检索结果-内蒙古大学图书馆

IEEE Conference on Vehicular Technology (VTC)

作者： Ishtiaque Ahmed Toke Md Fahad Monir Md Zoheb Hassan Tarem Ahmed Department of Computer Science and Engineering Independent University Bangladesh Department of Electrical and Computer Engineering Virginia Tech USA Department of Electrical and Computer Engineering Université Laval Quebec City Canada

ISBN: (数字)9798331517786

ISBN: (纸本)9798331517793

In the digital age, the agricultural industry faces unique challenges, including the efficient management and maintenance of farm vehicles and tools. This paper introduces a blockchain-based agricultural vehicle and tool rental system leveraging Hyperledger Fabric. By utilizing blockchain technology, the system ensures immutability, transparency, and trust among all parties involved. The primary focus is on creating a decentralized and secure platform that not only facilitates the rental process but also introduces next-generation farm vehicle and tool maintenance capabilities. Throughout the development process, we faced and overcame significant challenges, including the need for a custom-tailored blockchain solution to meet the unique requirements of agricultural asset management. The proposed solution enhances traceability and accountability, thereby reducing fraudulent activities and improving overall operational efficiency. A working demo of the system is available on GitHub, providing an open-source resource for researchers and developers. This accessibility enables further exploration and adaptation of the system across various fields, from supply chain management to peer-to-peer marketplaces. The blockchain’s immutability aspect serves as a cornerstone for building trust in digital transactions, offering potential applications in diverse sectors such as finance, healthcare, and government services. The implementation details, innovative approaches to technical obstacles, and practical implications of our solutions are thoroughly discussed, providing valuable insights for researchers and practitioners in blockchain technology and agricultural systems.

关键词： Vehicular and wireless technologies Supply chain management Distributed ledger Smart contracts Fabrics Blockchains Peer-to-peer computing Maintenance Asset management Software development management

来源：评论

学校读者我要写书评

暂无评论

ILASH: A Predictive Neural Architecture Search Framework for Multi-Task Applications

arXiv

引用

arXiv 2024年

作者： Rahman, Md Hafizur Rizvee, Md Mashfiq Shomaji, Sumaiya Chakraborty, Prabuddha Department of Electrical and Computer Engineering University of Maine United States Department of Electrical Engineering and Computer Science University of Kansas United States

Artificial intelligence (AI) is widely used in various fields including healthcare, autonomous vehicles, robotics, traffic monitoring, and agriculture. Many modern AI applications in these fields are multi-tasking in nature (i.e. perform multiple analysis on same data) and are deployed on resource-constrained edge devices requiring the AI models to be efficient across different metrics such as power, frame rate, and size. For these specific use-cases, in this work, we propose a new paradigm of neural network architecture (ILASH) that leverages a layer sharing concept for minimizing power utilization, increasing frame rate, and reducing model size. Additionally, we propose a novel neural network architecture search framework (ILASH-NAS) for efficient construction of these neural network models for a given set of tasks and device constraints. The proposed NAS framework utilizes a data-driven intelligent approach to make the search efficient in terms of energy, time, and CO2 emission. We perform extensive evaluations of the proposed layer shared architecture paradigm (ILASH) and the ILASH-NAS framework using four open-source datasets (UTKFace, MTFL, CelebA, and Taskonomy). We compare ILASH-NAS with AutoKeras and observe significant improvement in terms of both the generated model performance and neural search efficiency with up to 16x less energy utilization, CO2 emission, and training/search time. © 2024, CC BY-NC-SA.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Improving Cardiovascular Prediction Performance Using Machine Learning Based Feature Selection 17

Improving Cardiovascular Prediction Performance Using Machin...

