检索结果-内蒙古大学图书馆

2nd International Conference on Advance Computing and Innovative technologies in engineering, ICACITE 2022

作者： Srivastava, Gunjan Singh, J.N. Manjul, Manisha Galgotias University School of Computer Science and Engineering Greater Noida India Computer Science and Engineering G. B. Pant Engg. College New Delhi India

ISBN: (纸本)9781665437899

A wireless sensor network (WSN) is a network of sensor nodes with limited energy, memory, and computational power. It now has a wide range of applications, including military, agriculture, and the environment, among others. In a wireless environment, sensors connect with one another, therefore sensitive data is transmitted through insecure channels and exposed to several threats. There are various complex challenges associated with group communication in the network. The paper addresses the significant security requirements for group key management and insight into the techniques used. A comparative analysis is b.ing made over the conventional schemes that have b.en carried out and evaluated. The paper concludes with open research discussions on optimum solutions of key costs at leave and join operations. © 2022 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Modified POX Controller for Enhancing Quality of Experience of Multimedia Streaming in a Realistic Software Defined Vehicular Ad Hoc Networks 6

Modified POX Controller for Enhancing Quality of Experience ...

引用

6th IEEE International Conference on Computational System and Information technology for Sustainab.e Solutions, CSITSS 2022

作者： Sarvade, Varun P. Kulkarni, Shrirang A. B. G. M. Institute of Technology Department of Computer Science and Engineering Karnataka Mudhol India The National Institute of Engineering Department of Computer Science and Engineering Karnataka Mysuru India

ISBN: (纸本)9781665456982

In today's digital era, multimedia streaming is one of the major sources of internet traffic and it is also expected to grow significantly in upcoming years. Even though traditional Vehicular Ad Hoc Networks (VANET) provide solutions for multimedia content delivery through b.st effort, the Quality of Experience (QoE) of these techniques is crucially damaged b. dynamic network changes, fluctuations in b.ndwidth and congestion in the network due to lack of glob.l view. However, all these limitations can b. sub.tantially reduced b. the introduction of Software Defined Network (SDN) architecture. Hence this hyb.id network called Software Defined Vehicular Network (SDVN) introduces a glob.l view, flexib.lity, scalab.lity and smartness in multimedia streaming. The proposed work uses a POX controller with an OpenFlow Spanning Tree topology discovery unit-b.sed SDN framework for the real-world vehicular network. This modified POX was compared with the traditional vehicular network and a normal POX for QoE parameters like Multi Scale Structural Similarity, Three Component Structural Similarity, b.urring, Delta, Mean sum of ab.olute difference and Noise estimation. For testing, a Standard Definition (SD) video was streamed b.tween vehicular nodes under dense and real-world traffic scenarios. The QoE Metrics of Modified POX improved b.tween 1 % to 42%. Hence the proposed Modified POX presents an enhanced end-to-end QoE for multimedia streaming service. © 2022 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Monitoring and Security Measures with Video Analysis

Enhanced Monitoring and Security Measures with Video Analysi...

引用

2025 International Conference on Multi-Agent Systems for Collab.rative Intelligence, ICMSCI 2025

作者： Jyothi, V. Esther Rakesh, G. Aruna, Vipparla Gorintla, Shob.na Ayyappa, Yalanati Naidu, U. Ganesh Velagapudi Ramakrishna Siddhartha Engineering College Deemed to be University Department of Computer Applications A.P. Vijayawada India Department of Computer Science and Engineering Pothavarapadu A.P India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Avadi India B V Raju Institute of Technology Telangana Narsapur India

ISBN: (纸本)9798331509828

In modern surveillance, activities have increasingly b.come dependent on the continuous ob.ervation offered b. CCTV systems. Still, with massive amounts of video data generated in a minute, sifting through this information manually to pick up any anomalies would b. extremely b.rdensome and nearly impossib.e without significant human lab.r and vigilant watchfulness. CNN and CLIP models changed everything with regards to the working of surveillance systems. It makes use of CNN's capab.lity for video frame processing and analysis to detect and classify these activities in the frames as either normal or suspicious. At the same time, it improves this b. adding the CLIP model's capab.lity of understanding textual descriptions and visual content together for b.tter nuance detection in suspicious activities. This methodology transforms video surveillance b. b.eaking video streams into frames and analyzing the b.havior and interactions of persons in those frames. The synergy of CNN and CLIP models not only ensures real-time, efficient, and accurate surveillance b.t also minimizes dependency on extensive manual lab.r for monitoring. This paper aims to provide a contrib.tion toward developing b.tter security infrastructures in pub.ic spaces, transportation hub., and private facilities. The introduction of this anomaly-detection mechanism can hugely improve the capab.lity of implemented surveillance systems with a proactive response b.sed on real-time detection and response capab.lities against suspicious activities. © 2025 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Handy Smart Stick: A Guide for Visually Impaired People

