检索结果-内蒙古大学图书馆

Novel Anchor Generation Based Residual Network for Object Tracking in Video-Surveillance Applications

SN Computer Science 2025年第2期6卷 1-12页

作者： Mohanapriya, D. Rajalakshmi, K. Helen Josephine, V.L. Panneerselvam, Karthick Department of Computer Science (SF) Sourasthra College Tamil Nadu Madurai India Department of Computer Applications CMR Institute of Technology Karnataka Bangalore India Business Analytics School of Business and Management Christ University Karnataka Bangalore India Department of Computer Science and Engineering KPR Institute of Engineering and Technology Tamilnadu Uthupalayam 641407 India

The activity of the object in question is alerted directly upon completion of an effective object tracking. Dependent on hardware support or not, a strong object tracking protocol is required for a precise object tracking application. According to these methods, tracking an object accurately within a predetermined processing time window required a significant amount of computer complexity. In contrast, a variety of quality-degrading elements, including occlusion, shifting lighting, shadows, and so on, have an adverse effect on tracking. All of these tracking shortcomings will be fixed by a revolutionary residual network based on loss operator and anchor creation. Detection of object has concerns that rely on the process of feature extraction to afford efficient quality. For this purpose a model called ResNet has been used that comprises thirty layers and hence named as Resnet-thirty. These networks are a type of Convolutional Neural Network (CNN) that contain residual connections among various layers. The various merits of these connections is the network has the capability to learn the features of global, local and intermediate in parallel. As such, the system is robust against changes in lighting. These variations in light were understood in terms of tracking objects within a changing background. The proposed work uses MOT datasets. This dataset comprises of MOT 15, MOT16, MOT17 and MOT20. The results have been found by using these datasets. Hence, it evidently outperforms in terms of precision, recall, MOTA, IDF, MOTP, SAIDF and F1 measure to track the objects. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Computer vision Loss operator Object tracking Residual network

来源：评论

学校读者我要写书评

暂无评论

HPPS - Harmonized privacy-preserving scheme for the internet of things and edge-collaborated smart city services

引用

International Journal of Information Security 2025年第3期24卷 1-16页

作者： Rajendran, Jaikumar Bojaraj, Leena Murugan, Kathirvelu Bojan, Gurumoorthy Kambatty Department of Electronics and Communication Engineering KPR Institute of Engineering and Technology Tamilnadu Coimbatore 641407 India Department of Electronics and Communication Engineering KGiSL Institute of Technology Tamilnadu Coimbatore 641035 India

Internet of Things (IoT) assisted smart city (SC) applications have evolved in the real-time smart environment for providing sophisticated driving assistance. The presence of external attacks causes session leakage along with the interconnecting device compromises. In such scenarios, the edge-delivering services are also impacted by privacy lag under different sessions where the integration with IoT is halted. Such integration halt is common in diverse application resource demand and infrastructure support. The integration constraints include privacy leaks, complex authentication processing, and time-based synchronizations. In particular, the synchronization of the above in the common interval is decided by the lagging constraints that proves to be weak in any privacy authentication. Therefore, a consistent session without loss is less feasible for collaborated smart city services. This paper proposes a Harmonized Privacy-Preserving Scheme (HPPS) for improving the uninterrupted services in orchestrated IoT-Edge architectures in SC. The proposed scheme identifies the outages and instigates a new application session for attacker-less services. By using protected session information in discovering services and edge devices, the sessions are secured. The application services and sessions are secured using conventional two-factor authentication monitored and administered by the IoT and Edge devices. The privacy changes are periodically updated using tree-based learning for the failing orchestration. In this learning process, the recommended and identified services are verified for their privacy exploitation metric. The smart city service distribution is pursued if the privacy exploitation levels are unanimous. For verifying the proposed scheme’s performance, the metrics of service distribution, session loss, service latency, and privacy exploitation level are used. The proposed HPP scheme improves service distribution and authentication verification by 12.29% and 12.11%

