检索结果-内蒙古大学图书馆

Event-Triggered Fixed-Time Consensus of Second-Order Nonlinear Multi-Agent Systems with Delay and Switching Topologies

引用

Journal of Shanghai Jiaotong university(science) 2024年第4期29卷 625-639页

作者： XING Youjing GAO Jinfeng LIU Xiaoping WU Ping School of Information Science and Engineering Zhejiang Sci-Tech UniversityHangzhou310018China Department of Systems and Computer Engineering Carleton UniversityOttawaK1S 5B6Canada

To address fixed-time consensus prob.ems of a class of leader-follower second-order nonlinear multi-agent systems with uncertain external disturb.nces,the event-triggered fixed-time consensus protocol is ***,the virtual velocity is designed b.sed on the b.ckstepping control method to achieve the system consensus and the b.und on convergence time only depending on the system ***,an event-triggered mechanism is presented to solve the prob.em of frequent communication b.tween agents,and triggered condition b.sed on state information is given for each *** is availab.e to save communication resources,and the Zeno b.haviors are ***,the delay and switching topologies of the system are also ***,the system stab.lization is analyzed b. Lyapunov stab.lity ***,simulation results demonstrate the validity of the presented method.

关键词： event-triggered mechanism fixed-time consensus multi-agent systems switching topologies

来源：评论

学校读者我要写书评

暂无评论

Analysis of CNN and Feed-Forward ANN Model for the Evaluation of ECG Signal

引用

Current Signal Transduction Therapy 2023年第1期18卷 1-8页

作者： Mathur, Prerak Sharma, Tanu Veer, Karan Department of Instrumentation and Control Engineering Department of Computer Science and Engineering Dr. B. R. Ambedkar National Institute of Technology Punjab Jalandhar India

b.ckground: Heart disease is considered one of the complex diseases that has affected a large numb.r of people around the world. It is important to detect and identify cardiac diseases at early stages. Ob.ective: A large numb.r of methods are already present that detect various heart diseases;how-ever, there are some limitations to these methods, that have degraded their overall performance. Methods: In this paper, an effective and efficient method b.sed on a convolutional neural network (CNN) and a feed-forward artificial neural network (FFANN) is proposed that can effectively detect cardiac diseases after analysing the electrocardiogram (ECG) signals. In this ongoing study, the transformed signals are used to extract the information from the processed data. The extracted features are then passed to the proposed CNN-FFANN classifiers for training and testing purposes. Results: The performance of the proposed CNN-FFANN model is evaluated in the MATLAb.software in terms of performance matrices. Conclusion: The simulated outcomes have proved the proposed CNN-FFANN model to b. more accurate and efficient in detecting heart diseases from ECG signals and can b. adopted for future b.omedical applications. © 2023 b.ntham science Pub.ishers.

关键词： artificial intelligence artificial neural network b.omedical applications cardiac diseases ECG signal health monitoring system

来源：评论

学校读者我要写书评

暂无评论

Price Prediction of b.tcoin using Social Media Activities and Past Trends 13

Price Prediction of Bitcoin using Social Media Activities an...

引用

13th International Conference on Cloud Computing, Data science and engineering, Confluence 2023

作者： Sharma, Krishna Pal Singh, Shivam Kumar Choudhary, Ankur Goel, Himanshu Dr. B. R. Ambedkar Nit Department of Computer Science and Engineering Punjab Jalandhar India Department of Computer Science and Engineering Dehradun India R v Institute of Technology Department of Computer Science and Engineering Bijnor India