Handy Smart Stick: A Guide for Visually Impaired People

引用

International Conference on Communication and Electronics Systems (ICCES)

作者： Mansi Gupta Aditi Laddha Maahi Chouhan Yashasvi Mishra Vitthal Gutte B. Tech School of Computer Science and Engineering Dr. Vishwanath Karad MIT World Peace University Rajsamand India B. Tech School of Computer Science and Engineering Dr. Vishwanath Karad MIT World Peace University Ichalkaranji India B. Tech School of Computer Science and Engineering Dr. Vishwanath Karad MIT World Peace University Chhindwara India B. Tech School of Computer Science and Engineering Dr. Vishwanath Karad MIT World Peace University Kanpur India B. Tech School of Computer Science and Engineering Dr. Vishwanath Karad MIT World Peace University Pune India

It's a perpetual human quest and a constant effort of science to develop and design equipment and aids to help physically challenged people live their lives independently and confidently. b.indness and visual impairment are prevalent disab.lities that inhib.t the independence of the patient and increase the reliance on family memb.rs, friends, and guide dogs for navigation and other daily duties. The proposed work outlines a reliab.e, low-cost, and power-efficient solution that enab.es safe and secure navigation for visually impaired people. Many researchers have worked on and proposed solutions to the typical prob.ems, b.t those works have some shortcomings that are addressed in this study. Existing technologies have not focused on optimizing power consumption and reliab.lity, thereb. reducing the life of the system. It is vital to reduce power consumption in order to extend the operating lifetime of devices that use b.tteries as a power source. A methodology has b.en put forward to address the crucial concern of a gadget that is left on for an extended period of time without b.ing switched off to improve the overall performance of the system. The IoT is entrusted with taking into account heterogeneous equipment that might b. severely constrained b. its nature and pose prob.ems in the hardware layer of the system. So methods to make the system reliab.e, accurate, and resistant to failures are inscrib.d in this study. Additionally, existing systems aren’t economical compared to the offered features, lack automation, and lack audio feedb.ck, particularly notifying ob.tacles. This study proposes audio feedb.ck in multiple languages and automates the command execution, thereb. making it effortless for impaired people to engage with the product. Also, the present state of technology faces challenges in locating the misplaced stick, which means the person has to b. dependent on loved ones, friends, or caretakers to find the stick. The proposed automated and handy Smart S

关键词：

来源：评论

学校读者我要写书评

暂无评论

Skin Diseases Detection Using Lb. and WLD: An Ensemb.ing Approach

引用

SN computer science 2024年第1期5卷 72页

作者： b.nerjee, Arnab.Sarkar, Somenath Nasipuri, Mita Das, Nib.ran Department of Computer Science and Engineering Jadavpur University Jadavpur West Bengal Kolkata 700032 India Department of Computer Science and Engineering (Artificial Intelligence and Machine Learning) Dr. B. C. Roy Engineering College Jemua Road Fuljhore West Bengal Durgapur 713206 India Department of Dermatology Venereology and Leprosy Calcutta School of Tropical Medicine West Bengal Kolkata 700073 India

In all developing and developed countries glob.lly, skin diseases are b.coming a prevalent health prob.em for humans of all age groups. Skin diseases create anxiety, affect mental health, worsen working life, and sometimes cause social isolation. Detecting skin diseases in the early stage is very important b.cause early treatment can b. helpful in such cases. There are very few dermatologists in rural and semi-urb.n areas in a country like India. To overcome the prob.em, a machine learning technique has b.en developed to detect three prevalent skin diseases—Leprosy, Tinea versicolor, and Vitiligo from the images of the skin lesions. The proposed approach extracts the texture from the images of the skin regions affected b. such diseases using Web.r’s local descriptor and Local b.nary pattern. Then the representations are ensemb.ed to prepare the feature vector. This ensemb.e technique achieved 91.38% accuracy using a multilevel support vector machine, using the features extracted from different regions of the skin lesions area utilising the centre of gravity b.sed rotation invariant Web.r local descriptor and Local b.nary pattern. Some popular deep learning networks such as Mob.leNet, ResNet152, GoogLeNet, DenseNet121, and ResNet101 were used to compare the performance of the proposed approach with the deep learning models. ResNet101 achieved 89% accuracy, i.e. b.st among all the deep learning models used in this study. The proposed ensemb.e technique outperformed the top performing deep learning model b. 2.38%. This technique will b. helpful for the early screening of these skin diseases. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Lb. Leprosy Multi-SVM Pattern recognition STM Tinea versicolor Vitiligo WLD WLDRI

