检索结果-内蒙古大学图书馆

Automatic liver-vessel examination from CT slice using Kapur’s thresholding and watershed algorithm

Procedia computer Science 2024年 235卷 1824-1831页

作者： Seifedine Kadry Laith Abualigah Rubén González Crespo Elena Verdú Robertas Damasevicius Vijendra Singh Venkatesan Rajinikanth Department of Applied Data Science Noroff University College Kristiansand Norway Artificial Intelligence Research Center (AIRC) Ajman University Ajman 346 United Arab Emirates Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Computer Science Department Al al-Bayt University Mafraq 25113 Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman 19328 Jordan MEU Research Unit Middle East University Amman 11831 Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang 11800 Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya 27500 Malaysia Higher School of Engineering and Technology Universidad Internacional de La Rioja Logroño 26006 Spain Department of Applied Informatics Vytautas Magnus University 53361 Kaunas Lithuania School of Computer Science University of Petroleum and Energy Studies Dehradun 248007 India Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai 602105 India

computerized medical image examination (CMIE) plays a significant role in modern hospitals to achieve the necessary tasks, like segmentation and classification. By segmenting an image, we can extract a particular section for examination. A two-dimensional computed tomography (CT) slice was used for liver-vessel examination (LiVE). A simple automatic technique for supporting LiVE is being developed in this research. A CT slice is collected, a 3D to 2D conversion is done, (ii) Kapur’s tri-level thresholding and Hummingbird-Optimizer is used to enhance the CT slice, (iii) the watershed algorithm (WA) is used to extract the vessel, and (iv) the WA is compared and verified against the segmentation methods chosen. WA provides better segmentation results than other methods because it is an automatic approach. Using the chosen image database, the proposed technique achieves an overall segmentation accuracy of >97%. Other segmentation problems can be used in the future to verify the merit of this scheme.

关键词： liver CT liver-vessel Kapur’s thresholding hummingbird-optimizer watershed-algorithm

来源：评论

学校读者我要写书评

暂无评论

Security Analysis of IoT Networks using Diffusion Kernel Spike Attention Network with Atomic Optimization based Intrusion Detection System

Security Analysis of IoT Networks using Diffusion Kernel Spi...

引用

Data Intelligence and Cognitive informatics (ICDICI), International Conference on

作者： Manju Sharma Monika Sharma Lavanya Pramod Sharma Shashikala Gurpur Syed Noeman Taqui Department of Computer Science and Engineering University Institute of Engineering and Technology Maharshi Dayanand University Rohtak Haryana India Department of Computer Engineering The Technological Institute of Textile and Sciences Bhiwani Haryana India Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Viruthunagar Tamil Nadu India School of Engineering & Technology University of Technology Jaipur Rajasthan India Faculty of Law Symbiosis Law School (SLS) Symbiosis International (Deemed University) (SIU) Pune Maharashtra India Department of VLSI Microelectronics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798350389609

ISBN: (纸本)9798350389616

Recently, the most prominent study areas are Internet of Things (IoT) and its applications. The attributes of the Internet of Things (IoT) facilitate its practical uses in real life, but also leave it vulnerable to online attacks. Numerous IoT nodes gather, store, and handle personal data, making them a prime target for hackers. The main objective of a network intrusion detection system is to find network intrusions, which is essential to guaranteeing the Internet of Things' security. Numerous investigators have tackled this issue and have put out numerous intrusion detection methods. Cyberattack subcategories are hard to identify and performance improvement is a challenge for the existing system. This research project introduces a new method for security analysis in Internet of Things networks by creating the Diffusion Kernel Spike Attention Network with Atomic Optimization (DifK-SAN+AO). This research employs a Diffusion Kernel Spike Attention Network to counteract cyberthreats and provides an overall threat analysis of the Internet of Things. The classification of threat and normal patterns on an IoT network is the main topic of this research study. For every form of attack, the proposed model shows promising findings. We use empirically based, simulation-generated datasets (ToN-IoT, BoT-IoT, and CIC-IoT-23 datasets) to detect attacks directed on the IoT ecosystem. In order to perform a security analysis, the results can be compared using the security metrics that are calculated, including the accuracy, precision, recall, and F1-score factors. The experimental results are more reliable than current algorithms and show 99.2% accuracy in detecting a variety of threats. As it would be observed from the results of the simulations, this demonstrates how efficient our method is in assessing the impacts of the attacks in IoT networks and maintaining good performance values.

