检索结果-内蒙古大学图书馆

International Conference on Computing, Mathematics and engineering Technologies (iCoMET)

作者： Muhammad Ikram Salman Ahmed Safdar Nawaz Khan Marwat Dept. of Computer Systems Engineering University of Engineering and Technology Peshawar Pakistan

The emerging trend of distributed and renewable energy sources encourages energy trading in the electricity market. Various forms of energy markets are evolving for successful energy trading. The local energy market is one of them in which various participants are actively coordinating for optimal utilization of power. Such type of local energy markets provides individual prosumers to trade their surplus energy in the neighbourhood in peer-to-peer topology. The complexity of such type of local energy market is increasing in terms of structure, control, coordination, and cost estimation. For the cooperative behaviour of the local energy markets, a dual auction coordination control scheme is important to encourage more prosumers for energy trading. We proposed a novel scheme that performs dual auctions for prosumers in a decentralized fashion. We assessed dual auction matching by coordinating prosumers and consumers to sell and purchase energy in the local energy market. The aggregator performed balancing in the proposed dual auction scheme as an autonomous entity. The results were simulated in MATLAB and JADE for the complex prosumer peer-to-peer network. Our proposed scheme shows each peer dual auction matching improves from 0.95 to 2.03 for optimal hierarchal energy trading in energy markets. For peer participation, the participation ratio increased from 0.684 to 1.74 and optimal aggregator coordination from 9.18% to 19% in the local energy markets.

关键词： Renewable energy sources Costs Estimation Consensus control Market research Electricity supply industry Peer-to-peer computing

来源：评论

学校读者我要写书评

暂无评论

SB-AGT: A stochastic beam search-enhanced attention-based Gumbel tree framework for drug-drug interaction extraction from biomedical literature

引用

computers in Biology and Medicine 2025年 189卷 110011-110011页

作者： Saad, Eman Kishk, Sherif Ali-Eldin, Amr Saleh, Ahmed I. Communication and Information Technology Center Mansoura University Egypt Electronics and Communication Engineering Dept. Mansoura University Egypt Computer Engineering & Control Systems Dept. Mansoura University Egypt

Drug-Drug Interactions (DDI) and Chemical-Protein Interactions (CPI) detection are crucial for patient safety, as unidentified interactions may lead to severe Adverse Drug Reactions (ADRs). While extensive DDI and CPI information exists within biomedical literature, manual extraction by experts proves time-intensive and resource-demanding. This study presents SB-AGT: Stochastic Beam Search-enhanced Attention-based Gumbel Tree an innovative approach to automated DDI and CPI extraction through an attention-based architecture incorporating a modified Gumbel-Tree method with stochastic beam search optimization. SB-AGT leverages multi-head attention mechanisms and enhanced latent tree structures to effectively capture complex syntactic features and drug relationship patterns. Also, the methodology includes comprehensive preprocessing protocols and addresses dataset imbalance through hybrid sampling techniques. Experimental validation on the DDIExtraction 2013 and CHEMPROT datasets demonstrates the model's effectiveness, achieving precision, surpassing traditional approaches and showing competitive performance compared to contemporary pre-trained models. Through parametric analysis, we establish optimal beam search configurations that maximize the model's extraction accuracy. © 2025 Elsevier Ltd

关键词： Stochastic models

来源：评论

学校读者我要写书评

暂无评论

TRANSNATIONAL COLLABORATION ON LIFELONG LEARNING BETWEEN HIGHER engineering EDUCATION INSTITUTIONS: A UNIVERSITY PERSPECTIVE 51

TRANSNATIONAL COLLABORATION ON LIFELONG LEARNING BETWEEN HIG...

