检索结果-内蒙古大学图书馆

An effective object detection and tracking using automated image annotation with inception based faster R-CNN model

International Journal of Cognitive Computing in engineering 2024年第1期5卷 343-356页

作者： Vijiyakumar, K. Govindasamy, V. Akila, V. Department of Computing Technologies School of computing SRM institute of Science and Technology Kattankulathur campus Tamilnadu Chengalpattu district India Department of Information Technology Pondicherry Engineering College Pondicherry India Department of Computer Science and Engineering Pondicherry Engineering College Pondicherry India

The present study advances object detection and tracking techniques by proposing a novel model combining Automated Image Annotation with Inception v2-based Faster RCNN (AIA-IFRCNN). The research methodology utilizes the DCF-CSRT model for image annotation, Faster RCNN for object detection, and the inception v2 model for feature extraction, followed by a softmax layer for image classification. The proposed AIA-IFRCNN model is evaluated on three benchmark datasets: Bird (Dataset 1), UCSDped2 (Dataset 2), and Under Water (Dataset 3), to determine prediction accuracy, annotation time, Center Location Error (CLE), and Overlap Rate (OR). The experimental results indicate that the AIA-IFRCNN model outperformed existing models regarding detection accuracy and tracking performance. Notably, it achieved a maximum detection accuracy of 95.62 % on Dataset 1, outperforming other models. Additionally, it achieved minimum average CLE values of 4.16, 5.78, and 3.54, and higher overlap rates of 0.92, 0.90, and 0.94 on the respective datasets (1, 2 and 3). Hence, this research work on object detection and tracking using the AIA-IFRCNN model is essential for improving system efficiency and fostering innovation in the field of computer vision and object tracking. © 2024

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Blockchain Solutions for Decentralized Supply Chain Management: Challenges and Innovations 4

Blockchain Solutions for Decentralized Supply Chain Manageme...

引用

4th International Conference on Technological Advancements in Computational Sciences, ICTACS 2024

作者： Gupta, Ayush Kumar Agarwal, Ambuj Sharda School of Engineering and Technology Department of Computer Science and Engineering UP Greater Noida India

ISBN: (纸本)9798350387490

The article investigates how blockchain technology can be integrated into supply chain management (SCM) implementation. It brings to attention critical constraints impoverishing the traditional SCM methods such as unproductive nature, absence of ideas or information sharing, and centrally controlled decision making. The contemporary perspective uses the blockchain, specifically the Ethereum and Solana platforms, in attempts to enhance transparency, traceability, and efficiency. The use of smart contracts on Ethereum makes processes faster, thereby decreasing opportunities for loss and errors caused by waiting time during the transactions, but the transacting people face some limitations like expensive fees and slow speeds. Whereas Solana has the ability to quickly process transactions with lower fees, allowing for better use of real time applications in SCM, the platform supports a transaction throughput of 65000 TPS. Both platforms are discussed in the article while Solana is claimed to be better at cut-throat time factor, high volumes and the Proof of History mechanism helps in performance on cost efficiency and speed. The research goes on to suggest that Solana's transactions definitely have a potential of optimizing SCM by improving on the transparency factor, costs involved and collaboration among stakeholders. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Minimizing Grid Dependency and EV Charging Costs with PSO-Based Microgrid Energy Management

Minimizing Grid Dependency and EV Charging Costs with PSO-Ba...

引用

2024 IEEE East-West Design and Test Symposium, EWDTS 2024

作者： Khan, Abdul Moeed Bagheri, Mehdi School of Engineering and Digital Sciences Nazarbayev University Department of Electrical and Computer Engineering Astana Kazakhstan

ISBN: (纸本)9798331515768

Energy management in grid-connected systems Micro-grids (MG) has evolved rapidly in recent years as a result of environmental concerns, rising energy consumption, and the market liberalization of electricity merchandising. The Energy Management System (EMS) optimizes the utilization of MG's energy resources and power storage facilities in the supply-demand prices at the lowest cost possible. The purpose is to develop a Particle Swarm Optimization (PSO) EMS in MG, which assists in minimizing the dependence on the grid and decreasing the cost of Electric Vehicle (EV) charging by utilizing Renewable Energy Resources (RES) which comprises power production and power purchase from the electricity utility. An MG model for all over the distribution network contains photovoltaic (PV), wind turbine (WT), battery energy storage system (BESS), and various EVs, the load of which also varies. This paper analyzes the following operating conditions: The EV demand, the load and production variations, and the grid power costs to determine the effectiveness of an EMS that coordinates power from multiple sources. The study also supports the efficacy of the suggested EMS, as it proves that these systems contribute to the efficient EMS transactions with the grid, under the variety of pricing models and the integration of RES. In addition, the findings show that the integrated solution of the proposed PSO-based optimization decreases the costs by 8%. This recommends a scheduling strategy that lowers EV energy use and has a BESS charging /discharging management system during peak and off-peak hours. Also, the provision of EV charging is an effective way of cutting costs while at the same time preserving energy. © 2024 IEEE.

