检索结果-内蒙古大学图书馆

Amalgamation of Transfer Learning and Explainable AI for Internet of Medical Things

Recent Advances in computer science and Communications 2024年第4期17卷 40-53页

作者： Murugan, Ramalingam Paliwal, Manish Patibandla, Rama Seetha Maha Lakshmi Shah, Pooja Balaga, Tarakeswara Rao Gurrammagari, Deepti Raj Singaravelu, Parvathavarthini Yenduri, Gokul Jhaveri, Rutvij School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore632014 India School of Technology Pandit Deendayal Energy University Gujarat Gandhinagar India AP India Kallam Haranadhareddy Institute of Technology Andra Pradesh Guntur India Department of Computer Applications Kongu Engineering College Erode Perundurai India

The Internet of Medical Things (IoMT), a growing field, involves the interconnection of medical devices and data sources. It connects smart devices with data and optimizes patient data with real time insights and personalized solutions. It is mandatory to hold the development of IoMT and join the evolution of healthcare. This integration of Transfer Learning and Explainable AI for IoMT is considered to be an essential advancement in healthcare. By making use of knowledge transfer between medical domains, Transfer Learning enhances diagnostic accuracy while reducing data necessities. This makes IoMT applications more efficient which is considered to be a mandate in today’s healthcare. In addition, explainable AI techniques offer transparency and interpretability to AI driven medical decisions. This can foster trust among healthcare professionals and patients. This integration empowers personalized medicine, supports clinical decision making, and confirms the responsible handling of sensitive patient data. Therefore, this integration promises to revolutionize healthcare by merging the strengths of AI driven insights with the requirement for understandable, trustworthy, and adaptable systems in the IoMT ecosystem. © 2024 Bentham science Publishers.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

IoT Smart City Air Quality Monitoring System Using Arduino

IoT Smart City Air Quality Monitoring System Using Arduino

引用

2023 Intelligent Computing and Control for engineering and Business systems, ICCEBS 2023

作者： Gopinath, N. Chinnasamy, A. Sachin, K. Sakthiraj, S. Ravindharan, S. Sri Sairam Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India School of Computing Srmist Kattankulathur Campus Department of Data Science and Business Systems Chennai India

ISBN: (纸本)9798350394580

Many factors, including population growth, increased vehicle use, industrialization, and urbanisation, have contributed to an increase in pollution levels throughout time, which has a negative impact on human wellbeing by adversely affecting the health of those exposed to it. To keep an eye on In this project, we'll build an IOT-based air pollution monitoring system that will track the air quality via an internet-connected web server and sound an alarm whenit drops below a certain threshold, which occurs when harmful gases like CO2, smoke, alcohol, benzene, and NH3 are present in sufficient quantities. On the LCD and on the website, the air quality will be displayed in PPM for easy monitoring. You can use your mobiledevice to check the pollution level as part of this IOT project from anywhere. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Long-Short Term Memory with Byte Pair Encoding and Back Translation for Bangla-English Machine Translation 1st

Bidirectional Long-Short Term Memory with Byte Pair Encoding...

引用

1st International Conference on Machine Intelligence and Emerging Technologies, MIET 2022

作者： Tanvir, Md. Tasnin Oishy, Asfia Moon Akhand, M.A.H. Siddique, Nazmul Department of Computer Science and Engineering Khulna University of Engineering and Technology Khulna Bangladesh School of Computing Engineering and Intelligent Systems Ulster University Londonderry United Kingdom

ISBN: (纸本)9783031346187

Machine Translation (MT) has emerged as an important research area in the computational intelligence domain to translate huge online resources cost-effectively. Among different MT approaches, Neural based Machine Translation (NMT) is in widespread use nowadays. In NMT, Bidirectional Long-Short Term Memory (BiLSTM) is popular due to its higher accuracy and improved performance. This study investigates different performance improvements with standard BiLSTM for Bangla-English MT (BEMT). Attention (ATT) mechanism, Byte Pair Encoding (BPE) and Back Translation (BT) are integrated independently and combinedly through a systematic approach. Four different models such as BiLSTM+ATT, BiLSTM+ATT+BPE, BiLSTM+ATT+BT and BiLSTM+ATT+BPE+BT have been tested rigorously on a benchmark corpus. The effectiveness of ATT, BPE and BT on a BiLSTM model are identified by comparing the performance of the individual models. Finally, the integrated model of BPE and BT with BiLSTM showed the best generalization ability and outperformed other models. © 2023, ICST Institute for computer sciences, Social Informatics and Telecommunications engineering.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Blockchain Driven Metaheuristic Route Planning in Secure Wireless Sensor Networks

