检索结果-内蒙古大学图书馆

2024 International Conference on Measurement, Communication, and Virtual Reality, MCVR 2024

作者： Jomsri, P. Prangchumpol, D. Eamthanakul, B. Poonsilp, K. Pudprommarat, C. Dept. of Information Technology Suan Sunandha Rajabhat University Dusit Bangkok10300 Thailand Dept. of Computer Science Suan Sunandha Rajabhat University Dusit Bangkok10300 Thailand Dept. of Applied Science Faculty of Science and Technology Suan Sunandha Rajabhat University Bangkok Thailand

ISBN: (纸本)9781510691773

This study proposed to predict the immigration patterns of foreign workers in Thailand using machine learning techniques. The primary focus is to analyze how factors such as the year, month, area, and legal immigration type (MOU) influence the number of foreign workers entering the country. MOU represents the Memorandum of Understanding, a legal framework for foreign migration. By utilizing two distinct machine learning models—Linear Regression and Decision Tree—this research seeks to identify the most effective method for forecasting immigration trends. This study analyzes foreign worker immigration in Thailand using data collected from 2560 to 2561 B.E. The data used in this study includes key variables that are indicative of immigration movements, providing a comprehensive view of the factors influencing foreign migration. The findings reveal that the Decision Tree model outperforms Linear Regression in terms of accuracy at 0.99. This analysis is crucial for policymakers and stakeholders as it provides insights into the patterns of foreign worker immigration, enabling better planning and management of foreign worker resources. Understanding these patterns is essential for developing effective immigration policies and ensuring that foreign worker market needs are met in a regulated and orderly manner. The comparative analysis demonstrates the importance of selecting appropriate machine learning models for accurate predictions in the domain of foreign immigration. © 2025 SPIE.

关键词： Linear regression

来源：评论

学校读者我要写书评

暂无评论

Real-Time Human Body Sensors Data Classification using Supervised Machine Learning

Real-Time Human Body Sensors Data Classification using Super...

引用

Business Analytics for Technology and Security (ICBATS), International Conference on

作者： Muhammad Sajid Farooq Muhammad Farhan Khan Dept. of Computer Science Lahore Garrison University Lahore Pakistan Applied Science Research Center Applied Science Private University Amman Jordan Dept. of Forensic Sciences University of Health Sciences Lahore Pakistan

Supervised learning algorithms have recently been brought to the classification of medical data in an effort to boost diagnostic throughput and eliminate human-caused diagnostic errors. This measure was taken to improve diagnostic precision. To be carried out, the fully supervised learning process needs a large amount of accurately labelled data. Annotating data material, on the other hand, demands a large expenditure of time, effort, and resources. Using the self- supervised learning approach to solve this challenge has the potential to provide a variety of beneficial outcomes for everyone. When there is no direct supervision, pretext projects are regularly employed in independent study scenarios. This is done so that massive volumes of unsupervised data may be utilized to obtain supervised knowledge. Furthermore, by utilizing specialized, supervised information, the network is prepared to obtain representations that will be beneficial for still-growing professions. The two-step CPC-based classification framework (TCC) model is built completely using contrastive predictive coding and is divided into two distinct phases that are carried out in sequential order. Making use of the contrastive predictive coding (CPC) model, the initial step is to build a fictional position. It must be completed as quickly as possible. This activity must utilize the encoder to extract appropriate features from a broad variety of classes in order to achieve the goal that it has set out to achieve. The encoder will employ the skills they learned while working on the pretext in the second half, which will take place in a training setting under the guidance of an expert teacher. Finally, we assess the proposed framework by comparing it to the most recent and innovative research in the field. This allows us to highlight the framework’s success by displaying how well it compares to other cutting-edge and current industry efforts. Experiments will be conducted to compare the efficacy of the pr

关键词： Training Adaptation models Supervised learning Machine learning Predictive coding Predictive models Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An AR-Based Tool for Acquisition and Automatic Labeling of Human-Object Interactions From First Person Vision

An AR-Based Tool for Acquisition and Automatic Labeling of H...

引用

Metrology for Extended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE), IEEE International Conference on

作者： Luigi Seminara Francesco Ragusa Rosario Leonardi Giovanni Maria Farinella Antonino Furnari Dept. Math and Computer Science (DMI) University of Catania (UNICT) Catania Italy Dept. Math and Computer Science (DMI) University of Catania (UNICT) Next Vision S.r.l. - Spinoff of the University of Catania

We consider the problem of detecting Human-Object Interactions (HOIs) from images acquired through the use of wearable devices. Understanding human-object interactions allows to support users in different scenarios, ranging from everyday activities to industrial contexts. In particular, by detecting interactions, it is possible to provide assistance in using specific objects or enhance worker safety by alerting them when they are interacting with dangerous tools. The current approaches for detecting egocentric human-object interactions (EHOIs) require the collection and labeling of domain-specific data in order to fine-tune the models to work in a specific target environment. To reduce the labeling costs generally associated with this process, we developed a new tool that uses spatial mapping, hand poses estimation, and camera tracking capabilities available in the Augmented Reality stack of Microsoft HoloLens2 to collect and automatically label images of human-object interactions performed in the real-world. To assess the effectiveness of the proposed tool, we collected and automatically labeled a dataset of human-object interactions performed on an industrial panel. Experiments with two EHOI recognition models suggest that using the data collected by the proposed tool can improve model performance in the considered target domain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Maximum Likelihood Uncertainty Estimation: Robustness to Outliers

Maximum Likelihood Uncertainty Estimation: Robustness to Out...

