combining object detection with vehicular communication. The main motive of this research is to present about idea of integrating object detection model and vehicular communication. Additionally, we explore vehicular communication systems and their integral role in ensuring safe and efficient autonomous driving. The idea of object detection and vehicular communication is not only for autonomous vehicles but also for ADAS (Advanced Driver Assistance System)-equipped vehicles. © IFIP International Federation for Information Processing 2024.

关键词： Advanced driver assistance systems

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：