检索结果-内蒙古大学图书馆

Advanced Computing Technologies (ICoACT), International Conference on

作者： Dinesh Kumar K J. Gobinath Jayavadivel Ravi S. Saravanakumar Senthil P B. Prabhu Shankar Department of Computer Science and Engineering Vel Tech University Chennai India Department of Computer Science and Engineering Rajiv Gandhi College of Engineering Chennai India School of Computer Science and Engineering Presidency University Bengaluru India Department of Information Technology Paavai Engineering College Paachal India Department of Artificial Intelligence and Data Science T.J.S.Engineering college Chennai India Department of Artificial Intelligence and Machine Learning Vel Tech University Chennai India

ISBN: (数字)9798331509859

ISBN: (纸本)9798331509866

This research proposes a new approach for developing and implementing a smart communication system of IoT through developmental blockchain technology. Regarding the proposed solution, it is suggested that a distributed ledger can improve security, reliability, and efficiency of communication of IoT devices. They tackle issues such as data integrity, privacy and security in IoT networks as well as the problem of trust in such networks. The solution provides a decentralised and secure IoT ecosystem communication hence allowing monitoring, controlling and administration of the IoT build ecosystems in real time. Blockchain technology, however, when combined with nextgeneration communication interfaces and modern data analysis techniques, can offer various superior characteristics such as device identification, origin of information, etc. to IoT applications. It also enhances the dependability and capacity of IoT systems regarding capability and efficiency. Analysis and performance comparisons substantiate the performance benefits of the proposed intelligent communication system based on blockchain technology In addition these theoretical and performance analyses and experimental evaluation confirm the applicability and potential of the blockchain-based intelligent communication system to transform IoT communication models and facilitate the new generation of eIOT applications in a number of fields. The key to the solution to incorporate blockchain fundamental infrastructure to augment the communication channel of IoT devices. Using cryptography and consensus methodologies with the decentralized framework, integrity and confidentiality of the data is properly maintained because of the barriers of malicious interception or manipulation of the data. The communication system also boosts trust within the network participants because it offers a decentralized and immutable ledger of data transactions on the blockchain. Instead, one of the compelling benefits of this solution

关键词： Performance evaluation computers Communication systems Ecosystems Transforms Real-time systems Blockchains Internet of Things Reliability Monitoring

来源：评论

学校读者我要写书评

暂无评论

Actuation Sequence Tampering Attack Detection on Field-Level Micro-Electrode Dot Arrays Based on 2-Layer Authentication 23

Actuation Sequence Tampering Attack Detection on Field-Level...

引用

Proceedings of the 2023 13th International Conference on Communication and Network Security

作者： Xiaodong Guo Chenxi Lyu Zhenyi Chen Xiaoding Wang Ruishen Bao Chen Dong College of Computer and Big Data Fuzhou University China Department of Computer Science and Engineering University of South Florida USA College of Computer and Cyber Security Fujian Normal University China

ISBN: (纸本)9798400707964

As a next-generation digital microfluidic biochip (DMFB) platform, micro-electrode-dot -array (MEDA) play an important role in the biochemical industry with more advanced fluidic manipulation and higher reliability. As the MEDA biochip market has grown by leaps and bounds, there are still some issues with MEDA that have not kept pace in terms of security. One of them is that an attacker of a MEDA biochip can change the protocol parameters by tampering with the actuation sequence (AS) in the field before performing the bioassay, which can lead to catastrophic consequences. The attackers could be untrustworthy third parties introduced by the distributed supply chain and malicious remote parties at the time of cyber-physical MEDA biochip deployment. In this paper, a two-layer authentication solution for AS tampering attack detection is proposed, based on SHA-256 hash function to ensure the security of the authentication process and at the same time, it is able to detect and locate the tampered AS with simplicity, security and efficiency. Experiments demonstrate the obvious advantages in security, performance and applicability within a controllable time complexity.