引用

17th International Conference on Developments in eSystems engineering, DeSE 2024

作者： Naser, Marwah Abdulrazzaq Alsabah, Muntadher Abdulhussain, Sadiq H. Mahmmod, Basheera M. Hussain, Abir Al-Jumeily, Dhiya Department of Computer Engineering University of Baghdad Baghdad Iraq Medical Technical College Al Farahidi University Baghdad Iraq Department of Electrical Engineering University of Sharjah Sharjah United Arab Emirates School of Computer Science and Mathematics Liverpool John Moores University Liverpool United Kingdom

ISBN: (纸本)9798350368697

To date, cardiovascular disease (CVD) is responsible for a considerable number of deaths each year. Hence, developing an effective CVD prediction model is essential to reducing mortality rates. To this end, this paper makes use of different machine learning (ML) classifiers such as logistic regression (LG), K-nearest neighbor (KNN), support vector machine (SVM), gradient boosting (GB), and adaptive boosting (AdaB) to improve CVD prediction performance. In addition, this paper investigates the use of ML based on the ANOVA feature selection method and voting ensemble model by aggregating different ML classifiers to improve CVD prediction. The CVD performance is evaluated using key metrics such as accuracy, precision, recall, F1-score, and confusion matrix. The results demonstrate that the proposed approach achieves the highest CVD prediction accuracy compared to state-of-the-art methods recording 93.44%. The findings obtained in this paper suggest that the SVM ANOVA feature selection and ensemble approaches can be considered practical strategies for improving the prediction accuracy of CVD. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

ChemGenX: AI in the Chemistry Classroom 24

ChemGenX: AI in the Chemistry Classroom

引用

2024 International Symposium on Artificial Intelligence for Education, ISAIE 2024

作者： Abbas, Touqeer Javed, Umair Mehmood, Faisal Raza, Muneeb Li, Hui Department of Computer Science and Technology Beijing University of Chemical Technology Beijing China School of Electrical and Information Engineering Zhengzhou University Henan Zhengzhou China Beijing China

ISBN: (纸本)9798400707100

Generative AI is reshaping education by offering personalized learning experiences and innovative teaching methods. In this study, we introduced ChemGenX, an AI tool designed to enhance chemistry education by generating molecular structures with user-defined features. The primary objective is to simplify molecular design and improve student learning. Our approach utilizes the coherently aligned multimodal semantic space using pre-trained CLIP;generate text features from image features to seamlessly alleviate the need for text conditioning, resulting in accurate predictions of bond lengths, angles, and molecular structures. The model was trained on a comprehensive molecular dataset, achieving competitive performance in zero-shot text-to-image conversion. Pilot studies with high school students and teachers demonstrate its potential in generating accurate molecular structures, including key features like bond lengths and angles. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Bond length

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Algorithm For MRI Brain Alzheimer's Disease Prediction

Hybrid Deep Learning Algorithm For MRI Brain Alzheimer's Dis...

引用

2023 International Conference on Energy, Materials and Communication engineering, ICEMCE 2023

作者： Karthikeyan, D. Nivasini, R. Raja, Kiruba Thangam Madhivadhani, D. Sivakumar, B. Krishna Priya, A.T.R. Srm Institute of Science and Technology Department of Electrical and Electronics Engineering Kattankulathur Chennai India Iitm Research Park Guvi Geek Networks Tamilnadu Chennai India Vit University School of Computer Science Engineering and Information Systems Department of Software and Systems Engineering Vellore India Kings Engineering College Department of Electronics and Communication Engineering Sriperumbudur Chennai India Rohini College of Engineering and Technology Department of Computer Science and Engineering Kanyakumari India

ISBN: (纸本)9798350393378

Magnetic resonance imaging (MRI) has been used to study the structural makeup of the brain and analyse several neurological disorders and diseased areas. For the adoption of preventative measures, early recognition of Alzheimer's disease (AD) patients is essential. Here, a thorough inspection of the tissue arrangements obtained by MRI images of Outcome and Assessment Information (OASIS) dataset enables an exact characterization of certain brain diseases. There have been a number of division techniques for diagnosing AD that range in complexity. Compassion has been tested by deep learning techniques used to segment the structure of the brain and classify AD because they have the potential to uncover important information from vast amounts of data. In this paper the deep learning technique of Hybrid Dragonfly based GWO convolutional Neural Network (CNN) is achieved promising result for the diagnosis of AD. At image preprocessing wiener filter is used for removing the additive noises and the Gray Level Co-Occurrence Matrix (GLCM) extraction is implemented for texture analyzing. As a result, hybrid deep learning methods of CNN has the accuracy as 90% and the result of the image prediction are presented in this paper. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Designing an Advanced Situational Awareness Platform Using Intelligent Multi-Drones for Smart Farming Towards Agriculture 5.0 11

Designing an Advanced Situational Awareness Platform Using I...

