检索结果-内蒙古大学图书馆

International Conference on Intelligent System. and Sustainable Com.uting, ICISSC 2022

作者： Sowm.ashree, P. Sangeetha, J. Department of Computer Science and Engineering M. S. Ramaiah Institute of Technology Bangalore India

ISBN: (纸本)9789819947164

IoT applications span a good range of applications including agriculture, industry and transport. Although transport system.has changed people's lives and m.de daily activities easier, it has also been connected to negative outcom.s like road accidents. The m.jority of road accidents occur as a result of a driver's drowsiness. Drowsiness is a severe risk to road safety, which results in serious injuries and financial losses. Drowsiness detection in drivers is one am.ng the im.ortant applications of IoT that helps in saving drivers and passengers from.road accidents by warning the drivers at the right tim.. Various researchers have developed techniques to distinguish between drowsy and non-drowsy. In this paper, we analyze the different m.thods to detect drowsiness am.ng drivers. The three different m.thods are (i) Behavioral m.thods, (ii) Biological m.thods and (iii) Vehicular features-based m.thods. Behavioral m.thods use driver’s facial characteristics for detecting drowsiness. Biological m.thods use driver’s physical characteristics, whereas vehicular feature-based m.thods use vehicular features to detect drowsiness in driver. In this research review, we have explained and com.ared each of these m.thods in detail and also discussed their advantages and disadvantages. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

User’s Nostrum.Spot for Consulting and Prescribing Through Online 6th

User’s Nostrum Spot for Consulting and Prescribing Through ...

引用

6th International Conference on Inform.tion and Com.unication technology for Intelligent System., ICTIS 2021

作者： Padm.ni Devi, B. Rajaram. J. Jerish, B. Gowsick, S.B. Shriram. E. Department of Computer Science and Engineering M. Kumarasamy College of Engineering Tamil Nadu Thalavapalayam Karur639113 India

ISBN: (纸本)9789811935701

On the off chance that anybody is debilitated and needs to visit an expert for an assessm.nt for their health, the singular prerequisites to visit the center and postponem.nt until the expert is open. The client needs to be patience up to the response from.the respective person. Assum.ng that the respective doctor or m.dic for som. calam.ty reason, the patient can’t know about the cancelation. Is growing quickly, along these lines, one can utilize the versatile applications to conquer such issues and bother for the patients. This autom.tion application is avail for exploring specialists which is synchronically obtainable in our application, which that they be on the lookout for significant m.dicam.nts on tim. and on an organized plan through E-consultation, physical consultation to hom. or prescribing through online. The proposed work is a Health Care System.that avail oneself of a sm.rt phase that fix the appointm.nt of arranging from.consultant free tim.ng, effortless and dependable for our clients. Our system.will provide em.il notification for doctors and for client side, they will receive the confirm.tion em.il and the client will upload their report to get consulting through the already taken report for em.rgency. In our system. there is an option that will provide the suggestion form.to notify the adm.n as what they need. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： m.dicam.nts

来源：评论

学校读者我要写书评

暂无评论

Sim.larity Based Answer Evaluation in Academ.c Questions Using Natural Language Processing techniques 1

引用

7th International Conference on Inform.tion and Com.unication technology for Intelligent System., ICTIS 2023

作者： Santhiya, S. Elavarasan, S. Gandhikum.r, S. Gowsik, m.P. Department of Computer Science and Engineering M. Kumarasamy College of Engineering Thalavapalayam Tamilnadu Karur639 113 India

ISBN: (数字)9789819939824

ISBN: (纸本)9789819940394

Every organization, both educational and non-educational, adm.nisters conducting tests to check the. Along with objective questions, the question papers used to assess a student’s perform.nce include descriptive questions. In contrast to com.etitive exam., which include objective or m.ltiple-choice questions, school exam. typically include descriptive or subjective questions. m.chines can quickly and readily assess the objective responses, which is highly helpful for saving tim. and m.ney. However, because there is no autom.tic m.chanism.or computer to analyze student responses, schools and institutions have difficulties when analyzing descriptive questions. Due to the tim. and effort required by m.nual review, it is the end result since the evaluator's feelings have an effect on the evaluation's quality, which in turn has an effect on the student's perform.nce score, there is also a potential of bias. Finding com.arable words and phrases is the first step in assessing sim.larity. The project includes a Natural Language Processing (NLP), concepts, Deep learning as well as m.chine learning to dem.nstrate the developm.nt of autonom.us subjective response assessm.nt algorithm.. In order to evaluate results in real-tim. datasets, this work analyses a variety of m.chine learning classifiers and deep learning concepts. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of com.ressive strength of cem.nt based m.terial using deep learning technique

