检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Data Science and Network Security, ICDSNS 2024

作者： Pramod Pawar, Priyanka Kumar, Deepak Krupa, R. Pareek, Piyush Kumar Manoj, H.M. Deepika, K.S. University of the Cumberlands Information Technology Cumberlands United States Nitte Meenakshi Institute of Technology Mechanical Engineering Bengaluru India Nitte Meenakshi Institute of Technology Department of Artificial Intelligence & Machine Learning Bengaluru India Bms Institute of Technology and Management Computer Science and Engineering Bengaluru India Channabasaveshwara Institute of Technology Gubbi India

ISBN: (纸本)9798350373110

Today, smart devices permeate every part of our lives, ushering in a new technological era known as Internet of Things (IoT). There ration of cybersecurity risks due to the proliferation of smart devices in IoT contexts and the massive volumes of sensitive data they store. In order to determine the time and place of these attacks and to collect evidence that can lead to the identification of the perpetrators, digital forensics is essential. Research into digital forensics in an IoT setting is fraught with difficulties owing to factors such as the dispersed nature of data storage, the need to be able to track and verify the provenance of evidence, the difficulty in obtaining data from many sources, and the lack of visibility into the evidence collection procedure. This is why the research suggested merging two potential technologies to offer a complete answer. The research employed federated learning to train representations locally using data kept by IoT devices, with the help of a dataset that was created to mimic attacks on the IoT ecosystem. The study utilises the BoT-IoT dataset and employs a classification method called Shepard Interpolation Neural Network (SINN) with the Shuffled Frog-Leaping algorithm (SFLA). After that, in order to make the blockchain lightweight, the study aggregated data using blockchain by gathering parameters from the IoT gateway © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Fault Diagnosis Approaches in Memristor Crossbar Array 9

An Analysis of Fault Diagnosis Approaches in Memristor Cross...

引用

9th IEEE International Symposium on Smart Electronic Systems, iSES 2023

作者： Yadav, Dev Narayan Thangkhiew, Phrangboklang Lyngton Sengupta, Indranil Center for Artificial Intelligence and Machine Learning Siksha 'o' Anusandhan Bhubaneswar India Indian Institute of Information Technology Department of Computer Science and Engineering Guwahati India Indian Institute of Technology Department of Computer Science and Engineering Kharagpur India

ISBN: (纸本)9798350383249

The use of memristors has been explored for various applications due to its unique computing capability, in particular in-memory computing (IMC). IMC offers both storage and computation using the same hardware, which overcomes to a large extent the CPU-memory bottleneck that exists in current-day computing architectures. Memristors are often fabricated in a crossbar, which offers various benefits over other memory technologies, including in-memory computing, low power, and high density. However, the still immature nano-scale fabrication technology can lead to a number of faulty cells in the crossbar (typically, 30-40% faulty cells). For some applications like neuromorphic computing, a limited number of faults can be tolerated. However, for some other applications like Boolean function realization, a single faulty cell may lead to incorrect results. We therefore need a fault diagnosis approach to use the memristor devices efficiently. In this paper, we have analyzed various fault diagnosis approaches available in the literature. We observe that most of the existing approaches employ March-based test, which is used for conventional RAM. Nevertheless, memristor storage and operation techniques differ from conventional memory, necessitating a different approach and fault models to be used. © 2023 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

DocAssist: Signature Perception System using Deep learning

DocAssist: Signature Perception System using Deep Learning

引用

Computational intelligence and Computing Applications (ICCICA), International Conference on

作者： Pooja Sharma Ishika Miglani Lucky Sharma Panipat Institute of Engineering and Technology Samalkha India Artificial Intelligence and Machine Learning Panipat Institute of Engineering and Technology Samalkha India

ISBN: (数字)9798350306446

ISBN: (纸本)9798350306453

All In the realm of communication, individuals employ two primary modes: written and spoken language. Handwriting, in particular, serves as a powerful tool for conveying information and emotions across various contexts, including healthcare. Despite its widespread use, deciphering handwritten text remains a challenge due to variations in individual writing styles and the lack of standardization. This challenge is particularly pronounced in the medical field, where handwritten prescriptions can lead to serious consequences if misinterpreted. Our research addresses this issue by proposing DocAssist, a novel model that utilizes Convolutional Neural Networks to achieve an impressive 81% accuracy in recognizing doctors' handwriting. By leveraging machine learning and image recognition technologies, DocAssist aims to enhance prescription legibility, mitigate medication errors, and ultimately improve patient safety and healthcare outcomes. Through rigorous experimentation with the EMNIST dataset, our study demonstrates the effectiveness of DocAssist in accurately interpreting handwritten prescriptions, highlighting its potential to revolutionize prescription processing and alleviate the burden on healthcare professionals and pharmacists.

