检索结果-内蒙古大学图书馆

10th International Conference on Automation, Robotics, and Applications, ICARA 2024

作者： Aabitova, Gulnara Abalkanov, Miras Abitova, Gulnara A. Shuteyeva, Gulnur Aitmukhanbetova, Elvira Kulniyazova, Korlan Astana IT University Dep. Computer Engineeering Astana Kazakhstan State Univerity of New York at Binghamton Dept. Electical Engineering and Computer Science Binghamton United States Eurasian National University Dept. System Anslysis and Managemnt Astana Kazakhstan

ISBN: (纸本)9798350394245

The paper presents a comprehensive analysis of the integration of Cloud AI in real-time fraud detection, highlighting significant advancements and practical applications. It is identifying a key challenge such as data privacy and the need for scalable solutions, while also exploring the potential of innovative AI algorithms and strategic partnerships to enhance fraud detection capabilities. Through detailed case studies, the work is demonstrated the effective application of Cloud AI across various sectors. The study concludes that Cloud AI, despite not being a complete solution, plays a crucial role in strengthening fraud detection systems. Our findings suggest that strategic implementation of Cloud AI can lead to more adaptive and efficient systems, thereby significantly contributing to the economic sector's resilience against fraudulent activities. This paper underscores the transformative impact of Cloud AI in fraud detection, offering insights into its future potential and laying the groundwork for further advancements in this field. © 2024 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Alert system with IoT Techniques for Stray Children 2

Alert system with IoT Techniques for Stray Children

引用

2nd International Conference on Cybernetics and Innovations, ICCI 2023

作者： Pramkeaw, Patiyuth Ganokratanaa, Thittaporn Pinthong, Thidarat Kitprasert, Napathsorn King Mongkut's University of Technology Thonburi Media Technology Program Bangkok Thailand King Mongkut's University of Technology Thonburi Applied Computer Science Program Bangkok Thailand Phetchaburi Rajabhat University Dep. of Business Information Management Phetchaburi Thailand

ISBN: (纸本)9798350336573

The purpose of this research was to design, produce and evaluate a stray child warning system. The device has been designed by using 2 ESP8266 boards to receive signals as specified. The system will notify the information via Line Notify to let users know how far the board that acts as a Client is from the board that acts as an Access Point. Expressed in meters (m) in the notification line notify process. The test results of the system in terms of signal transmission between the Access Point and the Client can work well. Buzzer speaker and LED notification light according to the specified distance every time. Notifications to LINE Notify to mobile phones can be done every time. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

FOCUSED ACTIVE LEARNING FOR HISTOPATHOLOGICAL IMAGE CLASSIFICATION

arXiv

引用

arXiv 2024年

作者： Schmidt, Arne Morales-Álvarez, Pablo Cooper, Lee A.D. Newberg, Lee A. Enquobahrie, Andinet Katsaggelos, Aggelos K. Molina, Rafael Dep. of Computer Science and AI University of Granada Granada Spain Dep. of Statistics and Operations Research University of Granada Granada Spain Dep. of Pathology Northwestern University Chicago United States Kitware Inc Carrboro United States Dep. of Electrical Computer Engineering Northwestern University Evanston United States

Active Learning (AL) has the potential to solve a major problem of digital pathology: the efficient acquisition of labeled data for machine learning algorithms. However, existing AL methods often struggle in realistic settings with artifacts, ambiguities, and class imbalances, as commonly seen in the medical field. The lack of precise uncertainty estimations leads to the acquisition of images with a low informative value. To address these challenges, we propose Focused Active Learning (FocAL), which combines a Bayesian Neural Network with Out-of-Distribution detection to estimate different uncertainties for the acquisition function. Specifically, the weighted epistemic uncertainty accounts for the class imbalance, aleatoric uncertainty for ambiguous images, and an OoD score for artifacts. We perform extensive experiments to validate our method on MNIST and the real-world Panda dataset for the classification of prostate cancer. The results confirm that other AL methods are’distracted’ by ambiguities and artifacts which harm the performance. FocAL effectively focuses on the most informative images, avoiding ambiguities and artifacts during acquisition. For both experiments, FocAL outperforms existing AL approaches, reaching a Cohen’s kappa of 0.764 with only 0.69% of the labeled Panda data. © 2024, CC BY.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

AI-driven Risk Assessment and Decision-making in Healthcare Applications Using Machine Learning: A Case Study on Customer Twitter Feeds

AI-driven Risk Assessment and Decision-making in Healthcare ...

