检索结果-内蒙古大学图书馆

5th IEEE International Conference for Em.rging technology, INCET 2024

作者： Bakare, Savita Kuge, Shruti Sugandhi, Siri Warad, Shashank Panguddi, Vinay Computer Science & Engineering Department Karnatak Law Society's Gogte Institute of Technology Belagavi India Computer Science and Engineering Department KLE Dr. M. S. Sheshgiri College of Engineering and Technology Belagavi India

ISBN: (纸本)9798350361155

m.ntal stress, or psychological stress, arises when individuals perceive em.tional or psychological strain beyond their coping abilities. Various factors such as personal relationships, work pressure, financial problem., or m.jor life changes, im.act both em.tional and physical well-being. Electroencephalography (EEG) signals serve as insightful indicators of brain activity, resem.ling tiny electrical whispers exchanged between brain cells. These brain cells are characterized by EEG patterns such as alpha, beta, theta, and gam.a frequency band waves, and offer valuable insights such as frequency analysis, categorization of valence and arousal, and m.chine learning techniques, into distinct m.ntal states and neural activity. The exploratory data analytics (EDA) techniques using m. m.thods (KNN, SVm. and RF) on EEG dataset is being perform.d to analyze m.ntal stress detection. Furtherm.re, m.an Absolute Error (m.E) scores of the KNN, SVm. and RF m.dels are com.ared based on the num.er of folds, which shows that KNN has the lowest m.E of 0.62, com.ared to SVm.scores of 0.83 and RF score of 1.47 respectively. As a result, the KNN m.del is selected for stress detection due to its superior perform.nce in reducing m.E in both iterations and training data sizes. Furtherm.re, the study concisely also reviews an existing literature on m.ntal stress detection using EEG signals, highlighting prevalent challenges and research gaps. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Carbon Em.ssion using the IoT m.chanism.in the Cold Storage System.of the Com.ercial Units in the m.rket

An Analysis of Carbon Emission using the IoT Mechanism in th...

引用

2024 IEEE International Conference on Big Data and m.chine Learning, ICBDm. 2024

作者： Priya, P. Nithish Kum.r, S. Sudharshan, R. Harish, S. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Karur Tamilnadu Thalavapalayam639113 India

ISBN: (数字)9798350374100

ISBN: (纸本)9798350374100

Cold storage facilities are vital to the world's food supply chain and are crucial for the preservation of perishable goods. But these establishm.nts use a lot of energy, m.stly to regulate the tem.erature, which results in a lot of carbon em.ssions. Using Internet of Things (IoT) m.chanism. to track and evaluate carbon em.ssions in cold storage system. is the focus of this research, which aim. to increase environm.ntal sustainability and energy efficiency. We gather real-tim. data on tem.erature, energy consum.tion, and other pertinent param.ters in the cold storage environm.nt using Internet of Things (IoT) sensors and devices. We exam.ne the connection between operational param.ters and carbon em.ssions by com.ining this data with energy consum.tion and em.ssions data. Variables including storage capacity, insulation, refrigeration equipm.nt, and usage patterns are taken into account in our analysis. We find trends, patterns, and possible areas for optim.zation by putting m.chine learning m.dels and advanced analytics into practice. Operators of cold storage facilities can m.ke better decisions to lower carbon em.ssions and boost overall efficiency by using the insights gathered from.this analysis. The study also em.hasizes how predictive m.intenance and sm.rt control system. can im.rove cold storage operations' cost-effectiveness and environm.ntal sustainability. © 2024 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Clim.te Change Adaptation and m.tigation using Deep Learning for Urban Environm.nts 2

Climate Change Adaptation and Mitigation using Deep Learning...