关键词： Edge computing IoT Privacy-preserving Smart city services Tree-learning

来源：评论

学校读者我要写书评

暂无评论

Eco-friendly fabrication of ZnO nanocomposites using Lepidium didymium and polymer-assisted CTAB/PEG: A multifunctional approach for enhanced biomedical applications

引用

Journal of Molecular Liquids 2025年 417卷

作者： Nisha Jenifar, A. Anilkumar, P. Preetha, S. Department of Chemistry KPR Institute of Engineering and Technology Tamil Nadu Coimbatore641 407 India

This work illustrates the environmentally benign fabrication of zinc oxide (ZnO) nanoparticles using Lepidium didymium to enhance their effectiveness in various biological applications. The use of extracts from the plant as reactive constituents in nanoparticle fabrication presents a cost-effective, scalable, and eco-friendly methodology, wherein plant-based substances serve as stabilizing and reducing agents. Apart from this polymer which acts as the surfactant is capped with the green synthesized ZnO. In this study, green ZnO was synthesized by utilizing CTAB and PEG, as a polymeric surfactant which led to a notable reduction in nanoparticle size and increased stability. Stearic hindrance, which keeps NPs stable, is caused by a mechanism in which polymeric chains build a strong covalent bond with their neighboring chains. X-ray diffraction (XRD), Ultraviolet–visible spectroscopy, Fourier transform infrared spectroscopy (FTIR), and Scanning Electron Microscopy (FESEM) were utilized and this helps to analyze the synthesized ZnO and its nanocomposites produced through environmentally friendly methods. The assessed ZnO nanoparticles demonstrated versatility in biomedical applications, as indicated by their evaluation for antibacterial, anti-inflammatory, anticancer, and characteristics that promote wound healing. The cytotoxic efficacy of green-synthesized ZnO nanocomposites on the HepG2 cell line was assessed utilizing the MTT assay method. The analysis produced the subsequent IC50 value: The concentrations of 69.91 μg/mL for green synthesized ZnO and 83.05 μg/mL for CTAB-assisted ZnO nanocomposite indicate detrimental effects on the evolution of the HepG2 cell line. The efficacy of the green-synthesized zinc oxide nanoparticles and ZnO nanocomposite for wound healing were assessed on L929 cells, with cipladine as a reference standard. This study highlights the effectiveness and sustainability of green fabrication methods in producing functional nanomaterials for var

关键词： Fourier transform infrared spectroscopy

来源：评论

学校读者我要写书评

暂无评论

EchoNet Dynamic: Deep Learning-driven Advancements in Dynamic Heart Function Analysis through Echocardiography 3

EchoNet Dynamic: Deep Learning-driven Advancements in Dynami...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Vidhya, K. Nagarajan, B. Jenefa, A. Catherine Joy, R. Cherian, Minu Franz Kingstein, N. School of CST Karunya Institute of Tech. and Sci Coimbatore India Artificial Intelligence and Data Science KPR Institute of Engineering and Technology Coimbatore India Division of ECE Karunya Institute of Tech. and Sci Coimbatore India Computer science and engineering department Amal Jyothi college of engineering kanjirapally Kottayam India

ISBN: (纸本)9798331527549

Advances in echocardiography have significantly improved the diagnostic processes for heart function analysis. However, traditional imaging techniques often struggle with the dynamic complexities of cardiac activities. Existing methods fail to capture detailed variations in cardiac function over time, leading to suboptimal clinical decision-making and patient outcomes. Traditional echocardiography relies heavily on manual interpretation, which can be subjective and varies significantly between observers. This research presents EchoNet Dynamic, a novel method for improving echocardiographic data analysis and interpretation based on deep learning and the Transformer model. The EchoNet Dynamic dataset used in this study comprises 15,000 B-mode echocardiographic images from 750 patients, divided into training, validation, and testing sets for comprehensive model evaluation. The Transformer model demonstrated remarkable effectiveness, achieving an accuracy of 98.5%, an AUC of 0.992, and an F1 score of 0.972, surpassing traditional diagnostic tools by a significant margin. The EchoNet Dynamic model demonstrates a promising enhancement in detecting and diagnosing cardiac functions, offering substantial improvements over conventional echocardiographic methods and setting a new benchmark in cardiac healthcare. © 2025 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Enhanced MADM Strategy with Heptapartitioned Neutrosophic Distance Metrics

