检索结果-内蒙古大学图书馆

6th International Conference on Advancements in Computing, ICAC 2024

作者： Serasinghe, Chanukya Perera, Nashali Samarasinghe, Devindu Muthusinghe, Madusha Wijesundara, Malitha Sri Lanka Institute of Information Technology Dept. of Computer Science and Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Faculty of Humanities and Sciences Malabe Sri Lanka

ISBN: (纸本)9798331517878

The COVID-19 pandemic has expedited the shift in education to online learning, which has exposed shortcomings in virtual learning environments' personalization and engagement. This research addresses these issues by developing a web application designed to enhance student engagement and learning efficiency. The system has gamified collaboration features, video chapter segmentation, and personalized video recommendation system. The methodology comprises models for generating chapter titles and for precise video transcription, and machine learning algorithms for tailored suggestions depending on user input. Interactive Questions and Answers modules and real-time synchronized video playback are included. The results demonstrate how the system's personalized content, interactive tests, and teamwork tools increase user engagement and comprehension. The efficacy of personalized material and real-time synchronization in enhancing learning results is discussed. This innovative approach offers a comprehensive solution to the challenges of online education, creating a more immersive and interactive learning experience. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

An Efficient Analysis of Various Deep learning Model in Brain tumor Detection with MRI

An Efficient Analysis of Various Deep learning Model in Brai...

引用

Communication, Computing and Energy Efficient Technologies (I3CEET), International Conference on

作者： Deepak Upadhyay Kunj Bihari Sharma Mridul Gupta Abhay Upadhyay Satya Prakash Yadav Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era Deemed to be University Dehradun India School of Computer Science Engineering and Technology Bennett University Greater Noida India

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

This paper compares three of the popular deep learning models being VGG-16, VGG-19 and ResNet50 with respect to how they perform in the classification task. We investigate how much each model learns, the reduction of errors and inferences from data over epochs, through an in-dept. analysis of training and testing phases. The authors concluded that all the models perform efficiently; however, from the study results of performance and accuracy, VGG-19 and ResNet50 have a high-performance scale as well as super accuracy in their deep learning model which encourages business for application towards complex pattern recognition or predictive modelling. These results provide important intuitions on what deep learning architectures can do, and pave the path for further works in this area, b

关键词： Deep learning Training Analytical models Accuracy Computational modeling Predictive models Brain modeling Data models Residual neural networks Testing

来源：评论

学校读者我要写书评

暂无评论

3D Printed Conformal MIMO Antenna with Ladder Shaped Isolating Structure for Wireless Applications

3D Printed Conformal MIMO Antenna with Ladder Shaped Isolati...

引用

2023 IEEE Microwaves, Antennas, and Propagation Conference, MAPCON 2023

作者： Kulkarni, Jayshri Patel, Upesh Upadhyaya, Trushit Anguera, Jaume Garner, Brian Li, Yang Baylor University School of Engineering and Computer Science Waco United States Charotar University of Science and Technology Gujarat India Unversitat Ramon Llull Dept. of Electronics and Telecommunication Barcelona Spain

ISBN: (纸本)9798350328264

A 3D printed conformal Multiple Input Multiple Output (MIMO) antenna is proposed for 5G sub-6GHz and Wi-Fi 6E applications. The antenna is printed on a Ninjaflex substrate and consists of two identical radiators. An innovative 3D ladder-shaped structure is used as an isolating element between the radiators to reduce mutual coupling. The identical radiators have a fan-shaped structure engraved with a circular ring to operate in a dual band at a resonance of 3.35 and 6.6GHz. The overall footprint of the 3D printed MIMO antenna is only 45 × 25 mm2 and conforms to a -10dB impedance bandwidth of 40.54% (2.95-4.45 GHz) in the lower 5G sub-6GHz frequency band and 18.32% (5.95-7.15 GHz) in the upper Wi-Fi 6E frequency band. The 3D printed MIMO antenna demonstrates excellent radiation characteristics with a gain of more than 2dBi and efficiency of more than 95% in both the dual bands. The antenna's flexibility was also tested by bending it along the X and Y-axis at a radius of 30mm with successful results. © 2023 IEEE.

