检索结果-内蒙古大学图书馆

6th International Conference on Electrical engineering and Information and Communication Technology, ICEEICT 2024

作者： Najib, Taeef Muntasir, Fahim Wasi, Wasif Al Wazed Sidetrek Dhaka Bangladesh Brac University Dept. of Computer Science and Engineering Dhaka Bangladesh Rajshahi University of Engineering and Technology Dept. of Electrical and Electronic Engineering Rajshahi Bangladesh

ISBN: (纸本)9798350385779

Detecting surface faults on PCBs is critical for ensuring device dependability and performance. Manual PCB inspection methods like X-ray imaging struggle to ensure quality control due to limitations in speed and defect characterization. However, advanced automated technologies, such as object detection models like YOLOv8, have emerged as a more efficient solution. This study focuses on evaluating the performance of different YOLOv8 variants in identifying and classifying various defects on PCBs. A benchmark of how each modification of the model performs detection and the factors behind were investigated here. It was determined that, YOLOv8 is sensitive to the amount of data it is being trained on, as the larger models tend to overlearn on smaller datasets. YOLOv8-m had the best performance, 97.1% precision, concerning the time taken and epoch count, over others. Large YOLOv8 variants, such as YOLOv8x, are also computationally expensive. The models were trained for 200 epochs with a patience value set at 50. Both increasing the number of data points and the resources will improve the performance and facilitate the overall training procedures. A significant gap in automated electronics production is addressed by this study: precise PCB fault localization for higher reliability of the product. © 2024 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

An Investigation of Deep Neural Network based Techniques for Object Detection and Recognition Task in computer Vision 2

An Investigation of Deep Neural Network based Techniques for...

引用

2nd International Conference on Edge Computing and Applications, ICECAA 2023

作者： Sunil Kumar, Aithal S Mahesh, Kavitha St Joseph Engineering College Dept. of Computer Science and Engineering Mangalore India Nmam Institute of Technology Nitte Dept. of Computer Science and Engineering India Science and Engineering Nagarjuna College of Engineering & Technology Mudugurki Bengaluru India

ISBN: (纸本)9798350347579

Detection of objects and its recognition in visual sequences are the two critical tasks in the computer vision field. Various real-time applications such as autonomous vehicles, face recognition, health-care systems and space exploration requires highly reliable and precise object detection models. Traditional object detection and recognition algorithms are based on hand crafted and are considered to be erroneous, time consuming and expensive leading to the significant reduction of accuracy rate for object detection in large datasets. Recently, large number of promising deep neural networks models have been emerged for facilitating automated and accurate detection of varying scale objects and its precise recognition across various computer vision applications. Several GPU based neural models thereby incorporating context-aware capabilities have shown effective performance, which overcomes the drawbacks of traditional techniques. This research study provides an investigation of several popular deep learning models that exists for accurate object detection in various forms of visual sequences. Varying scale objects are detected frequently available in popular MS COCO and PASCAL datasets and their performance are evaluated utilizing one stage Yolo family and two stage Faster RCNN deep learning object detectors. At the end of the study, several future research directions for object detection task are discussed. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Predicting Mobile Prices with Machine Learning Techniques

Predicting Mobile Prices with Machine Learning Techniques

引用

2024 International Conference on Computational Intelligence and Computing Applications, ICCICA 2024

作者： Rana, Deepak Singh Dhondiyal, Shiv Ashish Singh, Sumeshwar Kukreti, Sanjeev Dhyani, Ashish Graphic Era Hill University Dept. Of Computer Science And Engineering Dehradun India Graphic Era Deemed To Be University Dept. Of Computer Science And Engineering Dehradun India Jaypee Institute Of Information Technology Dept. Of Computer Science And Engineering India Graphic Era Deemed To Be University Department Of Hospitality Management Uttrakahnd Dehradun India

ISBN: (纸本)9798350306446

Smartphones are increasingly vital to people on a daily basis. Telephones are utilized in all aspects of life, ranging from personal to professional, due to technological advancements. It serves a function beyond making phone calls. It enables internet connectivity and email reading. when not using the computer. The characteristics of a mobile phone are a crucial consideration when buying *** overall objective of this research is to find the best way to apply machine learning to estimate the retail pricing of smartphones based on their individual specs. Individuals who frequently use their phone are more attentive to selecting features. When purchasing a cell phone, a comparison is done based on the price-performance ratio. Phone features are regarded as performance. This research aims to forecast if mobile phones with certain features are considered economical or *** work is capable of being utilized in various marketing and business contexts to assist in making informed purchasing decisions by maximizing features while minimizing costs. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A 4x4 MIMO Antenna Array for the Wi-Fi7Access Point on a Metal Wall Application

A 4x4 MIMO Antenna Array for the Wi-Fi7Access Point on a Met...

