检索结果-内蒙古大学图书馆

2023 International Conference on Integrated Intelligence and Communication Systems, ICIICS 2023

作者： Mao, Pandi Liao, Xiaowen Xu, Daolian School of Electrical Engineering and Intelligent Manufacturing Chongqing Metropolitan College of Science and Technology hongqing Yongchuan China School of Arts and Media Chongqing Metropolitan College of Science and Technology Chongqing Yongchuan China Chongqing University College of Optoelectronic Engineering Chongqing Shapingba China

ISBN: (纸本)9798350315455

In order to meet the current training, employment and regulatory needs, the Hong Kong government will launch a comprehensive training program. The system consists of the main arm controller, sensor module, adjustable camera and image acquisition and processing system. The system has the advantages of high precision and reasonable price, and has broad market prospects. In this paper, the problem of autonomous motion control for tracking target is studied, and an active tracking control method for serial action output target is proposed. The learning strategy utilizes visual perception and depth improvement to make decisions, using consecutive frames' visual image as continuous control model for input state and output action. The system has the advantages of high precision and reasonable price, and has broad market prospects. Target tracking is an important application in video surveillance and a new research field in image processing. Video surveillance uses cameras to identify moving or multiple objects, widely used in human-computer interaction, security, traffic control, airports, subway stations, and mass activities. As a result, MUSIC obtained 96% of accuracy, 95% of precision, 94% of f-measure, and 91% of recall. © 2023 IEEE.

关键词： Ace image Face Image Processing sensor module Target tracking technology

来源：评论

学校读者我要写书评

暂无评论

A Security Enhanced Chaotic-Map-Based Authentication Protocol for Internet of Drones

引用

IEEE Internet of Things Journal 2024年第12期11卷 22301-22309页

作者： Mahmood, Khalid Ghaffar, Zahid Farooq, Muhammad Yahya, Khalid Das, Ashok Kumar Chaudhry, Shehzad Ashraf National Yunlin University Of Science And Technology Graduate School Of Intelligent Data Science Douliu64002 Taiwan National Yunlin University Of Science And Technology Graduate School Of Engineering Science And Technology Douliu64002 Taiwan Abu Dhabi University Department Of Mathematics And Statistics College Of Arts And Sciences Abu Dhabi United Arab Emirates Istanbul Gelisim University Department Of Electrical And Electronics Engineering Istanbul34310 Turkey Sabratah University Department Of Electrical Engineering Faculty Of Engineering Regdalen Libya Center For Security Theory And Algorithmic Research Hyderabad500 032 India Abu Dhabi University Department Of Computer Science And Information Technology College Of Engineering Abu Dhabi United Arab Emirates Nisantasi University Faculty Of Engineering And Architecture Department Of Software Engineering Istanbul34398 Turkey

The Internet of Drones (IoD) extends the capabilities of unmanned aerial vehicles, enabling them to participate in a connected network. In IoD infrastructure, drones communicate not only among themselves but also with users and a control center. This interconnected communication framework holds promise for various applications, from collaborative decision-making to real-time data exchange. However, the expansion of communication in IoD also introduces new challenges, particularly in terms of security, privacy and authentication. Unfortunately, the current authentication protocols are inadequate in offering robust security features against various attacks in the IoD environment. To address these security issues and limitations, we proposed a secure protocol for the IoD environment using chaotic maps and hash functions. In addition, we also employed a physically unclonable function in the development of the proposed protocol. We assess the security of the protocol through both informal and formal security analysis. The formal security analysis is conducted through a widely used random or real (RoR) model. The informal analysis shows the rigorous security features against various attacks, such as masquerading, anonymity violation, and physical cloning attacks. Moreover, we compare the performance of the devised protocol with similar existing protocols across important performance parameters, such as communication overhead, computation overhead, and security features. The devised protocol provides a 67.86% and 17.80% reduction in computation and communication overheads, respectively, as compared to related protocols. The analysis demonstrates the proposed protocol's capacity to support secure communication in the IoD environment and satisfy desirable security attributes. © 2014 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Two-Stream Deep Learning Architecture-Based Human Action Recognition