关键词： 3D 5G MIMO NinjaFlex Wi-Fi 6E

来源：评论

学校读者我要写书评

暂无评论

Enhancing Split Computing and Early Exit Applications through Predefined Sparsity

arXiv

引用

arXiv 2024年

作者： Capogrosso, Luigi Fraccaroli, Enrico Petrozziello, Giulio Setti, Francesco Chakraborty, Samarjit Fummi, Franco Cristani, Marco Dept. of Engineering for Innovation Medicine University of Verona Italy Dept. of Computer Science University of Verona Italy Dept. of Computer Science University of North Carolina Chapel Hill United States

In the past decade, Deep Neural Networks (DNNs) achieved state-of-the-art performance in a broad range of problems, spanning from object classification and action recognition to smart building and healthcare. The flexibility that makes DNNs such a pervasive technology comes at a price: the computational requirements preclude their deployment on most of the resource-constrained edge devices available today to solve real-time and real-world tasks. This paper introduces a novel approach to address this challenge by combining the concept of predefined sparsity with Split Computing (SC) and Early Exit (EE). In particular, SC aims at splitting a DNN with a part of it deployed on an edge device and the rest on a remote server. Instead, EE allows the system to stop using the remote server and rely solely on the edge device’s computation if the answer is already good enough. Specifically, how to apply such a predefined sparsity to a SC and EE paradigm has never been studied. This paper studies this problem and shows how predefined sparsity significantly reduces the computational, storage, and energy burdens during the training and inference phases, regardless of the hardware platform. This makes it a valuable approach for enhancing the performance of SC and EE applications. Experimental results showcase reductions exceeding 4 × in storage and computational complexity without compromising performance. The source code is available at https://***/intelligolabs/sparsity_sc_ee. © 2024, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Devising a Set of Compact and Explainable Spoken Language Feature for Screening Alzheimer's Disease

Devising a Set of Compact and Explainable Spoken Language Fe...

引用

International Symposium on Chinese Spoken Language Processing

作者： Junan Li Yunxiang Li Yuren Wang Xixin Wu Helen Meng Dept. of Systems Engineering & Engineering Management The Chinese University of Hong Kong Dept. of Computer Science & Engineering The Chinese University of Hong Kong

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

Alzheimer's disease (AD) has become one of the most significant health challenges in an aging society. The use of spoken language-based AD detection methods has gained prevalence due to their scalability due to their scalability. Based on the Cookie Theft picture description task, we devised an explain-able and effective feature set that leverages the visual capabilities of a large language model (LLM) and the Term Frequency-Inverse Document Frequency (TF-IDF) model. Our experimental results show that the newly proposed features consistently outperform traditional linguistic features across two different classifiers with high dimension efficiency. Our new features can be well explained and interpreted step by step which enhance the interpretability of automatic AD screening.

关键词： Visualization Scalability Large language models Linguistics Aging Feature extraction Alzheimer's disease

来源：评论

学校读者我要写书评

暂无评论

Small Data, Big Impact: A Multi-Locale Bone Fracture Detection on an Extremely Limited Dataset Via Crack-Informed YOLOv9 Variants

Small Data, Big Impact: A Multi-Locale Bone Fracture Detecti...

引用

Frontiers of Information Technology (FIT)

作者： Ammar Ahmed Abdul Manaf Ali Shariq Imran Zenun Kastrati Sher Muhammad Daudpota Dept. of Computer Science (IDI) Intelligent Systems and Analytics (ISA) Research Group NTNU Gjøvik Norway Dept. of Computer Science Sukkur IBA University Sukkur Pakistan Dept. of Informatics Linnaeus University Växjö Sweden

ISBN: (数字)9798331510503

ISBN: (纸本)9798331510510

Automated wrist fracture recognition has become a crucial research area due to the challenge of accurate X-ray interpretation in clinical settings without specialized expertise. With the development of neural networks, YOLO models have been extensively applied to fracture detection recently. However, detection models can struggle when trained on small datasets, which is often the case in medical scenarios. In this study, we utilize an extremely small multi-region fracture dataset and hypothesize that the structural similarities between surface cracks and bone fractures can allow YOLOv9 with a generalized efficient layer and programmable gradient information control to transfer knowledge effectively. We show that pre-training YOLOv9 on surface cracks rather than on COCO, which is how YOLO models are typically pre-trained, and fine-tuning it on the fracture dataset yields substantial performance improvements. We also show that knowledge gained from the surface cracks requires fewer epochs to converge and minimizes overfitting. We achieved state-of-the-art (SOTA) performance on the newly released FracAtlas dataset, surpassing the previously established benchmark. Our approach improved the mean average precision (mAP) score by 7% and sensitivity by 13%.

