检索结果-内蒙古大学图书馆

26th Pan-Hellenic Conference on informatics, PCI 2022

作者： Komninos, Andreas Tsigkas, Georgios Computer Engineering & Informatics Dept. University of Patras Patras Greece

ISBN: (纸本)9781450398541

Our time is characterized by big sprawling urban complexes that a majority of the human population chooses to live where interactions with the environment seem to be vanishing from our day to day lives. Our relationship with the planet's natural ecosystem is paramount to our survival and well-being, a relationship that begins to form during our childhood years. Considering the above we propose a novel system which aims to give the ability to children to interact with the natural environment even when they have no access to it, from the classrooms in which they spend considerable parts of their lives. Specifically the proposed system is based on the technology of the Digital Twin, a core pillar of the 4th Industrial Revolution, and is comprised of a smart birdhouse and an electronic Digital Twin. The smart birdhouse can be deployed in a natural environment and collect atmospheric data like humidity and temperature values as well as record audio and pictures of possible bird visitors. At the same time the collected data will be available to the end user through a dashboard platform for atmospheric parameters and the digital electronic twin which will play the collected sound or pictures. With the above system we aim to achieve a greater and meaningful engagement of children with their natural habitat even when their urban environment makes it impractical or unfeasible. © 2022 ACM.

关键词： Industry 4.0

来源：评论

学校读者我要写书评

暂无评论

Increasing Hosting Capacity of Uncontrollable Distributed Energy Resources in Isolated Power Systems

Increasing Hosting Capacity of Uncontrollable Distributed En...

引用

2023 IEEE PES Innovative Smart Grid Technologies Europe, ISGT EUROPE 2023

作者： Therapontos, Phivos Stavrou, Andreas Aristidou, Petros Electricity Authority of Cyprus Nicosia Cyprus Department of Electrical and Computer Engineering Nicosia Cyprus Dept. of Electrical and Computer Engineering and Informatics Cyprus University of Technology Limassol Cyprus

ISBN: (纸本)9798350396782

Due to the push for more sustainable generation, small-scale distributed energy resources (DERs) penetration has increased significantly. Most countries have no remote monitoring and control requirements for DERs below a certain size. Therefore, they can be labeled as uncontrollable DERs (UDERs). In isolated systems, the UDERs hosting capacity is limited due to frequency stability concerns, as it is impossible to modify or curtail their generation in a centralized manner. In this paper, we propose the utilization of the active power over-frequency reduction curve for increasing the hosting capacity of UDERs in isolated power systems. Cyprus’s power system has been used to evaluate the proposed solution’s performance. The optimal settings of the curve have been identified, and it was found that UDERs hosting capacity can be increased significantly with the proposed methodology. © 2023 IEEE.

关键词： frequency stability grid code requirements hosting capacity islanded systems uncontrollable distributed energy resources

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Prediction Using Artificial Intelligence Technology 4

Breast Cancer Prediction Using Artificial Intelligence Techn...

引用

4th International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Akila, V. Christaline, J. Anita Srm Institute of Science and Technology Vadapalani Dept. of Electronics and Communication Engineering Chennai India Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350343670

The aim of the project is to compare the performance of four different machine learning algorithms for breast cancer prediction such as decision tree, logistic regression, XG boost, and CAT boost. We used a dataset of patient medical records containing various clinical factors to train and test the algorithms. Accurate diagnosis and early detection are essential for enhancing patient outcomes. Data mining is a prominent tool in the healthcare industry for processing massive amounts of data. To examine massive amounts of complicated medical data, researchers use a variety of data mining and machine learning approaches. The use of these strategies can help medical practitioners forecast the onset of breast cancer. © 2024 IEEE.

关键词： Algorithms Breast cancer Data mining Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Federated Semi-Supervised Medical Image Classification Using Improved Inter-Client Relation Matching 8

Federated Semi-Supervised Medical Image Classification Using...

引用

8th International Conference on Data Science and Machine Learning Applications, CDMA 2025

作者： Ozdemir, Muhammed Said Sabbagh, Mais Erdem, Cigdem Eroglu Korcak, Omer Uludag, Kubra Marmara University Faculty of Eng. Department of Computer Engineering İstanbul Turkey Ozyegin University İstanbul Turkey Dept. of Electrical and Electronics Eng. Istanbul Turkey Marmara University Faculty of Engineering Department of Computer Engineering İstanbul Turkey

