检索结果-内蒙古大学图书馆

Deep Learning Based License Plate Number Recognition for Smart Cities

computers, Materials & Continua 2022年第1期70卷 2049-2064页

作者： T.Vetriselvi E.Laxmi Lydia Sachi Nandan Mohanty Eatedal Alabdulkreem Shaha Al-Otaibi Amal Al-Rasheed Romany F.Mansour Department of Computer Science and Engineering K.Ramakrishnan College of TechnologyTrichy620002India Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Computer Science&Engineering Vardhaman College of Engineering(Autonomous)Hyderabad501218India Department of Informatics and Computing Singidunum UniversitySerbia Computer Science Department College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11564Saudi Arabia Information Systems Department College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11564Saudi Arabia Department of Mathematics Faculty of ScienceNew Valley UniversityEl-Kharga72511Egypt

Smart city-aspiring urban areas should have a number of necessary elements in place to achieve the intended *** controlling and management of traffic conditions,increased safety and surveillance,and enhanced incident avoidance and management should be top priorities in smart city *** the same time,Vehicle License Plate Number Recognition(VLPNR)has become a hot research topic,owing to several real-time applications like automated toll fee processing,traffic law enforcement,private space access control,and road traffic *** VLPNR is a computer vision-based technique which is employed in the recognition of automobiles based on vehicle number *** current research paper presents an effective Deep Learning(DL)-based VLPNR called DLVLPNR model to identify and recognize the alphanumeric characters present in license *** proposed model involves two main stages namely,license plate detection and Tesseract-based character *** detection of alphanumeric characters present in license plate takes place with the help of fast RCNN with Inception V2 ***,the characters in the detected number plate are extracted using Tesseract Optical Character Recognition(OCR)*** performance of DL-VLPNR model was tested in this paper using two benchmark databases,and the experimental outcome established the superior performance of the model compared to other methods.

关键词： Deep learning smart city tesseract computer vision vehicle license plate recognition

来源：评论

学校读者我要写书评

暂无评论

Enhancing medical Image Diagnosis with Convolutional Neural Networks 2

Enhancing Medical Image Diagnosis with Convolutional Neural ...

引用

2nd IEEE International Conference on Advances in information Technology, ICAIT 2024

作者： Mahadevan, K. Pushparani, S. SashiRekha, K. Sivagami, V.M. Usharani, R. Department of Computer Science and Engineering CARE College of Engineering Tamil Nadu Trichy India Department of Computer Science and Engineering Meenakshi College of Engineering Tamil Nadu Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India Department of Information Technology Sri Venkateswara College of Engineering Tamil Nadu Chennai India Department of Computational Intelligence School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (纸本)9798350383867

This paper is a comparative analysis of medical image diagnosis algorithms with Convolutional Neural Networks (CNNs) and other methods;such as Support Vector Machine (SVM), Random Forest, and k-nearest Neighbors (k-NN) The study performs evaluations on datasets with multimodalities like medical images and diagnostic and various imaging modalities. Results shows that CNNs have the upper hand over traditional, static algorithms across several metrics that assesses the performance of the system such as accuracy, precision, recall, and F1. In particular, CNN precision was 90.5% while the recall was 93.7%, and the accuracy was 92.1% as well as F1-score 92.0%. In addition, the high area under the Receiver Operating Characteristic curve (AUC-ROC) of over 0.95 for the CNN also signed for its excellent discriminatory power. These outcomes only exemplify CNN usefulness in the diagnostic area because it is an exact and accurate method for analyzing medical images. Although the nets CNNs are deployed in clinical cases may help address concerns regarding interpretability, compliance with regulations, and ethical opinions, such issues still exist and require further exploration. Overall, this research takes the first steps in directing algorithmic approach towards medical diagnosis and show the feasibility in deployment of CNNs as inseparable pieces of equipment in modern healthcare. © 2024 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

WSports-50: An Image Dataset for Women’s Sport Action Classification 4th

WSports-50: An Image Dataset for Women’s Sport Action Class...