关键词： Measurement Accuracy Heuristic algorithms Network intrusion detection Network security Threat assessment Internet of Things Reliability Kernel Optimization

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Advances aiding Recognition and Classification of Indian Monuments and Landmarks 8

Machine Learning Advances aiding Recognition and Classificat...

引用

8th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and computer engineering, UPCON 2021

作者： Paul, Aditya Jyoti Ghose, Smaranjit Aggarwal, Kanishka Nethaji, Niketha Pal, Shivam Dutta Purkayastha, Arnab Department of Computer Science and Engineering Bharati Vidyapeeth's College of Engineering New Delhi India Cognitive Applications Research Lab India Department of Computer Science and Engineering Srm Institute of Science and Technology Chennai India Department of Electronics and Communication Engineering Srm Institute of Science and Technology Chennai India

ISBN: (纸本)9781665409629

Tourism in India plays a quintessential role in the country's economy with an estimated 9.2% GDP share for the year 2018. With a yearly growth rate of 6.2%, the industry holds a huge potential for being the primary driver of the economy as observed in the nations of the Middle East like the United Arab Emirates. The historical and cultural diversity exhibited throughout the geography of the nation is a unique spectacle for people around the world and therefore serves to attract tourists in tens of millions in number every year. Traditionally, tour guides or academic professionals who study these heritage monuments were responsible for providing information to the visitors regarding their architectural and historical significance. However, unfortunately this system has several caveats when considered on a large scale such as unavailability of sufficient trained people, lack of accurate information, failure to convey the richness of details in an attractive format etc. Recently, machine learning approaches revolving around the usage of monument pictures have been shown to be useful for rudimentary analysis of heritage sights. This paper serves as a survey of the research endeavors undertaken in this direction which would eventually provide insights for building an automated decision system that could be utilized to make the experience of tourism in India more modernized for visitors. © 2021 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Incorporation of Agents with Ontology to Develop a Healthcare Assessment Provision System 6

Incorporation of Agents with Ontology to Develop a Healthcar...

引用

6th International Conference on Contemporary Computing and informatics, IC3I 2023

作者： Hole, Yogesh Shather, Alaa Alrubayi, Ali Hussein Sabah, Hawraa Ali Al-Ghanimi, Hayder Alchilibi, Haider S.N.G Institute of Management and Research Pune India Engineering Al Kitab University Department of Computer Engineering & Technology Altun Kopru Kirkuk Iraq Al-Esraa University College Forensic Sciences Department Baghdad Iraq National University of Science and Technology Dhi Qar Iraq Engineering Hilla University College Department of Medical Instrumentation Techniques Babylon Iraq Al-Farahidi University Medical Laboratory Techniques Department Baghdad10022 Iraq

ISBN: (纸本)9798350304480

Extracting useful patient information from a multitude of web pages and traditional hospital systems, and afterwards displaying these search results in a comprehensible manner, is a challenging undertaking. This is achieved via the implementation of conventional methodologies that aid in the anticipation of infections and ailments, such as heart attacks and several others. However, a disheartening aspect is that these conventional approaches were inadequate in detecting early indications of the human health system. The resolution to this issue may be found by utilizing an agent-based integration method, facilitated by the utilization of ontologies. This research focuses on the integration of data linked to human health, both structured and unstructured, using a suggested system that utilizes ontological-based agents. These agents work together to coordinate and semantically integrate external data sources. The process of integrating data leads to the derivation of new knowledge based on a set of rules, so transforming it into a multi-agent decision support system. The algorithm under consideration demonstrates the capability to forecast individuals'health state by analyzing their performed activities. The study provides a comprehensive analysis of a methodology that focuses on human daily activities, specifically targeting the improvement of cardiovascular health in individuals. © 2023 IEEE.