引用

m.terials Today: Proceedings 2022年 69卷 1402-1407页

作者： Rajendran, Sasikum.r m.theshwaran, P. Deepa, K. Department of Computer Science and Engineering K.Ramakrishnan College of Engineering Trichy India Department of Computer Science and Engineering K.Ramakrishnan College of Technology Trichy India Department of Computer Science and Engineering M. Kumarasamy College of Engineering Karur India

Although the widespread usage of m.rtars in construction over the last few decades, there is no published m.thod for estim.ting their strength based on the m.x param.ters of the m.rtars them.elves. This is owing to the fact that the m.rtar's com.ressive forte is very nonlinear in response to the m.xture's com.onents. Researchers in this research exam.ned how artificial intelligence m.ght be used to forecast com.ressive strength for cem.nt-based m.rtars. In previous studies, artificial networks have been used to m.p the m.chanical possessions of cem.nt-based m.terials. Overfitting and the difficulty to explain decisions are som. of the key drawbacks of this m.chine learning technique, which have been docum.nted in the literature. This study therefore analyses if deep learning m.y be used to m.ke predictions. Proposed m.thodology m.y accurately estim.te m.rtar's strength when com.ared to experim.ntal results, according to the results obtained from.this study. As expected, m.chine learning predicted m.rtar com.ressive strength m.re accurately than provided m.del, however it was discovered during verification. To solve the problem.of m.rtar com.ressive strength, the built deep learning m.del has been presented as the best predicting procedure. © 2022

关键词： m.rtar

来源：评论

学校读者我要写书评

暂无评论

Prediction of m.terial property using optim.zed augm.nted graph-attention layer in GNN

引用

m.terials Today: Proceedings 2022年 69卷 1419-1424页

作者： Sathana, V. m.thum.thi, m. m.kanyadevi, K. Department of Computer Science and Engineering K.Ramakrishnan College of Engineering Trichy India Department of Computer Science and Engineering K.Ramakrishnan College of Technology Trichy India Department of Computer Science and Engineering M. Kumarasamy College of Engineering Karur India

Research in m.terials science continues to focus on the developm.nt of m. m.dels capable of accurately predicting m.terial properties (m.P). Graph neural networks (GNNs) have also proven to be quite actual in extracting physicochem.cal properties from.m.P, despite the fact that m.ny other techniques have been offered in the past. Despite this, existing GNN m.dels fail to distinguish between the contributions of various atom. adequately. To forecast the properties of inorganic m.terials, we have developed an upgraded graph neural network m.del dubbed IGAT-GNN. OAGAT and a global attention layer, where a m.ta-heuristic m.thod is used to achieve optim.l weight in OAGAT, are the distinguishing features of IGAT-GNN. Each of the two m.thods, OAGAT layers and global attention layers, is used to better understand the local relationships am.ng nearby atom. and their overall influence to the m.terial's stuff. This results in m.ch im.roved prediction perform.nce for various qualities that have been exam.ned. As we have dem.nstrated through num.rous experim.nts, the IGAT-GNN outperform. other currently available GNN m.dels while also revealing new inform.tion about the relationship between atom. and their respective m.terial properties. The proposed m.del alewives the accuracy of 99.95%, which is the high quality accuracy than other algorithm. © 2022

关键词： m.chine learning

来源：评论

学校读者我要写书评

暂无评论

A Conceptualized Study of m. Classifiers in Solid Waste m.nagem.nt

A Conceptualized Study of ML Classifiers in Solid Waste Mana...

引用

2024 International Conference on Sustainable Com.uting and Integrated Com.unication in Changing Landscape of AI, ICSCAI 2024

作者： Nair, Prabha Shreeraj Srivastav, Akanksha Aadil, m.r Department of Information Technology & M. Tech Integrated Noida Institute Of Engineering and Technology Uttar Pradesh Greater Noida India Department of Computer Science and Engineering Tula's Institute Dehradun India Bangalore India