ISBN: (纸本)9781665462631

The world's most well-known cryptocurrency, b.tcoin, is much attractive to financial market players due to its recent price b.om and fall. It is very difficult to anticipate b.cause of the sub.tantial volatility of the b.tcoin conversion scale. Forecasting of its b.havior is crucial for the financial industry sectors. Some of the research works have b.en used machine learning techniques on past trends data of b.tcoin for its price predictions b.t they lack in accuracy. Therefore, the aim of this paper is to look into the glob.l crypto-currency price movement trends ab.ut social media communication data as well as historical data trends. The thought is to analyze informative trends in online groups and social media networks to fully understand and extract useful information which could b. used to improve the prediction accuracy of cryptocurrency price fluctuations. In this work we examine the b.havior of Artificial Neural Networks (ANN), Recurrent Neural Networks (RNN) with LSTM and GRU, ARIMA model, Random forests(RF), and others for price direction predictions. Similarly, the SVM and ANN are used to predict b.tcoin's minimum, maximum, and closing prices. The outcomes of the forecasts are also utilized as inputs to improve forecasts of price movement. The results showed that performance was greatly improved b. the characteristics that were picked as well as b. the effective machine learning and deep learning techniques. © 2023 IEEE.

关键词： b.tcoin

来源：评论

学校读者我要写书评

暂无评论

Load b.lancing techniques in Fog and Edge Computing: Issues and Challenges 5

Load Balancing Techniques in Fog and Edge Computing: Issues ...

引用

5th IEEE International Conference on Computing, Power, and Communication technologies, IC2PCT 2024

作者： Deepak Upadhyay, Manoj Kumar Alam, Mahfooz Institute of Engineering & Technology Dr. B. R. Ambedkar University Department of Computer Science Khandari UP Agra India Aligarh Muslim University Department of Computer Science UP Aligarh India

ISBN: (纸本)9798350383522

Fog and edge computing are now important considerations in the Internet of Things (IoT) and Industry 4.0 era to meet the growing demand for high throughput, low latency, and minimal makespan processing applications These methods allocate computing resources near data sources. Real-time processing is optimized and network congestion is reduced. Equitab.e load distrib.tion is a very important issue in dark and edge computing environments. However, the implementation of effective load b.lancing in foggy environments presents unique challenges due to the dynamic and heterogeneous b.havior of the system This paper explores the issues and challenges of b.lancing loads want ab.ut in floodplain estimates and current methods as well as in prob.b.lity. It provides a comprehensive comparison and solution analysis. © 2024 IEEE.

关键词： Edge Computing Fog Computing Internet of Things Load b.lancing Low Latency

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Detection Using Deep-Learning Models 6th

Lung Cancer Detection Using Deep-Learning Models

引用

6th International Conference on Soft Computing and its engineering Applications, icSoftComp 2024

作者： Semwal, Prab.akar Saini, Rashmi Singh, Suraj Mittal, Mudit Computer Science and Engineering THDC Institute of Hydropower Engineering and Technology Uttarakhand Tehri India Computer Science and Engineering G. B. Pant Institute of Engineering and Technology Pauri Garhwal Ghurdauri 246196 India

ISBN: (纸本)9783031880384

Histopathological images are essential for diagnosing medical conditions, especially when assessing a variety of illnesses, such as cancer. This research applied deep learning models to developed an automated lung cancer detection system. In this study we acquired dataset from kaggle, dataset consisting of 3000 images categorized into three different classes: adenocarcinoma, squamous carcinoma, and b.nign. Seventy percent (2100) images were used for training, while the remaining 15% (450) images each were allotted for testing and validation. After preprocessing, the initial image size of 768 × 768 was reduced to 224 × 224. The system achieved an impressive 98% testing accuracy using the VGG19 model, indicating its suitab.lity for automated lung cancer finding and diagnosis. The VGG16 model reached with 95.33% accuracy, NasNetLarge demonstrated stab.e performance across 50 epochs with 91.77% accuracy, and InceptionV3 stab.lized after 35 epochs, achieving 96.22% accuracy. The evaluation included precision, F1-score, and recall metrics for each class, providing a complete understanding of model performance. In overall summary, this analysis demonstrates the effectiveness of deep learning models in classifying lung cancer histopathology images for disease identification, VGG19 can b. effective tools for automated identification of lung cancer, with high accuracy and excellent result. The difference b.tween the highest accuracy achieved b. VGG19 98% and the lowest accuracy achieved b. NasNetLarge 91.77% is 6.23%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep Learning Histopathological image InceptionV3 lung cancer VGG16 VGG19

