检索结果-内蒙古大学图书馆

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Raja, S.R. Arya, Hemlata Ramya, D. Sivakumar, S. Arigela, Arun Kumar Venu, Nookala Saveetha Deemed University SIMATS Saveetha College of Liberal Arts And Science Department of Computer Science Chennai India Department of Computer Science & Engineering Madhya Pradesh Gwalior India Sathyabama Institute of Science And Technology Electrical And Electronics Engineering Rajiv Gandhi Salai Chennai India Vel Tech Rangarajan Dr. Sagunthala R And D Institute of Science And Technology Department of Electrical And Electronics Engineering Chennai Tamilnadu Avadi600062 India Department of Csit Telangana Hyderabad India Centre For IoT Madhya Pradesh Gwalior474 005 India

ISBN: (纸本)9798350359299

This study investigates the use of Support Vector Machines (SVM), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN) to improve power utilization in green data centers. The study examines each model's individual capabilities in addressing key concerns about energy efficiency and sustainability. SVM is extremely accurate in workload prediction and resource allocation, whereas CNN excels in real-time monitoring and cooling system efficiency. RNN contributes by anticipating fluctuations in energy use and adapting to dynamic workload changes over time. The research uses ten hypothetical trials to demonstrate the models' consistent performance across multiple measures. These results suggest that SVM, CNN, and RNN have transformative potential in the development of flexible, efficient, and sustainable green data centers. The study adds to the larger discussion about green computing by emphasizing the role of powerful machine learning models in shaping the future of ecologically responsible data center operations. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Lightweight defect detection method of punched nickel-plated steel strip based on GhostNet

Lightweight defect detection method of punched nickel-plated...

引用

2023 International Conference on Pattern Recognition, Machine Vision and Intelligent Algorithms, PRMVIA 2023

作者： Li, Jianqi Liang, Yincong Du, Rui Wan, Jingying Cao, Binfang Liu, Huiting Hunan University of Arts and Sciences Hunan Provincial Key Laboratory for Control Technology of Distributed Electric Propulsion Aircraft Changde China Jishou University Hunan Provincial Key Laboratory for Control Technology of Distributed Electric Propulsion Aircraft Changde China Hunan University of Arts and Sciences College of Computer and Electrical Engineering Changde China

ISBN: (纸本)9798350346596

Aiming at the problem that the defects generated in the production and transportation of punched nickel-plated steel strips are not easy to be detected by deep learning methods, a lightweight, low-redundancy, and high-precision detection method is proposed in this paper. Firstly, a feature extraction network based on GhostNet is constructed, which reduces the amount of computation and feature redundancy while ensuring accuracy. Then the ECA module is applied to the detection head to perform weighted fusion of the features of different channels for better differentiation. Finally, the YOLO detection head is used for multi-scale detection. In the experiment, the mAP of 84.86% was obtained by this method, which proves that this method can be applied to the actual steel strip defect: detection. © 2023 IEEE.

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

A NOVEL MODEL FOR THE MATERIAL SELECTION OF SMART OBJECTS FOR HAND-REHABILITATION: A CASE STUDY 24

A NOVEL MODEL FOR THE MATERIAL SELECTION OF SMART OBJECTS FO...

引用

24th International Conference on engineering Design, ICED 2023

作者： Bos, Mikaël Ivar Karahanoǧlu, Armaǧan Haarman, Juliet Nizamis, Kostas Chair of Systems Engineering and Multidisciplinary Design Department of Design Production and Management Faculty of Engineering Technology University of Twente Enschede Netherlands Interaction Design Research Group Department of Design Production and Management Faculty of Engineering Technology University of Twente Enschede Netherlands Human Media Interaction Group Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Enschede Netherlands

Home hand rehabilitation for stroke is becoming increasingly important due to logistic and financial challenges. Developing Daily-life Integrated Hand-rehabilitation Products (DIHP) aims to enable the application of at-home rehabilitation. The materials of these products are essential for their success, however, selecting materials for DIHP has not been investigated yet. Previous research on material selection showed that it is done strictly on material properties or based on a human-centered approach. Hence, in this study, we propose a hybrid model for choosing materials for DIHP. To achieve this, we first combined the findings of previous material selection processes into a comprehensive material selection model. We applied this model in a case study, in which we first selected three materials based on their properties. Following, we 3d printed a DIHP out of the chosen materials and tested the feeling of the materials with multiple expert groups. Our findings suggest that the proposed material selection method is promising and highlights that our comprehensive model provides more insights when compared to a strict material property-based selection. © The Author(s), 2023. Published by Cambridge University Press.

关键词： 3D printing

来源：评论

学校读者我要写书评

暂无评论

Coordinated Multi-Robot Exploration and Slime Mould Algorithm for Multi-Robot Space Exploration

Coordinated Multi-Robot Exploration and Slime Mould Algorith...

