检索结果-内蒙古大学图书馆

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Choudhary, Nilam Rathore, Pramod Singh Kumar, Loveleen Rajaan, Rajesh Sharma, Aakriti Sinha, Dibakar Swami Keshvanand Institute of Technology Management & Gramothan Department of Computer Science & Engineering Jaipur India Manipal University Jaipur Department of Computer And Communication Engineering Jaipur India Manipal University Jaipur Department of Computer Science And Engineering Jaipur India

ISBN: (纸本)9798350394474

Due to the widespread use of face masks as a result of the COVID-19 pandemic, facial recognition technology, which is routinely employed for security screening in workplaces, is encountering substantial difficulties. These algorithms were commonly trained using photos of unmasked human faces, which posed challenges in recognising individuals wearing masks. In order to tackle this problem, this study introduces a deep learning model that is specifically tailored to properly identify individuals wearing masks. The model utilises the ResNet-50 architecture and has high proficiency in recognising individuals wearing face masks. The findings of this study can be incorporated into existing facial recognition software utilized for security screening purposes. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Virtual Twin Analytics: Advancing IoT Security through AI-Powered Software Informatics 1

Virtual Twin Analytics: Advancing IoT Security through AI-Po...

引用

1st International Conference on Software, Systems and Information Technology, SSITCON 2024

作者： Nanthini, S. Jain, Upma Arora, Renuka Bhatia, Rishu Sutaria, Kruti Patil, Harshal Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India Jagannath University Department of Computer Science and Engineering Haryana India Ganga Institute of Technology and Management Department of Electronics and Communication Engineering Haryana India Parul Institute of Engineering and Technology Faculty of Engineering and Technology Gujarat India School of Computer Science and Engineering Uttar Pradesh India

ISBN: (纸本)9798350352931

The Internet has grown in importance and impact over the years, causing people to become more reliant on it. The Internet has evolved into a major vector for cybercrime because to its ever-increasing user base. Over the last decade, the number of these computing systems - including desktops, laptops, smartphones, and the Internet of Things (IoT) - has skyrocketed. Among them, cell phones are practically integral to modern life. The popularity of web-based assaults has skyrocketed with the exponential growth in the number of individuals using the Internet. These web-based assaults are increasingly being combatted by security corporations. Unfortunately, new forms of these assaults are appearing all the time, making it hard for older security measures to stay up. Artificial intelligence (AI) is a source of optimism in the current cybersecurity landscape, offering a potential solution to the ever-changing digital dangers. The fast development of AI over the last decade has given rise to this optimism, because it is now impacting the expansion of every industry. With AI bringing so many advantages in every field, online security is one sector that just cannot afford to ignore it. This planned effort's work represents an advance in that direction. Critical online security issues have been the focus of this proposed work's study, which aims to address these issues using AI. Web security issues for desktop and mobile devices have been addressed in the proposed work. The planned work's contributions to online security are as follows: The 'MalCrawler' web crawler is a targeted tool for finding and exploring the web. This crawler makes it easy to gather websites, particularly ones that are harmful. It does a better job of collecting dangerous websites than a typical crawler. Additionally, it is built to circumvent the evasion strategies used by rogue websites. The crawler's ability to gather webpages - particularly dangerous ones - in order to provide datasets for ML-based an

关键词： Web crawler

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Classification Model for Medical Databases Using Hybrid Weights

引用

Journal of The Institution of Engineers (India): Series B 2024年第4期105卷 1005-1019页

作者： Ahammad, Shaik Hasane Mohammed, Thayyaba Khatoon Mandula, Preeti Chenabathini Nidumolu, Venkatram Suman, Maloji Hossain, Md. Amzad Rashed, Ahmed Nabih Zaki Department of ECE Koneru Lakshmaiah Education Foundation Vaddeswaram522302 India Department of Artificial Intelligence and Machine Learning School of Engineering Malla Reddy University Maisammaguda Dulapally Telangana Hyderabad500100 India Department of Electrical and Electronic Engineering Jashore University of Science and Technology Jashore7408 Bangladesh Electronics and Electrical Communications Engineering Department Faculty of Electronic Engineering Menoufia University Al Minufiyah Menouf32951 Egypt Department of VLSI Microelectronics Institute of Electronics and Communication Engineering Saveetha School of Engineering SIMATS Tamilnadu Chennai602105 India