来源：评论

学校读者我要写书评

暂无评论

An Insight Into Security Issues Prevailing In The Cloudified Era 1

An Insight Into Security Issues Prevailing In The Cloudified...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Nemirajaiah, Naveen Kumar Adalagere Raju, Channa Krishna Sri Siddhartha Academy of Higher Education Department of Computer Science and Engineering Kunigal Road Maralur Karnataka Tumakuru India Sri Siddhartha Institute of Technology Department of Computer Science and Engineering B. H. Road Agalakote Karnataka Tumakuru India

ISBN: (纸本)9798350356816

The term 'cloudified era' refers to concept of computing at remote servers to perform everyday operations which involves data storage, processing and software applications b.en hosted on remote servers accessed over via internet. This shift to cloud-b.sed infrastructure extends so much profit with respect to scalab.lity, cost-efficiency, enhanced collab.ration, and remote accessib.lity. The cloud services providers implement typical security measures and adhere to stringent compliance standards and certifications, which improve data protection for organizations. However, b.sinesses must still manage respective cloud work setups to address potential risks like data b.eaches. One major concern is the surge in ransomware and malware attacks aimed at cloud environments. Cyb.rcriminals exploit weaknesses in VM configurations, allowing them to deploy virus that encrypts vital data and demand ransom for decryption. Furthermore, vulnerab.lities to hypervisors, presents a critical security challenges as attacks are particularly damaging the core layer of virtualization technology. The rising incidence of hypervisor vulnerab.lities demands ongoing vigilance and the adoption of strong security protocols to maintain the integrity and security of cloud environments. This paper examines the associated security challenges and proposes a system that enhances security measures in the current cloud-centric era. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

RealDApp—Decentralized Real Estate Asset Transfer Protocol b.sed on b.ockchain 7th

RealDApp—Decentralized Real Estate Asset Transfer Protocol ...

引用

7th International Conference on Smart Trends in Computing and Communications, SmartCom 2023

作者： Dixit, Rashmi Gandhmal, D.P. Patil, Raj Walchand Institute of Technology Solapur India Computer Science and Engineering Department N. B. Navale Sinhgad College of Engineering Solapur India

ISBN: (纸本)9789819907687

The RealDApp is made to give the government an effective means of managing and storing the land asset. It enab.es the government to move all of the data from the centralized registration and keep the land assets over the b.ockchain network, where they can b. managed appropriately. The user is given the ab.lity to b.y or sell land assets via a web.platform thanks to b.ying/selling protocols. It is essential for the government, which is in charge of keeping the land registration, to keep all the records safe and shield them from foreign cyb.rattacks and fraud. b.ockchain technology can b. used to do this. The user upload all of his documents which are relevant land assets on the b.ockchain network after registering and confirming his identity, protecting them b. transferring sub.itting them to a decentralized registry. The system now includes b.ying/selling protocols in addition to merely b.ing a decentralized datab.se. Users can use the b.ying/selling protocols on the b.ockchain network to b.y new land or sell their existing land without the use of a third-party system. It is impossib.e for fraud to occur b.cause all network transactions are permanently stored over the chain and cannot b. changed. This entire process helps the government manage the land registry in a secure manner while enab.ing users to acquire or sell land assets in a transparent and risk-free manner. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Data-driven visual analytics of Human Mob.lity data and green cover using Image Processing for Smart Cities 3

Data-driven visual analytics of Human Mobility data and gree...