引用

11th International Conference on ICT for Smart Society, ICISS 2024

作者： Hermanus, Davy Ronald Supangkat, Suhono Harso Hidayat, Fadhil Bina Nusantara University Research Interest Group in Educational Technology Computer Science Department Indonesia School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia

ISBN: (纸本)9798350389654

With regard to Agriculture 5.0, the goal of this research is to create an intelligent platform for multi-drone collaboration that will improve situational awareness. This study examines the crucial phases in the Sensing, Understanding, and Action processes by fusing cutting-edge drone technology with creative coordination methods. Creating the architecture and foundation for drone collaboration, utilizing artificial intelligence for real-time data processing, and creating user interfaces that work are all part of the study technique. Area coverage, data quality, processing speed, and decision-making effectiveness are some of the performance evaluation measures. The goal of the research is to identify strategies for enhancing large-scale farming methods' resource management and operational effectiveness. The results will greatly enhance Agriculture 5.0 technologies and create avenues for the deployment of multi-drone collaboration platforms in a variety of high-situational awareness businesses. © 2024 IEEE.

关键词： Data quality

来源：评论

学校读者我要写书评

暂无评论

Democratizing the Federation in Federated Learning

Democratizing the Federation in Federated Learning

引用

IEEE Internatonal Conference on Mobile Adhoc and Sensor Systems (MASS)

作者： Ningxin Su Baochun Li Bo Li Department of Electrical and Computer Engineering University of Toronto Department of Computer Science Hong Kong University of Science and Technology

ISBN: (数字)9798350363999

ISBN: (纸本)9798350364002

Federated learning (FL) is a widely acknowledged distributed training paradigm that preserves the privacy of data on participating clients, and has become the de facto standard for distributed machine learning across a large number of edge devices. Conventional FL, however, has a rather rigid design, where the server is the dominant player that selects a subset of its clients to participate in each communication round, and clients are merely followers, and are not offered the freedom to accept or decline invitations from the server to participate. In addition, clients may become unavailable or very slow due to a wide variety of reasons, yet it may take an excessive amount of time for a conventional FL server to recognize that a particular client is unavailable. In this paper, we advocate for a more pragmatic paradigm in federated learning, called democratic federated learning, to offer more freedom to both servers and clients with respect to the ability to accept or decline requests, and to explicitly request to participate. In contrast to conventional federated learning, our paradigm allows (1) both the server and clients to participate and withdraw from the federated learning process at any time; (2) the server to decide whether to reject clients' updates based on the current model convergence steps, i.e., after satisfying the minimum required clients' updates received; and (3) the clients to adjust the local epochs based on their own training and communication time. Our experimental results on a variety of datasets and models have confirmed that democratic federated learning not only accelerates the convergence process but also improves the accuracy of converged models, and serves as a foundation for future explorations into client-centric models within the FL ecosystem.