引用

2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems, IACIS 2024

作者： Gudivaka, Rajya Lakshmi Kumar Gudivaka, Raj Prashanth, V. Almusawi, Muntather Saranya, N. Naga Wipro Andhra Pradesh India Platinum Infosys Irving TX United States Nitte Meenakshi Institute of Technology Department of Electrical & Electronics Engineering Bengaluru India The Islamic University Engineering College of Technical Engineering Department of Computers Techniques Najaf Iraq Saveetha College of Liberal Arts & Science Simats Department of Computer Applications Chennai India

ISBN: (纸本)9798350360660

In multi-robot space, conducting research is the critical task to perform flexible without presence of humans the multi-robots are used like landers and rovers for exploring the area which is unknown environment. The multi-robots face problems in exploring the area due improper planning and communication between the robots in specified paths. To solve the problem, Coordinated Multi-robot space Exploration Slime Mould Algorithm (CME-SMA) is proposed here. This integration includes a parallel communication protocol to enhance exploration efficiency and reduce computational complexity. The algorithm focuses on generating optimal collision-free paths in barrier-filled environments by first evaluating neighboring cells using deterministic CME for cost and utility values. SMA is then applied to refine the solutions further. The CME-SMA algorithm is validated through numerous simulations under various environmental conditions, demonstrating consistency in achieving expected outcomes such as exploration rate and time efficiency. The CME-SMA method explored the area is 98.79% with 0 failed run and execution time is 37.15 sec in map 1when compared with existing methods. © 2024 IEEE.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Health Care DNS Tunnelling Detection Method via Spiking Neural Network 3rd

Health Care DNS Tunnelling Detection Method via Spiking Neur...

引用

3rd International Conference on Emergent Converging Technologies and Biomedical Systems, ETBS 2023

作者： Kumar, Narendra Surendiran, R. Samuel, G. K. Jabash Bhavana, N. Shirgire, Anil Malar, A. Jasmine Gnana Qalid, Aznul Faculty of Science and Technology NIET NIMS University Rajasthan Jaipur303121 India School of Information Science Annai College of Arts and Science Tamilnadu Kumbakonam612503 India Department of Electrical and Electronics Engineering Rohini College of Engineering and Technology Kanyakumari India School of Computing and Information Technology REVA University Karnataka Bengaluru560064 India Department of Civil Engineering Dr D Y Patil Institute of Technology Maharashtra Pimpri Pune411018 India Department of Electrical and Electronics Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli627152 India Department of Artificial Intelligence Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur50603 Malaysia

ISBN: (纸本)9789819986453

A common DNS exploit that has been used for several decades to steal data is DNS tunneling. To avoid being detected as an intrusion from healthcare domain, the stolen health information is encoded and contained within DNS requests. Machine learning techniques for detection frequently make use of characteristics like DNS activity and healthcare network activity. The majority of features, such as time–frequency-related information, can only be obtained when data exfiltration occurs. Identifying a malicious query from a single DNS suggestion is key to preventing data exfiltration based on DNS tunneling. We can perceive DNS tunnelling before healthcare data exfiltration by not using internet traffic properties or DNS behavior information. In this paper, we describe a detection method based on deep learning that uses DNS query payloads as predictive variables in the models. Using the Spiking Neural network (SNN) in healthcare DNS Tunnelling Detection Method a DNS Tunnelling attack or not? Specificity, sensitivity, f1 score, accuracy, and Matthew's correlation coefficient (MCC) are the factors taken into account when evaluating the efficiency of the suggested model. In comparison to the Proposed Spiking neural network, the Existing Deep Neural Network (DNN), Mobile Net, and Recurrent Neural Network (RNN) technique improves the performance of a DNS tunneling detection method in a real-world network system. Results indicate that the suggested strategy is far more dependable than existing methods and achieves a 99.84% accuracy rate. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Embodied AI-Enhanced Vehicular Networks: An Integrated Large Language Models and Reinforcement Learning Method

arXiv

引用

arXiv 2025年

作者： Zhang, Ruichen Zhao, Changyuan Du, Hongyang Niyato, Dusit Wang, Jiacheng Sawadsitang, Suttinee Shen, Xuemin Kim, Dong In The College of Computing and Data Science Nanyang Technological University Singapore The Department of Electrical and Electronic Engineering City University of Hong Kong Pok Fu Lam Hong Kong The College of Arts Media and Technology Chiang Mai University Suthep 50200 Thailand The Department of Electrical and Computer Engineering University of Waterloo Canada The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