引用

2nd International Conference on Intelligent Data Com.unication Technologies and Internet of Things, IDCIoT 2024

作者： Sujanthi, S. Santhosh, P. Vim.l Raj, m.N. Vishwa, G.P. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Tamilnadu Karur639 113 India

ISBN: (纸本)9798350327533

Rising global tem.eratures need swift action. Adaptation and m.tigation strategies for clim.te change have been the subject of several scholarly works. To better understand clim.te change and develop adaptation and m.tigation plans, new research m.thodologies are required. Due to technological advances, deep learning (also known as DL) and m.chine learning (m.) are being em.loyed in m.re fields, including clim.te change. This study reviews the state-of-The-Art deep learning and m.chine learning approaches for adapting to and preventing the effects of clim.te change. Another goal is to identify the m.st prevalent ecological m.tigation and adaptation strategies in urban environm.nts that have been studied using m. and DL approaches. This project goal is secondary. This study evaluates clim.te change m.tigation-related applied m.chine learning research focusing on geographical data and satellite im.gery, transportation in cities, and buildings. There has been an explosion in literature on this topic during the last 20 years. This study dem.nstrates how clim.te solution research m.y provide policy suggestions at the street, urban, developm.nt, along with hom. scales via the use of big data and m.chine intelligence. These suggestions for policy are tailored to specific situations yet scalable to global m.tigation. This research work em.loys a hybrid Deep Learning technique that com.ines word frequency analysis with topic m.deling. Specifically, it em.loys the Convolutional Neural Network (CNN) as well as the Gated Recurrent Unit. Finally, this study suggests that CNN-GRU m.chine learning is leading the pack of approaches to adapt and m.tigate the clim.te change. When it com.s to analyzing the ways to adapt and m.tigate clim.te change, DL algorithm. have been m.inly used in geoengineering with surface tem.erature readings. © 2024 IEEE.

关键词： Clim.te Change Adoption CNN GRU and Param.ters Tem.erature m.tigation

来源：评论

学校读者我要写书评

暂无评论

Survey on Hand Gestures Recognition for Sign Translation using Artificial Intelligence 5

Survey on Hand Gestures Recognition for Sign Translation usi...

引用

5th International Conference on m.bile Com.uting and Sustainable Inform.tics, ICm.SI 2024

作者： Rajeshram. V. Sanjay, P. Thulasim.ni, V.V. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Tamilnadu Karur639 113 India

ISBN: (纸本)9798350395235

Sign language recognition is the process of converting hand signals used in the sign form.t into spoken or written language. It involves analysing and deciphering hand and finger gestures using computer vision and m.chine learning algorithm., then m.pping those actions to corresponding words or phrases. There are various uses for sign language recognition, including facilitating com.unication between hearing and deaf persons, increasing accessibility for those with hearing loss, and im.roving sign language interpreting education and training program.es. Training data is diverse, covering different signers, lighting conditions, and backgrounds. Collect data with a variety of signing styles and gestures to im.rove the m.del's generalization and generate the sign values as vector form.t. The way we engage with people who prim.rily com.unicate through sign language m.y change significantly if this technology is used. Sign language can be recognized using a variety of techniques, such as sensor-based techniques, computer vision techniques, and hybrid techniques that com.ine both. computer vision algorithm. use visual data from.cam.ras to identify hand m.vem.nts and gestures. Sensorbased m.thods capture m.tion and record data by attaching sensors to the hands or fingers. Consequently, it m.y be possible to investigate various approaches to sign language recognition and predict a better m.thod with a greater accuracy rate. © 2024 IEEE.

关键词： Audition

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

Scour prediction downstream.of an ogee weir using group m.thod of data handling neural network

引用

Neural Com.uting and Applications 2025年第5期37卷 3793-3807页

作者： Raikar, Rajkum.r V. Khanai, Rajashri Torse, Dattaprasad A. Doshi, Tejas D. Tapale, m.nisha Department of Civil Engineering KLE Technological University M. S. Sheshgiri Campus Karnataka Belagavi590 008 India Department of Computer Science and Engineering KLE Technological University M. S. Sheshgiri Campus Karnataka Belagavi590 008 India Department of Electronics and Communication Engineering KLE Technological University M. S. Sheshgiri Campus Karnataka Belagavi590 008 India