关键词： actuation sequence micro-electrode-dot-array security tempering attack

来源：评论

学校读者我要写书评

暂无评论

Digital Twin-based Dynamic Resource Provisioning Using Deep Q-Network on 6G-enabled Mobile Edge Networks

Digital Twin-based Dynamic Resource Provisioning Using Deep ...

引用

International Communication Systems and Networks and Workshops, COMSNETS

作者： Suja A. Alex Neha Singh Mainak Adhikari Department of Information Technology St. Xavier’s Catholic College of Engineering Nagercoil India Department of Computer Science Indian Institute of Information Technology Lucknow Lucknow India School of Data Science Indian Institute of Science Education and Research Thiruvananthapuram Thiruvananthapuram India

ISBN: (数字)9798331531195

ISBN: (纸本)9798331531201

The advancement of Digital Twin (DT) technology has enabled the creation of digital replicas of physical entitics, significantly enhancing the functionality and performance of mobile networks. However, this innovative approach also introduces considerable overload and performance challenges for mobile edge networks. To address these issucs, we propose a novel DT-enabled edge architecture for 6G-capable technology, employing a dynamic resource allocation strategy. The proposed approach, termed DT-based Dynamic Resource Provisioning (DT-DRP), leverages the capabilities of DT technology and Decp Reinforcement Learning (DRL) to dynamically allocate incoming tasks from mobile devices to edge devices. An intelligent DT server facilitates this allocation, optimizing resource use and improving network performance. The predictive capabilities of the framework are validated using the K-Nearest Neighbor (KNN) dlassifier at the edge network. Experimental results demonstrate that the proposed DT-DRP framework incorporates mobile devices into the DT network scamlessly, achieving superior performance in terms of minimum latency and high accuracy compared to bascline Q-learning algorithms across two medical datasets and various exccution scenarios. This research underscores the potential of DT technology in 6G networks and highlights its efficacy in enhancing mobile edge computing performance through intelligent resource management.

关键词： Performance evaluation 6G mobile communication Training Analytical models Nearest neighbor methods Dynamic scheduling Mobile handsets Resource management Servers Time factors

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Techniques for the Performance Analysis of Indian Mutual Fund Industry and Market Trends

Artificial Intelligence Techniques for the Performance Analy...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： S. Silvia Priscila M. Sakthivanitha M. Yogeshwari T. Shirley Devakirubai M. Mohamed Sirajudeen Department of Computer Science Bharath Institute of Higher Education and Research Tamil Nadu India Department of Information Technology VEL'S Institute of Science Technology and Advanced Studies Chennai Tamil Nadu India Department of Data Analyst Saveetha Liberal Arts and Science College Chennai Tamil Nadu India Department of Commerce Madras Christian College Chennai Tamil Nadu India Department of Computer Science Nilgiri College of Arts and Science (Autonomous) The Nilgiris Tamil Nadu India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

A basic examination of a mutual fund's strategy (growth or value), median market cap, rolling returns, standard deviation, and maybe a portfolio breakdown by industry, geography, and other factors make up a typical mutual fund analysis. Mutual fund analysis typically involves calculating the amount of management contribution to the portfolio and ranking equities according to industry. Analyzing a mutual fund portfolio involves a few phases, one of which comprehends the fund's design. This study examine the basic mutual fund parameters and explore the use of artificial intelligence (AI) methods, including data Mining, machine learning(ML), blockchain and predictive analytics in predicting market trends and assessing mutual fund performance. The purpose of this study is to give users a clear, concise, and professional overview of how to analyze the performance of mutual funds using AI Techniques

关键词： Industries Mutual funds Benchmark testing Market research Performance analysis Artificial intelligence Predictive analytics Portfolios Standards Investment

来源：评论

学校读者我要写书评

暂无评论

Cross Space and Time: A Spatio-Temporal Unitized Model for Traffic Flow Forecasting

arXiv

引用

arXiv 2024年

作者： Ruan, Weilin Wang, Wenzhuo Zhong, Siru Chen, Wei Liu, Li Liang, Yuxuan The Hong Kong University of Science and Technology Guangzhou China The Computer Science Department Jinan University Guangzhou China The School of Big Data and Software Engineering Chongqing University Chongqing China