Large databases are now frequently utilized to identify and diagnose medical disorders using extreme learning procedures. Due to its promising implementation and processing speed, the fundamental model of the study utilized for real-time applications is the ensemble classifier. Standard approaches associated with extreme learning practices project the inability for error prediction based on output layer hidden's selection under static weight selection. In this study, a unique weighted extreme learning machine (WELM) for predicting medical conditions is introduced. This research will help to solve the classification problems in the field of healthcare and medicine holds significant promise for improving the accuracy, validation, accountability, and reliability of medical data classification tasks. Moreover, the key objective for the weighted extreme learner's approach is to predict the illness by outlining the high-dimensional data applied for the case study. Typically, the practice proposed an ensemble model which functions the enhances the accurate predictions of high-dimensional cancer showing significant impact of the diagnosis and treatment planning. Furthermore, the WELM model effectiveness is validated through other ensemble learning simulations that include neural networks, random forest, PSO + NN, and ACO + NN techniques. Evaluation for the outcomes is verified through various medical datasets with attributes of the liver, ovarian, lung, diabetes, and DLBCL-Stanford. The results show that the WELM described is very computationally efficient which is related to true positive rate, accuracy, and error rate. © The Institution of Engineers (India) 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Access Authentication Protocol for Satellite Network Resource Slicing Based on Trust Measurement 24

A Lightweight Access Authentication Protocol for Satellite N...

引用

3rd International Conference on Cryptography, Network Security and communication Technology, CNSCT 2024

作者： Hu, Guangyu Guo, Chao Pan, Chenglei Liu, Peihe Department of Cyberspace Security Beijing Electronic Science and Technology Institute Beijing100070 China Department of Electronic and Communication Engineering Beijing Electronic Science and Technology Institute Beijing100070 China The Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China

ISBN: (纸本)9798400716959

With the abundance of satellite network resources, the rational utilization of resources has received widespread attention, and slicing satellite network resources is of great significance for the sensible use of resources. This article is based on satellite network resource slicing and existing trust evaluation schemes. It proposes a lightweight satellite network resource-slicing access authentication scheme based on high trust, targeting the characteristics of satellite network resources. This article introduces a trust system into the access authentication protocol to provide a lightweight access authentication protocol for high trust users. This scheme determines the slicing security policies users can use based on their trust level by evaluating their trust level in advance. This scheme satisfies the anonymity of user identity and the confidentiality of messages. The results of security verification and performance evaluation show that this scheme has high security while ensuring low computational overhead. © 2024 Copyright held by the owner/author(s).

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

An efficient hybrid multifactor mutual authentication and session key agreement scheme for patient monitoring system using IoMT

引用

Multimedia Tools and Applications 2024年第36期83卷 83805-83835页

作者： Rai, Shanvendra Paul, Rituparna Banerjee, Subhasish Meher, Preetisudha Department of Computer Science & amp Engineering National Institute of Technology Arunachal Pradesh Jote Itanagar Arunachal Pradesh Papumpare791113 India Department of Electronics & amp Communication Engineering National Institute of Technology Arunachal Pradesh Jote Itanagar Arunachal Pradesh Papumpare791113 India

The Internet of Medical Things (IoMT) provides such flexibility in our society where anyone can get medical treatment at any time, from anywhere. IoMT is a type of network where different resource-constraint physiological sensors are deployed in and/or on the human body that connects with the internet through the Gateway node, for monitoring purposes. However, due to the open nature of communication in the IoMT;the security, and privacy of patients' sensed data is very challenging, and that needs to be addressed, because any modification or alteration to it may lead to putting the life of a patient in danger. In this context, Chunka et al. proposed an authentication and key agreement (AKA) scheme for IoMT and claimed that the scheme has many security features and is easy to deploy. Unfortunately, it came to notice during this research that the scheme is vulnerable to multiple attacks, including replay, insider, smart card loss, eavesdropping, and server spoofing attacks, additionally failing to establish the session key agreement. So to overcome this issue, an efficient and improved multi-factor lightweight mutual AKA scheme is proposed through this article by incorporating a PUF-enabled sensor node and smart card for the users. To prove the superiority of the proposed schemes and to demonstrate the security features, the scheme is verified by formal security proof using the ROR model and informal proof using the AVISPA tool kit. In the end, a comprehensive analysis covering security, performance, and a comparative evaluation with existing similar approaches along with the Chunka et al. scheme demonstrates that the suggested approach not only achieves a higher level of protection against commonly recognized threats but also maintains an economically efficient mechanism concerning sensor nodes. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of Linear and Nonlinear Precoding for Massive MIMO

Performance Comparison of Linear and Nonlinear Precoding for...