引用

computers, Materials & Continua 2023年第3期74卷 5931-5949页

作者： Faheem Shehzad Muhammad Attique Khan Muhammad Asfand E.Yar Muhammad Sharif Majed Alhaisoni Usman Tariq Arnab Majumdar Orawit Thinnukool Department of Computer Science COMSATS University IslamabadWah CampusPakistan Department of Computer Science HITEC UniversityTaxilaPakistan Department of Computer Science Bahria UniversityIslamabadPakistan Computer Sciences Department College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia College of Computer Engineering and Science Prince Sattam Bin Abdulaziz UniversityAl-Kharaj11942Saudi Arabia Faculty of Engineering Imperial College LondonLondonSW72AZUK College of Arts Mediaand TechnologyChiang Mai UniversityChiang Mai50200Thailand

Human action recognition(HAR)based on Artificial intelligence reasoning is the most important research area in computer *** breakthroughs in this field have been observed in the last few years;additionally,the interest in research in this field is evolving,such as understanding of actions and scenes,studying human joints,and human posture *** HAR techniques are introduced in the ***,the challenge of redundant and irrelevant features reduces recognition *** also faced a few other challenges,such as differing perspectives,environmental conditions,and temporal variations,among *** this work,a deep learning and improved whale optimization algorithm based framework is proposed for *** proposed framework consists of a few core stages i.e.,frames initial preprocessing,fine-tuned pre-trained deep learning models through transfer learning(TL),features fusion using modified serial based approach,and improved whale optimization based best features selection for final *** pre-trained deep learning models such as InceptionV3 and Resnet101 are fine-tuned and TL is employed to train on action recognition *** fusion process increases the length of feature vectors;therefore,improved whale optimization algorithm is proposed and selects the best *** best selected features are finally classified usingmachine learning(ML)*** publicly accessible datasets such as Ut-interaction,Hollywood,Free Viewpoint Action Recognition usingMotion History Volumes(IXMAS),and centre of computer vision(UCF)Sports,are employed and achieved the testing accuracy of 100%,99.9%,99.1%,and 100%*** with state of the art techniques(SOTA),the proposed method showed the improved accuracy.

关键词： Human action recognition deep learning transfer learning fusion of multiple features features optimization

来源：评论

学校读者我要写书评

暂无评论

Week Ahead Electricity Power and Price Forecasting Using Improved DenseNet-121 Method

引用

computers, Materials & Continua 2022年第9期72卷 4249-4265页

作者： Muhammad Irfan Ali Raza Faisal Althobiani Nasir Ayub Muhammad Idrees Zain Ali Kashif Rizwan Abdullah Saeed Alwadie Saleh Mohammed Ghonaim Hesham Abdushkour Saifur Rahman Omar Alshorman Samar Alqhtani Electrical Engineering Department College of EngineeringNajran University Saudi ArabiaNajran61441Saudi Arabia Department of Computer Science COMSATS University IslamabadWah Campus22060Pakistan Faculty of Maritime Studies King Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computer Science Federal Urdu University of ArtsScience and TechnologyIslamabad44000Pakistan School of Electrical Engineering and Computer Science National University of Science and TechnologyIslamabad44000Pakistan Department of Computer Science and Engineering University of Engineering and TechnologyNarowal CampusLahore54000Pakistan Department of Electrical Engineering HITEC UniversityTaxila47080Pakistan College of Computer Science and Information Systems Najran UniversityNajran61441Saudi Arabia

