检索结果-内蒙古大学图书馆

10th IEEE World Forum on Internet of Things, WF-IoT 2024

作者： Papadopoulos, George Spachos, Petros University of Thessaly Department of Computer Science and Biomedical Informatics Greece University of Guelph School of Engineering GuelphON Canada

ISBN: (纸本)9798350373011

Indoor localization and tracking services are necessary for several popular applications from asset monitoring to location-based marketing. The use of Internet of Things (IoT) devices in those services has increased due to their low cost and ease of deployment. However, indoor services pose significant challenges due to the lack of GPS signals as well as the complexity of the indoor environment. Alternative approaches, mainly including wireless technologies, should be considered. In this work, we examine the feasibility of using wearable IoT devices for indoor tracking. Specifically, we use smartwatches and we examine the performance of Wi-Fi and Bluetooth Low Energy (BLE) for indoor tracking. According to experimental results, BLE outperformed Wi-Fi in terms of energy efficiency while Wi-Fi, on the other hand, demonstrated a slightly better accuracy in Line of Sight conditions. © 2024 IEEE.

关键词： Bluetooth

来源：评论

学校读者我要写书评

暂无评论

Assessing students' awareness and education of web accessibility in web development and interface design programs 10

Assessing students' awareness and education of web accessibi...

引用

10th International Conference on Socio-Technical Perspectives in Information Systems, STPIS 2024

作者： Henriksson, Elin Uddstrom, Anna van Bree, Lotte Department of Computer Science and Informatics School of Engineering Jönköping University Jönköping Sweden

In an era of growing digitization, technology is essential for communication and daily life. However, inaccessible websites, including in Sweden, create barriers for individuals with disabilities, often due to insufficient education and awareness among web developers. Our quantitative study aimed to assess the status of web accessibility education within Swedish web development and interface design programs. We analyzed curricula and surveyed 63 final-year students across 23 programs. Findings show that while most programs (18 out of 23) include web accessibility, integration levels vary. Only 2% of courses offered standalone accessibility objectives, and 7% incorporated it within other courses, leaving 91% without any. Student knowledge varied;69.8% were aware of accessibility guidelines and laws, but 30.2% were not. Additionally, only 26.2% of students reported acquiring knowledge about accessibility guidelines and laws from their current education. This underscores the need for better web accessibility education. © 2024 Copyright for this paper by its authors.

关键词： Accessibility accessibility guidelines education interface design WCAG web accessibility web development

来源：评论

学校读者我要写书评

暂无评论

Infodeslib: Python Library for Dynamic Ensemble Learning using Late Fusion of Multimodal Data 4

Infodeslib: Python Library for Dynamic Ensemble Learning usi...

引用

4th International Workshop on Knowledge-Infused Learning, KiL 2024

作者： Juraev, Firuz El-Sappagh, Shaker Abuhmed, Tamer College of Computing and Informatics Sungkyunkwan University Korea Republic of Faculty of Computer Science and Engineering Galala University Egypt

There has been a notable increase in research focusing on dynamic selection (DS) techniques within the field of ensemble learning. This leads to the development of various techniques for ensembling multiple classifiers for a specific instance or set of instances during the prediction phase. Despite this progress, the design and development of DS approaches with late fusion settings and their explainability remain unexplored. This work proposes an open-source Python library, Infodeslib, to address this gap. The library provides an implementation of several DS techniques, including four dynamic classifier selections and seven dynamic ensemble selection techniques, all of which are integrated with late data fusion settings and novel explainability features. Infodeslib offers flexibility and customization options, making it a versatile tool for various complex applications that require the fusion of multimodal data and various explainability features. Multimodal data, which integrates information from diverse sources or sensor modalities, is a common and essential setting for real-world problems, enhancing the robustness and depth of data analysis. These data can be fused in two main ways: early fusion, where different modalities are combined at the feature level before model training, and late fusion, where each modality is processed separately and the results are combined at the decision level. The library is fully documented following the Read the Docs standards. The documentation, code, and examples are available anonymously on GitHub at https://***/InfoLab-SKKU/infodeslib. © 2024 Copyright for this paper by its authors.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Adaptive iterated local search algorithm for dynamic patient admission scheduling problems

