检索结果-内蒙古大学图书馆

Deep Learning and SVM-Based Approach for Indian Licence Plate Character Recognition

computers, Materials & Continua 2023年第1期74卷 881-895页

作者： Nitin Sharma Mohd Anul Haq Pawan Kumar Dahiya B.R.Marwah Reema Lalit Nitin Mittal Ismail Keshta Department of Electronics&Communication Engineering Chandigarh UniversityMohali140413India Department of Computer Science College of Computer and Information SciencesMajmaah University11952Al-MajmaahSaudi Arabia Department of Electronics&Communication Engineering DCRUST Murthal131039India Department of Transportation Engineering IITKanpur208016Uttar PradeshIndia Department of Computer Science Applications PIETSmalkha132102India Skill Faculty of Science and Technology Shri Vishwakarma Skill UniversityPalwal121102India Computer Science and Information Systems Department College of Applied SciencesAlMaarefa UniversityRiyadhSaudi Arabia

Every developing country relies on transportation,and there has been an exponential expansion in the development of various sorts of vehicles with various configurations,which is a major component strengthening the automobile *** is a developing country with increasing road traffic,which has resulted in challenges such as increased road accidents and traffic oversight *** the lack of a parametric technique for accurate vehicle recognition,which is a major worry in terms of reliability,high traffic density also leads to mayhem at checkpoints and toll plazas.A system that combines an intelligent domain approach with more sustainability indices is a better way to handle traffic density and transparency *** Automatic Licence Plate Recognition(ALPR)system is one of the components of the intelligent transportation system for traffic *** study is based on a comprehensive and detailed literature evaluation in the field of *** major goal of this study is to create an automatic pattern recognition system with various combinations and higher accuracy in order to increase the reliability and accuracy of identifying digits and alphabets on a car *** research is founded on the idea that image processing opens up a diverse environment with allied fields when employing distinct soft techniques for *** properties of characters are employed to recognise the Indian licence plate in this *** licence plate recognition,more than 200 images were analysed with various parameters and soft computing techniques were *** comparison to neural networks,a hybrid technique using a Convolution Neural Network(CNN)and a Support Vector Machine(SVM)classifier has a 98.45%efficiency.

关键词： Intelligent transportation system automatic license plate recognition system neural network random forest convolutional neural network support vector machine

来源：评论

学校读者我要写书评

暂无评论

Historical Arabic Images Classification and Retrieval Using Siamese Deep Learning Model

引用

computers, Materials & Continua 2022年第7期72卷 2109-2125页

作者： Manal M.Khayyat Lamiaa A.Elrefaei Mashael M.Khayyat Computer Science Department Umm Al-Qura UniversityMakkahSaudi Arabia Computer Science Department King Abdulaziz UniversityJeddahSaudi Arabia Electrical Engineering Department Faculty of Engineering at ShoubraBenha UniversityCairoEgypt Department of Information Systems and Technology College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia

Classifying the visual features in images to retrieve a specific image is a significant problem within the computer vision field especially when dealing with historical faded colored ***,there were lots of efforts trying to automate the classification operation and retrieve similar images *** reach this goal,we developed a VGG19 deep convolutional neural network to extract the visual features from the images ***,the distances among the extracted features vectors are measured and a similarity score is generated using a Siamese deep neural *** Siamese model built and trained at first from scratch but,it didn’t generated high evaluation ***,we re-built it from VGG19 pre-trained deep learning model to generate higher evaluation ***,three different distance metrics combined with the Sigmoid activation function are experimented looking for the most accurate method formeasuring the similarities among the retrieved *** that the highest evaluation parameters generated using the Cosine distance ***,the Graphics Processing Unit(GPU)utilized to run the code instead of running it on the Central Processing Unit(CPU).This step optimized the execution further since it expedited both the training and the retrieval time *** extensive experimentation,we reached satisfactory solution recording 0.98 and 0.99 F-score for the classification and for the retrieval,respectively.

关键词： Visual features vectors deep learning models distance methods similar image retrieval

来源：评论

学校读者我要写书评

暂无评论

A Novel Biased Probability Neural Network (BPNN) and Regularized Extreme Learning Machine (RELM) based Hearing Loss Prediction System

Iraqi Journal for Computer Science and Mathematics

引用

Iraqi Journal for computer science and Mathematics 2023年第2期4卷 56-71页

作者： Selvaganesh, N. Shanthi, D. Rajesh Pandian, N. Department of Information Technology Sri Venkateswara College of Engineering Tamil Nadu Sriperumbudur602117 India Department of Computer Science and Engineering PSNA College of Engineering and Technology Kothandaraman Nagar Tamil Nadu Dindigul624622 India Faculty of Engineering and Technology Karnataka Bengaluru560069 India