引用

Computational Intelligence and Network Systems (CINS), International Conference on

作者： Abdelaziz Darwiesh Mohamed Elhoseny A.H. El-Baz Reem Atassi Mathematics Dep. Faculty of Science Damietta University New Damietta Egypt Information Systems Dep. Faculty of Computing and Info. University of Sharjah Sharjah UAE Computer Science Dep. Faculty of Computers and Artificial Intelligence Damietta University New Damietta Egypt Higher Colleges of Technology Dubai UAE

ISBN: (数字)9798331504106

ISBN: (纸本)9798331504113

This study presents an AI-driven strategy for enhancing decision-making in healthcare applications by assessing and managing potential risks through the analysis of customer interactions on social media platforms, specifically Twitter. We propose the use of machine learning models to outperform traditional lexical approaches, addressing the complexities inherent in risk detection. Natural language processing methods are employed to efficiently process and analyze textual data, enabling healthcare institutions to make informed decisions about risk management. By leveraging customer feedback from the X platform, our approach aids in the development of effective healthcare programs by identifying and classifying risks. We create three specialized datasets for risk analysis, risk assessment, and hazard classification to optimize the training and dep.oyment phases. In our case study, which focuses on tweets related to healthcare for US consumers, we find that over 50% of the sample identifies potential risks, with nearly 80% indicating medium levels of risk. Commonly identified risks include financial, operational, and strategic threats. The proposed methodology demonstrates an average accuracy of 82.66% in risk detection, identification, and assessment, confirming its effectiveness in supporting AI-driven decision-making in healthcare application development.

关键词： Training Accuracy Social networking (online) Computational modeling Decision making Blogs Medical services Natural language processing Complexity theory Risk management

来源：评论

学校读者我要写书评

暂无评论

Bayesian Network Structure Discovery Using Antlion Optimization Algorithm.

International Journal of Systematic Innovation

引用

International Journal of Systematic Innovation 2022年第1期7卷 46-65页

作者： Awla, Hoshang Qasim Kareem, Shahab Wahhab Mohammed, Amin Salih Computer science department Faculty of Science Soran University Erbil Iraq Dep. of Technical Information Systems Engineering Erbil Technical Engineering College Erbil Poly-technic University Erbil Iraq Department of Information Technology College of Engineering and Computer Science Lebanese French University Kurdistan Region Erbil Iraq

Bayesian networks have recently been used for discovering an optimal learning structure in machine learning. Bayes networks can describe possible dep.ndencies of explanatory variables. As a novel approach to studying the structure of a Bayesian network, the authors present the Antlion Optimization Algorithm (ALO). In the algorithm;deletion, rewind, insertion, and change are utilized to produce ALO to reach the best hull solution. Essentially, the technique used in the ALO algorithm imitates the antlions’ behaviors while hunting. The suggested approach is contrasted with simulated Annealing, Simulated Annealing Hybrid Bee, Greedy Search Hybrid Bee, optimization inspired by Pigeon, and greedy search using the BDe Score function. The researchers also studied the representation of the confusion matrix of these techniques using different reference data sets. The findings of the assessments reveal that the proposed algorithm works better than the other algorithms and has better consistency and score values. As shown by the experimental evaluations, the proposed method has a more reliable performance than other algorithms (including the production of excellent scores and accuracy values). © 2022. All Rights Reserved.

关键词： Antlion Optimization Bayesian Network Hunting Search Local & Global Search Metaheuristics Search and Score Structure Learning

来源：评论

学校读者我要写书评

暂无评论

Implementation and Design of Physical/Digital Switches Modified from Sonoff Product Based on Internet of Things 4

Implementation and Design of Physical/Digital Switches Modif...