引用

51st Annual Conference of the European Society for engineering Education, SEFI 2023

作者： Bennedsen, J. Øien, G. Dept. of Electro- and Computer Engineering Aarhus University Aarhus Denmark Center for Science and Engineering Education Development NTNU Trondheim Norway

ISBN: (纸本)9782873520267

Lifelong learning (LLL) is in focus in all European countries. Workforce upskilling and reskilling are seen as central elements in ensuring national competitiveness. Universities are main players in this effort but often find it difficult to find sustainable models for LLL activities, in terms of e.g., economy, student intake, and academic resources. Collaboration between universities can be one possible way forward to overcome such obstacles, and given the enhanced post-Covid digitalization is also increasingly made possible, even across borders. However, many universities also find such collaboration challenging, e.g., due to outdated legislation, lacking financial predictability, lacking academic capacity, or other factors. Studies done by the authors indicate that universities' perspectives are seldom present in the literature when barriers and enablers for LLL participation are analysed. This motivates us to particularly consider a university perspective here. This paper analyses responses to a questionnaire sent to 28 Nordic and Baltic universities, collecting information about successes, opportunities, and barriers for formal (i.e., ECTS-awarding) university-level LLL with professional content within engineering and technology. The respondents were management representatives representing an institutional view and having good knowledge of the institution's LLL offer (e.g., further education centre managers and LLL coordinators). 19 institutions answered, mostly with free text. Our analysis is done following constructivist grounded theory using an open and focused coding approach. The main aim is to identify the main barriers and success factors seen by the universities for upscaling LLL activities, and subsequently to suggest strategies for alleviating barriers and facilitating success factors. © 2023 SEFI 2023 - 51st Annual Conference of the European Society for engineering Education: engineering Education for Sustainability, Proceedings. All Rights Reserved.

关键词： engineering education

来源：评论

学校读者我要写书评

暂无评论

Addressing Weight Competition in Long Short-Term Memory (LSTM) Networks for Improving Temperature Prediction 12

Addressing Weight Competition in Long Short-Term Memory (LST...

引用

12th International Conference on Awareness Science and Technology, iCAST 2023

作者： Lin, Kun-Wei Li, Yu-Fan Lin, Che-Yu Jiang, Zheng-Han Chen, Wei-Jian dept. Computer Science and Information Engineering Chaoyang University of Technology Taichung Taiwan dept. Information Management Chaoyang University of Technology Taichung Taiwan

ISBN: (纸本)9798350324693

This conference paper presents a study on the application of Long Short-Term Memory (LSTM) networks to predict temperature changes in the upcoming week. During our research, we encountered the issue of weight competition within the LSTM architecture, which can lead to suboptimal predictions. To overcome this challenge, three novel methods including Independent Time Series (ITS) Model, Arithmetic Segmented Time Series (ASTS) Model and Arithmetic Segmented Rolling Time Series (ASRTS) Model, respectively, were used to address weight competition and enhance the accuracy of temperature change forecasts. The effectiveness of these methods were evaluated through extensive experiments and compared against standard LSTM models. The results demonstrate the significance of mitigating weight competition to achieve more reliable and accurate temperature predictions. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Image Segmentation: Inducing graph-based learning

arXiv

引用

arXiv 2025年

作者： Singh, Aryan Van de Ven, Pepijn Eising, Ciarán Denny, Patrick Data-Driven Computer Engineering Group Dept. of Electronic and Computer Engineering University of Limerick Ireland

This study explores the potential of graph neural networks (GNNs) to enhance semantic segmentation across diverse image modalities. We evaluate the effectiveness of a novel GNN-based U-Net architecture on three distinct datasets: PascalVOC, a standard benchmark for natural image segmentation, WoodScape, a challenging dataset of fisheye images commonly used in autonomous driving, introducing significant geometric distortions;and ISIC2016, a dataset of dermoscopic images for skin lesion segmentation. We compare our proposed UNet-GNN model against established convolutional neural networks (CNNs) based segmentation models, including U-Net and U-Net++, as well as the transformer-based SwinUNet. Unlike these methods, which primarily rely on local convolutional operations or global self-attention, GNNs explicitly model relationships between image regions by constructing and operating on a graph representation of the image features. This approach allows the model to capture long-range dependencies and complex spatial relationships, which we hypothesize will be particularly beneficial for handling geometric distortions present in fisheye imagery and capturing intricate boundaries in medical images. Our analysis demonstrates the versatility of GNNs in addressing diverse segmentation challenges and highlights their potential to improve segmentation accuracy in various applications, including autonomous driving and medical image analysis. Code Available at GitHub. © 2025, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

High-Performance File Searching with Rust: Parallelized Indexing for Enhanced Computational Efficiency 3

High-Performance File Searching with Rust: Parallelized Inde...

