检索结果-内蒙古大学图书馆

2024 International Conference on Communication, Computing and Internet of Things, IC3IoT 2024

作者： Mageswaran, J. Uma Indumathi, G. Kalpana, A.V. Elangovan, G. Lalitha, S.D. Nalini, S. Sohanda, Mayank Kumar Dept. of Computer Science Engineering Amrita School of Computing Vengal Campus Tiruvallur DistTamil Nadu India Srm Institute Of Science And Technology Ramapuram India Srm Institute Of Science And Technology Department Of Data Science And Business Systems Kattankulathur India R.M.K Engineering College Department Of Computer Science And Engineering India Srm Institute Of Science And Technolog Department Of Computing Technologies Kattankulathur India

ISBN: (纸本)9798350352689

Public bus stops in India are becoming more crowded due to the country's fast population expansion. People wait a long time for buses to come, then suddenly congregate around them when they do, packing the buses with people and pushing them up into the footboards, which causes accidents. An additional concern of overcrowding is theft. All of this is the result of numerous bus stops not having adequate information on when busses would arrive. The proposed work paves a very important role for the passengers. The passengers will be provided with the information of the arrival of next bus, seat occupancy and the total passengers inside the bus. The information about the seat occupancy, in-passengers and out-passengers is done with the help of Radio Frequency Identification (RFID) tags. The arrival of the next bus is determined by calculating the duration of the buses that are near using RFID readers placed in different bus stations. The count and the frequency will be interfaced in the web application. The passengers can check the application to know the occupancy and today's society where people can catch the right bus at the station and at the right time. This will solve the problems like waiting in bus stops and wasting time and going in a crowded bus. © 2024 IEEE.

关键词： Buses

来源：评论

学校读者我要写书评

暂无评论

Enhancing Credit Card Fraud Detection through LSTM-Based Sequential Analysis with Early Stopping

Enhancing Credit Card Fraud Detection through LSTM-Based Seq...

引用

Networking and Communications (ICNWC), International Conference on

作者： S. Jhansi Ida K. Balasubadra Skandarsini R R Lakshmi Narayanaa T Dept. of Computer Science and Business Systems RMK Engineering College Thiruvallur India Department of Information Technology RMD Engineering College Thiruvallur India

ISBN: (数字)9798350365269

ISBN: (纸本)9798350365276

There is still a serious problem with credit card fraud in the world of financial transactions, requiring innovative solutions to effectively detect and halt illicit behavior. This research presents a unique method of detecting credit card fraud by strategically implementing early pausing in a Long Short-Term Memory (LSTM) neural network. Leveraging the sequential dependencies inherent in transaction data, the LSTM model demonstrates remarkable efficacy in discerning fraudulent from legitimate transactions. The early stopping mechanism ensures that the model’s training halts at the optimal epoch, preventing over fitting and enhancing generalization. Our thorough analysis highlights the model’s versatility by demonstrating a dynamic compromise between recall and accuracy throughout training. Practical implications include enhanced fraud detection accuracy, reduced false alarms, and real-time decision support for financial institutions. The model’s adaptability and generalization make it a valuable asset in the ongoing battle against credit card fraud, contributing to a more secure financial environment. Future research directions may explore additional features and alternative architectures to further advance fraud detection capabilities.

关键词： Training Adaptation models Sequential analysis Credit cards Feature extraction Harmonic analysis Real-time systems

来源：评论

学校读者我要写书评

暂无评论

How does promoting the minority fraction affect generalization? A theoretical study of the one-hidden-layer neural network on group imbalance

arXiv

引用

arXiv 2024年

作者： Li, Hongkang Zhang, Shuai Zhang, Yihua Wang, Meng Liu, Sijia Chen, Pin-Yu The Dept. of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute United States New Jersey Institute of Technology United States The Dept. of Computer Science and Engineering Michigan State University United States IBM Research United States