引用

4th International Conference on Frontiers in Computing and Systems, COMSYS 2023

作者： Ray, Palash Bera, Asish Krejcar, Ondrej Bhattacharjee, Debotosh Nasipuri, Mita Department of Computer Science and Engineering Haldia Institute of Technology West Bengal Haldia India Department of Computer Science and Information Systems BITS Pilani Rajasthan Pilani India Center for Basic and Applied Science Faculty of Informatics and Management University of Hradec Kralove Rokitanskeho 62 Hradec Kralove500 03 Czech Republic Department of Computer Science and Engineering Jadavpur University West Bengal Kolkata India

ISBN: (纸本)9789819726134

Sport action recognition is an interesting area in computer vision. Categorization of sport actions, representing difficult and complex body postures, is regarded as a fine-grained visual classification problem. The Convolutional Neural Networks (CNNs) have attained enhanced performance over conventional feature descriptors in recognizing various sport activities. In general, though decent improvement has been gained using deep learning for sport action recognition, however, recognition of women’s sport activities is not widely explored. Even, no benchmark dataset depicting women’s sport action with sufficient variations is available yet for study. Hence, fine-grained image classification of diverse sport categories involving female/women athletics requires immediate research attention. To overcome this limitation, this paper proposes an image dataset comprising worldwide popular 50 sport categories of women players only. A simple deep learning model is proposed that extracts the high-level deep features using a backbone CNN. Then, these features are pooled from a collection of regular regions representing local discriminative information. The spatial pyramid pooling is applied for mining semantic information and enhancing feature aggregation for classification. The proposed method has achieved satisfactory performance on the Women Sports dataset using four standard backbone CNNs. Moreover, our method has achieved better accuracy on the Yoga-82 pose recognition dataset with a significant margin, e.g., 11.6% gain using ResNet-50 base CNN. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Analysis of Apt Attack for Source Tracing in Industrial Internet Environment 7

Analysis of Apt Attack for Source Tracing in Industrial Inte...

引用

7th International Conference on Contemporary Computing and informatics, IC3I 2024

作者： Shrivastava, Anurag Mittal, Tanusha Almusawi, Muntather Kumar, Yogendra Anandhi, R.J. Bhavana, Munugapati Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Tamilnadu Chennai India Graphic Era Deemed to be University Department of Computer Science & Engineering Dehradun India The Islamic university College of technical engineering Department of computers Techniques engineering Najaf Iraq Gla University Department of Electrical Engineering Mathura India New Horizon College of Engineering Department of Information Science Engineering Bangalore India Mlr Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India

ISBN: (纸本)9798350350067

As businesses become more dependent on networked digital devices, advanced persistent threats (APT) attacks are progressively becoming a component of the threat landscape. These types of attacks target essential pieces of infrastructure. This research paper presents an in-depth examination of source tracing in an industrial internet context, often known as an internet environment in the workplace. The purpose of this analysis is to reinforce the security posture against APT attacks. We are able to investigate a variety of strategies and procedures for tracing the origin of these assaults if we look closely at the fundamental aspects of advanced persistent threats (APT) attacks, such as entrance techniques, the spread of malware, and the removal of data. As a result of this, we investigate the essential aspects that comprise APT attacks. In addition, we discuss the challenges and limitations that are inherent to source tracing in industrial settings and provide workable solutions to these issues and limitations. Industrial companies will have the expertise and resources necessary to protect key infrastructure if advanced persistent threats can be effectively tracked down and neutralised. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Algorithms for Enhanced Precision in Automated medical Imaging Diagnoses to Improve Healthcare Outcomes 10

Deep Learning Algorithms for Enhanced Precision in Automated...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Neelaveni, P. Seethalakshmi, K. Rao, N.Venkatesvara Prabhu, M. Kanimozhi, K.V. Arunagiri, Bhuvaneswari Rajalakshmi Engineering College Department of Information Technology Chennai Thandalam India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Tamil Nadu Chennai India J.N.N.Institute of Engineering Department of Computer Science and Engineering Kannigaipair Chennai India Mohamed Sathak College of Arts and Science Department of Computer Science Tamil Nadu Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Adhiparasakthi Engineering College Department of Technology Tamil Nadu Melmaruvathur India

ISBN: (纸本)9798350353068

Over the last few years of when deep learning systems have been introduced into medical imaging procedures they are uncorrupted. They should be commended as the best ways of revolutionizing diagnosis processes and improving healthcare outcomes. This report focuses on detailed examination of deep learning for application to automated medical diagnostic, which is one of the most cutting-edge technology at present. Diverse input was the is collected by different kinds of modalities like X-ray, CT scan, MRI, and ultrasound. Also, this input modality is preprocessed to train and validate the proposed deep learning model. The network's architecture was appositely chosen, and the training strategy worked sense prep, which was made to improve the achieved success, included to the method of tuning and cross-validity was used. The qualitative analysis of accuracy, sensitivity and specificity was very good, which is a proof for a better performance of the novel method compared to the baseline ones. Furthermore, the qualitative data analysis and interpretability led to fundamental discussions on the model's performance and the decision-making procedure. Moreover, the model is of good generalizability, maintaining high accuracy on different datasets of validation group, therefore, it is predictive for clinical uses. Overall, this paper confirms wide application of deep learning methods in the field of machine learning-based medical diagnosis and highlights need of further research and development in the area of high tech ones which at present are highly dynamic by nature. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Algorithm-Driven Optimization of Cloud Computing Architectures for Superior Data Security and Efficiency 2