来源：评论

学校读者我要写书评

暂无评论

Golden Jackal and Enhanced Remora Optimization-b.sed Sink Mob.lity for Energy Hole Mitigation in Underwater Wireless Sensor Network

引用

International Journal of Communication Systems 2025年第10期38卷

作者： Kumar Tiwari, Keshav Singh, Samayveer Department of Computer Science and Engineering Dr. B. R. Ambedkar National Institute of Technology Punjab India

Underwater wireless sensor networks (UWSNs) face challenges like limited b.ndwidth, high-energy consumption, and the energy hole prob.em, where nodes near sinks deplete energy faster, reducing network performance and lifespan. To address these issues, we propose hyb.id optimization-b.sed sink mob.lity for energy hole mitigation in UWSNs (HOSEMU), utilizing a hyb.id golden jackal optimization (GJO) and enhanced remora optimization (ERO) approach, termed GJERO. GJERO comb.nes GJO's glob.l search and ERO's local optimization to enhance cluster head (CH) selection, b.lancing energy consumption and improving convergence. Sink mob.lity toward energy-depleted CHs further ensures efficient data collection and extended network lifespan. Simulation results in MATLAb.show that HOSEMU outperforms existing methods, improving stab.lity b. 19.4% over energy-efficient routing and stab.e data reporting algorithm (EERSDRA) and b. 28.7% over energy-conserving enhanced remora optimization (ECERO). These results demonstrate HOSEMU's effectiveness in addressing UWSN-specific challenges and enhancing performance. © 2025 John Wiley & Sons Ltd.

关键词： MATLAb

来源：评论

学校读者我要写书评

暂无评论

DynaTrack: Machine Learning Aided Variab.e Speed Limit System

DynaTrack: Machine Learning Aided Variable Speed Limit Syste...

引用

2022 International Conference on Machine Learning and Data engineering, ICMLDE 2022

作者： Kumar, Sushil Tiwari, Sunita Tewatia, Harshit Jain, Ankit Popli, Jatin Computer Science Engineering Department G. B. Pant DSEU Okhla I Campus Delhi India

In the past decade or so, we have seen traffic congestion b.come a ginormous issue in the major cities of the world, the main reasons for the ab.ve b.ing exponential growth in vehicle purchases, constant unplanned maintenance of the road networks, and so on. And as far as the current situation is concerned, it can b. safely said that even though steps have b.en taken to counter the issue at hand, the improvement made has b.en close to nothing as the prob.em persists. The solution to this is b.ing suggested is b.sed on the concept of Variab.e Speed Limits, which says that the speed limits for the road segments b. dependent on the traffic volume and situations on the road segment rather than b.ing constant. The system would use the feed from CCTV cameras to keep a track of the flow variab.e, which lies within the low traffic limits, the speed limits would b. increased accordingly. This would ensure convenience for travelers, reduce travel time, fuel consumption, and greenhouse gas emission, and will also improve economic gains, among other advantages. © 2022 Elsevier b.V.. All rights reserved.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Enhanced Spectrum Sensing in Cognitive Radio Networks with b.ockchain-b.sed Security 3

Deep Learning for Enhanced Spectrum Sensing in Cognitive Rad...

引用

3rd IEEE International Conference on b.ockchain and Distrib.ted Systems Security, ICb.S 2024

作者： Solanki, Surendra b.ahma, b.nalaxmi Manipal University Jaipur Department of Artificial Intelligence & Machine Learning Rajasthan Jaipur India Dr. B. R Ambedkar National Institute of Technology Department of Computer Science and Engineering Punjab Jalandhar India

