检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Rep, Ivan Čeperić, Vladimir Department of Electronics Microelectronics Computer and Intelligent Systems Faculty of Electrical Engineering and Computing Zagreb Croatia

Semantic textual similarity is the task of estimating the similarity between the meaning of two texts. In this paper, we fine-tune transformer architectures for semantic textual similarity on the Semantic Textual Similarity Benchmark by tuning the model partially and then end-to-end. We experiment with BERT, RoBERTa, and DeBERTaV3 cross-encoders by approaching the problem as a binary classification task or a regression task. We combine the outputs of the transformer models and use handmade features as inputs for boosting algorithms. Due to worse test set results coupled with improvements on the validation set, we experiment with different dataset splits to further investigate this occurrence. We also provide an error analysis, focused on the edges of the prediction range. © 2023, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Efficient IoT-based Patient Monitoring System for Heart Disease Prediction and Categorization using Optimized Cell Attention based Spiking Neural Network 8

An Efficient IoT-based Patient Monitoring System for Heart D...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Suryawanshi, P.B. Rawat, Ruchira Deepa, Battu Chakraborty, Subhra Mohanty, Aparajita Taqui, Syed Noeman Ibmrd Po Midc Nr College of Engineering Department of Mba Viladghat Ahmednagar Maharashtra Ahmednagar414 111 India Graphic Era Deemed to be University Department of Computer Science & Engineering Dehradun248 002 India Sv College of Engineering Department of Electronics and Communication Engineering Andhra Pradesh Tirupati517520 India Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Karnataka Bangalore560064 India Viman Nagar Maharashtra Pune411014 India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Vlsi Microelectronics Tamil Nadu Chennai602105 India

ISBN: (纸本)9798350376425

The smart healthcare patient monitoring system based on Internet of Things (IoTs) capabilities continuously gathers physiological information through wearable sensors attached to the person's body. In this concern, the proposed study presents a novel smart healthcare patient monitoring system based on Cell Attention Spiking Neural Network (CASNN). The proposed CASNN model is obtained by integrating Cell Attention Network (CAN) with Spiking Neural Network (SNN) that provides enhanced performance during heart disease prediction and classification. Initially, preprocessing is performed to remove unwanted noises and duplicate values from the raw physiological data. Secondly, selection of optimal feature subsets is carried out by utilizing Hybrid Mud Ring Osprey Optimization Algorithm (HMROOA). Finally, cardiac disease prediction and categorization is accomplished with the help of CASNN, in which the hyper parameters are optimized using War Strategy Optimization (WSO). As a result, the proposed model accurately identifies the presence or absence of heart disease, which helps in timely diagnosis of heart illness. The physiological data used for analysis is taken from UCI Heart Disease Kaggle Dataset in which 75% of data is used for training and 25% of data are used for testing. The investigational results show that the developed system achieves greater detection accurateness of 99.7%, which is better than the conventional heart disease prediction models. © 2024 IEEE.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

Design of a Method Using Machine Learning Techniques for the Maintenance and Diagnosis of Failures in Solar Panels

Design of a Method Using Machine Learning Techniques for the...

引用

2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024

作者： Chaturvedi, Abhay Lohumi, Yogesh Patil, Harshal Sharath, N. Vekariya, Daxa Taqui, Syed Noeman Gla University Department of Electronics and Communication Engineering Uttar Pradesh Mathura281406 India Graphic Era Deemed to Be University Department of Computer Science and Engineering Uttarakhand Dehradun248002 India Sri Balaji University Maharashtra Pune India Bgs Institute of Technology Adichunchanagiri University Department of Mechanical Engineering BG Nagar Mandya Karnataka571448 India Parul Institute of Engineering and Technology Parul University Department of Computer Science and Engineering Post Limda Gujarat 391760 India Saveetha Institute of Medical and Technical Sciences Department of Vlsi Microelectronics Saveetha School of Engineering Tamil Nadu Chennai602105 India

ISBN: (纸本)9798350375237

The increasing adoption of solar energy demands efficient maintenance strategies to ensure optimal performance and longevity of solar panel installations. This paper proposes a novel method leveraging machine learning techniques for the proactive maintenance and accurate diagnosis of failures in solar panels. The objective is to enhance the reliability and efficiency of solar energy systems while minimizing downtime and operational costs. The proposed method aims to empower solar panel operators with a proactive and intelligent maintenance system, allowing them to address potential issues before they escalate. By minimizing downtime and optimizing performance, this approach contributes to the sustainability and economic viability of solar energy installations. The effectiveness of the proposed method is demonstrated through experimental results and comparisons with traditional maintenance approaches. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Ai Machine Learning: Transformer Models For Enhanced Natural Language Processing - Techniques And Applications 12

Ai Machine Learning: Transformer Models For Enhanced Natural...