关键词： Data integration Decision support systems Healthcare Ontology

来源：评论

学校读者我要写书评

暂无评论

Development of a novel visual servoing probe test method for fault diagnosis of printed circuit boards

引用

IFAC-PapersOnLine 2023年第2期56卷 5248-5254页

作者： B. Tipary Á. Juniki F.G. Erdős E. Takács K. Németh Centre of Excellence in Production Informatics and Control Institute for Computer Science and Control Eötvös Loránd Research Network Budapest Hungary Department of Manufacturing Science and Engineering Faculty of Mechanical Engineering Budapest University of Technology and Economics Budapest Hungary University of Pannonia Veszprém Hungary

Printed circuit board (PCB) measurement and repair is a challenging task that requires experience and expertise to perform. PCB diagnosis and repair shops employ skilled operators to carry out the corresponding measurement tasks using measuring instruments (e.g., oscilloscopes, multimeters) in order to uncover the condition of a particular product. However, these tasks are often repetitive and meticulous, and additionally, the results need to be collected and carefully documented so that the gathered experience regarding the product can be re-used when the next product of the same type arrives into the shop. Nevertheless, the diagnosis of used PCBs is less researched and current flexible automation possibilities are limited. In this paper, a novel visual servoing probe test method and measurement tool are proposed to provide a flexible solution for PCB diagnosis with a higher level of automation. The aim of the approach is to reduce the burden on the operators by carrying out the repetitive measurement tasks and automatically storing the results while leaving the responsibility of measurement profile setup to the human expert. The proposed visual servo system uses manually teached-in measurement points, where template patterns are recorded using cameras, and it is capable of compensating positioning errors in the range of a couple of millimeters. The proof of concept of the proposed method is presented through motherboard measuring experiments, with a 99.7% success rate.

关键词： Flexible and reconfigurable manufacturing systems Quality assurance and maintenance Visual servo control Printed circuit board measurement Fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Improving Online Education in Educational Institutions through the Integration of Internet of Things (IoT)

Improving Online Education in Educational Institutions throu...

引用

International conference of Electronics, Communication and Aerospace technology (ICECA)

作者： Kottaimalai Ramaraj Ann Mathews Hp Lynsha Helena Pratheeba U Ramani K.L. Sujitha Thilagaraj M Department of Electronics and Communication Engineering Kalasalingam Academy of Research and Education Krishnankoil Tamilnadu India Department of Computer Science and Engineering CMR Institute of Technology Bengaluru India Department of Electrical and Electronics Engineering K Ramakrishnan College of Engineering Trichy India Department of Computer Science and Engineering MVJ College of Engineering Bengaluru India Department of Industrial Internet of Things MVJ College of Engineering Bengaluru India

ISBN: (数字)9798350367904

ISBN: (纸本)9798350367911

A key facilitating infrastructure for building intelligent structures that enable efficient in-person and virtual learning environments is the Internet of Things (IoT). The shift to smart learning, that includes IoT and Artificial Intelligence (AI) into the educational system, is enticing since it directly affects the motivation of learners, enrolment, participation, and in-depth understanding. Teaching and learning, management, examination, and class monitoring are only a few of the numerous issues that afflict conventional education. Many ingenious approaches to many facets of our lives are being made possible by modern advancements in information and communication technology (ICT); nonetheless, these imaginative concepts aren’t adequately incorporated into the framework of education. The COVID-19 pandemic scenario, in specific, has brought out the need for innovative, creative approaches in the field of teaching. The present research examines previous investigations in the field and discusses the following topics: (i) issues with the current educational system and potential fixes; (ii) the shift to smart learning; and (iii) scientific hurdles (such as technological and cultural barriers) in making the move to smart learning. In accordance with these outcomes, creative approaches to the issues with the conventional system-such as smart teaching, smart evaluation, smart school environment, and smart management-are presented. The business and academic community may now include IoT, AI, and ICT into smart learning owing to the aforementioned experimental research’s novel developments.