引用

Soft Computing 2025年第7期29卷 3241-3251页

作者： Turky, Ayad Sabar, Nasser R. Song, Andy Hussain, Abir Liatsis, Panos Department of Computer Science College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Computer Science and Information Technology La Trobe University MelbourneVIC3086 Australia School of Computing Technologies RMIT University Melbourne Australia Department of Electrical Engineering University of Sharjah Sharjah United Arab Emirates Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi United Arab Emirates

Healthcare resource management is essential for ensuring the quality of patient care. However, it can be a complex and costly task. This work addresses the patient admission scheduling (PAS) problem, a complex aspect of healthcare resource management. PAS aims to allocate patients to hospital beds within a planning horizon, subject to a variety of healthcare constraints. The goal is to maximize management efficiency and patient comfort to improve medical treatment. In this work, we consider a practical variant of PAS known as dynamic PAS (DPAS). DPAS considers several factors and constraints, such as the daily registration of new patients, urgent patients, uncertainties in stay lengths, operating theatre resources, and the surgery scheduling process. An effective and efficient adaptive iterated local search (AILS) algorithm is proposed to solve DPAS. To enable the search to explore the search space efficiently, the proposed AILS adaptively integrates a number of components. Two adaptive perturbation strategies are devised to locate unexplored areas in the search space. To exploit the newly discovered areas effectively, we propose an adaptive local search mechanism as an intensification strategy to find a high-quality solution. The proposed AILS algorithm is compared to benchmark problems used by existing algorithms. The experimental results demonstrate the effectiveness and efficiency of the proposed approach. Specifically, out of 30 tested instances, AILS obtains 17 of the best-known results using less computational time. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

DeBERTa-GRU: Sentiment Analysis for Large Language Model

引用

computers, Materials & Continua 2024年第6期79卷 4219-4236页

作者： Adel Assiri Abdu Gumaei Faisal Mehmood Touqeer Abbas Sami Ullah Department of Informatics for Business College of BusinessKing Khalid UniversityAbha61421Saudi Arabia Department of Computer Science College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia School of Electrical and Information Engineering Zhengzhou UniversityZhengzhou450001China Department of Computer Science and Technology Beijing University of Chemical TechnologyBeijing100029China Department of Computer Science Government College University FaisalabadFaisalabadPunjab38000Pakistan

Modern technological advancements have made social media an essential component of daily *** media allow individuals to share thoughts,emotions,and *** analysis plays the function of evaluating whether the sentiment of the text is positive,negative,neutral,or any other personal emotion to understand the sentiment context of the *** analysis is essential in business and society because it impacts strategic *** analysis involves challenges due to lexical variation,an unlabeled dataset,and text distance *** execution time increases due to the sequential processing of the sequence ***,the calculation times for the Transformer models are reduced because of the parallel *** study uses a hybrid deep learning strategy to combine the strengths of the Transformer and Sequence models while ignoring their *** particular,the proposed model integrates the Decoding-enhanced with Bidirectional Encoder Representations from Transformers(BERT)attention(DeBERTa)and the Gated Recurrent Unit(GRU)for sentiment *** the Decoding-enhanced BERT technique,the words are mapped into a compact,semantic word embedding space,and the Gated Recurrent Unit model can capture the distance contextual semantics *** proposed hybrid model achieves F1-scores of 97%on the Twitter Large Language Model(LLM)dataset,which is much higher than the performance of new techniques.

关键词： DeBERTa GRU Naive Bayes LSTM sentiment analysis large language model

来源：评论

学校读者我要写书评

暂无评论

PIT Performance Measurement using NFD Pipeline Parameters in Named Data Networking (NDN) 10

PIT Performance Measurement using NFD Pipeline Parameters in...

