检索结果-内蒙古大学图书馆

Advances in Computing research on science engineering and technology (ACROSET), International Conference on

作者： Neha Sehta Krupi Saraf Aditya Vinchi Department of Computer Science and Engineering Acropolis Institute of Technology and Research Indore India

ISBN: (数字)9798350388800

ISBN: (纸本)9798350388817

Handwritten Digit Recognition (HDR) refers to the computer’ s ability to identify and categorize hand written digits from various sources into 10 predetermined categories, ranging from 0 to 9. The issue of digit recognition is significant and crucial. Due to variations in size, thickness, location, and orientation of manually written digits, several challenges need to be addressed in order to evaluate the problem of recognizing handwritten digits. The diversity and variety in the composition techniques of different persons also impact the pattern and appearance of the digits. It refers to the approach of recognizing and organizing written numbers. It offers a diverse array of uses, such as automated bank checks, postal addresses, and tax paperwork, among others. The objective of this research is to employ a classification system to accurately identify handwritten numerals. The consequences of the most widely employed deep learning algorithms, such as multilayered perceptron network, in conjunction with convolution neural networks, are being discussed. Comparison of five neural network classifier shows that accuracy up to 99% can be achieved only in few epochs of training with default configuration of hyper-parameters.

关键词： Training Deep learning Handwriting recognition Accuracy Convolution Neural networks Finance Distance measurement Classification algorithms Object recognition

来源：评论

学校读者我要写书评

暂无评论

Vessel Segmentation Approach with Deep Neural Network Model for Detection of Diabetic Retinopathy 4

Vessel Segmentation Approach with Deep Neural Network Model ...

引用

4th International Conference on Recent Trends in computer science and technology, ICRTCST 2021

作者： Pahadiya, Prasham Tiwari, Prakhar Singh, Prashant Gupta, Surendra Shri G. S. Institute Of Technology And Science Electronics And Telecommunications Engineering Indore India Acropolis Institute Of Technology And Research Computer Science And Engineering Indore India Shri G. S. Institute Of Technology And Science Computer Science And Engineering Indore India

ISBN: (纸本)9781665466332

Diabetic Retinopathy is one reason of avoidable vision loss that frequently affects working people around the world. Blood vessel segmentation aids in the early identification of retinal fundus pictures, which is critical for diagnosing a variety of eye disorders. In this study, several U-net-based methods for identifying vessel segmentation pictures from the original retinal images are suggested. Pre-processing, U-net based model construction, model testing, and model assessment are the four phases in the suggested model's procedure. The original retinal images are sent via pre-processing, which uses image augmentation to enhance the amount of training data available. To train the model, augmented pictures are input into a U-net based model, which consists of encoder-convolution-decoder layers that create a U shape. On the DRIVE and STARE dataset, sensitivity, specificity, and accuracy are used to evaluate the model. State-of-the-art approaches are used to evaluate the proposed models. In terms of sensitivity, the model fared best. The model scored 94.3 percent on the DRIVE dataset and 90.6 percent on the STARE dataset, outperforming current approaches. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition Using Deep Learning Model on Crowd

Facial Expression Recognition Using Deep Learning Model on C...

引用

2024 International Conference on Advances in Computing research on science engineering and technology, ACROSET 2024

作者： Shakyawar, Prashant Singh, Upendra Prestige Institute of Engineering Management & Research Department of Computer Science and Engg. Indore India Shri G. S. Institute of Technology and Science Department of Information Technology Indore India