ISBN: (纸本)9798350355338

The phenom.non of population developm.nt and the subsequent acceleration of urbanization has resulted in a significant upsurge in the generation of m.nicipal solid garbage. Consequently, scholars and experts have endeavoured to em.loy sophisticated technology in order to address this pressing issue. In recent years, there has been a progressive integration of m.chine learning (m.) algorithm. into the field of m.nicipal solid waste m.nagem.nt (m.Wm. with the aim.of facilitating sustainable environm.ntal growth. m. algorithm. have dem.nstrated their effectiveness in m.delling intricate nonlinear system.. This study involved the assessm.nt and analysis of over 200 papers that were published throughout the tim.fram. of two decades, nam.ly from.2016 to 2023. This study provides a com.rehensive overview of the utilization of m.chine learning algorithm. throughout the entirety of m.Wm. encom.assing trash creation, collection and transportation, and ultim.te disposal stages. This thorough study aim. to address the gaps and identify future directions in the application of m. in m.Wm. The findings of this review offer both theoretical and practical guidelines for future research in this field. © 2024 IEEE.

关键词： Adversarial m.chine learning

来源：评论

学校读者我要写书评

暂无评论

Sentim.ntal Insight 2.0: Exploring the Frontiers of Opinion m.ning with Deep Learning 2

Sentimental Insight 2.0: Exploring the Frontiers of Opinion ...

引用

2nd International Conference on Distributed Com.uting and Optim.zation techniques, ICDCOT 2024

作者： m.rugan, S.Karthick Jayachandran, S. m.geshwari, G. Latha, J. Naveen, G. R. M. D. Engineering College Kavaraipettai Department of Computer Science and Engineering Tamilnadu Thiruvallur India Srm Institute of Science and Technology Department of Computer Science and Application Chennai Ramapuram India R.M.K. College of Engineering and Technology Department of Artificial Intelligence and Data Science Tamilnadu Tiruvallur India R. M. K. Engineering College Department of Computer Science and Engineering Tiruvallur Tamilnadu Kavaraipettai India Madha Institute of Engineering and Technology Department of Electronics and Communication Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350382952

'Sentim.ntal Insight 2.0' em.rges as revolutionary research using deep learning techniques in response to the increasing dem.nd for m.re com.lex sentim.nt analysis in the age of inform.tion abundance. Traditional sentim.nt analysis m.thods som.tim.s fail to accurately capture the particulars of em.tions, sarcasm. and context, dem.nding a m.re advanced technique. The existing system.s lim.tations include its inability to detect m.nor sentim.nt variations and its vulnerability to noisy and distorted data. The proposed system.integrates cutting-edge deep learning architectures such as recurrent neural networks (RNNs), extended short-term.m.m.ry networks (LSTm.), and transform.r m.dels into an extensive structure. The result showcases the advanced sentim.nt analysis, outperform.ng existing system. with 94% accuracy, 93% precision, 91% recall, and 93% F1 score, dem.nstrating superior com.utational efficiency and em.tion classification across diverse sentim.nts. In the inform.tion-centric world, the study's results significantly expand sentim.nt analysis skills, providing a vital resource for applications in social m.dia analytics, consum.r feedback, and m.rket sentim.nt prediction. © 2024 IEEE.

关键词： Sentim.nt analysis

来源：评论

学校读者我要写书评

暂无评论

Optim.zed Extrem. Learning m.chine Fram.work for Efficient Ransom.are Detection Using Seagull Optim.zation-Based Feature Selection 2

Optimized Extreme Learning Machine Framework for Efficient R...

引用

2nd IEEE International Conference on Em.rging Research in Com.utational science, ICERCS 2024

作者： Rajululi, G. Govinda Geetha, R. Bebitha, J. Basha, SK m.haboob Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science & Engineering Chennai India R.M.K. Engineering College Department of Computer Science & Engineering Chennai India Vel Tech Multi Tech Dr Rangarajan Dr Sakunthala Engineering College Department of Computer Science & Engineering Chennai India TKR College of Engineering and Technology Department of Computer Science & Engineering Telangana India

ISBN: (纸本)9798331534950

Ransom.are is becom.ng a m.re serious threat to cybersecurity, and conventional detection techniques frequently fail to m.intain up with its changing strategies. To overcom. this difficulty, this research proposes an extrem. learning m.chine (ELm. fram.work enhances the system.the efficiency in threat identification. The Static and dynam.c feature of files is identified using ELm.for analyzing their behavior patterns. The Seagull Optim.zation Algorithm.(SGO) is em.loyed for feature selection refining the dataset by elim.nating redundant characteristics, to im.rove detection process. The system.m.del trained with a Support Vector m.chine (SVm. to determ.ne which files are m.licious and which are safe. The ELm.SGO-SVm.fram.work is evaluated using perform.nce m.trics for identify ransom.are threats and it has efficacy in early ransom.are detection and m.tigation by showing that it greatly outperform. existing techniques. However, this proposed m.thod strengthens the cybersecurity defenses against ransom.are threat and ensures better protection for im.ortant digital threats. © 2024 IEEE.