关键词： YOLO Wrist Sensitivity Neural networks Bones Surface cracks Information technology X-ray imaging Overfitting Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Blockchain Integration for Robust Intellectual Property Protection in New Product Development (NPD) 3

Blockchain Integration for Robust Intellectual Property Prot...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Chinnasamy, P. Subashini, B. Nijanthan, Nijanthan Madasamy Raja, G. Swetha, Devulapally Sreenivasulu Reddy, L. School of Computing Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamilnadu India School of Computing Srmist Department of Data Science and Business Systems Kattankulathur India Paavai Engineering College Tamilnadu Namakkal India Paavai Engineering College Tamilnadu Namakkal India Vaagdevi Engineering College Dept. of Computer Science and Engineering Warangal Dist. Telangana Bolli Kunta506005 India School of Advanced Sciences Kalasalingam Academy of Research and Education Department of Mathematics Tamilnadu Krishnankoil India

ISBN: (纸本)9798331509675

The rapid advancement of Blockchain technology has led to its widespread application in several domains of digital activities, such as e-government concerns and monetary security. This article presents a smart contract-based Blockchain solution for protecting intellectual property rights in new product development. The proposed solution effectively tackles the challenges associated with the confidentiality of personally identifiable information, efficiency in storing transaction-related information, as well as cooperation and monitoring in IPR. Initially, we create a mathematical model based on smart contract enabled Blockchain and intelligent contracts. Subsequently, we develop algorithms for Blockchain generation, and intelligent contracts. The system is suitable for protecting IPR in a blockchain network, by implementation of distributed identity authentication and real-time extensible storage. These features enhance the security and expandability of circuit copyright protection based on blockchain technology. The experimental results demonstrate that the suggested algorithm has decreased the cost for communication and enhanced the effectiveness of storing information and administration. Furthermore, it demonstrates resilience against many common attacks such as double-spending assaults, while maintaining low cost and overhead. Additionally, it exhibits a superior level of security in comparison to three other competing algorithms. © 2025 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Enhancing Brain Tumor Detection in MRI Images Through Fine-Tuning of VGG 16 Networks: A Precision Diagnostic Approach

Enhancing Brain Tumor Detection in MRI Images Through Fine-T...

引用

Communication, Computing and Energy Efficient Technologies (I3CEET), International Conference on

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

This paper explores the impact of fine-tuning on brain tumour diagnosis using MRI data and a pre-trained VGG 16 model on ImageNet. Our objectives in fine-tuning the model were to improve its generalisation ability and diagnostic accuracy. Our results demonstrate a considerable improvement in the model's performance, with decreased validation loss and increased validation accuracy. The findings show that, despite the possibility of overfitting, fine-tuning is a helpful technique for deep learning model optimisation in medical image analysis. By enhancing diagnostic skills in healthcare, particularly in the early detection of brain tumours, this tactic may enhance patient outcomes.

关键词： Training Accuracy Magnetic resonance imaging Brain modeling Data models Telecommunication computing Tuning Optimization Monitoring Overfitting

来源：评论

学校读者我要写书评

暂无评论

The Impact of Weather Conditions on Renewable Energy Production: A Machine Learning Approach

The Impact of Weather Conditions on Renewable Energy Product...