Predicting spatio-temporal traffic flow presents significant challenges due to complex interactions between spatial and temporal factors. Existing approaches often address these dimensions in isolation, neglecting their critical interdependencies. In this paper, we introduce the Spatio-Temporal Unitized Model (STUM), a unified framework designed to capture both spatial and temporal dependencies while addressing spatio-temporal heterogeneity through techniques such as distribution alignment and feature fusion. It also ensures both predictive accuracy and computational efficiency. Central to STUM is the Adaptive Spatio-temporal Unitized Cell (ASTUC), which utilizes low-rank matrices to seamlessly store, update, and interact with space, time, as well as their correlations. Our framework is also modular, allowing it to integrate with various spatio-temporal graph neural networks through components such as backbone models, feature extractors, residual fusion blocks, and predictive modules to collectively enhance forecasting outcomes. Experimental results across multiple real-world datasets demonstrate that STUM consistently improves prediction performance with minimal computational cost. These findings are further supported by hyperparameter optimization, pre-training analysis, and result visualization. We provide our source code for reproducibility at https://***/r/STUM-E4F0. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Strengthening Authentication: The Role of Multi-Level Hashing in OSPA Protocol

Strengthening Authentication: The Role of Multi-Level Hashin...

引用

IoT Based Control Networks and Intelligent Systems (ICICNIS), International Conference on

作者： S. Hariharasudhan Vineetha Varghese K Malarvizhi S.P. Santhoshkumar T. Nalini D. Vikram Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai Department of Computer Science and Engineering Rathinam Technical Campus Coimbatore India Department of Computer Science al Business Systems Jct College of Engineering and Technology Coimbatore India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai Department of computer science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India Department of Artificial Intelligence Data Science Rathinam Technical Campus Coimbatore India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

Authentication is a crucial step in the cyber security process that confirms user identities. Even though they are widely used, traditional password based techniques are frequently vulnerable to attacks like guessing and password theft. This study presents the Optimal Strong Password Authentication (OSPA) protocol, which uses USB sticks to provide safe user authentication in order to address these issues. The Multi-Level Hashing Algorithm (MLHA), which dynamically picks hash functions during authentication to generate many layers of hashed passwords, is a key component of OSPA's effectiveness. By preventing eavesdropping efforts and reducing the possibility of unwanted access through guessing attacks, this method strengthens security. This protocol provides strong authentication procedures, protecting confidential data and improving overall cyber security posture by integrating MLHA into the OSPA architecture.

关键词： Hash functions Resistance Protocols Heuristic algorithms Authentication Passwords Universal Serial Bus computer crime Intelligent systems Eavesdropping

来源：评论

学校读者我要写书评

暂无评论

An IoT-based Bearded Dragon Enclosure Integrating YOLO Object Detection for Monitoring Food and Cleanliness

An IoT-based Bearded Dragon Enclosure Integrating YOLO Objec...

引用

IEEE Global Conference on Consumer Electronics (GCCE)

作者： Nanmanat Varisthanist Thanapat Tardtong Kittitach Jadee Krittakom Srijiranon Thammasat University Research Unit in Data Innovation and Artificial Intelligence Department of Computer Science Faculty of Science and Technology Thammasat University Pathumthani Thailand

Among exotic reptiles, bearded dragons (Pogona) are popular pets. As ectotherms, bearded dragons require special food and controlled environments, including temperature, humidity, ultraviolet light, and cleanliness. This research applied the Internet of Things (IoT) to control environments within the pet enclosure. In addition, the You Only Look Once (YOLO) deep learning algorithm applied to convolutional neural networks was used to create object detection to count crickets eaten by a dragon and detect feces inside the enclosure. To find the appropriate YOLO structure, three varied experiments were proposed, including different versions YOLO and sizes as well as hyperparameter tuning. Results were that YOLYv5s with 16 batches and 0.01 learning rate was the appropriate structure with an average precision of 0.8246 and 0.6051 for detecting crickets and feces, respectively, at a mean average precision of 0.7149. The proposed enclosure with object detection may improve efficiency and reduce redundancy in breeder tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