引用

computers, Materials & Continua 2023年第1期74卷 933-949页

作者： M.V.Rajesh T.Archana Acharya Hafis Hajiyev E.Laxmi Lydia Haya Mesfer Alshahrani Mohamed K Nour Abdullah Mohamed Mesfer Al Duhayyim Department of Computer Science and Engineering Aditya Engineering CollegeSurampalem533437India Department of Business Administration Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Accounting and Audit Azerbaijan State University of Economics(UNEC)BakuRepublic of Azerbaijan Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Information Systems College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Sciences College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Research Centre Future University in EgyptNew Cairo11845Egypt Department of Computer Science College of Sciences and Humanities-AflajPrince Sattam bin Abdulaziz UniversitySaudi Arabia

Recently,Internet of Things(IoT)has been developed into a field of research and it purposes at linking many sensors enabling devices mostly to data collection and track *** sensor network(WSN)is a vital element of IoT paradigm since its inception and has developed into one of the chosen platforms for deploying many smart city application regions such as disaster management,intelligent transportation,home automation,smart buildings,and other such IoT-based *** routing approaches were extremely-utilized energy efficient approaches with an initial drive that is,for balancing the energy amongst sensor *** clustering and routing procedures assumed that Non-Polynomial(NP)hard problems but bio-simulated approaches are utilized to a recognized time for resolving such *** this motivation,this paper presents a new blockchain with Enhanced Hunger Games Search based Route Planning(BCEHGS-RP)scheme for IoT assisted *** presented BCEHGS-RP model majorly employs BC technology for secure communication in the IoT supportedWSN *** addition,an effective multihop route planning approach was designed by the use of EHGS *** proposed EHGS technique is derived from the concept of Hill Climbing strategy(HCS)and HGS ***,a fitness function with two parameters namely residual energy(RE)and intercluster distance to elect optimal *** performance validation of the BCEHGS-RP model is experimented with under diverse number of *** experimental outcomes highlighted the better performance of the BCEHGS-RP technique on recent approaches.

关键词： Internet of things wireless sensor networks routing metaheuristics blockchain

来源：评论

学校读者我要写书评

暂无评论

An Approach to Detect Fake Profiles in Social Networks Using Cellular Automata-Based PageRank Validation Model Involving Energy Transfer

引用

SN computer science 2022年第6期3卷 423页

作者： Mitra, Arnab Kundu, Anirban Chattopadhyay, Matangini Banerjee, Avishek Department of Computer Science & Engineering SRM University-AP Amaravati 522240 India Department of Computer Science and Business Systems Netaji Subhash Engineering College Kolkata 700156 India School of Education Technology Jadavpur University Kolkata 700032 India Department of Computer Science and Business Systems Asansol Engineering College Asansol 713305 India

Social Network analysis has been considered as an important and promising research area in today’s digital era as many human users in their real lives are found to be directly influenced by such Online Social networks, and unfortunately, very often such human users have been found to be influenced in mostly negative ways caused by fake users of such Social Networks. For this reason, detection of user(s) influence and or, fake user detection in any Social Network scenario may play a crucial role in the reduction of vulnerability in Social Networks. To facilitate enhanced trustworthiness of Social Networks, a novel approach involving an energy transfer-based PageRank validation using Cellular Automata (CAs) has been presented and further has been investigated in this paper to explore its scope for possible usage in Social Network scenarios. For this purpose, a new metric, i.e., energy-based influence score (influence score), has been introduced in this paper to facilitate an easy and effective computation of user influence, in which the user influence is measured based on energy transfer among users of the Social Networks during sending and or, receiving connection requests. Furthermore, a detailed discussion towards possible fake profile(s) detection in any social network scenario facilitating proposed energy-based influence scores has been presented in the presented research. Several analyses of different data as collected from computer simulation and real-time web traffic have confirmed the efficiency and cost-effectiveness of our proposed approach. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Cellular automata (CAs) Energy-based influence score Fake profiles PageRank validation Social networks User profiles