Group imbalance has been a known problem in empirical risk minimization (ERM), where the achieved high average accuracy is accompanied by low accuracy in a minority group. Despite algorithmic efforts to improve the minority group accuracy, a theoretical generalization analysis of ERM on individual groups remains elusive. By formulating the group imbalance problem with the Gaussian Mixture Model, this paper quantifies the impact of individual groups on the sample complexity, the convergence rate, and the average and group-level testing performance. Although our theoretical framework is centered on binary classification using a one-hidden-layer neural network, to the best of our knowledge, we provide the first theoretical analysis of the group-level generalization of ERM in addition to the commonly studied average generalization performance. Sample insights of our theoretical results include that when all group-level co-variance is in the medium regime and all mean are close to zero, the learning performance is most desirable in the sense of a small sample complexity, a fast training rate, and a high average and group-level testing accuracy. Moreover, we show that increasing the fraction of the minority group in the training data does not necessarily improve the generalization performance of the minority group. Our theoretical results are validated on both synthetic and empirical datasets, such as CelebA and CIFAR-10 in image classification. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid ConvLSTM with Attention for Precise Driver Behavior Classification

Hybrid ConvLSTM with Attention for Precise Driver Behavior C...

引用

Artificial Intelligence and Knowledge engineering (AIKE)

作者： Ghulam Mustafa Seong-Je Cho Youngsup Hwang Dept. of Computer Engineering Sun Moon University Asan-si South Korea Dept. of Software Science Dankook University Yongin South Korea

Driving behavior classification plays an important role in many real-world applications, including traffic accident prevention, driver safety, usage-based insurance, and optimizing ridesharing services. In this research, we introduce a novel approach called Hybrid ConvLSTM with Attention for Driver Behavior Classification (HCLA-DBC), designed to achieve precise and reliable driver behavior classification. Our main focus is to distinguish three fundamental driving behavior classes: normal, drowsy, and aggressive, which play a vital role in supporting advanced driver-assistance systems (ADAS). To evaluate the performance of our proposed models, we conducted experiments using the publicly available UAH-DriveSet dataset. The evaluation comprised six distinct models, encompassing two machine learning models (SVM and Gradient Boosting) and four deep learning models (CNN, MLP, LSTM, and HCLADBC). Our HCLA-DBC model outperformed all other models and previous results on the same data. On the test data, it achieved an accuracy of 94.12%, precision of 94.24%, recall score of 94.12%, F1-score of 94.12%, and a macro-average ROC AUC of 98.83. These exceptional outcomes underscore the efficacy of our hybridized approach and its potential to significantly enhance driver behavior classification. The HCLA-DBC model not only promises new possibilities for driver behavior analysis but also paves the way for elevated ADAS capabilities and safer driving experiences.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Change Bit-dept. Procedure for Data Measured Preprocessing before Compression

Change Bit-Depth Procedure for Data Measured Preprocessing b...

引用

2022 IEEE International Multi-Conference on engineering, computer and Information Sciences, SIBIRCON 2022

作者： Levenets, Alexey V. Bondarenko, Vladislav V. Bahenov, Ruslan I. Belozerov, Oleg I. Belozerova, Svetlana I. Bogatenkov, Sergey A. Pacific National University Dept. Automation and System Engineering Khabarovsk Russia Sholom-Aleichem Priamursky State University Dept. Information Systems and Mathematics Birobidzhan Russia Far Eastern State Transport University Dept. Computer Technology and Computer Graphics Khabarovsk Russia South Ural State University Dept. Information Technology in Economics Chelyabinsk Russia

ISBN: (纸本)9781665464802

The paper proposes to change the bit-dept. of the original data sequence as a preprocessing of the measuring data, which is carried out before the compression procedure. In this case the digit capacity conversion is performed without accounting for the primary data sample boundaries. The simulation was carried out in the Matlab software environment. The findings of the authors' research are presented. They prove to be a promising approach for some types of the studied data at least and several digit capacity values. The analysis of autocorrelation function values showing the data correlation revealed by the conversion is used as an assessment of perspective of the active conversion. In this article the authors review the values of secondary maximums of autocorrelation function. Their occurrence shows the demonstration of the implied correlative correspondence. Such correlations can potentially allow the converted data to be compressed more effectively than the original data using the known compression methods. © 2022 IEEE.