Algorithm-Driven Optimization of Cloud Computing Architectur...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Pillai, N. Muthuvairavan Jesu Jayarin, P. David, D. Beulah Jeeva, K. Kumari, V Sheeja R.M.D Engineering College Department of Computer Science and Business Systems KavaraipettaiTamil Nadu Thiruvallur India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Information Technology Tamil NaduThandalam Chennai India Care College of Engineering Department of Computer Science and Engineering Tamil Nadu Trichy India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil NaduThandalam Chennai India

ISBN: (纸本)9798350384277

This paper examines how algorithm-driven optimization transforms cloud computing systems, focusing on data security and efficiency. Following a thorough cloud environment study, algorithms were picked and adapted to solve specific difficulties. After integration into the architecture, these algorithms were tested in a controlled simulation environment. CPU utilization rose from 70% to 90%, memory from 65% to 85%, storage from 60% to 80%, and network bandwidth from 75% to 95%. These improvements improve computational and storage efficiency. Intrusion detection became AI-based, and encryption increased from 128-bit to 256-bit. Data breaches dropped from 5 to 1 per year, while security standards compliance increased from partial to full. These improvements strengthened cloud security. The system became more responsive from 200 to 100 ms. Server load distribution evened out, peak load handling improved, and user experience rating rose from 3.5/5 to 4.5/5. These enhancements highlighted optimized load *** consumption dropped 30%, lowering operational costs. High cooling requirements became moderate due to energy-efficient infrastructure. Sustainability goals were met by reducing annual carbon footprint by 30%. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Mining Road Traffic Accident Data for Prediction of Accident Severity

Mining Road Traffic Accident Data for Prediction of Accident...

引用

2023 International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2023

作者： Bahiru, Tadesse Kebede Manjula, V.S. Akele, Tadesse Birara Tesfaw, Engdaw Ayalew Belay, Tadesse Destaw Kombolcha Institute of Technology Wollo University College of Informatics Dept. of Information Technology Amhara Kombolcha Ethiopia Kombolcha Institute of Technology Wollo University College of Informatics Pg Dept of Computer Science Amhara Kombolcha Ethiopia Kombolcha Institute of Technology Wollo University College of Informatics Dept. of Information System Amhara Kombolcha Ethiopia Wachamo University School of Computing and Informatics College of Engineering and Technology Dept. of Information Technology SSNPR Hosaena Ethiopia

ISBN: (纸本)9781665474511

As World Health Organization reports show more than 1.3 million people die each year from traffic accidents and more than twenty to fifty million people are harmed by non-fatal accidents. Understanding and identifying the major factors of road traffic accidents can help the stakeholders to take appropriate measures to minimize the accidents. Support Vector Machine (SVM), J48, and Naïve Bayes (NB) classification techniques are implemented to build a model that predicts accident severities and to identify road traffic accident factors. As experimental findings showed weather conditions, number of lanes, road lighting conditions, and speed limit are the determinant factors that cause more accident severity. Finally, the classification and prediction performance of the models are compared using various performance evaluation techniques. J48 classifier has better classification performance than Support Vector Machine and Naïve Bayes classifiers. Naïve Bayes is the classifier that showed the lowest performance than others, but it has good performance in classifying fatal accident severities rather than serious and slight accident severities. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Proposed Framework for Modifications to Artificial Intelligence/Machine Learning (Ai/Ml)-Based Software as A medical Device (SAMD) 7

Proposed Framework for Modifications to Artificial Intellige...

引用

7th International Conference on Contemporary Computing and informatics, IC3I 2024

作者： Shrivastava, Anurag Jain, Upma Al-Farouni, Mohammed Kumar, Yogendra Anandhi, R.J. Bhavana, Munugapati Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Tamilnadu Chennai India Graphic Era Deemed to be University Department of Computer Science & Engineering Dehradun India The Islamic university College of technical engineering Department of computers Techniques engineering Najaf Iraq Gla University Department of Electrical Engineering Mathura India New Horizon College of Engineering Department of Information Science Engineering Bangalore India Mlr Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India