引用

2023 IEEE International Conference on Electrical, computer and Energy Technologies, ICECET 2023

作者： Chili, Nompumelelo Mukubwa, Emmanuel Pillay, Nelendran Durban University of Technology Department of Electronic and Computer Engineering and Electrical Power Engineering Durban South Africa Moi University Electrical and Communication Engineering Eldoret Kenya Durban University of Technology Department of Electronic and Computer Engineering Durban South Africa

ISBN: (纸本)9798350327816

Massive Multiple-Input Multiple-Output (MIMO) answers the exponentially increasing demand for comprehensive fixed broadband and broadcast wireless communication services. Massive MIMO is a pivotal technology in the 5G and beyond (5GaB) wireless communication systems. This paper compares linear precoding algorithms such as Minimum Mean Square Error (MMSE), Neumann Series Approximation (NSA) with nonlinear precoders such as Tomlinson-Harashima Precoder (THP), and Lattice Reduction (LR) algorithm, the Lenstra-Lenstra-Lov'asz (LLL) precoder. The comparison was conducted using Bit-Error Rate (BER) and signal-to-noise ratio (SNR) performance measures. Simulated results prove that nonlinear precoders outperform linear precoding in high SNR regions. © 2023 IEEE.

关键词： Bit-Error Rate (BER) and Signal-to-Noise-Ratio (SNR) Broadband Broadcast Linear precoding Massive MIMO Nonlinear-precoding

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Fault Detection in Smart Grids 3

AI-Driven Fault Detection in Smart Grids

引用

3rd Odisha International Conference on Electrical Power engineering, communication and Computing Technology, ODICON 2024

作者： Pradeep, S. Rex, C. R. Edwin Selva Kalaiyarasi, D. Dhandapani, Ramya Sakthivel, M. Vijaipriya, K. S. A. Engineering College Department of Electronics and Communication Engineering Tamil Nadu 600077 India Vignana Bharathi Institute of Technology Department of Electrical and Electronic Engineering Telangana Hyderabad501301 India Panimalar Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai600123 India Sri Eshwar College of Engineering Department of Computer Science and Business Systems Tamil Nadu Coimbatore India Velammal College of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Madurai India Sri Sai Ranganathan Engineering College Department of Electronics and Communication Engineering Tamil Nadu Coimbatore India

ISBN: (纸本)9798350354379

The use of artificial intelligence (AI) for fault finding in smart grids, with the end goal of improving the reliability and efficiency of ultramodern power systems. Smart grids, which are distinguished by their intricate architectural design and massive data collection, are equipped with cutting-edge approaches for the quick and precise identification of breakdowns. Through the utilization of artificial intelligence techniques, such as Deep Reinforcement Learning (DRL) method can analyze big datasets, identify anomalies, and accurately predict implicit errors with a high degree of precision. In this research, artificial intelligence algorithms that are colorful are investigated, along with their effectiveness in real-time monitoring and defect finding within smart grids. The advantages of AI-driven defect discovery over traditional methods are demonstrated through case studies and simulations. These advantages include important breakthroughs in response time, delicacy, and functional adaptability. The incorporation of artificial intelligence into the management of smart grids holds the potential to bring about substantial breakthroughs in the areas of grid stability maintenance, time-out reduction, and energy distribution optimization. The purpose of this research is to provide a complete analysis of the role that artificial intelligence plays in defect finding. It also offers insight into future advances and practical applications in smart grid systems. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Segment differential aggregation representation and supervised compensation learning of ConvNets for human action recognition

引用

Science China(Technological Sciences) 2024年第1期67卷 197-208页

作者： REN ZiLiang ZHANG QieShi CHENG Qin XU ZhenYu YUAN Shuai LUO DeLin School of Computer Science and Technology Dongguan University of TechnologyDongguan 523808China Shenzhen Institute of Advanced Technology Chinese Academy of SciencesShenzhen 518055China School of Electronic Engineering and Automation Guilin University of Electronic TechnologyGuilin 541004China Department of the mechanical engineering Erlangen-Nuremberg UniversityErlangen 91508Germany School of Aerospace Engineering Xiamen UniversityXiamen 361102China

With more multi-modal data available for visual classification tasks,human action recognition has become an increasingly attractive ***,one of the main challenges is to effectively extract complementary features from different modalities for action *** this work,a novel multimodal supervised learning framework based on convolution neural networks(Conv Nets)is proposed to facilitate extracting the compensation features from different modalities for human action *** on information aggregation mechanism and deep Conv Nets,our recognition framework represents spatial-temporal information from the base modalities by a designed frame difference aggregation spatial-temporal module(FDA-STM),that the networks bridges information from skeleton data through a multimodal supervised compensation block(SCB)to supervise the extraction of compensation *** evaluate the proposed recognition framework on three human action datasets,including NTU RGB+D 60,NTU RGB+D 120,and *** results demonstrate that our model with FDA-STM and SCB achieves the state-of-the-art recognition performance on three benchmark datasets.