关键词： Handwriting recognition Accuracy Image recognition Medical services Writing Safety Mobile applications

来源：评论

学校读者我要写书评

暂无评论

A Security Analysis Model for IoT-ecosystem Using machine learning-(ML) Approach

引用

Recent Advances in Computer Science and Communications 2024年第6期17卷 39-47页

作者： Pradeep Kumar, N.S. Kantipudi, M. V. V. Prasad Praveen, N. Suresh, S. Aluvalu, Rajanikanth Jagtap, Jayant Dept.of ECE S.E.A College of Engineering and Technology Bangalore India Pune412115 India Dept. Of Electrical Engineering University of Technology and Applied Sciences Ibra Oman Dept.of CSE Balaji Institute of Technology & Science Warangal India Dept.of IT Chaitanya Bharathi Institute of Technology Hyderabad500075 India Dept.of AIML NIMS Institute of Computing Artificial Intelligence and Machine Learning NIMS University Rajasthan Jaipur India

Introduction: The attacks on IoT systems are increasing as the devices and communication networks are progressively integrated. If no attacks are found in IoT for a long time, it will affect the availability of services that can result in data leaks and can create a significant impact on the associated costs and quality of services. Therefore, the attacks and security vulnerability in the IoT ecosystem must be detected to provide robust security and defensive mechanisms for real-time applications. Method: This paper proposes an analytical design of an intelligent attack detection framework using multiple machine learning techniques to provide cost-effective and efficient security analysis services in the IoT ecosystem. Result: The performance validation of the proposed framework is carried out by multiple performance indicators. Conclusion: The simulation outcome exhibits the effectiveness of the proposed system in terms of accuracy and F1-score for the detection of various types of attacking scenarios. © 2024 Bentham Science Publishers.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection: Leveraging InceptionResNetV2 and LSTM for Enhanced Accuracy

Deepfake Detection: Leveraging InceptionResNetV2 and LSTM fo...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Saini, Aradhna Attiuttama Naaz, Sheenam Shivhare, Anushka Dhuriya, Gaurav Yadav, Neha G L Bajaj Institute of Technology and Management Computer Science and Engineering Greater Noida India G L Bajaj Institute of Technology and Management Artificial Intelligence and Machine Learning Greater Noida India Sharda University Computer Science and Engineering Greater Noida India Netaji Subhas University of Technology Computer Science and Engineering Delhi India

ISBN: (纸本)9798331508685

The antique adage "seeing is believing"is simply no longer actual, which has profound implications for a ramification of sides of our lives. Deepfakes are becoming less complicated and simpler to create as technology advances. In fact, with the right software program, you can do a part of it right out of your palm. it is challenging to pick out deepfakes. The capability of the human eye to differentiate among deepfakes has reduced. however, a few academics have tried to identify deepfake. Deepfakes are media that can be generated by synthetic intelligence (AI) using algorithms. artificial intelligence algorithms are designed to understand the traits of both the supply and the target photo. Subsequently, the target image is positioned on the pinnacle of the supply photograph. Our goal is to pick out video deepfakes by way of utilizing deep getting-to-know neural networks which include InceptionResNetV2 and LSTM. With the usage of transfer learning and the pre-trained InceptionResNetV2 CNN for characteristic extraction and vector production, we were able to efficaciously assemble a deepfake detection version. The capabilities had been used to train the LSTM layer, and the confusion matrix that was produced offers us the accuracy of testing and validation. The corresponding version's accuracy for 20 and 40 epochs was 84.75% and 91.48%, respectively. © 2025 IEEE.

关键词： Generative adversarial networks

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

Vortex Search Optimizer based Hybrid Watermarking Scheme for Securing the Medical Images 3

Vortex Search Optimizer based Hybrid Watermarking Scheme for...

引用

3rd IEEE Mysore Sub Section International Conference, MysuruCon 2023

作者： Murthy, G N Keshava Nalini, B.M. Madhura, G.K. Nayana, S.N. Siddaganga Institute of Technology Department of Electronics and Instrumentation Engineering Karnataka Tumakuru India East West Institute of Technology Department of Computer Science and Engineering Bengaluru560091 India Nitte Meenakshi Institute of Technology Artificial Intelligence and Machine Learning Bengaluru India

ISBN: (纸本)9798350340358

Preventing the duplication, modification, and claim of unauthorised ownership of digital content is one of the major issues caused by the growing use of computer capabilities. Watermarking is one way to put a visible or invisible watermark on a digital document in order to later show that the document is legitimate or belongs to its owner. concentrating on security issues in the storage and broadcast of images in the medical info scheme, as well as the special requirements for medical images for the protection of lesion regions. In this study, a hybrid watermarking strategy was presented utilising the Slantlet transform, randomised singular value decomposition, and optimisation methods (Vortex Search algorithm (VSA)) that are modelled after natural processes. The XOR encryption method is used to encrypt the watermark image. Extensive testing demonstrates that our novel approach works better than the current approaches based on the NC, SSIM, and PSNR. The PSNR of the suggested technique is between 58 and 59 dB, suggesting increased performance, and at a scale factor of 0.06, the SSIM and NC standards of the watermarked picture and the extracted watermark are nearly equal to. The recommended method outperforms past studies in the field in terms of usability, robustness, security, and invisibility, as well as its ability to repel local nonlinear geometric attacks. © 2023 IEEE.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

HealthApex: Complete Healthcare Assistance With Consent Based Analytics

HealthApex: Complete Healthcare Assistance With Consent Base...