ISBN: (纸本)9798350350067

The rapid adoption of software as a medical device (SAMD) driven by artificial intelligence and machine learning has brought about a fundamental shift in the medical industry. This shift has the potential to greatly improve clinical outcomes and the quality of care provided to patients. This shift has been responsible for a number of key achievements made in recent times. When seen in this context, the proposed legal framework for revisions to the AI/ML-SAMD appears as an essential response to the malleability of these technologies. To successfully navigate the tough process of modifying AI/ML-SAMD with the assistance of this framework. It does this by taking into consideration the need for rapid regulatory scrutiny and making an attempt to combine the promotion of innovation with the simultaneous preservation of patient safety. In other words, it ensures that patient safety is protected while also encouraging innovation. This abstract provides a summary of the fundamental components of the framework, as well as a discussion of the significance of those components with regard to fostering the development of moral AI/ML-SAMD within the context of the healthcare ecosystem. The healthcare sector is undergoing a change as a direct result of artificial intelligence and machine learning, which are improving patient outcomes, diagnostic accuracy, and treatment options. The research emphasizes the significance of specific AI and ML applications as well as the sector's embrace of this paradigm-shifting technology. In addition, the regulatory framework that has been presented is an important step towards guaranteeing the safe use of AI and ML in the medical field. © 2024 IEEE.

关键词： Artificial Intelligence Compliance Guidelines Healthcare Innovation Machine Learning Modifications Patient Safety Regulatory Framework Software as a medical Device

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Cloud Computing through Blockchain-based Resource Allocation and Green Contracts

Energy-Efficient Cloud Computing through Blockchain-based Re...

引用

2024 IEEE International Conference on Recent Advances in science and engineering Technology, ICRASET 2024

作者： Manikandan, G. Swaminathan, Subbiah Kanimozhi, K.V. Seethalakshmi, K. Rao, N.Venkatesvara Srm Institute of Science and Technology College of Engineering and Technology Department of Career Development Centre Tamil Nadu Kattankulathur India Rajalakshmi Engineering College Department of Information Technology Tamil Nadu Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India J.N.N.Institute Of Engineering Department of Computer Science and Engineering Ushaa Garden Kannigaipair-Periyapalayam Highway Chennai India

ISBN: (纸本)9798350388602

The study that is being carried out is a blockchain resource allocation, green contract, and renewable energy integration into the cloud computing environments as a way to increase efficiency, sustainability, and stakeholders' satisfaction. Through empirical analysis, significant improvements were observed across various metrics: the resource usage rate is up to 90% from 75%, 20%-800 kWh/hour reduction in energy consumption, a 20% decrease in heat emissions to 400 kg CO2/hour, cost efficiency is improved by 20% to $8 per hour. Moreover, the renewable energy usage was at 50%, which was followed by 50% fossil fuel dependency, in contrast, and a 100% carbon offset. Integrity was ensured with security threats eliminated, reporting and audit became much more transparent and together with the standards the compliance was achieved. Stakeholders such as Providers and End Users experienced enhanced success as the level of satisfaction was made the same for both cloud service providers and consumers This research result highlights the importance of the utilization of the blockchain enabled solutions in the optimization of resources, reducing the energy consumption, promoting the wide-range use of the renewable sources of the energy, enhancing the sector security and transparency therefore improving the satisfaction levels of all stakeholders in the cloud computing operation. The cooperation between scientists and various stakeholders has remained the key factor for implementing sustainable ways that will benefit the industry. © 2024 IEEE.

关键词： Blockchain Cloud Computing Green Contracts Renewable Energy Integration Resource Allocation

来源：评论

学校读者我要写书评

暂无评论

Context-aware Container Orchestration in Serverless Edge Computing

Context-aware Container Orchestration in Serverless Edge Com...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Guan, Peiyuan Chen, Chen Chen, Ziru Cai, Lin X. Hao, Xing Taherkordi, Amir University of Oslo Dept. of Informatics Oslo Norway University of Cambridge Dept. of Computer Science and Technology Cambridge United Kingdom Illinois Institute of Technology Dept. of Electrical and Computer Engineering Chicago United States Northwest Univesity School of Information Science and Technology Xi'an China

ISBN: (纸本)9798350351255

Adopting serverless computing to edge networks benefits end-users from the pay-as-you-use billing model and flexible scaling of applications. This paradigm extends the boundaries of edge computing and remarkably improves the quality of services. However, due to the heterogeneous nature of computing and bandwidth resources in edge networks, it is challenging to dynamically allocate different resources while adapting to the burstiness and high concurrency in serverless workloads. This article focuses on serverless function provisioning in edge networks to optimize end-to-end latency, where the challenge lies in jointly allocating wireless bandwidth and computing resources among heterogeneous computing nodes. To address this challenge, We devised a context-aware learning framework that adaptively orchestrates a wide spectrum of resources and jointly considers them to avoid resource fragmentation. Extensive simulation results justified that the proposed algorithm reduces over 95% of converge time while the end-to-end delay is comparable to the state of the art. © 2024 IEEE.

关键词： Quality of service

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：