引用

10th International Conference on Wireless and Telematics, ICWT 2024

作者： Sucipto, Adi Ahdan, Syaiful Iskandar Syambas, Nana Rachmana Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung40132 Indonesia Universitas Teknokrat Indonesia Faculty of Engineering and Computer Science 35132 Indonesia

ISBN: (纸本)9798350377057

Although NDN is an entirely new architecture, its design principles are based on the success of the current Internet, they represent our knowledge of the advantages and disadvantages of the current Internet architecture, and they can be implemented gradually using the operations of the current Internet. The Pending Interest Table (PIT), the Forwarding Information Base (FIB), and the Content Store (CS) are the three data structures found inside the NDN router. Interest sent upstream to the content source is tracked by the Pending Interest Table (PIT), for data to be transmitted to requesters downstream. PIT is also used for measurement, loop detection, and the containment of recently satisfied interest. In this study, we did the simulation to measure and analyze the performance of PIT in NDN using NFD Pipeline Measurements. The NDNSim simulator was used in the research to observe PIT performance. The findings of the simulation and analysis indicated that in an NDN network, Satisfied Interest was influenced by the granularity of a prefix. At the number of interests 1000, the results showed a decrease in packets, including a decrease of around 21% in the Ininterest packet, and around 30% inSatisfiedInterest and InData. The effect of Prefix length also decreased in Ininterest ranging from 0.014-0.015%, while in inSatisfiedInterest and InData it ranged from 4.2-8.5%. The PIT's performance was influenced by the length of the prefix and the number of interest messages the customer sent. © 2024 IEEE.

关键词： Natural gas pipelines

来源：评论

学校读者我要写书评

暂无评论

LSTM-XGBoost: An Ensemble Model for Blood Demand Distribution Forecasting – A Case Study in Zakho City, Kurdistan Region, Iraq

引用

Operations Research Forum 2025年第1期6卷 1-22页

作者： Zebari, Rizgar R. Zebari, Gheyath M. Al-zebari, Adel Mohammed, Marwan Aziz Department of Computer Science College of Science Knowledge University Erbil 44001 Iraq Department of Information Technology Technical College of Informatics Akre University for Applied Sciences Kurdistan Akre Iraq Department of Computer Engineering College of Engineering Knowledge University Erbil 44001 Iraq

A safe and adequate blood supply is essential for healthcare systems to function effectively. Accurately forecasting blood demand plays a key role in efficient inventory management and resource allocation. Traditional forecasting methods, like moving averages and ARIMA models, often fall short due to the complexity of factors influencing blood demand. This study introduces an innovative hybrid ensemble model that combines Long Short-Term Memory (LSTM) networks with XGBoost, harnessing their combined strengths to enhance forecasting accuracy. By analyzing blood donation data from the Zakho Blood Bank (January 1, 2015—July 22, 2022), the model outperforms individual LSTM and XGBoost models, excelling in metrics such as Mean Square Error (MSE) and Mean Absolute Error (MAE). These findings underscore the potential of advanced machine learning techniques to improve healthcare supply chain management and ensure the timely availability of critical blood supplies. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Blood banking Blood demand forecasting Healthcare supply chain LSTM network Machine learning XGBoost

来源：评论

学校读者我要写书评

暂无评论

Label-Free Biomolecule Detection with InP/AlGaAs Charge Plasma Dielectric-Modulated Vertical TFET Using TaN as Metal Gate

引用

IEEE Access 2025年 13卷 89667-89684页

作者： Elshafie, Hashim Alqahtani, Abdulrahman Saad Mubarakali, Azath Adarsh Rag, S. Venkatesh, M. Parthasarathy, P. King Khalid University College of Computer Science Department of Computer Engineering Abha61421 Saudi Arabia University of Bisha College of Computing and Information Technology Bisha67714 Saudi Arabia King Khalid University College of Computer Science Department of Informatics and Computer Systems Abha61421 Saudi Arabia Manipal Institute of Technology Department of Data Science and Computer Applications Manipal Academy of Higher Education Manipal576104 India CMR Institute of Technology Department of Electronics and Communication Engineering Karnataka Bengaluru560037 India