引用

2022 Workshop on Artificial Intelligence Safety, SafeAI 2022

作者： Nair, Deebul S. Hochgeschwender, Nico Olivares-Mendez, Miguel A. Dept. of Computer Science Bonn-Rhein-Sieg University of Applied Sciences Germany Institute for Software Technology Germany SpaceR Research Group University of Luxembourg Luxembourg

We benchmark the robustness of maximum likelihood based uncertainty estimation methods to outliers in training data for regression tasks. Outliers or noisy labels in training data results in degraded performances as well as incorrect estimation of uncertainty. We propose the use of a heavy-tailed distribution (Laplace distribution) to improve the robustness to outliers. This property is evaluated using standard regression benchmarks and on a high-dimensional regression task of monocular dept. estimation, both containing outliers. In particular, heavy-tailed distribution based maximum likelihood provides better uncertainty estimates, better separation in uncertainty for out-of-distribution data, as well as better detection of adversarial attacks in the presence of outliers. Copyright © 2022, for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Construction of Knowledge Graphs: State and Challenges

arXiv

引用

arXiv 2023年

作者： Hofer, Marvin Obraczka, Daniel Saeedi, Alieh Köpcke, Hanna Rahm, Erhard Dept. of Computer Science Leipzig University Germany Dresden Leipzig Germany Faculty Applied Computer Sciences and Biosciences Mittweida University of Applied Sciences Germany

With knowledge graphs (KGs) at the center of numerous applications such as recommender systems and question answering, the need for generalized pipelines to construct and continuously update such KGs is increasing. While the individual steps that are necessary to create KGs from unstructured (e.g. text) and structured data sources (e.g. databases) are mostly well-researched for their one-shot execution, their adoption for incremental KG updates and the interplay of the individual steps have hardly been investigated in a systematic manner so far. In this work, we first discuss the main graph models for KGs and introduce the major requirements for future KG construction pipelines. Next, we provide an overview of the necessary steps to build high-quality KGs, including cross-cutting topics such as metadata management, ontology development, and quality assurance. We then evaluate the state of the art of KG construction w.r.t the introduced requirements for specific popular KGs as well as some recent tools and strategies for KG construction. Finally, we identify areas in need of further research and improvement. © 2023, CC BY-NC-SA.

关键词： Quality assurance

来源：评论

学校读者我要写书评

暂无评论

Multilingual Sentiment Analysis using DistilBert

Multilingual Sentiment Analysis using DistilBert

引用

Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA), International Conference on

作者： Nishi Gupta Mandip Bhattarai Abhishek Chavan Dept. of Applied Science and Humanities Pimpri Chinchwad College of Engineering Pune Maharastra India Dept. of Computer Engineering Pimpri Chinchwad College of Engineering Pune Maharastra India

ISBN: (数字)9798331517953

ISBN: (纸本)9798331517960

In today's virtual age, studying feelings and sentiments through textual content and emojis is essential. This research article explores a way to use natural language processing (NLP) techniques to interpret feelings from textual content and emoji content. We used the distilbert-base-uncased-finetuned-sst2english version, a small variant model of BERT, to categorize feelings as positive or negative. Our experiments confirmed that the version executed extraordinarily properly throughout more than one language, with especially great effects on Indonesian textual content. Our assessment confirmed that the version has an excellent accuracy of91.50% and an F1 rating of 91.44% for Indonesian, highlighting its wonderful overall performance in this language. It additionally plays properly in English, French, German, Arabic, and Italian, even though overall performance may also range through language. These effects reveal the version's effectiveness for duties, social media monitoring, client comments evaluation, and inventory marketplace fashion assessment. We finish with a conclusion about the results of those findings.

关键词： Sentiment analysis Quantum computing Accuracy Social networking (online) Multilingual Artificial intelligence Monitoring Emojis

来源：评论

学校读者我要写书评

暂无评论

On the Parallelizability of Approval-Based Committee Rules

arXiv

引用

arXiv 2025年

作者： Fitzsimmons, Zack Hassan, Zohair Raza Hemaspaandra, Edith Dept. of Math. and Computer Science College of the Holy Cross WorcesterMA01610 United States Department of Computer Science Rochester Institute of Technology RochesterNY14623 United States

Approval-Based Committee (ABC) rules are an important tool for choosing a fair set of candidates when given the preferences of a collection of voters. Though finding a winning committee for many ABC rules is NP-hard, natural variations for these rules with polynomial-time algorithms exist. The Method of Equal Shares, an important ABC rule with desirable properties, is also computable in polynomial time. However, when working with very large elections, polynomial time is not enough and parallelization may be necessary. We show that computing a winning committee using these ABC rules (including the Method of Equal Shares) is P-hard, thus showing they cannot be parallelized. In contrast, we show that finding a winning committee can be parallelized when the votes are single-peaked or single-crossing for the important ABC rule Chamberlin-Courant. Copyright © 2025, The Authors. All rights reserved.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

Adaptive Context and Trust Aware Access Control Mechanism for Personal Health Record in Ubiquitous Environment

Adaptive Context and Trust Aware Access Control Mechanism fo...