来源：评论

学校读者我要写书评

暂无评论

Blockchain and Artificial Intelligence Applications to Defeat COVID-19 Pandemic

引用

computer systems science & engineering 2022年第2期40卷 691-702页

作者： Mohammed Baz Sabita Khatri Abdullah Baz Hosam Alhakami Alka Agrawal Raees Ahmad Khan Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityTaif P.O.Box 11099Taif 21944Saudi Arabia Department of Information Technology Babasaheb Bhimrao Ambedkar UniversityLucknow226025India Department of Computer Engineering College of Computer and Information SystemsUmm Al-Qura UniversityMakkah21955Saudi Arabia Department of Computer Science College of Computer and Information SystemsUmm Al-Qura UniversityMakkah21955Saudi Arabia

The rapid emergence of novel virus named SARS-CoV2 and unchecked dissemination of this virus around the world ever since its outbreak in 2020,provide critical research criteria to assess the vulnerabilities of our current health *** paper addresses our preparedness for the management of such acute health emergencies and the need to enhance awareness,about public health and healthcare *** view of this unprecedented health crisis,distributed ledger and AI technology can be seen as one of the promising alternatives for fighting against such epidemics at the early stages,and with the higher *** the implementation level,blockchain integration,early detection and avoidance of an outbreak,identity protection and safety,and a secure drug supply chain can be *** the opposite end of the continuum,artificial intelligence methods are used to detect corona effects until they become too serious,avoiding costly drug *** paper explores the application of blockchain and artificial intelligence in order to fight with COVID-19 epidemic *** paper analyzes all possible newly emerging cases that are employing these two technologies for combating a pandemic like COVID-19 along with major challenges which cover all technological and motivational *** paper has also discusses the potential challenges and whether further production is required to establish a health monitoring system.

关键词： Artificial intelligence information privacy machine learning coronavirus(COVID-19) SARS-CoV-2 epidemic

来源：评论

学校读者我要写书评

暂无评论

Optimal Resource Allocation Method for Device-to-Device Communication in 5G Networks

引用

computers, Materials & Continua 2022年第4期71卷 1-15页

作者： Fahd N.Al-Wesabi Imran Khan Saleem Latteef Mohammed Huda Farooq Jameel Mohammad Alamgeer Ali M.Al-Sharafi Byung Seo Kim Department of Computer Science King Khalid UniversityMuhayel AseerKSA Faculty of Computer and IT Sana’a UniversityYemen Department of Electrical Engineering University of Engineering and TechnologyPeshawarPakistan Department of Medical Instrumentation Techniques Engineering Electrical Engineering Technical CollegeMiddle Technical UniversityBaghdad10013Iraq Department of Information Systems King Khalid UniversityMayahel AseerKSA Department of Computer Science College of Computers and Information TechnologyUniversity of BishaKSA Department of Software and Communications Engineering Hongik UniversityKorea

With the rapid development of the next-generation mobile network,the number of terminal devices and applications is growing ***,how to obtain a higher data rate,wider network coverage and higher resource utilization in the limited spectrum resources has become the common research goal of ***-to-Device(D2D)communication technology and other frontier communication technologies have ***-to-Device communication technology is the technology that devices in proximity can communicate directly in cellular *** has become one of the key technologies of the fifth-generation mobile communications system(5G).D2D communication technology which is introduced into cellular networks can effectively improve spectrum utilization,enhance network coverage,reduce transmission delay and improve system throughput,but it would also bring complicated and various interferences due to reusing cellular resources at the same *** resource management is one of the most challenging and importing issues to give full play to the advantages of D2D *** resource allocation is an important factor that needs to be addressed in D2D ***,this paper proposes an optimization method based on the game-matching *** main idea is to model the optimization problem of the quality-of-experience based on user fairness and solve it through game-matching *** results show that the proposed algorithm effectively improved the resource allocation and utilization as compared with existing algorithms.

关键词： D2D communication resource allocation optimization networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Security with Machine Learning-based Finger-Vein Biometric Authentication System 5

Enhancing Security with Machine Learning-based Finger-Vein B...

引用

5th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2024

作者： Babu, G. Prakash Aswal, Upendra Singh Sindhu, M. Upadhye, Vijay Jagdish Natrayan, L. Patil, Harshal Acharya Institute of Technology Department of Computer Science and Engineering Karnataka Bangalore560 107 India Graphic Era Deemed to be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India R.M.K. Engineering College Department of Computer Science and Business Systems Tamil Nadu Thiruvallur601 206 India Parul Institute of Applied Sciences Research and Development Cell Parul University Department of Microbiology Gujarat Waghodia391760 India SIMATS Saveetha School of Engineering Department of Mechanical Engineering Tamil Nadu Chennai602105 India Computer Science and Engineering Symbiosis Institute of Technology Maharashtra Pune412 115 India