In the Smart Grid(SG)residential environment,consumers change their power consumption routine according to the price and incentives announced by the utility,which causes the prices to deviate from the initial ***,electricity demand and price forecasting play a significant role and can help in terms of reliability and *** to the massive amount of data,big data analytics for forecasting becomes a hot topic in the SG *** this paper,the changing and non-linearity of consumer consumption pattern complex data is taken as *** minimize the computational cost and complexity of the data,the average of the feature engineering approaches includes:Recursive Feature Eliminator(RFE),Extreme Gradient Boosting(XGboost),Random Forest(RF),and are upgraded to extract the most relevant and significant *** this end,we have proposed the DensetNet-121 network and Support Vector Machine(SVM)ensemble with Aquila Optimizer(AO)to ensure adaptability and handle the complexity of data in the ***,the AO method helps to tune the parameters of DensNet(121 layers)and SVM,which achieves less training loss,computational time,minimized overfitting problems and more training/test *** evaluation metrics and statistical analysis validate the proposed model results are better than the benchmark *** proposed method has achieved a minimal value of the Mean Average Percentage Error(MAPE)rate i.e.,8%by DenseNet-AO and 6%by SVM-AO and the maximum accurateness rate of 92%and 95%,respectively.

关键词： Smart grid deep neural networks consumer demand big data analytics load forecasting price forecasting

来源：评论

学校读者我要写书评

暂无评论

Optimizing Cloud Security with CNN and XGBoost Models for Intrusion Detection Systems 3

Optimizing Cloud Security with CNN and XGBoost Models for In...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Mogal, Amit Karbhari Anitha, V. Bhatt, Preeti Nitin Srivasatava, Kriti Devi, S. Rukmani Perada, Anvesh Mvp Samaj's Cmcs College Department of Computer Science and Application Nashik India School of Engineering and Technology Dhanalakshmi Srinivasan University Department of Computer Science and Engineering Trichy India Iimt College of Engineering Department of Electronics & Communication Engineering Greater Noida India Vile Parle India Saveetha College of Liberal Arts and Sciences Simats Deemed to be University Department of Computer Science Chennai India Drexel University Department of Electrical and Computer Engineering Philadelphia United States

ISBN: (纸本)9798331508456

Cloud computing and Internet growth have simplified certain formerly difficult activities. This advancement has also revealed many security weaknesses. Due to cyberattacks, organizations need Intrusion Detection Systems (IDS) to protect their data and networks. Preprocessing, feature selection, and model training comprise the suggested strategy. Preprocessing includes data cleansing, standardization, and labeling. Information gain, chi-square, and PSO are used to choose features. CNN-XGBoost trains the model. The CNN-XGBoost model outperforms solo CNN and XGBoost with an average accuracy of 92.08%. This accuracy proves the hybrid method's cloud computing breach detection usefulness. The study underlines the importance of enhanced IDS models in cyber risk reduction. CNN's feature extraction and XGBoost's classification power provide a powerful, efficient, and reliable cloud intrusion detection model. Modern organizations benefit from this network security method. © 2025 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

A Fast Response Fault Detection Technique for HVAC Transmission Line Using Machine Learning 10

A Fast Response Fault Detection Technique for HVAC Transmiss...

引用

10th IEEE International Conference on Power Systems, ICPS 2023

作者： Muntasir, Fahim Al Wazed Wasi, Wasif Nafis, Mahdee Hossain, M. Mofazzal Brac University Dept. of Computer Science and Engineering Dhaka Bangladesh Rajshahi University of Engineering and Technology Dept. of Electrical and Electronic Engineering Rajshahi Bangladesh Rajshahi University of Engineering and Technology Dept. of Electronics and Telecommunication Engineering Rajshahi Bangladesh University of Liberal Arts Bangladesh Dept. of Electrical and Electronic Engineering Dhaka Bangladesh

