检索结果-内蒙古大学图书馆

2022 IEEE PES Innovative Smart Grid Technologies Conference Europe, ISGT-Europe 2022

作者： Primorac, Mario Klaic, Zvonimir Znidarec, Matej Job, Josip Computer Science and Information Technology Osijek Faculty of Electrical Engineering Osijek Croatia

ISBN: (数字)9781665480321

ISBN: (纸本)9781665480321

Constant increase of electricity demand and integrated renewable energy sources in the grid results in harmonic distortions which can impair power quality (PQ). This paper proposes a methodology for the selection of shunt active power filters as a possible solution to these problems and suggests a way to determine the reference current of the filter. Presented analysis results of the installation of filter units at individual points of the test network, which represent real life distribution grid and power quality measurements, show positive effects of reducing the total harmonic distortion (THD). © 2022 IEEE.

关键词： Power quality

来源：评论

学校读者我要写书评

暂无评论

Survey on recent advances in IoT application layer protocols and machine learning scope for research directions

引用

Digital Communications and Networks 2022年第5期8卷 727-744页

作者： Praveen Kumar Donta Satish Narayana Srirama Tarachand Amgoth Chandra Sekhara Rao Annavarapu Department of Computer Science and Engineering Indian Institute of Technology(Indian School of Mines)Dhanbad826004India School of Computer and Information Sciences University of HyderabadHyderabad500046India Mobile&Cloud Lab Institute of Computer ScienceFaculty of Science and TechnologyUniversity of Tartu50090Estonia

The Internet of Things(IoT)has been growing over the past few years due to its flexibility and ease of use in real-time *** IoT's foremost task is ensuring that there is proper communication among different types of applications and devices,and that the application layer protocols fulfill this ***,as the number of applications grows,it is necessary to modify or enhance the application layer protocols according to specific IoT applications,allowing specific issues to be addressed,such as dynamic adaption to network conditions and ***,several IoT application layer protocols have been enhanced and modified according to application ***,no existing survey articles focus on these *** this article,we survey traditional and recent advances in IoT application layer protocols,as well as relevant real-time applications and their adapted application layer protocols for improving *** changing the nature of protocols for each application is unrealistic,machine learning offers means of making protocols intelligent and is able to adapt *** this context,we focus on providing open challenges to drive IoT application layer protocols in such a direction.

关键词： Internet of things Machine learning Application layer Request-response protocols Publish-subscribe protocols

来源：评论

学校读者我要写书评

暂无评论

Design of Wearable Device for Monitoring the Position of A Person with Dementia 5

Design of Wearable Device for Monitoring the Position of A P...

引用

5th International Seminar on Research of information technology and Intelligent Systems, ISRITI 2022

作者： Aisuwarya, Ratna Akbar, Ilham Universitas Andalas Faculty of Information Technology Computer Engineering Department Padang Indonesia

ISBN: (纸本)9781665455121

The incidence of missing persons with dementia is defined as wandering, a condition in which the person with dementia is lost track of their caregivers. We propose to develop a wearable system that can be used more effectively by people with dementia. The wearable device design aims to reduce the incidence of wandering in the dementia patient. The experimental results show that the system can determine the patient's position and the safe zone within a distance of 15 meters on the mobile application. The Euclidean formula for calculating the distance between a patient and a user as a caregiver or family gives relatively accurate results, with an average distance difference of 0.38 meters. The notification system in the form of vibration, sound, and background color on the application system can notify caregivers or families when the patient is outside a safe area with the coordinates of the patient and user with a 100% success rate. As a backup, SMS messages are sent by the system when the internet signal on the device is interrupted. Thus, the system can still send the location of the patient's google maps coordinates. It can be concluded that the system runs well when the device is in the zone and outside the safe zone. © 2022 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Examining Students' Learning Styles Impacted on Learning Outcome in the MOOC Course: A Case Study 23

Examining Students' Learning Styles Impacted on Learning Out...

引用

9th International Conference on Frontiers of Educational Technologies, ICFET 2023

作者： Nguyen, Viet Anh Computer Science Department Faculty of Information Tecnhology VNU University of Engineering and Technology Vietnam National University Hanoi Viet Nam

ISBN: (纸本)9798400707353

This article presents the results of a study examining the influence of learning styles on students' learning outcomes in the MOOC course. In this study, we analyzed the data of interaction and student learning outcomes after they finished the course by using a quantitative method that combines machine learning and learning analytics to answer two research questions: 1) Which student's learning styles have better learning outcomes? 2) Which learning activities have the utmost influence on learning outcomes? The data of 264 students taking the course is collected automatically through the LMS system. We perform clustering, labeling, and classification techniques to determine the student's learning styles according to the VARK [1] model. Quantitative analysis of the student group data identified learning styles to answer two research questions. The results showed that the students who identified the learning style as Kinesthetic had better academic results, with 58% of the students in this group in the top 5% of students who have the highest score. When considering how learning styles affect learning outcomes, activities that interact with the learning system have more influence on learning outcomes than other learning activities. Although this is only the result of a case study, it can be applied to develop MOOC courses tailored to specific students by implementing appropriate learning content types for the learner can get a better result. © 2023 ACM.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Impact of Multimedia Sensor Placement to Car Licence Number Detection 2022

Impact of Multimedia Sensor Placement to Car Licence Number ...