引用

Smart Systems for applications in Electrical sciences (ICSSES), International Conference on

作者： G Jagadamba G Chayashree R Chethan Dept. of Computer Science and Engineering Ramaiah University of Applied Sciences Bengaluru Karnataka Dept. of Infromation Sceince and Engineeing Vidya Vardaka College of Engineering Mysuru Karnataka Dept. of Mathemetics Siddaganaga Institute of Technology Tumakuru Karnataka

ISBN: (数字)9798331507671

ISBN: (纸本)9798331507688

In the ubiquitous world, Personal health record (PHR) is shared with authorized entity in a patient-centric health records exchange model. However, due to privacy concerns, access control over PHR is achieved through authentication techniques. But, scalability, flexible access, context-aware and efficient user withdrawal have remained the most significant challenges for control over the PHR data access. In this paper, a health record access framework is proposed for PHR access. The adoption of context based three-factor authentication techniques achieves scalable and fine-grained PHR access control. The proposed scheme allows dynamic variation of access policies to support efficient on-demand access under non-emergency and emergency scenarios.

关键词： Access control Privacy Adaptive systems Scalability Authentication Smart systems

来源：评论

学校读者我要写书评

暂无评论

Systematic Literature Review of Security Control Assessment Challenges 12

Systematic Literature Review of Security Control Assessment ...

引用

12th IEEE International Conference on Control System, Computing and Engineering, ICCSCE 2022

作者： Abu Othman, Noor Ashitah Norman, Azah Anir Mat Kiah, Miss Laiha Universiti Malaya Faculty of Comp. Science & Information Technology Kuala Lumpur Malaysia Universiti Teknologi MARA Faculty of Computer & Math. Sciences Melaka Malaysia Universiti Malaya Faculty of Computer Science & Information Technology Dept. of Information Systems Kuala Lumpur Malaysia Universiti Malaya Faculty of Computer Science & Information Technology Dept. of Computer System &Technology Kuala Lumpur Malaysia

ISBN: (数字)9781665483391

ISBN: (纸本)9781665483391

The advancement of cybersecurity has called for active effective information security management. Security control (SC) assessment must be empowered to ensure that security implementation is effective and provides expected protection. Lack of comprehensive literature analysis on SC assessment compared to risk and threats assessments are concerning. This research aims to systematically review the trends of SC assessment by identifying, categorizing and analyzing the challenges and available solutions of SC assessment. 34 articles were qualitatively selected with a definite contribution in SC assessment. These articles were reviewed using thematic analysis according to Theme 1: Assessment Challenges, and Theme 2: Proposed Solution. Findings from each theme are systematically categorized to answer research questions. The results of this review are significant in identifying the issues and areas of improvement for future research and can serve as the baseline for SC assessment characteristics. © 2022 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Defensive Adversarial Training for Enhancing Robustness of ECG based User Identification∗

Defensive Adversarial Training for Enhancing Robustness of E...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Jeong, Hongbi Son, Junggab Kim, Hyunbum Kang, Kyungtae Hanyang University Dept. Applied Artificial Intelligence Major in Bio Artificial Intelligence Ansan Korea Republic of University of Nevada Las Vegas Dept. Computer Science Las VegasNV89154 United States Incheon National University Dept. Embedded Systems Engineering Incheon Korea Republic of Hanyang University Dept. Applied Artificial Intelligence Ansan Korea Republic of

ISBN: (纸本)9781665468190

Electrocardiogram (ECG) based user identification has received considerable attention with the advent of wearable devices. It provides emerging applications including personal healthcare a convenient way to authenticate users as the process can be performed at the moment the user makes contact with the device. However, a recent study discovered that injecting noise into the signal transmitted from the user to an application can effectively hinder the classification process. Many efforts have been made to deal with this noise injection attack, but most approaches have focused on noise removal. In contrast, this paper proposes Defensive Adversarial Training (DAT), which involves training a model with various noisy data to enhance the robustness of deep learning-based identification algorithms. We used two types of noise, Gaussian and Laplacian, to create noisy data. In addition, a sliding-window technique was used to effectively extract useful features and to achieve better accuracy. Our simulation results demonstrate that the proposed approach is highly robust to noise injection attacks and even against random noise. A comparative analysis with noise removal schemes also shows that the proposed DAT significantly enhances the robustness of ECG-based user identification. © 2022 IEEE.

关键词： Electrocardiograms

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：