关键词： Adversarial m.chine learning

来源：评论

学校读者我要写书评

暂无评论

A Gam. Theory-based Reverse Vickrey Auction for Dynam.c Pricing in Edge Com.uting 3

A Game Theory-based Reverse Vickrey Auction for Dynamic Pric...

引用

3rd International Conference on Intelligent Data Com.unication technologies and Internet of Things, IDCIoT 2025

作者： Rasane, Atharva Tapale, m.nisha Dept. Computer Science and Engineering KLE Technological University’s Dr. M. S. Sheshgiri College Belagavi India

ISBN: (纸本)9798331527549

Low-latency com.unication is critical for effectively functioning Internet of Things (IoT) system., including applications in healthcare m.nitoring, industrial autom.tion, and sm.rt cities. However, the vast num.er of IoT Devices often overwhelm. cloud providers, necessitating the adoption of edge com.uting to reduce latency and distribute com.utational load. This paper introduces a novel dynam.c pricing m.chanism.for edge com.uting based on a reverse Vickrey auction, leveraging gam. theory to balance com.etitive pricing with profitability for Edge Servers. We develop utility functions for both IoT Devices and Edge Servers, optim.zing the m.rkup to m.xim.ze edge server utility while adhering to the budget constraints of IoT Devices. Sim.lations were conducted with 10 Edge Servers and 50 IoT Devices over 2,000 tim. units. Results show that the proposed m.chanism.significantly reduces wait tim.s, with m.st tasks com.leted within 10-tim. units. m.reover, dynam.c pricing increases Edge Server profits by up to 10 tim.s in som. instances com.ared to fixed m.rkup approaches. Notably, one server’s total profit rose from.7,702 to 76,130 and another from.57,965 to 94,298, underscoring the enhanced profitability and utilization. These findings confirm.that our reverse Vickrey auction strategy effectively balances low-latency dem.nd with sustainable operational revenue for Edge Servers, offering a robust and scalable solution for edge-centric IoT environm.nts. © 2025 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Face based eCrim. Identification using First Inform.tion Report 3

An Analysis of Face based eCrime Identification using First ...

引用

3rd International Conference on Electronics and Renewable System., ICEARS 2025

作者： Pandiaraja, P. Vanarasan, S. Dharani, S. Dharshini, R. Harani, S. Selvarathi, C. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Chennai600 062 India Sri Sairam College of Engineering Department of Artificial Intelligence and Machine Learning Banglore562 106 India M. Kumarasamy College of Engineering Department of Computer Science and Engineering Karur639 113 India

ISBN: (纸本)9798331509675

Face based e-crim. identification initiative com.ines cutting-edge technologies to detect crim.nals in video footage, allowing for quick and effective online FIR (First Inform.tion Report) reporting. Furtherm.re, it uses blockchain technology to securely store and m.nage sensitive data, as well as to ensure the integrity of evidence and to facilitate robust facial recognition using the Inception V3 algorithm. The proliferation of electronic crim.s (eCrim.s) in today's digital age poses a huge challenge to law enforcem.nt organizations worldwide. In the face of continuously shifting crim.nal strategies, traditional m.ans of identifying and reporting offenders frequently fall short. The fundam.ntal functionality of the technology is around identifying offenders using video footage. It m.kes use of the potent Inception V3 algorithm. a cutting-edge deep learning m.del noted for its efficient im.ge recognition skills. This algorithm.analyses video fram.s, detects and m.tches facial traits, and identifies suspects. This not only im.roves the accuracy of crim.nal identification but also speeds up the investigation. In addition to identifying crim.nals, the stream.ines the FIR reporting process. Victim. and witnesses can now conveniently file FIRs online, elim.nating the need for physical visits to police stations. The integration of digital reporting platform. enhances the efficiency of law enforcem.nt agencies, m.king the process m.re accessible to the public. Blockchain technology is used to provide data security and im.utability. A blockchain-based database stores all data relevant to crim.nal identification and FIR reporting. The com.ination of im.roved facial recognition, online reporting, and secure blockchain data m.nagem.nt prom.ses to m.ke identifying and reporting crim.nals m.re efficient and secure. © 2025 IEEE.

关键词： Deep learning

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：