ISBN: (纸本)9798350388800

In the field of computer vision, Facial Expression Recognition (FER) is an essential problem that automates emotion analyzing and understanding in human facial expressions. Facial occlusions, changing lighting conditions and overlapping facial attributes in crowded environments make it difficult to recognize the expression of emotions. In this research we are solving a problem of group friendly facial expression recognition using deep neural network models. We also tested a number of complex deep neural network architectures to learn fine-grained patterns and representations in human face videos or images. In training and testing these models, resources such as AffectNet which encompasses a broad spectrum of people with various facial expressions is utilized to make them robust against most general cases in crowds. The results of the deep neural network model are presented, revealing its ability to detect facial expressions efficiently with high accuracy and recall. This is supported by the performance of their models being around 80-94 % in terms of accuracy and F1-score, based on different studies. Their benefits involve deploying state-of-the-art architectures and performing robustly on large scale datasets;fusing multi-modal for improved recognition, learning temporal relationships will be well established technologies;scalability to resource-constrained environments. © 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

Revolutionizing Healthcare with Federated Learning: A Comprehensive Review

Revolutionizing Healthcare with Federated Learning: A Compre...

引用

Advances in Computing research on science engineering and technology (ACROSET), International Conference on

作者： Snehlata Mishra Ritu Tondon Narendra Pal Singh Rathore Computer Science & Engineering SAGE University Indore India Computer Science & Engineering Acropolis Institute of Technology and Reserach Indore India

ISBN: (数字)9798350388800

ISBN: (纸本)9798350388817

Federated learning has become a game-changing paradigm in healthcare, offering secure and private federated model training across dispersed data sources. This thorough analysis examines the uses, developments, and challenges of federated learning in healthcare. Beginning with an elucidation of its fundamental principles, we examine its potential to revolutionize healthcare delivery by facilitating collaborative model training without data sharing. We survey diverse applications, including disease diagnosis, personalized treatment recommendations, drug discovery, and population health management, highlighting federated learning's impact on improving patient outcomes and healthcare efficiency. Technological advancements, such as differential privacy and secure aggregation, driving federated learning adoption, are explored. Despite its promise, federated learning faces challenges including data heterogeneity, model communication overhead, privacy concerns, and regulatory barriers. We discuss these challenges and propose solutions and future research directions. This review provides a comprehensive understanding of federated learning's role in healthcare, addressing opportunities, limitations, and future prospects.

关键词： Training Federated learning Reviews Soft sensors Distributed databases Collaboration Medical services Data models Drug discovery Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

GAIT based human Parkinson’s disease detection using fused features with multi-kernel support vector machine

引用

International Journal of Information technology (Singapore) 2025年第3期17卷 1387-1395页

作者： Jhapate, Arun Kumar Shrivastava, Hemang Department of Computer Science and Engineering Sagar Institute of Research and Technology Madhya Pradesh Bhopal India Institute of Advance Computing SAGE University Madhya Pradesh Indore India

Gait analysis plays a pivotal role in the detection and monitoring of Parkinson’s disease (PD), offering insights into motor impairments characteristic of the condition. This study proposes a novel approach employing advanced feature extraction and machine learning algorithms to enhance the classification of PD depends on gait features. In this study, both local as well as global features are extracted from the gait images to facilitate a classification process. Local feature extraction is achieved using an optimized convolutional neural network (OCNN), while global feature extraction is done by the Swin Transformer architecture. To further improve feature extraction, an Adaptive Glowworm Swarm Optimization (AGSO) algorithm is applied to improve the performance of the CNN. The fused local and global features are then fed into a Multi-Kernel Support Vector Machine (MK-SVM) classifier, which serves as the core of the proposed model. The performance of the model is evaluated using the GAIT-IT datasets, assessing metrics such as accuracy, precision, recall, and F-measure. As a result of the proposed model, performance is superior to that of traditional methods in terms of accuracy and reliability, offering a promising approach for PD detection based on gait analysis. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Gait analysis Global features Local features Machine learning Multi kernel SVM Optimized CNN Parkinson’s disease Swin transformer

来源：评论

学校读者我要写书评

暂无评论

TypeScript: An Open-Source Programming Language with Options for Robust Development and Large-Scale Applications

TypeScript: An Open-Source Programming Language with Options...