Hearing loss or hearing impairment is one of the most leading cause highly affecting the people around the world in present days. Additionally, this disease primarily affects children and adults, which has an impact on their daily lives, careers, education, and other aspects of their lives. Therefore, it has to be correctly identified and diagnosed so that early therapies can be given to save people's lives. The many kinds of automated hearing loss prediction/detection systems are created for this aim in conventional works. The majority of the current research focuses on applying prediction techniques based on machine learning and deep learning to diagnose diseases. Its shortcomings include challenging computational procedures, longer training and testing times, greater mis-prediction outcomes, and incorrect outputs. Therefore, the proposed work objects to develop a Human Age - Hearing Impairment & Level (HAHIL) prediction system by using the machine learning methodologies. In this study, we describe a computer-aided strategy to forecast hearing loss and then prevent it. Here, three distinct prediction models are deployed for age prediction, hearing loss detection, and its severity level prediction. The Biased Probability Neural Network (BPNN) technique is utilized to predict the age based on simulated human acoustical signals. Then, the Regularized Extreme Learning Machine (RELM) mechanism is deployed for predicting the hearing impairment by constructing the weight and target matrices. During evaluation, the performance of the proposed HAHIL prediction system is validated and tested by using various evaluation indicators. The effectiveness of our computer-aided hearing loss prediction methods has been proven to be very high and they can be applied to the actual application system. Also, it provides an increased accuracy up to 99%, which is highly superior than the existing prediction models. © 2023 Multidiscip. Sci. J. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Application of Stork Optimization Algorithm for Solving Sustainable Lot Size Optimization

引用

computers, Materials & Continua 2024年第8期80卷 2005-2030页

作者： Tareq Hamadneh Khalid Kaabneh Omar Alssayed Gulnara Bektemyssova Galymzhan Shaikemelev Dauren Umutkulov Zoubida Benmamoun Zeinab Monrazeri Mohammad Dehghani Department of Mathematics Al Zaytoonah University of JordanAmman11733Jordan Faculty of Information Technology Al-Ahliyya Amman UniversityAmman19328Jordan Department of Mathematics Faculty of ScienceThe Hashemite UniversityP.O.Box 330127Zarqa13133Jordan Department of Computer Engineering International Information Technology UniversityAlmaty050000Kazakhstan Faculty of Engineering Liwa CollegeAbu Dhabi41009United Arab Emirates Department of Electrical and Electronics Engineering Shiraz University of TechnologyShiraz***Iran

The efficiency of businesses is often hindered by the challenges encountered in traditional Supply Chain Manage-ment(SCM),which is characterized by elevated risks due to inadequate accountability and *** address these challenges and improve operations in green manufacturing,optimization algorithms play a crucial role in supporting decision-making *** this study,we propose a solution to the green lot size optimization issue by leveraging bio-inspired algorithms,notably the Stork Optimization Algorithm(SOA).The SOA draws inspiration from the hunting and winter migration strategies employed by storks in *** theoretical framework of SOA is elaborated and mathematically modeled through two distinct phases:exploration,based on migration simulation,and exploitation,based on hunting strategy *** tackle the green lot size optimization issue,our methodology involved gathering real-world data,which was then transformed into a simplified function with multiple constraints aimed at optimizing total costs and minimizing CO_(2) *** function served as input for the SOA ***,the SOA model was applied to identify the optimal lot size that strikes a balance between cost-effectiveness and *** extensive experimentation,we compared the performance of SOA with twelve established metaheuristic algorithms,consistently demonstrating that SOA outperformed the *** study’s contribution lies in providing an effective solution to the sustainable lot-size optimization dilemma,thereby reducing environmental impact and enhancing supply chain *** simulation findings underscore that SOA consistently achieves superior outcomes compared to existing optimization methodologies,making it a promising approach for green manufacturing and sustainable supply chain management.

关键词： Optimization supply chain management sustainable lot size optimization bio-inspired metaheuristic stork

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence based machine learning algorithm for prediction of cancer in female anatomy

引用

Multimedia Tools and Applications 2025年第16期84卷 15735-15761页

作者： Ghantasala, G S Pradeep Hung, Bui Thanh Chakrabarti, Prasun R, Sathiyaraj Pellakuri, Vidyullatha Department of Computer Science and Engineering Alliance College of Engineering and Design Alliance University Karnataka Bangalore India Data Science Laboratory Faculty of Information Technology Industrial University of Ho Chi Minh city Ho Chi Minh City Viet Nam Deputy Provost ITM SLS Baroda University Gujarat Vadodara India Department of CSE GITAM School of Technology GITAM University Bengaluru India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram Guntur India