ISBN: (纸本)9798350318739

High voltage alternating current (HVAC) transmission lines are the only way to transmit electrical energy from the power plant to the utilities. There are several types of transmission line faults that can interrupt the power supply, sometimes even resulting in national blackout. To ensure a highly reliable power supply system, detecting the faults in the quickest of time is crucial. This research used machine learning and neural network algorithm to find five different types of faults using data from a real power transmission line in Bangladesh. Apart from the accuracy of the methods, the focus was given on the response time in identifying the faults. The two boosting methods CatBoost and XGBoost stood out as the most precise among all the algorithms, achieving excellent accuracy and detection time in between 20 ms to 30 ms. The response time of all the methods was found to be in millisecond range, making them perfect for not only long term faults, but also to be implied in transient fault analysis. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Sensor System for Real-time Water Quality Monitoring 46

Sensor System for Real-time Water Quality Monitoring

引用

46th ICT and Electronics Convention, MIPRO 2023

作者： Simonoska, Elena Bogatinoska, Dijana Capeska Dimitrievski, Ile Malekian, Reza University of Information Science and Technology 'St. Paul the Apostle' Ohrid Macedonia Malmö University Department of Computer Science and Media Technology Malmö205 06 Sweden University of Pretoria Department of Electrical Electronic and Computer Engineering Pretoria0002 South Africa

ISBN: (纸本)9789532331042

Water pollution is a global issue that has an impact on the entire ecosystems' life cycles. Traditional sampling and laboratory testing techniques are labor-intensive and error-prone, making them ineffective for quickly detecting changes in water quality. This paper presents the development of a low-cost, portable and efficient prototype sensor-based system for monitoring water quality in real-time. The system consists of a microcontroller, temperature, turbidity, pH, and distance sensors, and an application for a visual representation of the data. Extensive testing was carried out to ensure uninterrupted operation. The prototype is a user-friendly sensor system that can be positioned close to the target area in order to assist in preventing environmental and biological harm. This can ensure safe, healthy, and sustainable water supplies for the communities, environment, and the economy. Continuous monitoring of water parameters can also help avoid critical situations. The experimental results demonstrate a successful development of a smart water quality monitoring system with potential applications in various scenarios. © 2023 MIPRO Croatian Society.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Heads-Up Multitasker: Simulating Atention Switching On Optical Head-Mounted Displays

Heads-Up Multitasker: Simulating Atention Switching On Optic...

引用

2024 CHI Conference on Human Factors in Computing Sytems, CHI 2024

作者： Bai, Yunpeng Ikkala, Aleksi Oulasvirta, Antti Zhao, Shengdong Wang, Lucia J. Yang, Pengzhi Xu, Peisen Dept. of Computer Science National University of Singapore Singapore Dept. of Computer Science Aalto University Espoo Finland Dept. of Information and Communications Engineering Aalto University Helsinki Finland School of Creative Media Dept. of Computer Science City University of Hong Kong Hong Kong Hong Kong Dept. of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge United States Dept. of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft Netherlands Dept. of Computer Science IPAL National University of Singapore Singapore

ISBN: (纸本)9798400703300

Optical Head-Mounted Displays (OHMDs) allow users to read digital content while walking. A better understanding of how users allocate attention between these two tasks is crucial for improving OHMD interfaces. This paper introduces a computational model for simulating users' attention switches between reading and walking. We model users' decision to deploy visual attention as a hierarchical reinforcement learning problem, wherein a supervisory controller optimizes attention allocation while considering both reading activity and walking safety. Our model simulates the control of eye movements and locomotion as an adaptation to the given task priority, design of digital content, and walking speed. The model replicates key multitasking behaviors during OHMD reading while walking, including attention switches, changes in reading and walking speeds, and reading resumptions. © 2024 Copyright held by the owner/author(s)

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An Internet of Things Assisted Autism Spectrum Disorder Prediction Using Deep Learning Principles with Medical Image Processing Assistance

An Internet of Things Assisted Autism Spectrum Disorder Pred...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart electrical Systems, ICSES 2024