引用

12th International Conference on Internet of Everything, Microwave, Embedded, Communication and Networks, IEMECON 2024

作者： Pragith, S. Karthik, G.M. Sripriya, T. Rajasekaran, E. Periannasamy, S. Manthandi Aslam, Mohamed Zubair M.A. Department of Computer Science Engineering Vellore Institute of Technology Tamil Nadu Vellore India Vellore Institute of Technology Tamil Nadu Vellore India Department of ECE Jeppiaar Institute of Technology Tamil Nadu Chennai India Department of Science and Humanities V.S.B Engineering College Tamil Nadu Karur India Department of Electronics and Communication Engineering Mallareddy Engineering College for Women Maisammaguda Hyderabad India Department of AI &DS Dhanalakshmi College of Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350387315

Modern technologies are needed to strengthen network security defenses because of the increase in cyber attacks in recent years. Because deep learning in particular allows for real-time threat identification and thorough performance evaluation, artificial intelligence (AI) has become a powerful tool for improving cybersecurity measures. This study examines how deep learning methods can be used in AI cybersecurity frameworks, with an emphasis on how well they can detect and counteract changing cyberthreats. The use of convolutional neural networks (CNNs) and deep neural networks (DNNs) for anomaly detection and pattern identification in network traffic is specifically discussed. The study also investigates the integration of AI-driven analytics to assess the performance and efficacy of security protocols, offering insights into optimizing defensive strategies against sophisticated cyber attacks. By leveraging AI capabilities, organizations can achieve proactive threat management, enhance incident response times, and fortify their networks against emerging cyber threats. This abstract sets the stage for a comprehensive exploration of AI's role in cybersecurity, highlighting its transformative impact on network security operations. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

The Design and implementation of a double layered Security Network with an Authentication System through Block chain Technology 3

The Design and implementation of a double layered Security N...

引用

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Shakeel, Mohammed Krishnammal, P. Muthu Vekariya, Vipul Akram, Shaik Vaseem Kumar, Parvathapuram Pavan Kapila, Dhiraj Invertis University Faculty of Computer Applications Bareilly India VIT-AP University School of Electronics Engineering Andhra Pradesh Amaravati India Parul University Department of PIET India Uttaranchal University Uttaranchal Institute of Technology India St. Martin's Engineering College Department of ECE Telangana Secunderabad India Lovely Professional University Department of Computer Science & Engineering Punjab Phagwara India

ISBN: (纸本)9798350399264

With more and more connected devices joining IoT networks, protecting their communications is becoming more difficult. The distributed ledger technology known as blockchain has the potential to solve the security issues plaguing 5G-enabled IoT networks. This article provides a layered blockchain security strategy to protect Internet of Things networks and make their deployment simpler. Using clustering, the complex multi-layer structure is simplified. The K-unknown clusters in the IoT network are generated by use of a hybrid Evolutionary Computation Methodology involving Simulated Annealing and Genetic Algorithms. The chosen cluster chiefs have authority over local authentication and permissions. By creating a private blockchain network on a local level, cluster administrators and critical nodes can streamline their interactions. This type of blockchain also facilitates authentication on a network, but it also adds an extra layer of security and integrity. The proposed framework makes use of Hyperledger Fabric, an open-source implementation of Distributed ledger technology. The encryption of data transmitted between nodes is ensured by the use of a global distributed ledger technology, which is instated in the base stations. As opposed to previously disclosed methods, simulation results show that the proposed clustering algorithm is effective. Finally, it is shown that the envisaged portable cryptocurrency architecture achieves a better latency/capacity tradeoff than a conventional global blockchain. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Medical Image Segmentation Using Deep Learning Techniques: Advancement and Challenges 3

Medical Image Segmentation Using Deep Learning Techniques: A...