引用

IEEE International Conference on Big Data

作者： Recep Özbay Merve Çelebi Uraz Yavanoğlu Dept. Of Computer Forensics Graduate School of Informatics Gazi University Ankara Turkey Dept. Of Computer Education and Instructional Technologies Faculty of Education Hatay Mustafa Kemal University Hatay Turkey Dept. of Computer Engineering Faculty of Engineering Gazi University Ankara Turkey

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

In recent decades, obtaining energy from wind, solar, and hydro energy has brought hope for a sustainable future. Machine learning (ML) significantly impacts the field of energy systems. ML techniques have emerged as a powerful tool for analyzing and optimizing energy systems. This approach can potentially reduce the cost of analyzing a device by focusing solely on the data generated during its operation. This paper investigates the application of regression models to predict renewable energy production based on weather conditions, aiming to enhance the reliability and efficiency of renewable energy systems. Experiments are performed using Decision Tree (DT), k-nearest Neighbors (KNN), Multiple Linear (MLR), Polynomial (PR), Random Forest (RF), and Support Vector (SVR) Regression algorithms. The performances of ML models are compared based on the evaluations obtained through the Coefficient of Determination (R2), and error measures namely Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE), and Root Mean Square Error (RMSE). RF is the most successful algorithm in predicting renewable energy production depending on weather conditions as it has the highest R2 value and the lowest error measures.

关键词： Radio frequency Renewable energy sources Costs Wind energy Biological system modeling Measurement uncertainty Production Nearest neighbor methods Prediction algorithms Reliability

来源：评论

学校读者我要写书评

暂无评论

Impact on mental health due to COVID-19 pandemic: A cross-sectional study in Bangladesh

引用

Clinical eHealth 2023年第1期6卷 42-52页

作者： Pathan, Refat Khan Biswas, Munmun Yasmin, Suraiya Uddin, Mohammad Amaz Das, Anindya Khandaker, Mayeen Uddin Faruque, M.R.I. Sarker, Moniruzzaman Dept. of Computing and Information Systems School of Engineering and Technology Sunway University Selangor Bandar Sunway 47500 Malaysia Dept. of Computer Science and Engineering BGC Trust University Bangladesh Chittagong 4381 Bangladesh Department of Computer and Information Science Tokyo University of Agriculture and Technology Koganei - 184-0012 Tokyo Japan Dept. of Computer Science and Engineering Chittagong University of Engineering and Technology Chittagong 4349 Bangladesh Dept. of Electrical and Electronic Engineering Chittagong University of Engineering and Technology Chittagong 4349 Bangladesh Center for Applied Physics and Radiation Technologies School of Engineering and Technology Sunway University Selangor Bandar Sunway 47500 Malaysia Space Science Centre Universiti Kebangsaan Malaysia 43600 UKM Selangor Bangi Malaysia Department of Marketing Sunway University Business School Sunway University Selangor Bandar Sunway 47500 Malaysia Faculty of Graduate Studies Daffodil International University Daffodil Smart City Birulia Savar Dhaka – 1216 Bangladesh

The government of Bangladesh has implemented the “Stay Home” policy following the WHO recommendation to resist the community transmission of Covid-19. As a result, the routine activities of all government, semi-government establishments, including educational institutions, are severely affected, and the country's economic growth becomes slowed down. To overcome such a situation, the relevant authorities have introduced the “Work from Home” policy for the employees and “Remote Education” for students. However, due to the persistence of multi-dimensional socio-economic problems, many employees and students face big challenges in performing their regular jobs while adopting such a policy. Consequently, enormous psychological anxiety has been developed for all people, including students, parents, employees, etc., and concurrently created severe changes in their behavior. This study aims to analyze the reasons for the behavioral changes of the employees, students, academic staff, and family members of different ages due to psychological anxiety, stress, or physical issues. A comprehensive online-based survey has been carried out on people working in various sectors in Bangladesh. A modified Apriori Algorithm has been used to sort out the associations between the causes and types of behavioral changes. Analyzed data revealed a massive human behavioral change in most participants. This finding indicates that the negligence of those significant human behavioral changes may cause a higher risk of creating psychological imbalance. Therefore, there is a need to have a solid understanding of the reasons for the behavioral changes and set up standard guidelines to maintain “Work from Home” in this Covid-19 situation to avoid psychological imbalance. Based on this study, some suggestions have been given for implementation by the government on an urgent basis. © 2023

关键词： Apriori algorithm Behavioral changes Covid-19 outbreak Family crisis Work from home

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：