关键词： action recognition segment frame difference aggregation supervised compensation learning ConvNets

来源：评论

学校读者我要写书评

暂无评论

Implementation of Secure and Verifiable Access Control Procedures using the NTRU Cryptosystem to Store Big Data in the Cloud Environment

引用

Recent Patents on engineering 2025年第2期19卷 57-70页

作者： Babu B, Ravindra Saxena, Swati Widjaja, Gunawan Vinodha D, Vedha Omarov, Batyrkhan Ramaiah, Gurumurthy B. Vats, Prashant Adama Ethiopia Department of Computer Science KCG College of Technology Chennai India Universitas Krisnadwipayana Jawa Barat 13077 Indonesia Department of Electronics and Communication Engineering JCT College Of Engineering and Technology Pichanur Coimbatore India International University of Tourism and Hospitality Turkistan Kazakhstan Technical and Vocational Training Institute Addis Ababa Ethiopia Department of Computer Science and Engineering Faculty of Engineering and Technology SGT University Haryana Gurugram India

Background: Due to their complexity and size, deploying ciphertexts for clouds is considered the most useful approach to accessing large data stores. Methods: However, access to a user's access legitimacy and improving a decrypted text on the cloud depending on an improved access policy (AP) specified by the data owner are the key challenges for making large data storage realistic and effective in clouds. The traditional ways either totally remove the problem of AP development or offer renewal to arbiter power, but in real-time, enhancing the AP is essential to maximising security and handling agility. Results: In this patent paper, a safe and verifiable access control program characterised by the NTRU cryptographic system for large storage of data in the clouds is proposed. Primarily, an improved NTRU decryption protocol to deal with the decryption failures of the prime NTRU is established, and in addition, the program is analysed for its security strength and computational performance. When a new AP is specified by the data owner, the cloud server allows the program to improve ciphertext and allows the owner to verify the upgrade to oppose the cloud's fraudulent behaviour. Conclusion: It enables (i) checking the user's legitimacy to access the data owner and qualified users, and (ii) allowing the user to verify the data provided by other users for the recovery of the right user. Strong analysis can prevent and block delinquency from various attacks, namely the collusion attack that could potentially target fraud users. © 2025 Bentham Science Publishers.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Analysis of Post-Traumatic Stress Disorder (PTSD) Using Electroencephalography 15

Analysis of Post-Traumatic Stress Disorder (PTSD) Using Elec...

引用

15th International Conference on Computing communication and Networking Technologies, ICCCNT 2024

作者： Yamunarani, T. Zaki, Wan Suhaimizan Bin Wan Elango, S. Chandrasekaran, Gokul Yamuna, S. Kavin Kumar, K. Maheswaran, S. Ksr Institute for Engineering and Technology Department of Biomedical Engineering Tiruchengode India Universiti Tun Hussein Onn Malaysia Faculty of Electrical and Electronic Engineering Johor Malaysia Nandha Engineering College Department of Electrical and Electronics Engineering Erode India Karpagam Institute of Technology Department of Electronics and Communication Engineering Coimbatore India Velalar College of Engineering and Technology Department of Electronics and Communication Engineering Erode638012 India Kongu Engineering College Department of Electronics and Communication Engineering Perundurai Erode638060 India

ISBN: (纸本)9798350370249

This article proposes a Post-Traumatic Stress Disorder (PTSD) detection system based on EEG and machine learning techniques. The first step involves pre-processing the EEG signals to eliminate unwanted artifacts and enhance their quality. To extract features, the Short-Time Fourier Transform (STFT) technique is employed, which provides a time-frequency representation of the brain activity. Feature selection is performed to determine the most relevant and discriminative features for classification, using Select K Best and Mutual Information Regression techniques. The Histogram-Based Gradient Boosting (HistGradientBoost) and Light Gradient Boost Machine algorithms are used to compare and choose the best algorithm for classification. Histogram-Based Gradient Boosting (HistGradientBoost) yielded an accuracy of 75.66% followed by Light Gradient Boost Machine which gave an accuracy of 75.62%. The proposed system seeks to classify EEG patterns with precision, distinguishing between states indicative of PTSD and those that are not. This effort aims to advance the development of more precise and effective diagnostic tools for PTSD. Extensive experimentation and evaluation on a suitable dataset are conducted to assess the effectiveness and reliability of the approach. Analyzed in different environments like indoors with infrastructure, and the same communicated to the caretakers through IoT. © 2024 IEEE.

关键词： Electroencephalography

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：