引用

3rd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2025

作者： Sinha, Snehil Kalwani, Prabir Shah, Aayush Gonsalves, Jesleena SVKM's Nmims University Mukesh Patel School of Technology Management and Engineering Dept. of Computer Engineering Mumbai India

ISBN: (纸本)9798331521691

Conventional file explorer tools have many limitations, from sluggish performance to cluttered user interfaces. The Windows File Explorer is often criticized for its slow performance, taking an exorbitant amount of time to load search results, especially for extensive file collections. In contrast, the Rust-based file searcher employs parallelization to rapidly parse the file system and build a comprehensive index. This index is stored in memory using a HashMap data structure, providing constant-time lookups. This study presents a high-performance alternative using the Rust programming language to address these shortcomings. The study shows the advantages of parallelization of search in Rust and then compares file search using Rust and traditional Windows file explorer on multiple parameters, including Search time, CPU usage, and Memory usage. The Rust-Based File Searcher provides faster results at around 80 to 180 milliseconds compared to 4-16 seconds using Windows File Search. © 2025 IEEE.

关键词： File Search Parallelization Rust Programming

来源：评论

学校读者我要写书评

暂无评论

Proposal for the Support Method Presentation Model Utilizing Nursing Home Insights 9

Proposal for the Support Method Presentation Model Utilizing...

引用

9th International Conference on Business and Industrial Research, ICBIR 2024

作者： Nakajima, Yoko Yuki, Masamune Ptaszynski, Michal Honma, Hirotoshi Akiba, Tomoyoshi Masui, Fumito Institute of Technology Kushiro Colloege Dept. of Creative Engineering Kushiro Japan School of Regional Innovation and Social Design Engineering of Kitami Institute of Technology Kitami Japan Toyohashi University of Technology Dept. of Computer Science and Technology and Engineering Toyohashi Japan

ISBN: (纸本)9798350383010

One of the significant problems faced by dementia group homes is the high caregiver turnover rate. In particular, there is an urgent need to prevent the turnover of new caregivers and work toward ensuring and improving the quality of care. To address this issue, we are developing a care method support system that utilizes two databases: a personal attributes database and a care case database ([1]-[3]). The personal attributes database extracts personal attributes such as hobbies and previous occupations of residents from care records and care conference minutes. The care case database extracts cases of resident problems, their solutions, and the original text containing them. The care method support system presents candidates for appropriate responses to problems faced by residents based on these databases. In this study, we generated two care suggestion models: Care Suggestion Model: This model applies text similarity to the care case database to suggest candidates for appropriate responses to unregistered problems. Personalized Care Suggestion Model: This model applies clustering to the personal attributes database and generates a care suggestion model that considers personal attributes. We compared the two models and tested the usefulness of the model. © 2024 IEEE.

关键词： Nursing

来源：评论

学校读者我要写书评

暂无评论

Understanding and Promoting Earnest Completion in Online Textbooks 129

Understanding and Promoting Earnest Completion in Online Tex...