Breast and cervical cancers account for more than 85 percent of all cancer-related fatalities in developing nations, according to the World Cancer Research Fund. As a result, breast and cervical cancer have become one of the leading causes of mortality among women worldwide. This field is still in its infancy, with only a few studies in gynaecology and computer science looking into the detection of breast and cervical cancer. According to the researchers, medical records and early testing from individuals with breast and cervical cancer will be used in this study to determine the prognosis of those suffering from the diseases. To assess our cervical cancer predictions, we employed machine learning models such as Optimized Hybrid Ensemble Classifier (OHEC), which were trained on patient behavior and variables revealed to be associated with patient behavior. The datasets in this study have a substantial number of missing values, and the distribution of those values has been altered as a function of the missing values. OHEC classifier performance has been shown to improve when the number of features is reduced and the problem of high-class imbalance is resolved, because the accuracy, sensitivity, and specificity of the classifier, as well as the number of false positives, were used to demonstrate the success of feature selection in the suggested model's predictive analysis. This has been demonstrated through the use of numerous tests involving categorization challenges. The study underscores the critical significance of early detection and prognosis in combating breast and cervical cancers, which remain leading causes of mortality worldwide. Through the utilization of machine learning models like the OHEC, the authors have demonstrated the potential for improved predictive accuracy and clinical outcomes. The findings highlight the importance of addressing challenges such as missing data and class imbalance in enhancing the performance of predictive models for effective

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Electricity Consumption Classification using Various Machine Learning Models

EAI Endorsed Transactions on Energy Web

引用

EAI Endorsed Transactions on Energy Web 2024年 11卷 1-6页

作者： Paikaray, Bijay Kumar Jena, Swarna Prabha Mondal, Jayanta Van Thuan, Nguyen Tung, Nguyen Trong Mallick, Chandrakant Bhubaneswar India Department of Electronics and Communication Engineering Centurion of University of Technology and Management Odisha India School of Computer Engineering KIIT Deemed to be University Bhubaneswar India Faculty of Engineering Technology Hung Vuong University Viet Nam Quality Assurance Dong A University Viet Nam Department of Computer Science & Information Technology GITA Autonomous College Odisha Bhubaneswar India

INTRODUCTION: As population has increased over successive generations, human dependency on electricity has increased to the point where it has become a norm and indispensable, and the idea of living without it has become unthinkable. OBJECTIVES: Machine learning is emerging as a fundamental method for performing tasks autonomously without human intervention. Forecasting electricity consumption is challenging due to the many factors that influence it;embracing modern technology with its heavy focus on machine learning and artificial intelligence is a potential solution. METHODS: This study employs various machine learning algorithms to forecast power usage and determine which method performs best in predicting the dataset based on different variables. RESULTS: Eight models were tested, including Linear Regression, DT Classifier, RF Classifier, KNN, DT Regression, SVM, Logistic Regression, and GNB Classifier. The Decision Tree model had the greatest accuracy of 98.3%. CONCLUSION: The Decision Tree model’s accuracy can facilitate efficient use of electricity, leading to both conservation of electricity and cost savings, and be a guiding light in future planning. Copyright © 2024 Paikaray, B.K. et al., licensed to EAI. This open-access article is distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transforming, and building upon the material in any medium so long as the original work is properly cited.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of Homomorphic Encrypted Convolutional Neural Network Inference Among HElib, Microsoft SEAL and OpenFHE

Performance Comparison of Homomorphic Encrypted Convolutiona...

引用

2023 IEEE Asia-Pacific Conference on computer science and Data engineering, CSDE 2023

作者： Zhu, Haoyun Suzuki, Takuya Yamana, Hayato Waseda University Department of Computer Science Tokyo Japan Waseda University Department of Computer Science and Communications Engineering Tokyo Japan Waseda University Faculty of Science and Engineering Tokyo Japan

ISBN: (纸本)9798350341072

Homomorphic encryption (HE) offers a promising solution for maintaining data privacy even during calculation, as it allows for the evaluation of ciphertexts. Several HE libraries have been released, but selecting the best-suited library for HE beginners can be challenging. This paper provides insights into the selection process by comparing three popular HE libraries: HElib, Microsoft SEAL, and OpenFHE. To evaluate the performance of these libraries, we implemented a convolutional neural network inference using each of the three libraries and analyzed its latency. Our experimental results show that Microsoft SEAL achieves the shortest latency, less than 56% of OpenFHE and less than 17% of HElib. In terms of ease of use, OpenFHE surpasses the other libraries because it eliminates the need for programmers to consider rescaling during calculations and has more choices on different key-switching algorithms. In contrast, utilizing automatic rescaling with OpenFHE results in 5x longer latency than manual rescaling. © 2023 IEEE.

关键词： Libraries

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Neurological Diagnostics: Integrating 6G Technology with Deep Learning for Enhanced Detection of Multiple Sclerosis and Myelitis

Revolutionizing Neurological Diagnostics: Integrating 6G Tec...