引用

2023 International Conference on System, Computation, Automation and Networking, ICSCAN 2023

作者： Ramaprabha, J. Prema, P. Gunasekar, S. Srmist Department of Computing Technologies Chengalpattu Kattankulathur India Panimalar Engineering College Department of Information Technology Chennai India New Horizon College of Engineering Department of Artificial Intelligence and Machine Learning Karnataka Bengaluru India

ISBN: (纸本)9798350315127

HealthApex is an advanced web application in the field of health industry. It is a perfect amalgamation of artificial intelligence and Health System. This application consists of various modules for prediction of chronic diseases atan early stage. It uses a number of machine learning algorithms such as Decision Tree Classifier, Random Forest etc. It also comes with other features such as Real-Time COVID Dashboard and Old Age Care Unit. It also helps in locating nearby medical emergency services. A smart Sentiment and Communication Bot will interact with the users in real time regarding their health problem and will suggest the required assistance. Hence, this web application is made keeping in mind the wellbeing of general public. © 2023 IEEE.

关键词： learning systems

来源：评论

学校读者我要写书评

暂无评论

AI-Optimized Placement and Routing for PCB Design 9

AI-Optimized Placement and Routing for PCB Design

引用

9th International Conference on Science, technology, engineering and Mathematics, ICONSTEM 2024

作者： Sathyaraj, P. Arulkumar, S. Ajina, A. Beshir, Kedir Umasankar, L. Arularasan, A.N. Rmk College of Engineering And Technology Department of Electronics And Communication Engineering Tamil Nadu Puduvoyal601206 India Wachemo University Department of Electrical And Computer Engineering Ethiopia M S Ramaiah Institute of Technology Department of Artificial Intelligence And Machine Learning Bangalore560054 India S.A. Engineering College Department of Electrical And Electronics Engineering Tamil Nadu Tiruvallur600077 India Panimalar Engineering College Department of Artificial Intelligence And Data Science Tamil Nadu Chennai600123 India

ISBN: (纸本)9798350365092

Rapid electronic device development requires more complicated and densely packed PCB designs. These systems need properly placed and connected electrical components for best performance and reliability. Complexity and time restrictions are rendering manual methods ineffective. Therefore, AI-based PCB insertion and routing automation methods have been developed. This research suggests using AI to optimize PCB component arrangement and routing. The system uses machine learning and optimization to improve design efficiency. The AI system creates layouts that match performance requirements, decrease signal interference, and meet manufacturing limits using previous design data and user preferences. A learning module that updates its knowledge base, an algorithm that chooses between design objectives, and real-time user input are examples. Signal integrity, thermal issues, and manufacturability are considered while modifying design requirements. Evaluation of the suggested methodology shows considerable gains in design efficiency, time-to-market, and electronic system performance. This research improves AI-automated PCB design, enabling more complex and effective electrical systems. AI in PCB design will revolutionize the industry by solving complicated design problems and speeding up the development of cutting-edge electronics. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An Effective Expectation of Diabetes Mellitus via Improved Support Vector machine through Cloud Security

An Effective Expectation of Diabetes Mellitus via Improved S...

引用

2023 IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2023

作者： Lal N, Dayanand Hema, K. Spoorthi, T. Chegoni, Ramesh Madhura, K.G. Gitam School of Technology Gitam University Department of Computer Science & Engineering India Cmr Technical Campus Department of It Kandlakoya India Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India

ISBN: (纸本)9798350398465

Nerve pain, eye difficulties, skin issues, renal problems, heart disease, depression, and a host of other illnesses are all linked to diabetes if left untreated. In an effort to lengthen the human lifespan, scientists all around the world have applied a variety of methods for early disease prediction. Diseases of the eyes, heart, and kidneys are prioritised because they can cause serious consequences and even death if left untreated. After conducting an in-depth analysis of the strategies used by several researchers, the following models were constructed and tested using the datasets most frequently favoured by leading scientists throughout the world. Diabetic retinopathy (DR) is an eye condition, and this research seeks to construct a hybrid learning model for early prediction of DR. The proposed approach combines elements of both machine learning and Deep learning. Score Level Fusion is the last arbiter of the model's precision. Images from the first dataset of its sort reflecting the Indian population, the Indian Diabetic Retinopathy Imaging Dataset, were used to make the prediction. Predicting the DR and recommending the necessary treatment to patients is possible based on severity levels, which ultimately leads to the elimination of blindness. © 2023 IEEE.

关键词： Forecasting

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：