引用

4th IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022

作者： Tsao, Yung-Chung Kuo, Yaw-Wen Wu, Chia-Chun Tsai, Yin-Te Hsu, Chihcheng Li, Chiyang Wang, Han-Ching National Chi Nan University Dep. of Electrical Engineering Nantou County Taiwan National Quemoy University Dep. of Industrial Engineering and Management Kinmen County Taiwan Providence University Dep. of Computer Science and Communication Engineering Taichung City Taiwan National Central University Dep. of Information Management Taoyuan Country Taiwan College of Science and Technology National Chi Nan University Nantou County Taiwan Xinhe Elementary School Xindian District New Taipei City Taiwan

ISBN: (数字)9781728195797

ISBN: (纸本)9781728195797

While more home appliances are designed and manufactured, Sonoff serial home assistant alliances are designed and manufactured by eWeLink for many cheap and convenient devices controlled with exclusive APPs. Sonoff home assistant alliances are popular and well-known to attract many developers who can develop unofficial software to enhance the closed APPs designed by eWeLink and make flexible applications based on original hardware such as Tasmota and parameterized open-source APPs. We follow the above-mentioned developers to design a firmware that controls and is controlled based on message queue telemetry transport (MQTT) protocol from a cloud platform and the internet of thing (IoT) based architecture. The Sonoff home assistant alliances installed by the designed firmware can be controlled with one or more groups through a clouding platform by existing physical power-sockets from one-to-one controlling by eWeLink APPs. Under the proposed architecture, those Sonoff serial home assistant alliances are easily used like traditional power sockets for old-age users, who only use physical switches with touch-panel with MCU-based controllers to control power sockets. We designed digital switches on the website by browsers and physical touch panels as traditional switches work indep.ndently and coexist to meet most users with software-based APPs. The proposed architecture can be implemented and dep.oyed as a proof of concept (PoC) for the usability and validity. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Review of Grid-Connected Inverters and Control Methods Under Unbalanced Grid Conditions

A Review of Grid-Connected Inverters and Control Methods Und...

引用

Power Electronic and Drive Systems and Technologies Conference (PEDSTC)

作者： Milad Ghavipanjeh Marangalu Fazal Ur Rehman Naser Vosoughi Kurkdjian Dep. Of Electrical and Computer Engineering Computer Queen’s University Kingston Ontario Canada Dep. Information Engineering Computer Science and Mathematics University of L’Aquila L’Aquila Italy Faculty of Electrical and Computer Engineering San Diego State University San Diego CA USA

ISBN: (数字)9798331533946

ISBN: (纸本)9798331533953

Grid-connected inverters play a pivotal role in integrating renewable energy sources into modern power systems. However, the presence of unbalanced grid conditions poses significant challenges to the stable operation of these inverters. This review paper provides a comprehensive overview of grid-connected inverters and control methods tailored to address unbalanced grid conditions. Beginning with an introduction to the fundamentals of grid-connected inverters, the paper elucidates the impact of unbalanced grid voltages on their performance. Various control strategies, including voltage and current control methods, are examined in detail, highlighting their strengths and limitations in mitigating the effects of grid imbalance. Lastly, the review identifies emerging trends and future research directions in the field, emphasizing the need for innovative solutions to address the evolving challenges posed by unbalanced grid conditions in the context of renewable energy integration.

关键词： Current control Photovoltaic systems Renewable energy sources Technological innovation Reviews Pressing Market research Inverters Power systems Voltage control

来源：评论

学校读者我要写书评

暂无评论

Implementation and Design of Water Flow Meter of Smart Home Integrated with Environment Monitor System 4

Implementation and Design of Water Flow Meter of Smart Home ...

引用

4th IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2022

作者： Tsao, Yung-Chung Kuo, Yaw-Wen Wu, Chia-Chun Tsai, Yin-Te Hsu, Chihcheng Ho, Liulin Wang, Han-Ching National Chi Nan University Dep. of Electrical Engineering Nantou County Taiwan National Quemoy University Dep. of Industrial Engineering and Management Kinmen County Taiwan Providence University Dep. of Computer Science and Communication Engineering Taichung City Taiwan National Central University Dep. of Information Management Taoyuan Country Taiwan College of Science and Technology National Chi Nan University Nantou County Taiwan Xinhe Elementary School Xindian District New Taipei City Taiwan