ISBN: (纸本)9798350395235

Biometric authentication systems have gained popularity as the necessity for secure individual identification has expanded. Iris, hand geometry, fingerprints, retina, vein patterns on the fingers and palms, and voice patterns are all common biometric features. Biometric recognition systems based on finger-veins are becoming more common due to their numerous advantages, including low danger of duplication or fraud, minimum invasiveness, and excellent identification accuracy. Motivated by these advantages, our research looks into the subject of finger-vein authentication. Similar to identification, exploration of hidden patterns within data is essential for effective finger-vein recognition. The study employs two feature extraction approaches, the Local Binary Pattern (LBP) and the Gabor filter, as well as two machine learning models, the Adaptive Neuro-Fuzzy Inference System (ANFIS) and the Support Vector Machine (SVM). Using finger-vein images from the SDUMLA HMT database, this study evaluates four distinct feature extraction and ML model combinations. The simulation results highlight the excellent accuracy of 97.72%, False Acceptance Rate (FAR) of 3.1%, and False Rejection Rate (FRR) of 1.41% attained by LBP with ANFIS. In addition to performance measurements, the study examines the amount of time required for each task. © 2024 IEEE.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

AI-Based Detection and Analysis of Phishing Domains: Leveraging Machine Learning for Enhanced Cybersecurity

AI-Based Detection and Analysis of Phishing Domains: Leverag...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Dhanalakshmi, R. Vijayaraghavan, N. Kumar, Akhil Beni Prathiba, B. Sahaya School of Computer Science and Engineering Vellore Institute of Technology - Chennai Center for Cyber Physical Systems Chennai India Kcg College of Technology Department of Mathematics Chennai India Scset Bennett University Greater Noida India School of Computer Science and Engineering Vellore Institute of Technology Center for Cyber Physical Systems Chennai India

ISBN: (纸本)9798331510022

In the ever-evolving landscape of cyber security, the prevalence of phishing attacks poses a formidable threat to information security systems worldwide, compromising data integrity and eroding user trust. This paper introduces an innovative solution harnessing artificial intelligence to identify and analyze phishing domains, particularly focusing on newly registered domains from public databases like WHOIS. This approach is crucial as traditional security measures often prove insufficient against the sophistication of phishing tactics. Our proposed AI-driven system employs an analysis strategy. It utilizes machine learning to conduct an in-depth backend code and content analysis. This involves comparing suspect and legitimate sites for structural and syntactical disparities, utilizing deep learning models trained on extensive datasets of known phishing and authentic domains. These methodologies offer a nuanced evaluation, crucial for distinguishing sophisticated phishing attempts from genuine domains. Additionally, the system excels at identifying malicious links within these domains, enhancing its overall protective capabilities. The efficiency of our solution lies in its capacity for real-time, accurate threat detection. We introduce a probabilistic scoring mechanism that assesses the likelihood of a domain being a phishing site, facilitating informed decision-making for cyber security personnel. Furthermore, our system is designed for seamless integration into existing cyber security frameworks, providing versatility and ease of use. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of YOLOv8, RCNN, and SSD Object Detection Models for Precision Poultry Farming Management 3

Performance Analysis of YOLOv8, RCNN, and SSD Object Detecti...

引用

3rd IEEE International Conference on Applied Electromagnetics, Signal Processing, and Communication, AESPC 2023

作者： Kaliappan, Vishnu Kumar Manjusree, S.V. Shanmugasundaram, Kavyanjali Ravikumar, Lakshana Hiremath, Gangadhar Baniekal Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore641407 India Kpr Institute of Engineering and Technology Department of Computer Science Engineering Tamil Nadu Coimbatore641407 India Wasp Autonomous Systems Pvt Ltd Karnataka Ballari India

ISBN: (纸本)9798350358742

In precision poultry farming, detecting multiple objects is challenging. While Convolutional Neural Networks (CNNs) excel in single-object detection, addressing the complexity of multi-object detection, requires advanced approaches. To overcome this challenge, we implement advanced algorithms like YOLOv8, SSD, and Faster RCNN. The primary goal is to analyze their performance, focusing on accuracy, speed, and adaptability. We aim to balance computational efficiency with optimal resource utilization, considering hardware constraints. Integrating these models into precision farming systems and adapting to environmental variations are key challenges. This project specifically aims to validate YOLOv8's effectiveness, and yields an accuracy around 98% in poultry farming scenarios. This research contributes insights to advance precision poultry farming practices. © 2023 IEEE.

关键词： Object detection

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：