关键词： Battery storage

来源：评论

学校读者我要写书评

暂无评论

High-Frequency Power Loss Investigation of Pavement Materials in Roadway Inductive Charging System

引用

IEEE Transactions on Transportation Electrification 2025年第3期11卷 7475-7487页

作者： Zheng, Zilong Chen, Xiao Wang, Yao Zhang, Hua Wang, Hao Lu, Fei Drexel University Department of Electrical and Computer Engineering PhiladelphiaPA19104 United States The State University of New Jersey Department of Civil and Environmental Engineering at Rutgers New BrunswickNJ08901 United States Nanyang Technological University School of Electrical and Electronic Engineering Jurong West 639798 Singapore Lehigh University Department of Electrical and Computer Engineering BethlehemPA18015 United States

The rapid advancement of electric vehicles (EVs) offers a significant reduction in carbon emissions by replacing fossil fuels with more sustainable energy sources. This article studies wireless charging technology for EVs, focusing on high-frequency power losses. It presents an experimental investigation into the inductive power transfer (IPT) system’s efficiency under various pavement materials (specifically, asphalt and concrete), revealing significant power losses due to material electromagnetic properties. This research provides insights into optimizing IPT system design through empirical analysis of power losses across different frequencies and magnetic flux densities. Three main contributions are highlighted: quantifying power loss density, developing an empirical equation for magnetic losses, and identifying the significant impact of pavement materials on overall system efficiency. A 17.8-kW IPT system is implemented to measure and validate the power losses in pavement materials. This research underscores the critical need for interdisciplinary approaches to enhance the feasibility of IPT systems for future autonomous and smart city applications. © 2015 IEEE.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

Tomato Leaf Disease Detection Using CNN Models 4

Tomato Leaf Disease Detection Using CNN Models

引用

4th International Conference on Technological Advancements in Computational Sciences, ICTACS 2024

作者： Garba, Ahmad Ahmad Jain, Vihsal Singla, Kanika School of Engineering and Technology Sharda University Department of Computer Science & Engineering Greater Noida India

ISBN: (纸本)9798350387490

Tomato plants are vulnerable to different types of diseases, which can lead to significant reductions in yield and quality. Accurate and early detection is therefore crucial to mitigate these losses. This research proposes the use of deep learning approach for detecting tomato leaf diseases by utilizing Convolutional Neural Networks (CNNs). The study employs a custom CNN model and transfer learning techniques, and also utilize a large dataset of tomato leaf images. The proposed approaches showed promising result with high accuracy in distinguishing between healthy and diseased leaves. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Design and Development Museum Ticketing System (MTS) with Design Thinking Method 7

Design and Development Museum Ticketing System (MTS) with De...

引用

7th Information Systems International Conference, ISICO 2023

作者： Yudhanto, Yudho Pratisto, Eko Harry Purnomo, Fendi Aji Hidayat, Taufiqurrakhman Nur Haqimi, Nur Azizul Ardhi, Ovide Decroly Wisnu Department of Informatics Engineering Vocational School Universitas Sebelas Maret Surakarta57126 Indonesia

This research journal describes the process of providing solutions to museum ticketing problems with the application of an online ticket management system. The process of making this MTS (Museum Ticketing System) uses the Design Thinking method to complete the stages of making business processes with use cases, ERD (Entity Relationship Diagram), databases and their relations, programming with PHP, wireframes and UI/UX mockups. The final step is to carry out the functional testing process with the black-box method. And researchers tested the display using usability testing with the result of getting a value of 74.35 with 40 user respondents. © 2023 The Authors. Published by Elsevier B.V.

关键词： Design

来源：评论

学校读者我要写书评

暂无评论

Analysis of User Acceptance in Fire Extinguisher Simulation Applications with Virtual Reality Technology 7

Analysis of User Acceptance in Fire Extinguisher Simulation ...

引用

7th Information Systems International Conference, ISICO 2023

作者： Purnomo, Fendi Aji Pratisto, Eko Harry Yudhanto, Yudho Hidayat, Taufiqurrakhman Nur Ardhi, Ovide Decroly Wisnu Pratiwi, Almiraluthfi Department of Informatics Engineering Vocational School Universitas Sebelas Maret Surakarta57126 Indonesia

This article discusses the use of Virtual Reality (VR) applications to provide comprehensive training scenarios for emergency services such as fire extinguishers. This study presents an initial prototype with 3 levels of variations of fire models that help extinguish virtual fire as a VR training scenario. The Fire Extinguishing VR Application that has been developed is based on literacy technical provisions for fire management in urban areas by the State Minister for Public Works. The prototype provides a VR experience to application users based on the ease of use and learning of fire fighting through questionnaires. The results confirm the value of using VR for training procedures that are difficult to implement in the real world can be realized with 3 levels of fire simulation. A score with a percentage of 92% stated that the application was easy to recognize and use and a score of 89% stated that the application could be used to learn how to extinguish every variation of the fire level scenario that occurred. © 2023 The Authors. Published by Elsevier B.V.