引用

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Gopinath, B. Vinay Kumar, V. Kag, Hitesh Joshi, Kapil Rajput, Akshay Kapila, Dhiraj Kumaraguru College of Technology Department of Electronics and Communication Engineering Tamilnadu Coimbatore641049 India Anurag University Department of Ece Telangana Hyderabad India Marwadi University Department of CE-AI Rajkot India Uttaranchal University Uttaranchal Institute of Technology India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India Lovely Professional University Department of Computer Science & Engineering Punjab Phagwara India

ISBN: (纸本)9798350399264

An abundance of articles documenting the efficacy of deep learning in the area of medical picture segmentation attest to its widespread adoption and application for this purpose. A comprehensive topical overview of deep learning algorithms for medical picture segmentation is provided. There are two novel additions to this study. As a first step, we classify the most popular literatures according to a multi-level structure that ranges from coarse to fine, in contrast to traditional questionnaires that straightforwardly divide literatures of deep learning on medical image segmentation into several groups and incorporate articles in depth for each group. Second, although unsupervised learning methods were introduced in many older surveys, they are not widely used now, therefore this work only covers supervised and poorly supervised methods. We provide a literature review of supervised learning strategies, focusing on three key areas: network block design, backbone network selection, and loss function optimization. We explore the literature on weakly supervised learning strategies in terms of data enhancement, transfer learning, and interactive categorization, each of which stands on its own. This study organizes the literatures in a totally different way from previous ones, making it easier for readers to comprehend the key logic and leading them to consider acceptable advances in medical picture segmentation utilizing deep learning methodologies. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Spam Identification Scheme over Social Networking Environment Using Deep Learning Principles 3

A Real-Time Spam Identification Scheme over Social Networkin...

引用

3rd IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2023

作者： Mahalakshmi, P. Mahalakshmi, V. Vinothkumar, E.S. Senthilkumar, B. Dinesh, M. Krishnaprasanna, R. Rajalakshmi Engineering College Department of IT Tamil Nadu Chennai India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electrical and Electronics Engineering Tamil Nadu Chennai India Tamil Nadu Chennai India V.S.B. Engineering College Department of EEE Tamil Nadu Karur India Saveetha Engineering College SIMATS Department of VLSI Microelectronics Tamil Nadu Chennai India Sathyabama Institute of Science and Technology Department of ECE Tamil Nadu Chennai India

ISBN: (纸本)9798350317022

Every single day, millions of people all around the world utilize various social networking platforms. The usage of social media platforms like Twitter and Face Book may result in both positive and bad results for users. These outcomes are not mutually exclusive. The most popular social networking sites have recently been a primary target for spammers who wish to disseminate large numbers of undesired and maybe harmful information. For example, Twitter has quickly become one of the most commonly used platforms ever, which has led to a large increase in the amount of spam that is posted on the network. Users who really use Twitter are irritated and frustrated by tweets from bogus accounts that promote meaningless products, services, or websites. There has also been an increase in the ease with which hazardous chemicals may be transmitted by presenting users with misleading information while using bogus identities. This has led to an increase in the likelihood that people would be harmed. In the field of contemporary social media, two of the most popular research subjects are the elimination of spam and the verification of users on Twitter. In the event that they continue to disseminate dangerous advertisements, spam accounts on social networking websites pose a substantial threat to the safety of the internet and should be eliminated as quickly as possible. This article explores the origins of spam accounts on social networks like Twitter, as well as the distinguishing characteristics of spam accounts, with the goal of improving spam identification. Twitter is one of the most popular online social networks (OSNs), and its members include ministers, business moguls, Hollywood actors, and Fortune 500 companies. The platform's 313 million monthly active users are responsible for publishing around 500 million tweets each and every month on it. Due to Twitter's rising popularity, spammers have developed an interest in the platform. These malicious actors exploit the servi

关键词： ANN Artificial Neural Network Deep Learning Principle LPSIM Social Networking Spam Identification Mechanism Twitter

来源：评论

学校读者我要写书评

暂无评论

Development of Real-Time Thermal Monitoring of GaN-based Power Inverter Modules Using Digital Twin

Development of Real-Time Thermal Monitoring of GaN-based Pow...

引用

Electronic Components and Technology Conference (ECTC)

作者： Bin He Jaydeep Saha Rahul Sadanand Bhujade Gongyue Tang Sanjib Kumar Panda Institute of Microelectronics (IME) Agency for Science Technology & Research (A*STAR) Republic of Singapore Department of Electrical & Computer Engineering (ECE) National University of Singapore Republic of Singapore

ISBN: (数字)9798350375985

ISBN: (纸本)9798350375992

This study addresses the critical challenge of thermal management in Gallium Nitride (GaN)-based Power Inverter Modules (PIM) for electric vehicles (EV), presenting a novel digital twin development for real-time electro-thermal analysis. The innovation lies in integrating a 1D Modelica model with a Computational Fluid Dynamics (CFD) model, enhanced by Reduced-Order Modeling (ROM), to simulate and monitor the GaN chips' thermal behavior under a liquid cooling loop. This comprehensive approach enables real-time thermal monitoring and provides detailed thermal visibility across the PIM. Utilizing test data from India and incorporating three types of virtual sensors, the study showcases the digital twin's application in optimizing multi-speed cooling control under varied traffic conditions, typical of congested tropical developing countries. The results offer a pathway to cost-effective, efficient thermal management solutions, contributing to the sustainability and performance of the electric vehicle ecosystem.