关键词： Training Technological innovation Electric potential Education Transforms Writing Regulation Information and communication technology Internet of Things Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Supply Chain Management Using Blockchain: Opportunities, Challenges, and Future Directions 2

Supply Chain Management Using Blockchain: Opportunities, Cha...

引用

2nd International Conference on informatics, ICI 2023

作者： Rajchandar, K. Shameem, A. Biswas, Piali Geetha, B.T. Arunkumar, J.R. Lakineni, Prasanna Kumar SR University Department of CS and AI Warangal Telangana India AMET University AMET Business School India Kolhan University Department of Commerce Jamshedpur Co-Operative College Jamshedpur Jharkhand India SIMATS Saveetha School of Engineering Department of ECE Tamil Nadu India Modern Institute of Technology and Research Centre Department of Computer Science and Engineering Alwar Rajasthan India GITAM University GITAM School of Technology Department of CSE Visakhapatnam India

ISBN: (纸本)9798350343830

Blockchain innovation is being proclaimed as a unique advantage. Numerous examiners see blockchain innovation as a troublesome creation. Blockchain innovation has grabbed the eye of scholastics, chiefs, and specialists the whole way across the world. Blockchain is widely regarded by these entities as a highly disruptive technology that is already reshaping businesses and their supply chain models. Blockchain has the potential to transform supply chain (SC) processes in various ways, such as enhancing SC provenance, improving security, and reengineering business operations. An increasing number of recent studies have explored the use of blockchain in supply chains. Some have shown significant awareness of blockchain's role in functional transparency across various sectors, including e-commerce, agriculture, and public administration. We emphasize the identification of valuable opportunities, potential cultural implications, the current state of the art in advancements, as well as significant trends and challenges. We research a few modern areas, including transportation, fabricating, and auto, flight, finance, innovation, energy, medical care, horticulture and food, online business, and schooling, among others, that can be effectively overhauled with blockchain. The main aim of the study presents a complete evaluation of 178 examination distributions and examines different components of blockchain innovation in SC and coordinated operations the board. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Hybrid Heuristic Optimization of Deep Learning Models for Robust Plant Disease Detection

Hybrid Heuristic Optimization of Deep Learning Models for Ro...

引用

Emerging Smart Computing and informatics (ESCI), Conference on

作者： K. Ananthajothi Pravin R. Kshirsagar Tan Kuan Tak Kailash Kumar Department of Computer Science and Engineering Rajalakshmi Engineering College Chennai India Department of Electronics & Telecommunication Engineering J D College of Engineering & Management Nagpur India Electrical Power Engineering Programme Singapore Institute of Technology Singapore College of Computing and Informatics Saudi Electronic University Riyadh Kingdom of Saudi Arabia

ISBN: (数字)9798331515683

ISBN: (纸本)9798331515690

Plant diseases directly affect farm output by lowering grain, fruit, and vegetable quality, threatening global food security. Thus, farmers inspect plant leaves with their eyes. Plant leaf monitoring is unreliable and error-prone. A multitude of deep learning algorithms have been developed to detect plant leaf diseases; however, most rely on low-resolution photos utilizing convolutional neural nets (CNNs). This research seeks to create an improved nine-layer the CNN network model for the accurate classification of leaf-related illnesses. A contrast enhancement approach is used to pre-process plant leaf pictures. Following binary thresholding, the pre-processed pictures are separated into leaf images and abnormality segmented using the "Enhanced U-Net (EU-Net)" approach. A Multilevel Feature Fusion Network Convolutional Neural Network (MFFN-CNN) is employed to categorize illnesses of leaves based on segmented images. The "Hybrid Leader Cat Swarm Optimization(HLCSO)" method improves U-Net parameter optimization. The effectiveness of the leaf diagnostic model is demonstrated experimentally employing a variety of factors through the use of numerous baseline approaches.