UAV-Enabled Relaying and Edge Computing: Hybrid Network Optimization

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Ma, Bo Ye, Jiawei Feng, Shaohan Li, Chuanhuang Niyato, Dusit Kim, Dong In Hangzhou310018 China Nanyang Technological University College of Computing and Data Science 639798 Singapore Sungkyunkwan University Department of Electrical and Computer Engineering Suwon16419 Korea Republic of

This paper exploits an Unmanned Aerial Vehicle assisted Mobile Edge Computing (UAV-MEC) system to meet the computation demand of User Equipments (UEs). However, in conventional UAV-MEC architecture, a UAV is dedicated only to one single service, which will inevitably limit overall system performance. To address the above issue of the conventional UAVMEC architecture, we propose a hybrid UAV-MEC model. In this model, a UAV is treated as an agent to provide either relay or computing services. Moreover, we propose an MEC Multiple Agent UAV Trajectory and User Association Policy Gradient (MEC-MAUTUA-PG) algorithm to optimize offloading strategies of the UEs as well as the trajectory design of UAV. We show the superiority of the proposed algorithm in terms of delay and the safety of trajectory design of UAV in the environment. © 1967-2012 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Smaller Language Models are capable of selecting Instruction-Tuning Training data for Larger Language Models

arXiv

引用

arXiv 2024年

作者： Mekala, Dheeraj Nguyen, Alex Shang, Jingbo Department of Computer Science & Engineering University of California San Diego United States Halıcıoğlu Data Science Institute University of California San Diego United States

Instruction-tuning language models has become a crucial step in aligning them for general use. Typically, this process involves extensive training on large datasets, incurring high training costs. In this paper, we introduce a novel training data selection based on the learning percentage of the samples. We assert that current language models possess the capability to autonomously select high-quality training data, leading to comparable or improved performance compared to training on the entire dataset. Our experiments span different-sized models, revealing that this characteristic holds for models ranging from 1B (small) to 13B (large) in size. Moreover, we demonstrate an interesting finding that the data hardness transfers across model sizes, and a smaller 350M model can effectively curate high-quality training data with hard samples for a larger 13B model, resulting in an equally or superior instruction-tuned model compared to training on the complete dataset. Utilizing open-sourced OPT and Llama-2 models up to 13B in size, two publicly available instruction-tuning training datasets and evaluated by both automatic metrics & humans, our paper introduces a novel approach to training data selection, showcasing a more efficient alternative. © 2024, CC BY.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human Activity Recognition Through Sensor Fusion And Hybrid Deep Learning Model

Enhancing Human Activity Recognition Through Sensor Fusion A...

引用

Acoustics, Speech, and Signal Processing Workshops (ICASSPW), IEEE International Conference on

作者： Adane Nega Tarekegn Mohib Ullah Faouzi Alaya Cheikh Muhammad Sajjad Department of Computer Science The Software Data and Digital Environments (SDDE) Research Group Norwegian University of Science and Technology (NTNU) Gjøvik Norway

Wearable-based human activity recognition (HAR) is essential for several applications, such as health monitoring, physical training, and rehabilitation. However, most HAR systems presently depend on a single sensor, typically a smartphone, due to its widespread use. To improve performance and adapt to various scenarios, this study focuses on a smart belt equipped with acceleration and gyroscope sensors for detecting activities of daily living (ADLs). The collected data was pre-processed, fused and used to train a hybrid deep learning model incorporating a CNN and BiLSTM network. We evaluated the effect of window length on recognition accuracy and conducted a performance analysis of the proposed model. Our framework achieved an overall accuracy of 96% at a window length of 5 seconds, demonstrating its effectiveness in recognizing ADLs. The results show that belt sensor fusion for HAR provides valuable insights into human behaviour and could enhance applications such as healthcare, fitness, and sports training.

关键词：

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：