引用

2024 International Telecommunications Conference, ITC-Egypt 2024

作者： Noureldeen, Rana M. Elshshtawy, Rahma A. Elgohary, Omnia A. Wahba, Fatma Alzahraa A. Attia, Marco K. Abo Elazm, Zeinab B. Khattap, Mohamed G. Galal Eldeen Mohamed Ali Hassan, Hend Mostafa, Mariam Ibrahim, Nayra Ramadan, Reem Refaat, Yomna Khaled, Mennatallah Maher, Ali Abd Elaziz, Mohamed Gamal Abdellatif Ibrahim, Ahmed Faculty of Applied Health Sciences Galala University Suez435611 Egypt Faculty of Computer Science and Engineering Galala University Suez435611 Egypt Artificial Intelligence Science Program Faculty of Computer Science and Engineering Galala University Suez435611 Egypt Air Defense College Department of Electronics and Electrical Communications Engineering Alexandria Egypt

ISBN: (纸本)9798350351408

This paper proposes an alternative detection frame-work for multiple sclerosis (MS) and idiopathic acute transverse myelitis (ATM) within the 6G-enabled Internet of Medical Things (IoMT) environment. The developed framework relies on the implementation of a deep learning technique known as Dense Convolutional Networks (DenseNets) in the 6G-enabled IoMT to enhance prediction performance. To validate the performance of DenseNets, we compared it with other deep learning techniques, including Convolutional Neural Networks (CNN) and MobileNet, using real-world datasets. The experimental results show the high performance of DenseNets in predicting MS and ATM compared to other methods, achieving an accuracy of nearly 90 %. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Broken Rotor Bar Fault Detection in Induction Machines Based on Rectified Three-Phase Stator Currents 10

Broken Rotor Bar Fault Detection in Induction Machines Based...

引用

10th International Conference on Signal Processing and Intelligent Systems, ICSPIS 2024

作者： Hajnayeb, Saeed Amerian, Fatemeh Marzebali, Mohammad Hoseintabar Abolghasemi, Vahid Seyyedbarzegar, Seyyed Meysam Shahrood University of Technology Faculty of Electrical Engineering Department Shahrood Iran School of Computer Science and Electronic Engineering Department University of ESSEX Colchester United Kingdom

ISBN: (纸本)9798331532543

Induction machines are widely used in industrial and household applications due to their efficiency in electromechanical energy conversion. However, broken rotor bars can significantly disrupt machine performance, typically manifesting as sideband harmonics near the fundamental frequency which can be utilized for fault detection. Nonetheless, frequency leakage can impede fault detection, concealing fault until substantial damage occurs. The proposed method, based on the rectified three-phase stator current (RTPSC), effectively reduces leakage frequency while maintaining the fault characteristic frequency (FCF) at its original amplitude. In addition, generate the fundamental harmonic at a frequency of 6 times. This approach aims to is to enhance diagnostic capabilities in the maintenance and monitoring of induction machines, improving operational efficiency and it also reduces the chance of catastrophic failures. The proposed methodology is tested on cases involving one, two, and three broken rotor bars, with the simulation results validated through experimental verification. © 2024 IEEE.

关键词： Stators

来源：评论

学校读者我要写书评

暂无评论

Selective Text Encryption Using RSA for E-governance Applications for Pdf Document

Selective Text Encryption Using RSA for E-governance Applic...

引用

International Conference on Network Security and Blockchain Technology, ICNSBT 2023

作者： Adhikari, Subhajit Karforma, Sunil Assistant Professor BSH Department Institute of Engineering and Management University of Engineering and Management Kolkata India Research Scholar Department of Computer Science University of Burdwan Burdwan India Faculty Department of Computer Science The University of Burdwan Burdwan India

ISBN: (纸本)9789819944323

When data travels through an insecure medium, security must be enforced. The confidentiality of the exchanged data must be guaranteed with the help of encryption techniques. Selective encryption is a very powerful tool for encrypting textual data in a resource constrained environment. In the context of e-governance, textual data is very important and must be protected from any kind of security threat using selective text encryption. In this paper, a fast and efficient selective encryption technique based on an RSA asymmetric key encoding approach is presented. After fetching the whole textual information in the encryption phase, the user will search for a particular word or phrase using regular expression. After that, the selected data will be encrypted using the RSA-1024-bit algorithm and written to a new encoded document with the remaining text data. In the phase of decoding the data, only the encoded text of the document is considered. The experimental result confirms that the encrypting method is secure in terms of statistical security tests and fast in terms of computation time. Our encoding method can be implemented to encrypt any multimedia data like images, audio, and videos. This proposed technique can be used in IOT devices where resources are limited. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Cryptography

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：