关键词： Temperature sensors Temperature measurement Computational modeling Thermal management Electric vehicles Real-time systems Digital twins

来源：评论

学校读者我要写书评

暂无评论

Condition Monitoring and Maintenance Management with Grid-Connected Renewable Energy Systems

引用

computers, Materials & Continua 2022年第8期72卷 3999-4017页

作者： Md.Mottahir Alam Ahteshamul Haque Mohammed Ali Khan Nebras M.Sobahi Ibrahim Mustafa Mehedi Asif Irshad Khan Department of Electrical and Computer Engineering(ECE) King Abdulaziz UniversityJeddah 21589Saudi Arabia Advance Power Electronics Research Lab Department of Electrical EngineeringJamia Millia IslamiaNew Delhi 110025India Department of Electrical Power Engineering Faculty of Electrical Engineering and CommunicationBrno University of TechnologyBrno 61600Czech Republic Center of Excellence in Intelligent Engineering Systems(CEIES) King Abdulaziz UniversityJeddah 21589Saudi Arabia Computer Science Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah 21589Saudi Arabia

The shift towards the renewable energy market for carbon-neutral power generation has encouraged different governments to come up with a plan of *** with the endorsement of renewable energy for harsh environmental conditions like sand dust and snow,monitoring and maintenance are a few of the prime *** problems were addressed widely in the literature,but most of the research has drawbacks due to long detection time,and high misclassification *** to overcome these drawbacks,and to develop an accurate monitoring approach,this paper is motivated toward the understanding of primary failure concerning a grid-connected photovoltaic(PV)system and highlighted along with a brief overview on existing fault detection *** on the drawback a data-driven machine learning approach has been used for the identification of fault and indicating the maintenance unit regarding the operation and maintenance ***,the system was tested with a 4 kWp grid-connected PV system,and a decision tree-based algorithm was developed for the identification of a *** results identified 94.7%training accuracy and 14000 observations/sec prediction speed for the trained classifier and improved the reliability of fault detection nature of the grid-connected PV operation.

关键词： Fault detection machine learning fault ride through

来源：评论

学校读者我要写书评

暂无评论

Advanced IoT Intrusion Detection for Intelligent Homes using Optimized Cross-Contextual Transformers with a Dynamic City Game Framework 8

Advanced IoT Intrusion Detection for Intelligent Homes using...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Muthulingam, Gurusigaamani Ayyanar Dhasmana, Gulshan Purushothaman, S. Honnaiah, Sharath Ronald, Bindu Soudagar, Manzoore Elahi M. Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamil Nadu Krishnankoil626126 India Graphic Era Deemed to be University Department of Computer Science & Engineering Dehradun248 002 India Sathyabama Institute of Science and Technology Department of Electronics and Communication Tamil Nadu Chennai India Credit Acceptance Karnataka Bangalore India Vimannagar Maharashtra Pune411014 India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Vlsi Microelectronics Tamil Nadu Chennai602105 India

ISBN: (纸本)9798350376425

Ensuring data security against unauthorized access in smart homes is crucial, but implementing deep learning methods can be challenging due to potential issues such as accuracy loss, time complexity, and increased error rates. This study introduces a novel approach to address these challenges: the Securing Intelligent Home with a Transformer-Based IoT Intrusion Detection System (IDS) using an Optimized Cross-Contextual Point Running City Game Transformer Network (O2CPRCG-TransNet). This innovative method leverages advanced DL approaches to improve the security and reliability of Intelligent home environments. The study utilizes the IoT-bot dataset, which is pre-processed using the Grid-Constrained Data Purification Method (GCDP) to ensure high-quality input. The purified data is then optimized through the Giant Trevally Optimizer Algorithm (GTOA), which selects the most significant features to improve classification performance. Classification is performed using the O2CPRCG-TransNet architecture, which is specifically designed to address the complexities of Intelligent home security. To ensure secure data transmission, the system incorporates Somewhat Homomorphic Fuzzy-based Elliptic Curve Cryptography (SWH-FECC). Experimental results, obtained using the Python platform, demonstrate that the proposed approach achieves superior performance, with an accuracy of 98% and a recall of 0.993, compared to existing methods. These findings underscore the effectiveness of the proposed method and its potential for broader application in enhancing Intelligent home security. © 2024 IEEE.

关键词： Smart homes

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：