ISBN: (纸本)9798331539696

Traditional centralized machine learning faces chal-lenges with 'data label scarcity' and 'data privacy', especially in medical data classification. Semi-supervised learning leverages unlabeled data, while federated learning protects data privacy by decentralizing model training. In this study, we introduce an improved inter-client relation matching algorithm for semi-supervised federated medical image classification (iFedIRM). The FedIRM algorithm defines a loss function to transfer the knowledge of disease relationships from labeled clients to unlabeled clients to extract discriminative information from unlabeled data using per-category mean feature vectors. Our approach enhances the FedIRM algorithm by incorporating per-category feature covariance matrices for better feature representation and using group-based averaging for model aggregation. We utilize the ConvNeXt architecture as the backbone, and apply a confidence threshold to filter unreliable pseudo-labels. Experiments on three medical datasets show improved accuracy, F1, and AUC metrics. Code will be available at https://***/msoz7/iFedIRM. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Valid Keypoint Augmentation based Occluded Person Re-Identification

引用

Transactions of the Korean Institute of Electrical Engineers 2022年第7期71卷 1002-1007页

作者： Kim, Sejun Kang, Sungjae Choi, Hyomin Kim, Seong Soo Seo, Kisung Department of Electronics Engineering Seokyeong University Korea Republic of Department of Electronics and Computer Engineering Seokyeong University Korea Republic of Dept. of Electrical & Electronic Engineering Yonam Institute of Technology Korea Republic of

Occluded person re-identification is a challenging task which aims to search for or distinguish the specific person as human body is occluded by obstacles or other persons or by oneself. Some recent State of the art works which adopt transformer and/or pose-guided methods improve the feature representation and performances, but there is a room to enhance them in both representation and heavy structure. In this paper, we suggest to efficiently improve the transformer-based Re-ID method for the occluded person as follows. First, in data augmentation to improve Re-identification performance, instead of deleting an arbitrary area, only the part containing the keypoint feature of a person is deleted for effective learning in occlusion. Second, a consistency loss between global and local features of a body part is proposed for improving the discrimination to recognize the identical person. We compare the mAP and Rank-1 performances of our approach and various existing methods on the Occluded-Duke dataset. Experimental results show that our proposed model outperforms the competitive methods. © 2022 Korean Institute of Electrical Engineers. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Different Hardware Platforms in Wireless Sensor Networks 4

Performance Analysis of Different Hardware Platforms in Wire...

引用

4th International Conference on Signal Processing and Communication, ICSPC 2023

作者： Jebarani, P. Esther Jone, Amir Anton Jose, Tony Paul, J. John Jose, Shelja Kumar, Pradeep Kovai Kalaimagal College of Arts and Science Coimbatore Dept. of Computer Science India Karunya Institute of Technology and Sciences Coimbatore Dept. of Electronics and Communication Engineering India Indira Gandhi Institute of Engineering and Technology Dept. of Electronics and Communication Engineering Kothamangalam India

ISBN: (纸本)9798350300772

Wireless Sensor Networks (WSN) encompasses rapid development in research area through large scale applications. The main objective is to compare four different hardware platforms such as Rene, Mica, Spec and Blue in order to find efficient hardware platform that can provide best performance within certain constraints while working on TinyOS as operating system. The four different hardware platforms are compared on the basis of certain constraints such as data communication, rendezvous(mJ/day), alarm checking, sensing, sleep (units in mJ/day), expected lifetime (units in years). According to this investigation, mica outperforms the four different platforms in terms of decoupling between RF and data path speed, bit rate, and timing accuracy. However, future specifications will be found to be more efficient based on CMOS processes and RF radio technology, which results in lower costs, smaller sizes, lower power requirements, and a decrease in complexity. © 2023 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Resource Efficient Federated Learning for Deep Anomaly Detection in Industrial IoT applications 24

Resource Efficient Federated Learning for Deep Anomaly Detec...

引用

24th International Conference on Digital Signal Processing, DSP 2023

作者： Gkillas, Alexandros Lalos, Aris Industrial Systems Institute Athena Research Center Greece University of Patras Dept. of Computer Engineering and Informatics Greece

ISBN: (纸本)9798350339598

Anomaly data constitute a thorny problem in numerous industrial applications. In recent years, deep learning enabled anomaly detection has emerged as a critical direction, however the improved detection accuracy and reconstruction is achieved with the utilization of large neural networks with more layers and nodes, increasing their storage and computational cost. Moreover, the data collected in edge devices contain user privacy, introducing challenges that can be successfully addressed by the very recent on-device privacy-preserving distributed machine learning paradigm, known as federated learning (FL). This paradigm allows edge devices to locally train and exchange models increasing also the communication cost. Thus, in order to deal with the increased communication, processing and storage challenges introduced by FL based deep anomaly detection NN pruning is expected to have significant benefits towards both reducing the processing, storage and communication complexity but also towards avoiding the over fitting problem. With this focus, a novel compression-based optimization problem is proposed at the server-side of a FL paradigm that simultaneously fusses the local models broadcast by the edge devices and performs pruning generating a much more compressed model to be deployed at the edge devices with no accuracy loss even if the training is performed using a small subset of data instances, achieving compression rates greater than 99%. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Enhancing Device Authentication in IoT Security Application using Artificial Intelligence: A Survey 3

Enhancing Device Authentication in IoT Security Application ...