作者： Bindhu, A. Mol, A. Sruthi Ravi, T. Bodkhe, R.G. Safori, Amjad Omar Vijayalakshmi, S. Infant Jesus College of Arts and Science for Women Department of Computer Science Mulagumoodu India Sathyabama Institute of Science and Technology Department of Ece Chennai India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India R.M.K. Engineering College Department of Electronics and Communication Engineering Chennai India Zaraa University Faculty of Media Department of Journalism and Digital Media Zaraa 13110 Jordan University of Business and Technology Jeddah21448 Saudi Arabia

ISBN: (纸本)9798331543617

Characteristics of the complex neuro-developmental condition Autism Spectrum condition (ASD) include impaired social communication and restricted, repetitive patterns of behavior. This study presents a novel approach for identifying ASD in young infants by integrating deep learning, Internet of Things (IoT) and medical image processing. The goal of this research is to create comprehensive and discriminative features by combining wearable sensor data with brain imaging and smart home environments. For the greatest results, early diagnosis is essential. The proposed method called IoT based Autism Predictive Framework (IoTAPF) has a high detection rate of 97.8% and is cross-validated against the current Learning based Autism Detection Strategy (LADS). The proposed approach aims at improving diagnostic specificity which helps in forecasting behaviors and thus pushing earlier interventions, providing better support for ASD individuals and their families. The paper discusses the design and implementation of the framework, including sensor integration, data management, and predictive modeling. Preliminary results from pilot studies are presented, demonstrating the framework's potential to improve diagnostic accuracy and support individualized care plans. The proposed solution represents a significant advancement in the application of IoT technology for early autism detection and management, paving the way for more proactive and data-driven approaches in the field of neuro-developmental disorders. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Optimal Deep Dense Convolutional Neural Network Based Classification Model for COVID-19 Disease

引用

computers, Materials & Continua 2022年第1期70卷 2031-2047页

作者： A.Sheryl Oliver P.Suresh A.Mohanarathinam Seifedine Kadry Orawit Thinnukool Department of Computer Science and Engineering St.Joseph’s College of Engineering600119ChennaiIndia Department of Computer Science and Engineering KPR Institute of Engineering and TechnologyCoimbatore641407India Faculty of Engineering Karpagam Academy of Higher EducationCoimbatore641021India Faculty of Applied Computing and Technology Noroff University CollegeKristiansand4608Norway Research Group of Embedded Systems and Mobile Application in Health Science College of ArtsMedia and TechnologyChiang Mai UniversityChiang Mai50200Thailand

Early diagnosis and detection are important tasks in controlling the spread of COVID-19.A number of Deep Learning techniques has been established by researchers to detect the presence of COVID-19 using CT scan images and ***,these methods suffer from biased results and inaccurate detection of the ***,the current research article developed Oppositional-based Chimp Optimization Algorithm and Deep Dense Convolutional Neural Network(OCOA-DDCNN)for COVID-19 prediction using CT images in IoT *** proposed methodology works on the basis of two stages such as pre-processing and ***,CT scan images generated from prospective COVID-19 are collected from open-source system using IoT *** collected images are then preprocessed using Gaussian *** filter can be utilized in the removal of unwanted noise from the collected CT scan ***,the preprocessed images are sent to prediction *** this phase,Deep Dense Convolutional Neural Network(DDCNN)is applied upon the pre-processed *** proposed classifier is optimally designed with the consideration of Oppositional-basedChimp Optimization Algorithm(OCOA).This algorithm is utilized in the selection of optimal parameters for the proposed ***,the proposed technique is used in the prediction of COVID-19 and classify the results as either COVID-19 or *** projected method was implemented in MATLAB and the performances were evaluated through statistical *** proposed method was contrasted with conventional techniques such as Convolutional Neural Network-Firefly Algorithm(CNN-FA),Emperor Penguin Optimization(CNN-EPO)*** results established the supremacy of the proposed model.

关键词： Deep learning deep dense convolutional neural network covid-19 CT images chimp optimization algorithm

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：