ISBN: (数字)9781728195797

ISBN: (纸本)9781728195797

More home appliances were designed and manufactured in the market, but fewer commercial products related to water-flow monitoring are sold in the current market. Water-related costs and expenses are cheaper than others, but water is one of the critical survival necessities for human beings. Thus, the home appliances or the smart home needs to pay attention to ubiquitous water resources as one of the limited natural earth resources. We follow the above-mentioned issues to achieve an internet of things (IoT) based architecture to design a flow-monitoring information collecting device (FMICD). Hall sensors were used to collect the water-flow consumption and to upload the information of the environment monitor system which was implemented in the previous research. In the proposed architecture, the FMICDs are designed and developed with the MCU-based controller binding to a water-flow meter (Model: YF-S201) equipped to monitor water consumption. We implemented FMICDs in the Xinhe Elementary School in the Xindian District of New Taipei City in Taiwan to validate the usability and feasibility of the study with a website (http://***:9999/***) to offer related users and staff to validate the usability in the study. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Functional Local Mean K-Nearest Neighbor: introducing a novel metric for improved algorithm performance

Functional Local Mean K-Nearest Neighbor: introducing a nove...

引用

Intelligent Systems and computer Vision (ISCV)

作者： Mohammed Sabri Ali Yahyaouy Antonio Balzanella Rosanna Verde Jamal Riffi Hamid Tairi Dep. of Computer Science Sidi Mohamed Ben Abdellah University Fez Morocco Dep. of Mathematics and Physics University of Campania Luigi Vanvitelli Caserta Italy

ISBN: (数字)9798350350180

ISBN: (纸本)9798350350197

Classifying high-dimensional data is problematic due to the curse of dimensionality, which complicates the analysis and accuracy of classification models. This research introduces an innovative classification approach for functional data through a novel functional metric. This metric leverages both the original curves and their derivatives to ascertain the nearest neighbors for new queries. While the classical functional K-nearest neighbor (KNN) classifier is a straightforward and effective nonparametric method for pattern classification, its performance can be compromised by the neighborhood size k and the simplistic majority voting within k-neighborhoods, particularly in scenarios characterized by small sample sizes and the presence of outliers. To address these challenges, this study proposes a locality constrained based KNN, aimed at enhancing the classification efficacy of functional data. A novel K-nearest neighbor technique, utilizing neighborhood local mean, has been developed to improve classification accuracy and decrease dep.ndency on the neighborhood size parameter k. The performance of the proposed Functional Locality Mean KNN (FLMKNN) algorithm is rigorously evaluated against functional KNN methodology across various real functional datasets commonly referenced in scholarly research. Comprehensive experiments underscore the superior performance and robustness of our approach to classifying functional data.

关键词： Accuracy Sensitivity Time series analysis Pattern classification Nearest neighbor methods Vectors Robustness

来源：评论

学校读者我要写书评

暂无评论

Initial Case Study Findings for Requirements on Work-Related Health Aspects

Initial Case Study Findings for Requirements on Work-Related...

引用

IEEE International Requirements Engineering Conference Workshops (REW)

作者： Elizabeth Bjarnason Johanna Persson Christofer Rydenfält Dep. Of Computer Science Lund University Lund Sweden Dep. Of Design Sciences Lund University Lund Sweden

Most work implies the use of digital systems and tools, thus, digital technology plays a vital role in modern work environments. Even so, ergonomics and usability of IT systems and digital tools used at work are often weak, which causes work-related health problems including physical, visual, cognitive, and stress-related issues. We pose that one important reason for these types of issues is the lack of methods and guidelines for how to include usability and ergonomics in requirements engineering, in general, and, in particular, when procuring digital systems for use in the workplace. In our ongoing research project, we are exploring how work-related health aspects are handled in requirements specifications used for public procurement of IT systems for municipal care and health care services. We have acquired procurement documentation from 92 (of 290) Swedish municipalities and are in the process of performing qualitative content analysis of a subset of these. In this paper, we describe our overall research approach and provide some initial observations based on analysis of three public procurements. We observe a variation in how requirements specifications are structured and present an initial set of work-related health aspects to consider when specifying requirements for IT systems to be used in the workplace.

关键词：

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：