引用

2024 International Symposium on Antennas and Propagation, ISAP 2024

作者： Su, Hsin-Lung Zhan, You-Sheng Dept. of Computer and Communication National Pingtung University Taiwan Dept. of Computer Science and Information Engineering National Pingtung University Taiwan

ISBN: (纸本)9798350364774

A 4×4 CPW MIMO Antenna array with an artificial magnetic conductor (AMC) reflector is presented for Wi-Fi7 access point on a metal wall application in the study. The 10-dB impedance of the integrated MIMO antenna array covers the Wi-Fi 7 operating bands, and the transmission coefficients are under -15 dB in the whole Wi-Fi7 bands. This proposed integrated MIMO antenna is low profile and has good total radiation efficiency (over 60%). The height of the integrated MIMO antenna array is 6.325 mm. © 2024 IEEE.

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

Network Intrusion Detection System Using Decision Tree and KNN Algorithm 3

Network Intrusion Detection System Using Decision Tree and K...

引用

3rd International Conference on Power Electronics and IoT Applications in Renewable Energy and its Control, PARC 2024

作者： Singh, Km Shivani Singh, Khundrapam Johnson National Institute of Technology Dept. of Computer Science and Engineering Manipur Imphal India

ISBN: (纸本)9798350309409

The complexity of attacks is increasing, making it increasingly difficult to effectively discover breaches. A network intrusion detection system is needed to handle the aforementioned problem. An automated software program called a network intrusion detection system alerts administrators when someone attempts to compromise the system by participating in hazardous behaviors. A system or network is protected from harmful invasions by hardware and software firewalls. They function like filters, removing any data that could put the system or network at risk. We aimed to design the best intrusion detection system possible so that it could distinguish between 'normal' and 'attacked' categories of network data with high accuracy. The best accuracy can be obtained by using soft computing techniques like Decision Trees and KNN. We tested a variety of techniques, such as preprocessing the data, feature selection, principal component analysis (PCA) reduction, standardization, and normalization, in order to increase our model's accuracy scores. We also assess the two approaches' results according to their accuracy in order to decide which way is more effective. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Arrhythmia Classification Using Graph Neural Networks Based on Correlation Matrix

Arrhythmia Classification Using Graph Neural Networks Based ...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Han, Seungwoo Tokyo University of Agriculture and Technology Dept. of Electrical Engineering and Computer Science Japan

ISBN: (纸本)9798350386226

With the advancements in graph neural network (GNN), there has been increasing interest in applying GNN to electrocardiogram (ECG) analysis. In this study, we generated an adjacency matrix using correlation matrix of extracted ECG features and applied a GNN to classify arrhythmias. Our work was compared with existing approaches from the literature. The results demonstrated that precision and recall for all arrhythmia classes exceeded 50%, suggesting that proposed method can be considered an approach for arrhythmia classification. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

An optimal group-wise non-rigid image registration technique based clinical decision support for dementia prediction

引用

Multimedia Tools and Applications 2025年 1-26页

作者： Mary, F. Sheeja Asanambigai, V. Fred, A. Lenin Assistant Professor Senior Grade School of Computing Dept. of CSE Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Chennai India Computer Science and Engineering Annamalai University Chidambaram India Dept. of CSE Mar Ephraem College of Engineering and Technology Marthandam India

The fundamental challenge in clinical practice is predicting whether patients with cognitive symptoms or impairment will improve or stay stable. Population ageing is a worldwide phenomena with various impacts. Among dementia, Alzheimer disease (AD) is common in the elderly which is the most common form of dementia and may contribute to 60–70% of cases. An early and precise AD diagnosis enhances patient quality of life. In this study, we propose an optimal group-wise non-rigid image registration technique for dementia (AD) prediction. We introduce an improved cuckoo search optimization (ICSO) algorithm to search optimal group-wise dense correspondence in large image sets in non-rigid image registration which reduce dimensionality of the search space. Then, we illustrate a teacher-student learning based optimization algorithm which cooperates with PLS regression to extract deformation which separates the relationship information suitable for each other from the raw relationship information. After that, we compute the distribution of morphologies of age by fitting smooth percentile curves to these scores using hybrid capsule neural network with least Median Square (hybrid CNN-LMS) curve fitting model. Finally, the simulation results of proposed hybrid CNN-LMS technique are compared to the existing methods to analyze the measures. We observed that the accuracy of our proposed hybrid CNN-LMS technique is 96.23% and 95.82% for RSS and ANDI datasets respectively. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