This paper investigates adaptive transmission strategies in embodied AI-enhanced vehicular networks by integrating large language models (LLMs) for semantic information extraction and deep reinforcement learning (DRL) for decision-making. The proposed framework aims to optimize both data transmission efficiency and decision accuracy by formulating an optimization problem that incorporates the Weber-Fechner law, serving as a metric for balancing bandwidth utilization and quality of experience (QoE). Specifically, we employ the large language and vision assistant (LLAVA) model to extract critical semantic information from raw image data captured by embodied AI agents (i.e., vehicles), reducing transmission data size by approximately more than 90% while retaining essential content for vehicular communication and decision-making. In the dynamic vehicular environment, we employ a generalized advantage estimation-based proximal policy optimization (GAE-PPO) method to stabilize decision-making under uncertainty. Simulation results show that attention maps from LLAVA highlight the model’s focus on relevant image regions, enhancing semantic representation accuracy. Additionally, our proposed transmission strategy improves QoE by up to 36% compared to DDPG and accelerates convergence by reducing required steps by up to 47% compared to pure PPO. Further analysis indicates that adapting semantic symbol length provides an effective trade-off between transmission quality and bandwidth, achieving up to a 61.4% improvement in QoE when scaling from 4 to 8 vehicles. © 2025, CC BY.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

SMRT: Surveillance Monitoring and Recognition Techniques for Analyzing Service Behavior in Blurred and Unsteady Video

引用

Journal of Internet technology 2025年第3期26卷 347-355页

作者： Zhang, Qiaoyun Yang, Shih-Yang Lin, Yu Keh, Huan-Chao Roy, Diptendu Sinha School of Artificial Intelligence Chuzhou University China Department of Computer Science and Information Engineering Tamkang University Taiwan Department of Media Arts Kang-Ning University Taiwan Department of Nursing Kang-Ning University Taiwan Department of Computer Science and Engineering National Institute of Technology Meghalaya India

With the rapid development of the service industry and increasing customer expectations, traditional mystery shopper audit methods face several challenges, such as time-consuming manual analysis, significant subjective bias, and difficulty in accurately quantifying complex service behaviors. To overcome these limitations, this paper introduces an innovative approach called Surveillance Monitoring and Recognition Techniques (SMRT) for analyzing service behavior. The proposed SMRT achieves precise classification of service behaviors through a two-phase process: coarse-grained and fine-grained analysis. In the coarse-grained phase, the proposed SMRT preprocesses blurred video to extract and emphasize relevant external features, specifically detecting and capturing ‘person’ objects in video frames, thereby effectively filtering out irrelevant frames and reducing computational load. In the fine-grained phase, it performs spatiotemporal feature extraction and utilizes Transformer models to conduct a detailed comparison of target behavioral features across video segments. Simulation results demonstrate that the proposed SMRT significantly enhances recognition performance in terms of accuracy, and F1-score compared to existing methods. © 2025 Taiwan Academic Network Management Committee. All rights reserved.

关键词： Service industry

来源：评论

学校读者我要写书评

暂无评论

A Review of Smart Contract Blockchain Based on Multi-Criteria Analysis:Challenges and Motivations

引用

computers, Materials & Continua 2023年第5期75卷 2833-2858页

作者： Norah M.Alshahrani M.L.Mat Kiah B.B.Zaidan A.H.Alamoodi Abdu Saif Department of Computer System&Technology Faculty of Computer Science&ITUniversity of MalayaLembah Pantai50603Kuala LumpurMalaysia Department of Computer Science Applied CollageKing Khalid UniversityP.O.Box 62569AbhaSaudi Arabia Future Technology Research Center National Yunlin University of Science and Technology123 University RoadSection 3DouliouYunlin64002Taiwan Department of Computing Faculty of ArtsComputing and Creative Industry(FSKIK)Universiti Pendidikan Sultan IdrisTanjung MalimMalaysia Department of Electrical Engineering Faculty of EngineeringUniversity of MalayaKuala Lumpur50603Malaysia

A smart contract is a digital program of transaction protocol(rules of contract)based on the consensus architecture of *** contracts with Blockchain are modern technologies that have gained enormous attention in scientific and practical applications.A smart contract is the central aspect of a blockchain that facilitates blockchain as a platformoutside the cryptocurrency *** development of blockchain technology,with a focus on smart contracts,has advanced significantly in recent ***,research on the smart contract idea has weaknesses in the implementation sectors based on a decentralized network that shares an identical *** paper extensively reviews smart contracts based on multi-criteria analysis,challenges and ***,implementing blockchain in multicriteria research is required to increase the efficiency of interaction between users via supporting information exchange with high *** blockchain in the multi-criteria analysis is necessary to increase the efficiency of interaction between users via supporting information exchange and with high confidence,detecting malfunctioning,helping users with performance issues,reaching a consensus,deploying distributed solutions and allocating plans,tasks and joint *** smart contract with decision-making performance,planning and execution improves the implementation based on efficiency,sustainability and ***,the uncertainty and supply chain performance lead to improved users’confidence in offering new solutions in exchange for problems in smart *** includes code analysis and performance,while development performance can be under development.