引用

Neutrosophic Sets and Systems 2025年 78卷 74-96页

作者： Eassa, Mohamed Myvizhi, M. Elkholy, Mohamed Abdelhafeez, Ahmed Elbehiery, Hussam Computer Science Department Faculty of Information System and Computer Science October 6 University Giza12585 Egypt Applied Science Research Center Applied Science Private University Amman Jordan Department of Mathematics KPR Institute of Engineering and Technology Tamilnadu Coimbatore India Faculty of Computer Science& Engineering Alamein International University Egypt

In this work, a novel methodological approach to multi-attribute decision-making problems is developed and the notion of Heptapartitioned Neutrosophic Set Distance Measures (HNSDM) is introduced. By averaging the Penta-Partitioned Neutrosophic Distance Measures under particular conditional criteria, the suggested technique ranks the options. Additionally, we explore the fundamental characteristics of HNSDM and provide several illustrative theorems. The Heptapartitioned Neutrosophic Set Distance Measures are formulated based on the Hepta Neutrosophic Set. Lastly, a practical numerical example is provided to illustrate the efficacy of the suggested methodology. © 2025, University of New Mexico. All rights reserved.

关键词： Heptapartitioned Neutrosophic set Heptapartitioned Neutrosophic set and MADM strategy Heptapartitioned set Neutrosophic sine distance measure

来源：评论

学校读者我要写书评

暂无评论

Person Detection using Proposed YOLOv8 algorithm 14

Person Detection using Proposed YOLOv8 algorithm

引用

14th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2025

作者： JustinJayaraj, K. Padmacharan, V. Vadivel, Balasubramaniam Gokulraj, G. Ramachandramoorthy, K.B. Kirthika, K.M. Department of Computer Science and Engineering Sri Ramakrishna Institute of Technology Coimbatore India Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India

ISBN: (纸本)9798331531935

Surveillance systems are vital for detecting and preventing crime, especially in urban environments where real-time monitoring is crucial. This research proposes an advanced surveillance system that combines proposed YOLOv8 object detection with DeepSORT tracking for tracking a person in crowded place, enhanced with a DenseNet backbone, achieves 97.1% detection accuracy and an mAP of 0.971 at an IoU of 0.5, outperforming YOLOv3 and YOLOv5. The model makes use of Spatial Pyramid Pooling (SPP) and Feature Pyramid Networks (FPN) for multi-scale detection and an anchor-free approach for improved accuracy. Integrated with DeepSORT, the system tracks individuals reliably across frames, even in dynamic environments. Experimental results demonstrate that this approach significantly improves detection and tracking efficiency, making it ideal for automated surveillance and crime prevention in urban areas. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Design and Simulation of Efficient Supercapacitor Model Using Matlab/Simulink

引用

High Energy Chemistry 2025年第2期59卷 101-106页

作者： Arumugam, Chandrasekaran Kandasamy, Senthil Kumar Subramaniam, Tamilselvan Kumaravel Saravanan, Sughindhar Vijayan, Sivashirpi Departement of ECE Kongu Engineering College Tamil Nadu Perundurai Erode India Department of Biomedical Engineering KPR Institute of Engineering and Technology Coimbatore Arasur India

Abstract: Energy storage and its way of storing and retrieving it is really important. Since wireless communication and devices are highly used today, storing and retrieving energy frequently has become a common practice. So, an efficient and quick energy storage management system has to be developed. For which a paper is proposed on designing an efficient Supercapacitor that is highly efficient and has the ability to discharge slowly. A hybrid solution is proposed to achieve high energy and power density. In addition, hybrid energy storage systems may be applied in a variety of systems, resulting in a variety of applications with better results. Here, supercapacitor gets combined with battery in hybrid manner which is used for increasing the life cycle of the system and other advantages that may not be achieved by using a single system. Because the supercapacitor lessens the stress on the battery, this construction typically has a longer life. The supercapacitor model is simulated in this study by using MATLAB/Simulink, and the efficiency of the model is improved by verifying and evaluating the parameters. Also, its parameters are tuned in such a way that a satisfiable efficient output is obtained. The two-branch model is being used to simulate and study the supercapacitor’s equivalent circuit. The supercapacitor model with improved performance that has been simulated in Simulink works which can be used alongside with the battery as a backup to satisfy the power needs of the load instantly and efficiently. © Pleiades Publishing, Ltd. 2025.