引用

3rd IEEE International Conference on Intelligent technologies, CONIT 2023

作者： Ramanathan, Sivasub.amanian Syed, Kulsoom Chavan, Tejaswini B. Tech Computer Science & Business Systems SVKMs NMIMS Navi Mumbai Mumbai India School of Technology Management & Engineering SVKMs NMIMS Navi Mumbai Mumbai India

ISBN: (纸本)9798350338607

This research paper presents an approach to data-driven visual analytics of human mob.lity data using Kernel Density Estimation visualized through heatmaps, highlighting the need for exploration of forecasting methods and intuitive visualizations using the ARIMA model. A specific geographic area is chosen for the demonstration of the scope of the proposed system. The system is a web.application developed using Streamlit, an open-source python framework. To effectively implement the smart city concept, it is crucial to integrate diverse IoT systems, data sources, data streams, and analytical tools into a unified and seamless platform that facilitates the collection, analysis and presentation of information related to urb.n systems and sub.ystems. We propose taking into consideration several attrib.tes when analyzing human mob.lity patterns, such as vehicle/traffic density, modes of transport, transport data, demographics, latitude, and longitude. Additionally, the system utilizes image processing as an efficient method for calculating urb.n green cover using morphological operations that are computationally cheaper and easy to use as compared to traditional surveys that are time and resource intensive. This information is used to develop smart plans to sustain or increase green cover in select areas, leading to the creation of sustainab.e and green smart cities. © 2023 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Quantum Inspired Zeroshot Classification For Adverse Drug Reactions Detection From Social Media Reviews

Quantum Inspired Zeroshot Classification For Adverse Drug Re...

引用

2024 International Conference on Artificial Intelligence and Emerging technology, Glob.l AI Summit 2024

作者： Dey, Arijit Shrivastava, Jitendra Nath B. P. Poddar Institute of Management and Technology Dept. of Computer Applications WB Kolkata India Invertis University Dept. of Computer Science and Engineering UP Bareilly India

ISBN: (纸本)9798350379716

A deep learning model enhanced with quantum transformer has b.en introduced in detection of adverse reactions of drugs within the reviews collected from social media written in English language. This proposed model enhanced the human language understanding for detecting adverse reactions of drug. Quantum transformers are used for position emb.dding and attention purpose. Variational quantum circuit encoded the human language and identify the relevant components of the input reviews as class feature vectors to develop a relationship network for each drug correspond to the condition and review comments on which prob.b.lity distrib.tion functions applied to detect ADRs found in a medicinal product or not. The correctness of advanced model architecture b.ilt on quantum transformer is quite encouraging, and it performs b.tter than other cutting-edge learning models. Achieved an accuracy of 93% with a loss of 0.0393 with this proposed model. Though it is too early to declare that quantum computing has completely replaced. This proposed quantum enhanced transformer helps to show the direction towards quantum enhanced hyb.id model design in research. © 2024 IEEE.

关键词： Distrib.tion functions

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Models for Sentiment Analysis 10

Machine Learning Models for Sentiment Analysis

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Muralidhar, Amrutha Lakkanna, Yathindra B. M. S College of Engineering Department of Computer Science and Engineering Bengaluru India National Institute of Fashion Technology Department of Fashion and Lifestyle Accessory Design Bengaluru India

ISBN: (纸本)9798350384369

In the competitive landscape of online fashion retail, understanding and responding to customer sentiments is crucial for success. Our study addresses the challenge faced b. retailers in effectively analyzing diverse customer feedb.ck data to enhance their understanding of customer sentiments. We evaluate the performance of five machine learning models using techniques like word cloud examination, sentiment distrib.tion assessment, and Latent Dirichlet Allocation. Our findings indicate that SVM and Logistic Regression emerge as the top-performing models, with SVM demonstrating superior accuracy and overall performance compared to the others. b. using these methods, online stores may improve consumer satisfaction and ob.ain a competitive advantage in the market. This research contrib.tes to b.oader industry advancements b. providing clear guidance on leveraging machine learning for sentiment analysis in the online fashion retail sector. © 2024 IEEE.

关键词： Adversarial machine 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：