引用

Advances in Computing research on science engineering and technology (ACROSET), International Conference on

作者： Shreyansh Kushwah Chanchal Bansal Shreyansh Rathore Vandana Kate Divyanshi Bargal Divesh Vishwakarma Dept. of Computer Science and Information Technology Acropolis Institute of Technology and Research Indore India

ISBN: (数字)9798350388800

ISBN: (纸本)9798350388817

JavaScript is widely used for web and application development but is criticized for its dynamic nature. TypeScript, an open-source language developed by Microsoft, addresses theseconcerns by introducing optional static typing. Released in 2012, TypeScript is a syntactical superset of JavaScript, offering features to enhance code quality and support large-scale applications. However, despite its benefits, the adoption of TypeScript is not without challenges. From a research perspective, further investigation is needed to understand the impact of TypeScript on software development practices, its integration with existing JavaScript codebases, and its effectiveness in improving overall software quality and developer productivity. Such research can provide valuable insights into the evolution of programming languages and their adaptation to changing technologies and industry demands.

关键词： Industries Productivity computer languages Codes Collaboration Software quality Software development management

来源：评论

学校读者我要写书评

暂无评论

Study of Machine Learning Classifiers for Intrusion Detection System 1

引用

3rd International Conference on Data, engineering, and Applications, IDEA 2021

作者： Mishra, Akshita Thakur, Archana Acropolis Institute of Technology and Research Madhya Pradesh Indore India School of Computer Science & IT Devi Ahilya University Madhya Pradesh Indore India

ISBN: (数字)9789811946875

ISBN: (纸本)9789811946868

Intrusion detection systems are an important part of our network security system. Furthermore, with the development in technologies, new attacks have been developed and attack types have also changed, hereby affecting more people and organizations. Cyber security research studies have been working on strengthening intrusion detection systems and intrusion detection methods. Machine learning has become a boon for this area also and is being actively applied to improving intrusion detection systems. Zero-day attacks or novel attacks have become a major problem. Therefore, machine learning methods need to be trained with newer attacks for detecting novel attacks quickly. Hence, we have used the CICIDS 2017, dataset which consists of many cutting-edge intrusions for testing and training purposes. In this work, we have concentrated on Supervised Machine Learning Classifiers and have selected 8 classifiers based on various works of literature available. These classification models have been evaluated on the basis of training time, testing time, train score, accuracy, and area under curve. As the result of this work, it has been found that decision trees and random forest have achieved an accuracy of almost 99% and within a considerable time limit. This work of ours is mainly concentrated on the use of classifiers for the intrusion detection system. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Exploring Agile Methodologies in Educational Software Development- A Comparative Analysis and Project Management Insights

Exploring Agile Methodologies in Educational Software Develo...

引用

International Conference on ICT in Business Industry & Government (ICTBIG)

作者： Vandana Kate Shilpa Bhalerao Vanshika Sharma Dept. of Computer Science and Information Technology Acropolis Institute of Technology and Research Indore India Dept. of Computer Science and Technology Acropolis Institute of Technology and Research Indore India

In the realm of academic research, the task of determining the most suitable Software Development Life Cycle (SDLC) becomes complex, owing to the diverse project requirements, rapidly changing technology, team skills and experience, organizational culture and readiness, flexibility and adaptability needs, and decision-making complexity. It requires a thorough analysis of various factors to make a wise decision that aligns with the project's goals and constraints. A variety of models, including Waterfall, Prototyping, and Spiral, offer distinct sets of advantages and disadvantages. Agile modeling is a flexible and iterative software development strategy that emphasizes collaborative modeling and rapid feedback. The agile philosophy promotes transparency, effective communication, and embracing change to meet evolving project needs efficiently and effectively. An In-Depth Examination of Agile Methodologies versus Conventional Approaches gives a deeper understanding of their respective strengths, weaknesses, and applicability. Also as the educational institutes increasingly recognize the importance of providing industry-relevant skills and preparing students for dynamic work environments, agile methodologies are likely to play a vital role in shaping the future of education and fostering the success of students in their careers. In this paper, we have explored the practical application of well-established Agile methodologies including Scrum, Kanban, Lean, Extreme Programming (XP), Feature Driven Development, and Dynamic Systems Development Method (DSDM) within the context of educational institutions and project management.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Review and Explore the Transformative Impact of Artificial Intelligence (AI) in Smart Healthcare Systems

Review and Explore the Transformative Impact of Artificial I...