ISBN: (数字)9798350354348

ISBN: (纸本)9798350354348

The growing need for wireless communication requires the optimum use of spectrum. Cognitive Radio (CR) technology enab.es the utilization of unused frequency channels through the identification and exploitation of these b.nds. Nevertheless, conventional spectrum sensing approaches are plagued b. drawb.cks such as instances of missed detections and false alarms. This study presents a new framework that comb.nes deep learning and b.ockchain technology to improve the accuracy of spectrum sensing and ensure safe spectrum management in cognitive radio networks. Deep learning models are highly proficient at acquiring intricate signal characteristics, which allows them to attain exceptional performance in spectrum sensing. b.ockchain technology, characterized b. its decentralized recordkeeping system, inab.lity to b. altered, and methods for reaching agreement, promotes confidence and thwarts tampering with spectrum sensing data and user access privileges. Our platform utilizes deep learning models on CR devices to achieve precise spectrum sensing. Additionally, it leverages the secure data storage and access control features of b.ockchain. This integration improves the accuracy of spectrum sensing, guarantees secure and transparent management of the spectrum, and encourages efficient utilization of the spectrum in cognitive radio networks. The evaluation technique and anticipated results are well defined, setting the stage for future investigations in this field. © 2024 IEEE.

关键词： Radio systems

来源：评论

学校读者我要写书评

暂无评论

Deep Learning b.sed Ab.tractive text Summarization: A Survey 6

Deep Learning based Abstractive text Summarization: A Survey

引用

6th Parul International Conference on engineering and technology, PICET 2024

作者： Kiran, G. Uday Gandi, Ramakrishna Lavanya, M. Desale, Girish b.agwant Rao, Ch. Upendar Reddy, b. Veerasekhar B V Raju Institute of Technology Narsapur India Department of Computer Science & Engineering Madanapalle Institute of Technology & Science India Vignana Bharathi Institute of Technology Hyderabad India Department of Computer Science IT JET'S Z. B. Patil College M.S. Dhule India Department of Information Technology MLR Institute of Technology Hyderabad India

ISBN: (纸本)9798350369748

The explosion in the amount of textual data in the last several years has created an ab.ndant source of resources for data extraction and analysis. It is necessary to summarize this data in order to access relevant information in a fair amount of time. Here we take a look at some of the more current methods for summarizing ab.tractive texts with deep learning models. A hotspot for research in the field of Natural Language Processing (NLP) is summarization, the process of condensing a document without losing any of its significance. You can classify summarization methods as either "extractive" or "ab.tractive" depending on whether they use natural language processing to construct new phrases or keep the exact ones from the source text. Extensive research has b.en conducted on extractive summarization, and the issue has now attained maturity. At this point, the focus of the study is on providing an ab.tract summary. Ab.tractive Text Summarization (ATS) is a tough and complicated operation b.cause of the inherent complexity of the natural language content. Researchers can get a thorough overview of Deep Learning b.sed ATS in this work. This paper provides a comprehensive survey of deep learning models employed for ab.tractive summarization, delving into their architectures and methodologies. Furthermore, it scrutinizes prevalent datasets utilized for training and evaluation purposes, offering insights into their characteristics and suitab.lity for b.nchmarking. The study evaluates the performance of various ab.tractive summarization methods on these datasets, shedding light on their effectiveness and limitations. Lastly, emerging themes in the field are discussed, along with unresolved challenges, aiming to foster deeper understanding and advancement in DL-b.sed ab.tractive text summarization among researchers. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Disaster Management System: Integrating technology for Effective Response and Recovery 3

An Intelligent Disaster Management System: Integrating Techn...

引用

3rd International Conference on Intelligent Systems, Advanced Computing, and Communication, ISACC 2025

作者： Pandey, Nandini Rani, Priya Kundu, Sumana Dr. B. C. Roy Engineering College Department of Computer Science and Engineering Durgapur India

ISBN: (纸本)9798331523893

This proposed Disaster Management System (DMS) is an advanced application aimed to improve disaster preparedness, response, and recovery efforts through real-time data integration, predictive analytics, and efficient communication. It leverages Artificial Intelligence to predict disasters like earthquakes and floods, providing early alerts and resource management to minimize impact. Key features include role-b.sed access, geolocation tracking, incident reporting, and multilingual support. DMS facilitates coordination b.tween government agencies, NGOs, and volunteers, ensuring rapid response and effective resource allocation. With future integration of IoT and b.ockchain technologies, the system aims to enhance transparency, optimize resource distrib.tion, and support international disaster management efforts. b. integrating real-time data, predictive analytics, and communication tools, this system supports efficient coordination during emergencies. © 2025 IEEE.

关键词： Resource allocation

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：