关键词： Data compression

来源：评论

学校读者我要写书评

暂无评论

Vulnerability Testing on IoT Networks Using Machine Learning Algorithm

Vulnerability Testing on IoT Networks Using Machine Learning...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing systems, ADICS 2024

作者： Mohandas, R. Prasanna, D.S.John Deva Baiju, B.V. Nathiya, S. Rajkumar, T. Dhiliphan Sivashankar, C. Srm Institiute Of Science And Technology Department Of Computational Intelligence Chennai Kattankulathur India Srm Institiute Of Science And Technology Department Of Datascience And Business Systems Chennai Kattankulathur India Vit University TamilNadu Vellore India Prince Shri Venkateshwara Padmavathi Engineering College Department Of Electronics And Communication Engineering Ponmar Chennai India Kalasalingam Academy Of Research And Education Dept. Of Computer Science And Engineering Tamilnadu Krishnankovil India Department Of Computer Science And Engineering Chennai India

ISBN: (纸本)9798350364828

The increasing growth of Internet of Things (IoT) devices has created a wide attack surface for cyber criminals to carry out more destructive cyber attacks;therefore, the number of cyber attacks in the information security industry is increasing rapidly. As attackers use new and innovative methods to launch cyber-oriented attacks, many of these strikes have succeeded in their malicious goals. Anomaly-based intrusion detection systems (IDS) use machine learning techniques to detect and classify attacks on IoT networks. Faced with unpredictable network technologies and various infiltration methods, traditional machine learning technologies are powerless. In abounding areas of research, kernel learning methods prove that they accurately determine pathological abilities. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

In-Home Cluttered Environment Gait Analysis using mm-Wave Radar

In-Home Cluttered Environment Gait Analysis using mm-Wave Ra...

引用

IEEE MTT-S International Microwave Bio Conference ((IMBIOC)

作者： Hajar Abedi Ahmad Ansariyan Plinio P Morita Jennifer Boger Alexander Wong George Shaker dept. Electrical and Computer Engineering University of Waterloo Waterloo Canada School of Public Health Sciences University of Waterloo Waterloo Canad dept. Systems Design Engineering University of Waterloo Waterloo Canada

ISBN: (数字)9798350351057

ISBN: (纸本)9798350351064

This paper presents a novel method for human gait analysis in cluttered in-home environments using mm-wave radar systems, leveraging novel signal processing and unsupervised machine learning to extract gait parameters accurately amidst obstacles, multipath, and ghosts. Our approach accurately identifies gait parameters such as stride length and walking speed while walking on a curvy path, outperforming traditional techniques. The findings highlight the potential of mm-wave radar for non-invasive, privacy-preserving gait monitoring, with significant implications for healthcare, elderly care, and ambient assisted living. This work advances human motion analysis technology and opens new avenues for in-home monitoring applications.

关键词： Legged locomotion Microwave technology Radar clutter Medical services Radar signal processing Sensors Biomedical monitoring

来源：评论

学校读者我要写书评

暂无评论

Towards Motor Imagery Classification of Finger Tapping by Both Hands for Controlling a Finger-Arm Bionic Robot

Towards Motor Imagery Classification of Finger Tapping by Bo...

引用

International Winter Workshop on Brain-computer Interface (BCI)

作者： Seong-Hyun Yu Young-Min Go Hyeong-Yeong Park Seo-Jin Lee Minji Lee Ji-Hoon Jeong Dept. Computer Science Chungbuk National University Cheongju Republic of Korea School of Computer Science Chungbuk National University Cheongju Republic of Korea Dept. Biomedical Software Engineering The Catholic University of Korea Bucheon South Korea

In motor imagery, the greatest attention was paid to decoding signals from large muscles. However, there is a missing piece in helping people with finger issues or paralysis. This study investigates the potential advancements in neurorehabilitation by exploring the discriminative capabilities of electroencephalography (EEG) based classification in finger tapping. To improve neurorehabilitation strategies, we performed a comparative analysis of finger tapping classification during motor imagery and execution tasks. Using EEG signals, we employed machine learning and deep learning techniques, including support vector machines (SVM), linear discriminant analysis (LDA) and EEGNet. Our results indicate promising differences in EEG signatures between the two paradigms, with SVM, LDA, and EEGNet demonstrating varying degrees of efficacy in classification. These findings suggest potential implications for customized neurorehabilitation interventions. The study contributes to the affirmative possibility of effective rehabilitation strategies and is of particular relevance for patients with impaired motor function.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Phishing URL Classification Using FastText Character Embeddings and Hybrid Deep Learning

Robust Phishing URL Classification Using FastText Character ...