引用

129th ASEE Annual Conference and Exposition: Excellence Through Diversity, ASEE 2022

作者： Gordon, Chelsea Lysecky, Roman Vahid, Frank zyBooks Dept. of Electrical and Computer Engineering Univ. of Arizona United States Dept. of Computer Science and Engineering Univ. of California Riverside United States

Digital textbooks are becoming more common in college-level computer, engineering, and science courses. For various reasons, some students quickly click on reading activities to earn completion points, without earnestly attempting the activities. We analyzed student earnestness in digital computer science and engineering textbooks across a semester. We found that student earnestness declines significantly as the semester progresses. We also found that earnestness levels at a semester's start have a tremendous impact on earnestness throughout the semester, namely that lower average earnestness at a semester's onset leads to a significantly more rapid decline. For example, one course with an initial 90% earnestness score fell to 76% by week 6, whereas another course with an initial 72% score dropped dramatically to just 32% by week 6. This finding emphasizes the importance of instructors ensuring students recognize the utility of the textbook activities from a course's start, and ensure that the activity workload is reasonable too, to start students with high earnestness. We close with recommendations for encouraging earnest completion early in the semester, which is crucial for maintaining earnest completion throughout the course. © American Society for engineering Education, 2022.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Improving Fake News Detection with a Mixture of Experts: Leveraging Sentiment Analysis and Sarcasm Detection as Core Expert Models

Improving Fake News Detection with a Mixture of Experts: Lev...

引用

Advancements in Computing (ICAC), International Conference on

作者： Tharindu Gunasekara Disira Thihan Sansika Kodithuwakku Dinuka Dissanayake Harinda Fernando Samitha Vidhanaarachchi Archchana Sindhujan dept. of Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka dept. of Computer Computer Systems Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka dept. of Computer Science and Electronic Engineering University of Surrey United Kingdom

ISBN: (数字)9798331517878

ISBN: (纸本)9798331517885

Fake news continues to proliferate, posing an increasing threat to public discourse. The paper proposes a framework of a Mixture of Experts, Sentiment Analysis, and Sarcasm Detection experts for improved fake news detection. This approach captures the emotional cues in the text through a Sentiment Analysis expert, which is based on bidirectional encoder representations from Transformers (BERT) models with sentiment vectors generated using SentiWordNet and Integrated Gradients. It combines a sarcasm detection expert based on BERT, recognizing sarcasm and its type to help classify fake news. By fusing these experts through a Mixture of Experts gateway, subtle linguistic cues often found in fake news are more effectively analyzed, leading to improved accuracy in detecting misinformation. Experimental results are presented as 96% for the Sarcasm expert with the BERT base model and 83% for the Sentiment Analysis expert with the distilled version of the BERT (DistilBERT) base model, proving the effectiveness of the proposed approach in beating traditional methods.

关键词： Sentiment analysis Analytical models Accuracy Bidirectional control Logic gates Linguistics Transformers Encoding Vectors Fake news

来源：评论

学校读者我要写书评

暂无评论

Browser Preference Prediction for computer Users using Machine Learning 9

Browser Preference Prediction for Computer Users using Machi...

引用

9th IEEE International Conference on Computing, engineering and Design, ICCED 2023

作者： Pratondo, Agus Ismail, Nanang Novianty, Astri Telkom University School of Applied Sciences Dept. of Multimedia Engineering Bandung Indonesia UIN Sunan Gunung Djati Faculty of Engineering Dept. of Electrical Engineering Bandung Indonesia Telkom University School of Electrical Engineering Dept. of Computer Engineering Bandung Indonesia

ISBN: (纸本)9798350370126

Using machine learning techniques to predict people' preferred web browsers has become a powerful way to improve user experience and personalize web browsing. In a time where social media interactions are a part of everyday life, it is critical to recognize and accommodate personal preferences. This study presents the Random Forest algorithm as the selected approach and investigates the role of prediction in web browser preference. The system provides a tailored and efficient surfing experience by utilizing user information to anticipate browser preferences. The experimental findings highlight the model' s predictive power with a noteworthy accuracy rate of 96.2 percent. This high accuracy suggests that the model is able to recognize and accommodate the individual preferences of users. The predictive model has a great deal of promise for practical uses with its level of accuracy, making it an invaluable resource for marketers, user experience designers, and web developers. By employing the insights gained from this study, practitioners can better tailor their services to individual users, contributing to an improved browsing experience in everyday life. (Abstract) © 2023 IEEE.

关键词： Forecasting

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：