关键词： Deep learning Plant diseases Image segmentation Computational modeling Neural networks Convolutional neural networks Particle swarm optimization informatics Optimization Monitoring

来源：评论

学校读者我要写书评

暂无评论

An Exploratory Study of Diverse Models and Datasets for Transfer Learning based Image Classification on Sparse Data

An Exploratory Study of Diverse Models and Datasets for Tran...

引用

Moratuwa engineering research Conference (MERCon)

作者： Jathurshan Pathmarasa Udaya Wijenayake Ruchire Eranga Wijesinghe Bhagya Nathali Silva Department of Computer Engineering Faculty of Engineering University of Sri Jayewardenepura Nugegoda Sri Lanka Department of Electrical and Electronic Engineering Faculty of Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka Center for Excellence in Informatics Electronics & Transmission (CIET) Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Information Technology Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (数字)9798331529048

ISBN: (纸本)9798331529055

Transfer learning is a powerful technique for image classification, especially when dealing with limited data. However, selection of the best transfer learning approach and model remains challenging, since the strategy is highly influenced by the scenario. This work conducted a thorough analysis of four transfer learning approaches for binary classification, and multiclass classification using four pretrained models i.e. MobileNetV2, MobileNetV3Large, EfficientNetB0, and EfficientNetB5. The test accuracy was measured with respect to the sample size considering the effects of data augmentation and fine tuning. The key finding of the study revealed that data augmentation has improved the test accuracy by up to $11.8 \%$. Moreover, the lightweight models marked a breakthrough by outperforming large scale models’ accuracy for sparse data settings when fine tuning (FT) and data augmentation (DA) are applied appropriately. Hence, this work provides a comprehensive overview on selecting different transfer learning approaches for sparse data classification by exploring diverse models and datasets, while discussing the consequences and challenges for future real-world applications.

关键词： Knowledge engineering Accuracy Transfer learning Optical wavelength conversion Data augmentation Feature extraction Size measurement Data models Tuning Image classification

来源：评论

学校读者我要写书评

暂无评论

The Effectiveness of a Simplified Model Structure for Crowd Counting

arXiv

引用

arXiv 2024年

作者： Chen, Lei Gao, Xinghang Chao, Fei Chang, Xiang Lin, Chih-Min Gao, Xingen Lin, Shaopeng Zhang, Hongyi Lin, Juqiang The School of Opto-Electronic and Communication Engineering Xiamen University of Technology Xiamen China The Department of Artificial Intelligence School of Informatics Xiamen University Xiamen China The Department of Computer Science Institute of Mathematics Physics and Computer Science Aberystwyth University Aberystwyth United Kingdom The Department of Electrical Engineering Yuan Ze University Taoyuan City320 Taiwan

In the field of crowd counting research, many recent deep learning based methods have demonstrated robust capabilities for accurately estimating crowd sizes. However, the enhancement in their performance often arises from an increase in the complexity of the model structure. This paper discusses how to construct high-performance crowd counting models using only simple structures. We proposes the Fuss-Free Network (FFNet) that is characterized by its simple and efficieny structure, consisting of only a backbone network and a multi-scale feature fusion structure. The multi-scale feature fusion structure is a simple structure consisting of three branches, each only equipped with a focus transition module, and combines the features from these branches through the concatenation operation. Our proposed crowd counting model is trained and evaluated on four widely used public datasets, and it achieves accuracy that is comparable to that of existing complex models. Furthermore, we conduct a comprehensive evaluation by replacing the existing backbones of various models such as FFNet and CCTrans with different networks, including MobileNet-v3, ConvNeXt-Tiny, and Swin-Transformer-Small. The experimental results further indicate that excellent crowd counting performance can be achieved with the simplied structure proposed by us. Copyright © 2024, The Authors. All rights reserved.

关键词： Complex networks

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：