关键词： Fire extinguishers

来源：评论

学校读者我要写书评

暂无评论

GAN-generated Synthetic Data and SVM-based Feature Selection for Improved Cardiovascular Disease Prediction

GAN-generated Synthetic Data and SVM-based Feature Selection...

引用

2023 Medical Technologies Congress, TIPTEKNO 2023

作者： Mandan, Amel Sulaiman Hazzaa, Nidhal Mohsin Yildiz, Oktay Informatics Institute Gazi University Computer Science Department Ankara Turkey Gazi University Faculty of Engineering Department of Computer Engineering Ankara Turkey

ISBN: (纸本)9798350328967

Early diagnosis requires cardiovascular disease forecasting. Past patient interests can improve machine learning predictions. This study uses a Generative Adversarial Network (GAN) to augment data to address the issue of insufficient datasets. Our objective is to use the GAN and feature selection (FS) to tackle the issue of class imbalance. The study assesses the efficacy of three different machine learning (ML) algorithms in predicting coronary artery disease (CAD). The UCI repository provided the Z-Alizadeh sani dataset for our analysis. A GAN was used to balance an imbalanced dataset. We used GAN to augment data and synthesise data to improve the models. Support Vector Machine (SVM) as feature selection tool was used to extract more effective attributes. We trained and tested CAD prediction using machine learning algorithms using 5-fold cross validation. We compared the machine-learning algorithm's outcomes with and without GAN-based data enhancement and feature selection to evaluate its predicted accuracy. According to results GAN and feature selection improved accuracy, sensitivity, and specificity for all algorithms, suggesting that generated data and selected attributes can identify positive and negative cases. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study of Artificial Intelligence and Cybersecurity on Bitcoin, Crypto Currency and Banking System

引用

Annals of Data Science 2024年第1期11卷 103-135页

作者： Choithani, Tamanna Chowdhury, Asmita Patel, Shriya Patel, Poojan Patel, Daxal Shah, Manan Department of Computer Science and Engineering Indus University Gujarat Ahmedabad India Department of Electrical Engineering Nirma University Gujarat Ahmedabad India Department of Electronics and Communication Engineering Nirma University Gujarat Ahmedabad India Department of Chemical Engineering School of Technology Pandit Deendayal Energy University Gujarat Gandhinagar382426 India

In recent years cryptocurrencies are emerging as a prime digital currency as an important asset and financial system is also emerging as an important aspect. To reduce the risk of investment and to predict price, trend, portfolio construction, and fraud detection some Artificial Intelligence techniques are required. The Paper discusses recent research in the field of AI techniques for cryptocurrency and Bitcoin which is the most popular cryptocurrency. AI and ML techniques such as SVM, ANN, LSTM, GRU, and much other related research work with cryptocurrency and Bitcoin have been reviewed and most relevant studies are discussed in the paper. Also highlighted some possible research opportunities and areas for better efficiency of the results. Recently in the past few years, artificial intelligence (AI) and cybersecurity have advanced expeditiously. Its implementation has been extensively useful in finance as well as has a crucial impact on markets, institutions, and legislation. It is making the world a better place. AI is responsible for the simulation of machines that are replicas of human beings and are intelligent enough. AI in finance is changing the way we communicate with money. It helps the financial industry streamline and optimize processes from credit judgments to quantitative analysis marketing and economic risk management. The main goal of this research has been investigating certain impacts of artificial intelligence in this contemporary world. It's centered on the appeal of artificial intelligence, confrontation, chances, and its influence on professions and careers. The research paper uses AI to enable banks to generate financial resources and to provide valuable customer services. The application of the growing Indian banking sector is part of everyday life made up of several banks like RBI, SBI, HDFC, etc. and these banks have digitally implemented using chat-bots that have brought benefits to the customers. © The Author(s), under exclusive licence t

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Securing the Future of Electronic Health Records with Blockchain Integration 3

Securing the Future of Electronic Health Records with Blockc...

引用

3rd International Conference on Trends in Electrical, Electronics and computer engineering, TEECCON 2024

作者： Khan, Andleeb Nand, Parma Bhushan, Bharat Sharda School of Engineering & Technology Department of Computer Science & Engineering UP Greater Noida India

ISBN: (纸本)9798331505714

The use of blockchain technology is meant to revolutionize the way in which traditional systems work. This technology has paved way for more secure solutions thereby leveraging the concepts of data privacy and authentication. Electronic health records are digitally stored health data of the patients which includes their history of diagnosis along with their reports generated by the hospitals. But these records also face the concerns of data privacy and security as they are prone to tempering, leakage and duplication. To address these concerns researchers have come up with the use of blockchain in electronic health records. Since blockchain is a decentralized and immutable ledger-based platform, it offers more secure and private solutions to the healthcare sector. This paper presents a framework based on blockchain for EHRs in order to enhance their security. It also makes use of Interplanetary file system as a distributed data storage platform which is compatible with Web 3 based environments. This addresses the issue of scalability of the system. The proposed framework proves to be better in terms of privacy, scalability, security and cost when compared with the recent literatures. This system can further be extended by integrating multi-factor authentication as a future direction for research. © 2024 IEEE.

关键词： Electronic health record

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：