This study introduces a label-free biosensing method for biomolecule detection utilizing an InP/AlGaAs charge plasma dielectric-modulated vertical tunnel field-effect transistor (InP/AlGaAs VTFET) featuring TaN as the metal gate. The device comprises a nanocavity beneath the gate metal adjacent to the tunnelling junction, where biomolecules engage with the dielectric material, resulting in fluctuations in the drain current. A twin metal gate architecture with laterally split dielectrics is employed to eliminate short-channel effects. The biosensor has exceptional sensitivity, attaining a peak drain current sensitivity of 2.5 × 10 cm2 for biomolecules such as albumin (k = 7). The gadget proficiently identifies biomolecules with varying dielectric constants and charge distributions, enabling adaptable label-free detection of diverse targets. The study examines the influence of dielectric constant on critical metrics such as Energy Band Diagrams, Drain Current, Drain Sensitivity, and subthreshold swing (SS). The overlap between the source and pocket regions, along with the introduction of an auxiliary gate, optimizes the electrical characteristics. Simulation results show that the proposed InP/AlGaAs VTFET achieves a maximum sensitivity of 3.5 × 103, outperforming configurations without overlap (2 × 103), highlights the potential of proposed InP/AlGaAs VTFET for scalable, high-sensitivity, label-free biomolecule detection. © 2013 IEEE.

关键词： Junction gate field effect transistors

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of Start-up Success Rate Prediction Using Machine Learning Techniques 3

Comparative analysis of Start-up Success Rate Prediction Usi...

引用

3rd International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2024

作者： Belgaum, Mohammad Riyaz Viswanath, Ediga Kasi Chakradhar, Pavukolla Goud, Ediga Chenna Kesava Chandu, Kuruva G. Pullaiah College of Engineering and Technology Department of Computer Science and Engineering Kurnool India Multimedia University Faculty of Computing and Informatics Cyberjaya Malaysia

ISBN: (纸本)9798350391565

Software startups create innovative products or services using programming, which can lead to a need for products from potential customers. Researchers suggest that trial and error methodology can increase the success rate of these organizations by evaluating assumptions about client needs before fostering a product. However, programming new businesses typically do not require trial and error. The study aims to predict the success of startup companies in their early development stages by analyzing their success based on initial funding. A study of 106 unsuccessful software start-ups was conducted to predict the success rate. The experimentation progression model (X Pro) was developed to show that effective experimentation requires understanding trial and error, setting objectives, conducting tests, analyzing results, and acting based on new knowledge. The findings provide insights into supporting procedures and approaches that enhance trial- and-error reception in developing new business models. Researchers can become aware of potential factors leading to startup disappointment and take precautions to avoid them. The research focuses on using web-based open sources, including social networking services and the web, to model the task. The study uses machine learning techniques like Random Forest, Gradient Boost Classifier, XG Boost, and Ada Boost Classifier. The analysis provides insights into the types of useful signals discovered on the web and market mechanisms underlying the funding process. This approach offers a more comprehensive approach to predicting startup success. © 2024 IEEE.

关键词： Ada (programming language)

来源：评论

学校读者我要写书评

暂无评论

Semi-Automated Video Archiving Using Object Detection, Tracking and Ontological Annotation 4

Semi-Automated Video Archiving Using Object Detection, Track...

引用

4th International Conference on Artificial Intelligence, Robotics and Control, AIRC 2023

作者： Ayman, Shehab Eldeen Hussein, Walid Karam, Omar H. The British University in Egypt Faculty of Informatics and Computer Science Department of Software Engineering Cairo Egypt The British University in Egypt Faculty of Informatics and Computer Science Department of Computer Science Cairo Egypt

ISBN: (纸本)9798350348248

In light of this unmistakable exponential data expansion, visual media archiving must be rethought. Human generated meta-data might not be sufficient for efficient data retrieval. Object detection and object recognition enable the generation of computer-generated meta data that improve the storage and retrieval of data. We present a semi-automated approach for preserving video footage that combines object identification and ontologies. This significantly cuts down on search time, data scrubbing by providing only the relevant information making for more efficient queries. © 2023 IEEE.

关键词： computer vision

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：