关键词： Blockchain smart contract MCDM MADM

来源：评论

学校读者我要写书评

暂无评论

SOCIAL NETWORK INFLUENCE ON RESIDENTIAL SOLAR PHOTOVOLTAIC ADOPTION IN AN AGENT-BASED ELECTRICITY SYSTEM MODEL

SOCIAL NETWORK INFLUENCE ON RESIDENTIAL SOLAR PHOTOVOLTAIC A...

引用

ASME 2024 International Design engineering Technical Conferences and computers and Information in engineering Conference, IDETC-CIE 2024

作者： Russo, Gina Dello Wu, Lei Lytle, Ashley Odonkor, Philip School of Systems and Enterprises Stevens Institute of Technology HobokenNJ07030 United States Department of Electrical and Computer Engineering Stevens Institute of Technology HobokenNJ07030 United States School of Humanities Arts and Social Sciences Stevens Institute of Technology HobokenNJ07030 United States School of Systems and Enterprises Stevens Institute of Technology HobokenNJ07030 United States

ISBN: (纸本)9780791888377

As the United States phases out traditional fossil fuels in favor of renewable energy sources, it is important to capitalize on all available avenues to increase renewable penetration. In the last decade, the costs associated with residential solar photovoltaic (PV) installations have decreased significantly, providing more homeowners with the opportunity to generate their own clean electricity. Research has found that the decision to invest in a residential solar PV system is guided by economic, social, and personal factors. Accounting for such complexities, the joint power of agent-based modeling and social network analysis is leveraged in this study to evaluate the effect of social influence on solar PV adoption. Featuring residential consumer agents with data-driven attributes, a logistic regression function to predict solar adoption, and random and small-world social network implementations, this work simulates residential solar PV adoption in New Jersey. Results indicate that including social influence in an agent-based electricity system model leads to increased installed residential solar capacity, but not necessarily higher adoption rates. These findings suggest that, with an understanding of the intricacies of consumer social networks, there are potential opportunities to bolster residential solar installations through low-cost social campaigns that motivate individuals to adopt home solar through their social ties. Copyright © 2024 by ASME.

关键词： Clean energy

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Enabled Predictive Model for P2P Energy Trading in TEM

引用

computers, Materials & Continua 2022年第4期71卷 1473-1487页

作者： Pudi Sekhar T.J.Benedict Jose Velmurugan Subbiah Parvathy E.Laxmi Lydia Seifedine Kadry Kuntha Pin Yunyoung Nam Department of Electrical and Electronics Engineering Vignan’s Institute of Information Technology(Autonomous)Visakhapatnam530049India Department of Computer Applications Government Arts&Science CollegeKanyakumari629401India Department of Electronics and Communication Engineering Kalasalingam Academy of Research and EducationKrishnankoil626126India Department of Computer Science and Engineering Vignan’s Institute of Information Technology(Autonomous)Visakhapatnam530049India Department of Applied Data Science Noroff University CollegeKristiansandNorway Department of ICT Convergence Soonchunhyang UniversityKorea Department of Computer Science and Engineering Soonchunhyang UniversityKorea

With the incorporation of distributed energy systems in the electric grid,transactive energy market(TEM)has become popular in balancing the demand as well as supply adaptively over the *** classical grid can be updated to the smart grid by the integration of Information and Communication technology(ICT)over the *** TEM allows the Peerto-Peer(P2P)energy trading in the grid that effectually connects the consumer and prosumer to trade energy among *** the same time,there is a need to predict the load for effectual P2P energy trading and can be accomplished by the use of machine learning(DML)*** some of the short term load prediction techniques have existed in the literature,there is still essential to consider the intrinsic features,parameter optimization,*** *** this aspect,this study devises new deep learning enabled short term load forecasting model for P2P energy trading(DLSTLF-P2P)in *** proposed model involves the design of oppositional coyote optimization algorithm(OCOA)based feature selection technique in which the OCOA is derived by the integration of oppositional based learning(OBL)concept with COA for improved convergence ***,deep belief networks(DBN)are employed for the prediction of load in the P2P energy trading *** order to additional improve the predictive performance of the DBN model,a hyperparameter optimizer is introduced using chicken swarm optimization(CSO)algorithm is applied for the optimal choice of DBN parameters to improve the predictive *** simulation analysis of the proposed DLSTLF-P2P is validated using the UK Smart Meter dataset and the obtained outcomes demonstrate the superiority of the DLSTLF-P2P technique with the maximum training,testing,and validation accuracy of 90.17%,87.39%,and 87.86%.

关键词： Energy trading distributed systems power generation load forecasting deep learning peer-to-peer

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：