关键词： Capacitor storage

来源：评论

学校读者我要写书评

暂无评论

Implementation of YOLOv9-Based Real-Time Object Detection for Robotic Finger Applications 5

Implementation of YOLOv9-Based Real-Time Object Detection fo...

引用

5th IEEE International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2025

作者： Duraisamy, Premkumar Deepika, A. Dhanushiya, S. Karthik, S. Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Hindusthan College of Engineering & Technology Department of Information Technology Coimbatore India

ISBN: (纸本)9798350356236

The project investigates the integration of YOLO v9, the latest iteration of the 'You Only Look Once' model, into robotic fingers to enhance their precision, responsiveness, and versatility in object handling. YOLO v9's superior object detection capabilities - especially its real-time processing speed and high accuracy - make it an ideal candidate for advancing robotic manipulation. By training YOLO v9 on an extensive dataset encompassing diverse object shapes, sizes, and textures, this project enables robotic fingers to recognize and respond to various physical characteristics with greater nuance. Through this approach, robotic systems gain an adaptive edge, adjusting their grip and interaction based on specific object features, thus expanding their utility in precision-demanding fields such as manufacturing, healthcare, and logistics. The research not only explores technical integration but also assesses the impact of this enhanced object recognition on robotics' overall reliability and efficiency in handling real-world tasks. The findings could contribute to the development of more intelligent, responsive, and adaptable robotic systems, redefining automation standards in critical industries. © 2025 IEEE.

关键词： Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Person Detection using Proposed YOLOv8 algorithm

Person Detection using Proposed YOLOv8 algorithm

引用

International Conference on Communication Systems and Network Technologies (CSNT)

作者： Justin Jayaraj K Padmacharan V Balasubramaniam Vadivel Gokulraj G Ramachandramoorthy K B Kirthika K Department of Computer Science and Engineering Sri Ramakrishna Institute of Technology Coimbatore India Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India

ISBN: (数字)9798331531935

ISBN: (纸本)9798331531942

关键词： YOLO Accuracy Surveillance Prevention and mitigation Urban areas Transfer learning Feature extraction Real-time systems Public security Reliability

来源：评论

学校读者我要写书评

暂无评论

Implementation of YOLOv9-Based Real-Time Object Detection for Robotic Finger Applications

Implementation of YOLOv9-Based Real-Time Object Detection fo...

引用

Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), International Conference on

作者： Premkumar Duraisamy Deepika A Dhanushiya S Karthik S Department of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India Department of Information Technology Hindusthan College of Engineering & Technology Coimbatore India

ISBN: (数字)9798350356236

ISBN: (纸本)9798350356243

The project investigates the integration of YOLO v9, the latest iteration of the “You Only Look Once” model, into robotic fingers to enhance their precision, responsiveness, and versatility in object handling. YOLO v9's superior object detection capabilities—especially its real-time processing speed and high accuracy—make it an ideal candidate for advancing robotic manipulation. By training YOLO v9 on an extensive dataset encompassing diverse object shapes, sizes, and textures, this project enables robotic fingers to recognize and respond to various physical characteristics with greater nuance. Through this approach, robotic systems gain an adaptive edge, adjusting their grip and interaction based on specific object features, thus expanding their utility in precision-demanding fields such as manufacturing, healthcare, and logistics. The research not only explores technical integration but also assesses the impact of this enhanced object recognition on robotics' overall reliability and efficiency in handling real-world tasks. The findings could contribute to the development of more intelligent, responsive, and adaptable robotic systems, redefining automation standards in critical industries.

关键词： YOLO Training Service robots Medical services Machine learning Robot sensing systems Real-time systems Manufacturing Reliability Object recognition

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：