引用

Advances in Computing research on science engineering and technology (ACROSET), International Conference on

作者： Sneha Nagar Mukesh Patidar Rashid Sheikh Sudhanshu Singh Ashutosh Kashiv Ankit Jain Shravan Kumar Namdeo Pranav Paranjpe Devendra Singh Mandloi Department of Electronics and Communication Engineering Indore Institute of Science and Technology Indore India Department of Computer Science & Engineering Parul Institute of Engineering and Technology Parul University Vadodara India Department of Computer Science & Engineering Acropolis Institute of Technology and Research Indore India Department of Electronics and Communication Engineering Indian Institute of Technology Indore Indore India

ISBN: (数字)9798350388800

ISBN: (纸本)9798350388817

Because of its high level of complexity and data collection capabilities, the healthcare industry employs artificial intelligence (AI) more than other sectors. Artificial intelligence is becoming an increasingly important part of our daily routines. AI's features include extremely low error rates, constant accessibility, quick analysis, and real-time data dissemination. This paper examines the crucial role of artificial intelligence in intelligent healthcare systems, with a particular emphasis on enhancing healthcare delivery. Artificial intelligence in healthcare is rapidly evolving, with the potential to significantly enhance patient care, diagnosis, treatment, and cost distribution. It also presents issues of transparency, honesty, and availability. This study will look into the benefits, drawbacks, and other aspects of artificial intelligence in intelligent healthcare systems.

关键词： Technological innovation Reviews Navigation Telemedicine Medical services Real-time systems Planning Artificial intelligence Prognostics and health management Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

A Novel Technique of Ranking of Transmission Lines for Maintenance Prioritization Accounting Annual Outage Time and Operational Severities

引用

Journal of The Institution of Engineers (India): Series B 2023年第6期104卷 1185-1196页

作者： Singh, Pushpendra Arya, Rajesh Titare, L.S. Purey, Pradeep Choube, S.C. Arya, L.D. Department of Electrical Engineering Rajkiya Engineering College Banda AKTU Lucknow UP Banda210201 India Department of Information Technology Acropolis Institute of Technology and Research MP Indore453771 India Department of Electrical Engineering Govt. Engineering College MP Ujjain456010 India Department of Electronic Engineering Maharaja Ranjit Singh College of Professional Sciences MP Indore452001 India Department of Electrical & Elex. UIT MP Bhopal452 003 India Department of Electrical Engineering Shri G S Institute of Technology and Science MP Indore452003 India

This paper describes a novel index for ranking of transmission lines for maintenance purpose. Preventive maintenance of transmission lines may be carried out based on prioritization of lines index. The index is based on severity indices, namely (a) thermal limits, (b) voltage limit violation, (c) voltage stability margin and (d) annual outage time. Thus in maintenance prioritization of lines, annual outage time (reliability index) and operational severity have been considered. The index has been obtained by multiplying the operational severity index with the annual outage time to reflect the true picture for the prioritization of transmission lines for maintenance purposes. It is stressed here that the objective of the paper is to provide an assessment of transmission line outage severity so as to provide a ranking list of lines based on peak load for maintenance prioritization. Lines that have higher index can be selected in priority for maintenance from the list. Maintenance activities involve reduction in failure rate and average repair time thereby giving desired availability. Results have been obtained for determining the maintenance priorities of transmission lines using derived index on three standard test systems. © 2023, The Institution of Engineers (India).

关键词： Electric lines

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：