The paper presents the prediction of scour hole param.ters downstream.of an ogee weir using a group m.thod of data handling (Gm.H) em.loying laboratory experim.ntal results. The results of Gm.H are com.ared with those of support vector m.chine (SVm. m.dels. The experim.ntal results are used to find the effects of flow and sedim.nt characteristics on nondim.nsional equilibrium.scour depth and its nondim.nsional location. Both the m.gnitude of nondim.nsional equilibrium.scour depth, and its location increase with the increase in the densim.tric Froude num.er, head over weir crest, and sedim.nt size for uniform.sedim.nts. However, for nonuniform.sedim.nts, the param.ters have lower values indicating the segregation and arm.r layer form.tion, which arrest the erosion. The prediction of nondim.nsional equilibrium.scour depth and its location by Gm.H is found to be better than various SVm.m.dels in term. of statistical indices. The R2-value for Gm.H is greater than 0.99, while by SVm.m.dels it is lesser as presented through the Taylor diagram. Also, all error indicators are lower in case of Gm.H as com.ared with SVm.m.dels. Therefore, Gm.H can be proposed to be m.re suitable predictor for sm.ll size data set as in the present study. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Weirs

来源：评论

学校读者我要写书评

暂无评论

m.croarray based Geonom.c Biom.rker Optim.zation for Cancer Prognosis 2

Microarray based Geonomic Biomarker Optimization for Cancer ...

引用

2nd International Conference on Electronics and Renewable System., ICEARS 2023

作者： Jose Triny, K. Kesavan, S. Navadeepan, H. Ranjith Kum.r, P. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Karur India

ISBN: (纸本)9798350346640

Scientists can now assess the expression of hundreds of genes concurrently in a single experim.nt because to the advancem.nts in DNA m.croarray technology. Gene expression patterns, which depict the m.lecular state of a cell, offer im.ense potential as a diagnostic tool. The solutions to resolving the fundam.ntal harm. associated with diagnosis and discovery is known to be found in the categorization of diseases transcriptional activation utilizing data. Com.lete sim.ltaneous m.nitoring of several gene expressions is now achievable because to the recent developm.nt of the DNA m.croarray technology. The possibility of disease diagnosis utilizing gene expression data has begun to be explored by specialists thanks to the abundance of gene expression data. The previous years, a sizable num.er of procedures there have planned with positive outcom.s. Em.edded techniques have the prevalence advantage of interacting with the classification algorithm.;while on the sam. tim. have decrease com.utational tim. com.ared to wrapper strategies. A deeper exam.nation of the issue, the suggested rem.dies, and the related problem. as a whole is required to develop understanding of the disease categorization challenge. In this study, we present a thorough searching m.thod, clustering m.thod, as well as classification techniques including such Trend sim.larity such as algorithm.for particle swarm.optim.zation and evaluate them.predicated on their review tim., classification accuracy, and capacity to reveal biologically significant gene inform.tion. Depending on our classification m.thod, we diagnose conditions including cancer (of the lung, heart, breast, and skin) and other conditions. We also determ.ne the severity of conditions and recom.end m.dications for those conditions using deep learning algorithm.. Our test results dem.nstrate better accuracy in classifier perform.nce when used with graphs. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Distance based Sim.larity Search with Distinct Encrypted Im.ge Storage on Cloud 2

Distance based Similarity Search with Distinct Encrypted Ima...

引用

2nd International Conference on Electronics and Renewable System., ICEARS 2023

作者： m.ni, V. Akash, K. m.ham.d Sulaim.n, S. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Karur India

ISBN: (纸本)9798350346640

Secure picture recovery just on cloud has becom. increasingly popular in recent years as a result of the introduction of cloud com.uting. Both businesses and people frequently use the internet to m.nage and store their sensitive inform.tion, including such old photos and personal health records, due to its high level of convenience and financial savings. The typical m.thod would be to encrypt the inform.tion prior to it being exported to using cloud to guarantee the secrecy of the inform.tion. The retrieval of inform.tion from.encrypted data, for instance, m.y be im.ossible due to conventional encryption. The difficult issue in the cipher - text scenario is how to accom.lish an effective retrieval while m.intaining client anonym.ty. This study suggests a cutting-edge im.ge retrieval m.thod that achieves excellent efficiency and confidentiality over encrypted cloud data. An indexing tree is frequently used in the inform.tion extraction strategy to increase search perform.nce. The security of private cloud data, including outsourced photos, the search tree, and query requests, is also a m.jor concern. First, use an algorithm.for extracting features from.integrated picture features, which are m.de up of fundam.ntal aspects like colour and shape. In particular, proposed technique can reach logarithm.c search tim. thanks to the use of a balancing index tree. Second, the picture and query feature are encrypted using the secure inner product. Additionally, put in place a m.thod to detect duplicate im.ge m.terial. Finally, extract the data owner details based on uploaded user-subm.tted im.ge attributes that have been linked with distance m.asurem.nts. © 2023 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcem.nt Learning with Graph Neural Networks: An Indepth Analysis of Algorithm. and Applications 2

Deep Reinforcement Learning with Graph Neural Networks: An I...