关键词： Training Data privacy Federated learning Ecosystems Distributed databases Smart systems Servers Standards Convergence Pragmatics

来源：评论

学校读者我要写书评

暂无评论

Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling

arXiv

引用

arXiv 2025年

作者： Li, Xiao Zhang, Zekai Li, Xiang Chen, Siyi Zhu, Zhihui Wang, Peng Qu, Qing Department of Electrical Engineering and Computer Science University of Michigan United States Department of Computer Science & Engineering Ohio State University United States

This work addresses the critical question of why and when diffusion models, despite being designed for generative tasks, can excel at learning high-quality representations in a self-supervised manner. To address this, we develop a mathematical framework based on a low-dimensional data model and posterior estimation, revealing a fundamental trade-off between generation and representation quality near the final stage of image generation. Our analysis explains the unimodal representation dynamics across noise scales, mainly driven by the interplay between data denoising and class specification. Building on these insights, we propose an ensemble method that aggregates features across noise levels, significantly improving both clean performance and robustness under label noise. Extensive experiments on both synthetic and real-world datasets validate our findings. © 2025, CC BY.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Projections for High-Performance Concrete Strength Forecasting 4

Deep Learning Projections for High-Performance Concrete Stre...

引用

4th International Conference on Innovative Practices in Technology and Management, ICIPTM 2024

作者： Tipu, Rupesh Kumar Shah, Owais Ahmad Vats, Satvik Arora, Sujata K. R. Mangalam University School of Engineering & Technology Gurugram India Graphic Era Hill University Department of Computer Science & Engineering Dehradun India Noida International University Department of Electrical & Electronics Engineering Gautam Budh Nagar India

ISBN: (纸本)9798350307757

This study explores the application of a Multilayer Perceptron (MLP) deep learning model to predict the compressive strength of High Performance Concrete (HPC). The dataset, comprising 1030 samples, undergoes meticulous preprocessing, including normalization within a 0-1 range. The MLP model is trained and evaluated, yielding impressive performance metrics such as an R2 score of 0.918201, MSE of 13.76, RMSE of 3.71 MPa, MAE of 4.79 MPa, and a low MAPE of 0.02. Additionally, a comprehensive 10-fold cross-validation ensures the model's robustness and generalization ability. Visualizations in actual versus predicted plots and radar plots provide intuitive insights into the model's predictive prowess. Hyperparameter tuning further refines the model. The study establishes the MLP model as a reliable tool for predicting HPC compressive strength, offering significant implications for enhancing the precision and efficiency of concrete engineering practices. © 2024 IEEE.

关键词： Compressive strength

来源：评论

学校读者我要写书评

暂无评论

Teachers' Data Literacy Skills for Pedagogical Decision Making: Needs Analysis in Lithuania and Germany 14

Teachers' Data Literacy Skills for Pedagogical Decision Maki...

引用

14th International Scientific and Practical Conference on Environment. Technology. Resources, ETR 2023

作者： Melnikova, Julija Batuchina, Aleksandra Ahrens, Andreas Zascerinska, Jelena Department of Pedagogy Faculty of Social Sciences and Humanities Klaipeda University Klaipeda Lithuania Department of Electrical Engineering and Computer Science Faculty of Engineering Hochschule Wismar Wismar Germany Department of Education Faculty of Engineering Hochschule Wismar Wismar Germany

ISBN: (纸本)9781713874881

The purpose of the article is to analyse the needs of general education schoolteachers' data literacy skills that are important for the effective use of learning analytics in the teaching-learning process. The theoretical part of the article presents the idea of big data in education, highlights the aspects of pedagogical value of learning analytics technologies, provides the overview of learning analytic tools. Some overview and comparison of spread of learning analytics tools in general education schools in Lithuania and Germany is presented in the context of data-driven education. The empirical part of the article presents some results from a big qualitative study of teachers' experiences applying learning analytics tools in teaching - learning process. The main question of the current research is what data literacy skills teachers need in order to use learning analytics tools and make data based pedagogical decisions. Semi-structured interviews were conducted with 10 Lithuanian and 9 German teachers from general education schools, who already have had experience in working with learning experience platforms (digital learning platforms that integrate learning analytics tools). Interview data were analysed by means of content analysis. The results of the qualitative study showed that in order to use learning analytics tools it is important for teachers to have such skills as: digital literacy, data collection, data analysis and interpretation, etc. Comparative analysis of informantsanswers showed that teachers in Lithuania and Germany expressed similar needs for data literacy skills. © 2023 Rezekne Higher Education Institution. All rights reserved.

关键词： Decision making

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：