ML Assisted Web Application Firewall 12

ML Assisted Web Application Firewall

引用

12th International Symposium on Digital Forensics and Security, ISDFS 2024

作者： Kalariya, Pranav Jethva, Manthan Alginahi, Yasser University of Windsor Electrical and Computer Engineering Dept. Windsor Canada Computer Science Dept. Adrian College MI United States

ISBN: (纸本)9798350330366

This study presents the development and implementation of a sophisticated Web Application Firewall (WAF) empowered by machine learning techniques to bolster cybersecurity measures. Traditional WAFs primarily rely on rule-based systems, which may struggle to adapt to the evolving nature of web-based threats. In contrast, our proposed solution leverages machine learning algorithms to dynamically analyze and respond to emerging cyber threats, providing a more proactive and adaptive defense mechanism. The core functionality of the system involves the continuous monitoring of incoming web traffic, extracting relevant features, and utilizing a machine learning model to classify the traffic as either benign or malicious. The model is trained on historical data to recognize patterns and behaviors indicative of various cyber threats, including SQL injection, cross-site scripting, and other common attack vectors. Through this learning process, the system becomes adept.at discerning malicious activities and adapting its defense strategies accordingly. The proposed model helps achieve higher precision in identifying the threat requests from normal requests. © 2024 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Authentication and Authorization in Zero Trust IoT: A Survey 35

Authentication and Authorization in Zero Trust IoT: A Survey

引用

35th Irish Systems and Signals Conference, ISSC 2024

作者： James, Meha Newe, Thomas O'Shea, Donna O'Mahony, George D. Munster Technological University Dept. Computer Science Cork Ireland University of Limerick Dept. Electronic and Computer Engineering Limerick Ireland

ISBN: (纸本)9798350352986

A critical challenge in implementing Zero trust (ZT) in Internet of Things (IoT) environments is ensuring secure authentication and authorization mechanisms. The work in this article delves into the intricate realm of ZT by critically examining the state-of-the-art authentication and authorization processes within the ZT framework for IoT. Despite the wealth of work on ZT and Zero Trust Architecture (ZTA), notable research gaps persist, specifically in identity authentication and fine-grained access control. Given the vast and diverse ecosystem of IoT devices, device identification complexities arise from a lack of unique hardware identifiers, rendering traditional methods susceptible to cyber-attacks, such as, spoofing. For dynamic IoT environments, achieving the optimal implementation in access policies poses a significant challenge. Numerous ZTA methodologies, integrating access controls, blockchain frameworks, and advancements in Artificial Intelligence (AI) and Machine Learning (ML), have been implemented to tackle these challenges. However, research gaps remain, particularly in understanding the behavioral aspects within these frameworks. As a result, this article focuses on identifying how device behavioral aspects can improve authentication and authorization in ZT for IoT. Finally, the article concludes by highlighting how these challenges can serve as future research directions. © 2024 IEEE.

关键词： Authorization

来源：评论

学校读者我要写书评

暂无评论

Role of IoT in Smart Cities: A Review, Applications, Open Challenges and Solutions 3

Role of IoT in Smart Cities: A Review, Applications, Open Ch...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Vivek, Kolla Swetha, Gurrala Kumar M, V. T. Ram Pavan Veni, Anusuri Krishna Praveen, Neti Kale, Masthan Rao Dept. of Cse Andhra Pradesh Ongole India Dept. of Cse Telangana India Kakaraparti Bhavanarayana College Dept. of Computer Science Andhra Pradesh Vijayawada India Madanapalle Institute of Technology & Science Dept. of Computer Science & Engineering - Data Science Andhra Pradesh Madanapalle517325 India Srkr Engineering College Dept. of Computer Science and Design Andhra Pradesh Bhimavaram India Dept. of Cse Andhra Pradesh Ongole India

ISBN: (纸本)9798331509675

Smart cities have emerged as a response to the fast expansion of metropolitan areas;these places strive to improve the lives of their residents while simultaneously promoting environmentally responsible growth. To maximize urban services, the Internet of Things (IoT) is an essential technology that allows for the seamless integration of sensors, devices, and systems. This allows smart cities to become a reality. With an emphasis on smart transportation, energy management, healthcare, environmental monitoring, and public safety, this paper explores the critical role of IoT in smart cities. Data security, privacy, scalability, and interoperability are some of the problems that arise when smart cities use IoT, despite the revolutionary potential it has. These obstacles are thoroughly examined in this work, along with possible solutions to these problems. This study gives a thorough overview of the IoT and its impact on smart city development, innovation, and urban resilience by focusing on the present situation, applications, and unanswered questions. © 2025 IEEE.

关键词： Digital Technology Drainage Monitoring Fire detection Smart City Waste Management

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：