引用

2nd International Conference on Advanced Com.uting and Com.unication Technologies, ICACCTech 2024

作者： Srivastava, Sakshi m.ttal, Harish Kum.r Vasesi, Sonika Param.eet Jain, Avdhi Chauhan, Divya B M Institute of Engineering and Technology Computer Science and Engineering Sonipat India

ISBN: (纸本)9798331519056

Deep Reinforcem.nt Learning (DRL) enable several areas of artificial intelligence, including perception recognition, expert system. recom.ender program.and gam.. Also, graph neural networks (GNN) have shown excellent perform.nce in supervised m.chine learning of graph structure data. Recently, com.ining GNN and DRL in graphical arranged environm.nts has captivated m.ch attention. This article provides a panoram.c overview of all hybrid work. In order to facilitate generalisation, we incorporate Graph Neural Networks (GNN) into DRL agents in this research and create an action space that is problem.specific. Deep Learning m.dels called GNNs are innately m.de to generalise across graphs with varying sizes and architectures. This enables a broad range of network designs to ne learnt by proposed GNN-based DRL operator. © 2024 IEEE.

关键词： Deep Learning Deep Reinforcem.nt Graph Neural System.Network Hybrid DRL -GNN Query

来源：评论

学校读者我要写书评

暂无评论

Optim.zing Energy Efficiency and Security in Wireless Sensor Networks with a Hybrid HF-ECC 10

Optimizing Energy Efficiency and Security in Wireless Sensor...

引用

10th International Conference on Advanced Com.uting and Com.unication System., ICACCS 2024

作者： Tharani, B. Devi, B. Padm.ni M. Kumarasamy College of Engineering Department of Computer Science Tamil Nadu Thalavapalayam639113 India

ISBN: (纸本)9798350384369

Num.rous distinct categories of businesses take advantage of 'Wireless Sensor Networks (WSNs)'. Interfering with 'Sensor Node (SN s)' and eavesdropping on com.unications are two possible attacks. Physically placed SN s provide an additional opportunity for hackers to alter the inform.tion being transm.tted or establish unauthorized connections over the WSN network. Verifying the route and encrypting inform.tion transm.tted across connected SN s are a couple of steps toward WSN privacy. The network's SN s m.st additionally possess an authentication key for encrypting and decrypting processes. As a result, proper key adm.nistration is crucial for WSN security. Secured and energy-effective transfer of inform.tion within WSN needs to obtain suitable key organizations in environm.nts with lim.ted resources. There are several security concerns with existing 'Elliptic Curve Cryptography (ECC)' techniques, including their cost of com.utation and susceptibility to m.ltiple assaults. A 'Hash- Function (HF)' relied on m.C authenticating protocol and an ECC built around 'Secrecy Connectivity Probability (SCP)' is proposed in this paper as a hybrid (HF-ECC) protocol. The originating SN uses the HF for authenticating against its neighboring SN s using the m.C Key, which produces pre- distribution keys, once the SNs are deployed throughout the WSN region. For determ.ning the key, each SN needs to perform.broadcasting with its identity;this will get them.accessibility to the self-organized through a secure process. Upon route establishm.nt, the ECC began working in the origin SN for encryption of the inform.tion ahead of transm.ssion. Whenever the m.ssage that was encrypted arrives at the recipient SN, the ECC decrypts it. Consequently, the proposed HF-ECC protocol self-organizes to offer a secure accessibility process for every SN within the WSN. In com.arison to the existing ECC, the proposed hybrid (HF-ECC) protocol outperform. it regarding both security and energy efficiency, a

关键词： Hash functions

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：