引用

Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON), 2019 IEEE International Conference on

作者： Abdullah Al-Sakib Zishad Hossain Limon Anamul Sakib Md Nuruzzaman Pranto Md Ariful Islam Shayma Sultana Md. Redwan Ahmed Shafiur Rahman Dept. of Information Technology Westcliff University CA USA Dept. of Computer Science Westcliff University CA USA Dept. of Business Administration International American University CA USA Dept. of Management Information System International American University CA USA Dept. of Computer Science and Engineering East West University Dhaka Bangladesh Dept. of Software Engineering Daffodil International University Dhaka Bangladesh

ISBN: (数字)9798331534400

ISBN: (纸本)9798331534417

Phishing attacks are a major cybersecurity threat that resulted in over 1.2 million incidents in the first half of 2020. These attacks caused substantial financial losses and posed risks to individuals and organizations. Being able to identify fraudulent websites is crucial in order to effectively address these potential risks. This study introduces a novel method for detecting phishing URLs by using word and character embeddings to capture complex URL patterns. We used a dataset of 80,000 URLs, including 50,000 legitimate ones and 30,000 phishing instances, and applied thorough preprocessing techniques. We utilized word embeddings in FastText to handle unseen words, with the added advantage of n-gram representations. Additionally, we captured character-level features through dense character embeddings. We trained several machine learning and deep learning models, and one model, the Convolutional Bidirectional LSTM (CBiLSTM), stood out with an accuracy of 99.01% and an F1-score of 99.08%. Furthermore, we made a thorough comparison with the most advanced techniques available, and our findings demonstrated clear superiority over previous research. This study presents an effective approach for classifying phishing URLs, providing a valuable tool to combat fraud and protect against identity theft, thereby helping to minimize the financial and emotional harm experienced by victims.

关键词： Deep learning Uniform resource locators Training Adaptation models Phishing Prevention and mitigation Encoding Tokenization Real-time systems Robots

来源：评论

学校读者我要写书评

暂无评论

Malware Detection and Classification for Internet of Things Using Self-Attention Based Long Short-Term Memory 3

Malware Detection and Classification for Internet of Things ...

引用

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Sudhakar, K. Husain, Saif O. Babu, D. Raja Kumar, M. Ashok Dineshkumar, R. Nitte Meenakshi Institute Of Technology Dept. Of Ai & Ds Bengaluru India College Of Technical Engineering The Islamic University Department Of Computers Techniques Engineering Najaf Iraq Sr University Department Of Electrical And Electronics Engineering Warangal India Skyline University Nigeria Department Of Computer Science Software Engineering And Cyber Security Kano State Nigeria Saveetha School Of Engineering Saveetha Institute Of Medical And Technical Sciences Saveetha University Department Of Electronics And Communication Engineering Chennai India

ISBN: (纸本)9798350318609

The Internet of Things (IoT) connects numerous intelligent devices providing security features that interact with default settings accessed through applications. Additionally, Deep Learning (DL)-based mechanisms was involved for malware detection to identify and mitigate attacks. The Adaptive Synthetic Sampling (ADASYN) technique addresses class imbalances, especially when splitter class instances are distributed data in complex patterns. The proposed Self-Attention based Long Short-Term Memory (LSTM) classification method facilitates the handling of long-range dependencies in transferred data sequences offering high flexibility and adaptability to varying input lengths. For feature selection Particle Swarm Optimization (PSO) is utilized iteratively optimizes a solution in a high-dimensional space although it may have a low convergence rate due to its iterative process. The obtained results demonstrate the proposed Self-Attention based LSTM model achieves better accuracy reaching 98.05% on the NSL-KDD dataset and 99.01 % on the UNSW-NB15 dataset. These results ensure accurate classification compared to other existing methods, such as Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). © 2024 IEEE.

关键词： Internet of things

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：