引用

11th International Conference on Software and computer Applications, ICSCA 2022

作者： Amelia, Afritha Zarlis, Muhammad Suherman, Suherman Efendi, Syahril Graduate Program of Computer Science Faculty of Computer Science and Information Technology University of Sumatera Utara Indonesia Computer Science Faculty of Computer Science and Information Technology University of Sumatera Utara Indonesia Electrical Engineering Faculty of Engineering University of Sumatera Utara Indonesia

ISBN: (纸本)9781450385770

A vehicle has a license plate and can be identified by the license number attached to the vehicle plate. For detection and recognition, multimedia sensors can be used so that it requires a vehicle tracking application that has a vehicle monitoring function and has implications for various fields. One of them is a multimedia sensor that requires an optimal design and method in the form of the number of multimedia sensors to be used, the placement of the multimedia sensor positions and solutions in the event of a system failure. To achieve multimedia sensor performance, research on multimedia sensors is carried out using a camera type with Phase Detection Auto Focus (PDAF) technology which is similar to a pair of right and left eyes to see an object. The objects detected were 2 cars, where the car passed the camera sensor at a speed of 10-15 km/hour 20 times. Changes in the distance of the vehicle to the camera affect the disparity value and the object's accuracy value, namely and the object's Accuracy value of the minimum disparity value of 6.20×106 of 16.88×109. © 2022 ACM.

关键词： Disparity Vehicle plate Phase Detection Auto Focus (PDAF) Tracking application Object accuracy

来源：评论

学校读者我要写书评

暂无评论

Handheld UHF Quad Antennas With Reinforced Mechanical Characteristics 5

Handheld UHF Quad Antennas With Reinforced Mechanical Charac...

引用

5th IEEE International Conference on Smart Systems and Technologies, SST 2022

作者： Barić, Tomislav Glavaš, Hrvoje Hederić, Željko Faculty of Electrical Engineering Computer Science and Information Technology Osijek Osijek Croatia

ISBN: (数字)9781665482158

ISBN: (纸本)9781665482158

Due to the specificity of the application, directional hand-held antennas for outdoor use are subject to mechanical damage. Therefore, when choosing directional hand-held antennas for outdoor use, in addition to considering electrical and electromagnetic characteristics of antennas, special attention should also be paid to the mechanical characteristics of antennas. Quad antennas, although they have excellent electrical and electromagnetic characteristics due to the complexity of their construction, and unsatisfactory mechanical characteristics have not found application as hand-held antennas for outdoor use. This paper presents a new idea in the design and construction of a quad antenna that has reinforced mechanical characteristics. This paper presents the design of compact handheld quad antennas suitable for outdoor mobile applications. The antennas were tested in practice, they were subjected to various mechanical stresses. Impressive mechanical strength and compactness of the antenna have been achieved. The numerical electromagnetics code software 4nec2 is used to design, analyze and optimize the presented antennas. The presented antennas operate at a frequency of 446 MHz. The voltage standing wave ratio (VSWR) of all presented antennas was measured by a vector analyzer and is better than 1.5. There was a small deviation between simulated and measured results. Possible reasons for this discrepancy are listed and commented on. © 2022 IEEE.

关键词： Reinforcement

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Low-Latency IoT Communications

Federated Learning for Low-Latency IoT Communications

引用

Computing and information technology (ICCIT-1441), 2020 International Conference on

作者： Mohammed M Alenazi Computer Engineering Faculty of Computers and Information Technology University Of Tabuk

ISBN: (数字)9798350353839

ISBN: (纸本)9798350353846

Many sectors have been transformed by the growth of the Internet of Things devices, but it also presents difficulties, particularly in the latency of data exchange. In this research, I suggest a unique distributed federated learning architecture for low-latency Internet of Things communications. I empower IoT devices to jointly train machine learning models without compromising data privacy by utilizing federated learning techniques. To accomplish low-latency IoT communications, the architecture prioritizes communication efficiency optimization. Use Python to create this design and provide experimental data to show how successful.

关键词： Data privacy Federated learning Computational modeling computer architecture Data models Internet of Things Data communication Low latency communication information technology Optimization

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning-Based Classification Framework for Annotated Histopathology Lung Cancer Images

A Deep Learning-Based Classification Framework for Annotated...