引用

3rd International Conference on Communication, Control, and Intelligent Systems, CCIS 2024

作者： Brogya, Maame Serwah Dumfeh Ayuso, Enrique Shukla, Aasheesh Goyal, Amit Kumar Sain, Mangal Dongseo University Dept. of Computer Engineering Busan Korea Republic of Gla University Department of Electronics and Communication Mathura India Chandigarh University Department of Computer Science and Engineering Mohali140413 India

ISBN: (纸本)9798331528201

Technological advancement over the last decade has seen significant technological development, particularly in IoT, which is the most used and commercialized. This is due to its convenience, as it gives users remote control of their appliances via portable devices like smartphones and tablets, without needing to be physically present or close to those devices. As IoT technologies continue to grow and new innovative solutions for everyday applications are being developed there are more interconnected devices and large volumes of data being generated every second. However, the rapid growth of IoT has heightened security concerns, especially around device authentication. This paper reviews IoT authentication complexities and explores Machine Learning solutions under AI, comparing various algorithms and, providing a foundation for researchers and developers in the field. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Comparison of Fast Frequency Response Methods in the Low-Inertia Grid of Cyprus 3

Comparison of Fast Frequency Response Methods in the Low-Ine...

引用

3rd International Conference on Energy Transition in the Mediterranean Area, SyNERGY MED 2024

作者： Argyrou, Andreas Panagi, Savvas Aristidou, Petros Electricity Authority of Cyprus Distribution System Operator Nicosia Cyprus Cyprus University of Technology Dept. of Electrical & Computer Engineering & Informatics Limassol Cyprus

ISBN: (纸本)9798350375923

Modern electric power systems with high levels of penetration of renewable energy sources (RES) often present frequency security problems. The lack of inertia due to the reduced number of synchronous generators in these systems, in combination with the usual inability of RES to provide frequency support, leads to system operators having to curtail RES or rely heavily on Under Frequency Load Shedding schemes to ensure frequency security. Fast Frequency Reserves (FFR) have been proposed as a solution to strengthen the frequency support of the system and alleviate security problems. FFR allows mitigating Rate of Change of Frequency, Nadir, and post-fault frequency steady-state problems after an event. In this paper, we present, analyze, implement and compare five FFR controllers to alleviate frequency security problems in low-inertia grids. The low-inertia, islanded, Cyprus dynamic model is used to quantify the results and exhibit the impact on a real system. © 2024 IEEE.

关键词： Synchronous generators

来源：评论

学校读者我要写书评

暂无评论

A Fast Response Fault Detection Technique for HVAC Transmission Line Using Machine Learning 10

A Fast Response Fault Detection Technique for HVAC Transmiss...

引用

10th IEEE International Conference on Power Systems, ICPS 2023

作者： Muntasir, Fahim Al Wazed Wasi, Wasif Nafis, Mahdee Hossain, M. Mofazzal Brac University Dept. of Computer Science and Engineering Dhaka Bangladesh Rajshahi University of Engineering and Technology Dept. of Electrical and Electronic Engineering Rajshahi Bangladesh Rajshahi University of Engineering and Technology Dept. of Electronics and Telecommunication Engineering Rajshahi Bangladesh University of Liberal Arts Bangladesh Dept. of Electrical and Electronic Engineering Dhaka Bangladesh

ISBN: (纸本)9798350318739

High voltage alternating current (HVAC) transmission lines are the only way to transmit electrical energy from the power plant to the utilities. There are several types of transmission line faults that can interrupt the power supply, sometimes even resulting in national blackout. To ensure a highly reliable power supply system, detecting the faults in the quickest of time is crucial. This research used machine learning and neural network algorithm to find five different types of faults using data from a real power transmission line in Bangladesh. Apart from the accuracy of the methods, the focus was given on the response time in identifying the faults. The two boosting methods CatBoost and XGBoost stood out as the most precise among all the algorithms, achieving excellent accuracy and detection time in between 20 ms to 30 ms. The response time of all the methods was found to be in millisecond range, making them perfect for not only long term faults, but also to be implied in transient fault analysis. © 2023 IEEE.

关键词： Machine learning

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：