引用

作者： Hamed, Esraa A.-R. Salem, Mohammed A.-M. Badr, Nagwa L. Tolba, Mohamed F. Faculty of Computer and Information Sciences Ain Shams University Cairo Cairo Egypt Media Engineering and Technology GUC Cairo Egypt

Cancer is the second leading cause of death globally, with one in six people dying from it. It occurs when abnormal cells divide uncontrollably and spread to other organs in the body. Lung cancer is one of the most common and deadliest types of cancer. Several methods, such as X-rays, CT scans, PET-CT scans, bronchoscopies, and biopsies, can be used to diagnose lung cancer. Studies have shown that the type of histology in lung cancer is linked to the diagnosis and treatment course, making early and accurate detection of lung cancer histology crucial for improving survival rates. Artificial intelligence (AI) can aid in the automation of cancer detection, allowing for the evaluation of more cases in less time and at a lower cost. The main objective of this research is to evaluate the effectiveness of a newly proposed CNN model in distinguishing between benign and malignant lung cancer images obtained from digital pathology. To conduct the experiment, the LC25000 dataset, containing 5000 images for each category, was utilized, resulting in a total of 10,000 images. The findings of the proposed CNN model were then compared to those of existing deep learning models, demonstrating its ability to accurately identify cancerous tissues with a maximum accuracy of 99.9% to 100%, while also reducing processing time. These outcomes can play a crucial role in the development of a precise and automated system for identifying various types of lung cancer. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in Univariate Time Series: HOT SAX vesus LSTM-Based Method 12th

Anomaly Detection in Univariate Time Series: HOT SAX vesus L...

引用

12th EAI International Conference on Context-Aware Systems and Applications, ICCASA 2023

作者： Anh, Duong Tuan Hoai, Tran Long Department of Information Technology HCMC University of Foreign Languages and Information Technology Ho Chi Minh City Viet Nam Faculty of Computer Science and Engineering Ho Chi Minh City University of Technology Ho Chi Minh City Viet Nam

ISBN: (纸本)9783031588778

Anomaly detection in time series has been an important and challenging research topic. There have been several methods proposed for detecting anomaly subsequences in a time series. The majority of these methods is classified into the window-based category, which applies a sliding window with a fixed length to extract subsequences before finding out anomaly subsequences. A well-known algorithm in this category is HOT SAX algorithm. Recently, deep neural network models, especially Long Short Term Memory (LSTM) network, are also applied for time series anomaly discovery. LSTM-based methods for time series anomaly detection belong to prediction-based category. So far, there has been no research work to compare the performance of LSTM-based method to that of any traditional window-based method in time series anomaly detection. The research question investigated in this paper is that whether the newly developed LSTM-based method for time series anomaly detection is superior to the traditional algorithms, such as HOT SAX or not. In this study, we give an empirical comparison between LSTM-based method and HOT SAX in time series anomaly detection. Extensive experiments on seven benchmark time series indicate that LSTM-based method is not superior to HOT SAX since it brings out the same detection accuracy as HOT SAX while it incurs much higher computational overhead. © ICST Institute for computer Sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Distance Technique to Optimize the K-Nearest Neighbor Algorithm 2

A Hybrid Distance Technique to Optimize the K-Nearest Neighb...

引用

2nd International engineering Conference on Electrical, Energy, and Artificial Intelligence, EICEEAI 2023

作者： Abdulmuttaleb Al-Musawi, Hussein Ali Aljaidi, Mohammad Sara, Massar Boostani, Reza School of Engineering Shiraz University Electrical and Computer Engineering Faculty Cse and It Dept. Shiraz Iran Zarqa University Faculty of Information Technology Department of Computer Science Zarqa13110 Jordan College of Engineering University of Business and Technology Jeddah21448 Saudi Arabia

ISBN: (纸本)9798350373363

Plenty of Bayesian-consistent, heuristic and statistical classifiers have been introduced. Although support vector machines, deep neural networks, and random forests exhibit acceptable performance in several fields, their primary challenge lies in the lengthy training phase, especially when dealing with big data. K-nearest neighbors (KNN) is one of the simplest, Bayesian consistent and most common algorithms for classification tasks which locally makes its decision and there is no need to any training phase, can be implemented by parallel processing algorithms which makes it suitable to deal with big datasets. The core of this classifier relies on measuring the distance between test samples and its neighbors. Therefore, designing a hybrid distance technique to better find relevant neighbors is of interest. In this research, a weighted combination five distances has been proposed to optimize the performance of the KNN algorithm on diverse 28 datasets. To select appropriate weights of distances for each dataset, particle swarm optimization algorithm was used due to its simplicity and high convergence speed. The proposed method was applied to the datasets, demonstrating acceptable performance compared to its rivals. © 2023 IEEE.

关键词： Classification (of information)

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：