检索结果-内蒙古大学图书馆

2024 Photonics and Electromagnetics Research Symposium, PIERS 2024

作者： Haidi, Junas Nugroho, Agustinus Agung Munir, Achmad Institut Teknologi Bandung Radio Telecommunication and Microwave Laboratory School of Electrical Engineering and Informatics Indonesia University of Bengkulu Faculty of Engineering Department of Electrical Engineering Indonesia Institut Teknologi Bandung Faculty of Mathematics and Natural Science Department of Physics Indonesia

ISBN: (纸本)9798350375909

This paper discusses the investigation of magneto-dielectric material properties composed of a resonator and a Yttrium Iron Garnet (YIG) material using Substrate Integrated Waveguide (SIW) structure. The investigation results are expected to be applicable enhancing the performance of SIW-based and other radio frequency devices. To investigate its properties, simulation and experiment are conducted using a three-layer SIW structure. Meanwhile, to enhance the performance, a 48 wires-made resonator is utilized and incorporated onto the SIW structure. The research findings indicate that the SIW structure with resonator exhibits a single resonant peak at the frequency of 2.95 GHz. This peak appears due to the increase of electric field from the resonator and the reinforcement of electric field produced by the SIW structure. Furthermore, by incorporating YIG material together with the resonator onto the SIW structure, an additional resonant peak is yielded at the frequency of 1.65 GHz. It is noteworthy that this resonant peak is obtained without an external magnetic field. The increase of external magnetic field intensity will activate the magnetic properties of YIG material. The stronger the magnetic field from YIG material as the increase of external magnetic field intensity, the further the resonant peak shifts toward higher frequencies. This means that the proposed SIW structure is capable to characterize the properties of magneto-dielectric material, where the resonator contributes in enhancing the electric field at the frequency of 2.95 GHz, and the YIG material provides in strengthening the magnetic field at the frequency of 1.65 GHz. © 2024 IEEE.

关键词： Surface discharges

来源：评论

学校读者我要写书评

暂无评论

Increasing of security of an actual social networks 27

Increasing of security of an actual social networks

引用

27th IEEE International Conference on Intelligent engineering Systems, INES 2023

作者： Pekarcik, Peter Kuchcakova, Tatiana Valko, David University of Košice Faculty of Electrical Engineering and Informatics Department of Computers and Informatics Košice Slovakia

ISBN: (纸本)9798350328516

One of the most visited web pages nowadays is undoubtedly social networks. Millions of users visit them every day, creating posts, adding comments, or sharing posts from other users. It is true that almost everything can be added to a social network today, leading to the creation of large communities where different untruthful or hateful speeches may arise. These speeches can be transferred to the real world. The increasing number of social network users necessitates an increase in their security. In the first chapter of our work, we examine the current state of the most widely used social networks and introduce a new system for enhancing their security. We then propose the system. Our design contains various UML diagrams mentioned in the second chapter. In conclusion, we discuss the advantages and disadvantages of our design and suggest possible future expansions for our system. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Stress vs. Calmness: Machine Learning Classification Using Publicly Available Dataset 15th

Stress vs. Calmness: Machine Learning Classification Using P...

引用

15th International Scientific Conference on Distance Learning in Applied informatics, DiVAI 2024

作者： Balogh, Zoltán Fodor, Kristián Kandó Kálmán Faculty of Electrical Engineering Óbuda University Budapest Hungary Faculty of Natural Sciences and Informatics Constantine the Philosopher University Nitra Slovakia

ISBN: (纸本)9783031812606

Sensor networks are becoming increasingly crucial in the realm of technology, as they are present in a diverse array of applications spanning from industrial processes to environmental monitoring, as well as healthcare and wearable devices. The advancement of technologies like wearable devices is presently undergoing notable progress to enhance and render accessible the monitoring of physiological indicators to users. Through the analysis of data collected from these devices and the utilization of contemporary machine learning techniques, it is feasible to attain precise management of the user’s mental and emotional condition in real time. The focus of this study revolves around physiological data and the categorization of emotional states predicated on the gathered physiological data employing multiple machine learning algorithms. A pivotal aspect of the investigation involves the preprocessing stage of the data, encompassing tasks such as data equilibrium and the selection of optimal hyperparameters to heighten classification precision. The analysis of this data has the potential to furnish us with a more profound understanding of diverse matters, such as user health assessment, stress identification, and aiding in physical training. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Analysis on Performance of Semi-Real-Time Transcription on Health App 18

Analysis on Performance of Semi-Real-Time Transcription on H...

引用

18th International Conference on Telecommunication Systems, Services, and Applications, TSSA 2024

作者： Indrasary, Yoenie Nugraha, Daniel Prihatmanto, Ary Setijadi Sarief, Ivany Gunawan, Rudy Yunautama, Dhema School of Electrical Engineering and Informatics Institut Teknologi Bandung Doctoral Program of Electrical Engineering and Informatics Bandung Indonesia State Polytechnic of Banjarmasin Banjarmasin Indonesia School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Universitas Sangga Buana Faculty of Engineering Dept. of Electrical Engineering Bandung Indonesia Universitas Sangga Buana Directorate of Vocational Dept. of Informatics Engineering Bandung Indonesia

ISBN: (纸本)9798331527686

The fragmentation of health information systems has hindered seamless data exchange in healthcare services, posing challenges in achieving efficient, real-time access to patient health data. This study addresses these issues by evaluating the implementation of a semi-real-time transcription system using a distributed architecture with a message broker to enhance the documentation of clinical examination processes in primary health services. The research focuses on assessing the feasibility of this approach by measuring key performance indicators such as latency and word error rate (WER) during clinical conversation transcription. Audio recordings were segmented into shorter fragments to simulate real-time transcription, and data transmission was conducted through the Advanced Message Queuing Protocol (AMQP). The findings demonstrate that the average latencys achieved by semi-real-time transcription system is 7.7s, indicating its potential suitability for clinical documentation applications that do not require strict real-time processing. However, glitches observed in the message broker's forwarding mechanism suggest the need for further optimization to ensure consistent performance. Future work aims to develop strategies to minimize transcription errors, enhance reliability, and improve the overall integration of this system in healthcare settings. This study contributes to the advancement of health information systems by offering architecture into scalable and effective methods for semi-real-time data transcription and interoperability. © 2024 IEEE.

关键词： Audio recordings

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Gamification Aspects of Digital Educational Tools Using Gamification Classification 32

Analysis of the Gamification Aspects of Digital Educational ...

引用

32nd International Conference on Software, Telecommunications and Computer Networks, SoftCOM 2024

作者： Bozic, Ana Vrcelj Hoic-Bozic, Natasa Dlab, Martina Holenko Stancin, Kristian Jagust, Tomislav Civil Engineering Technical School in Rijeka Rijeka Croatia University of Rijeka Faculty of Informatics and Digital Technologies Rijeka Croatia University of Zagreb Faculty of Electrical Engineering and Computing Zagreb Croatia

ISBN: (纸本)9789532901382

Nowadays, gamification is increasingly being used in education to increase student motivation. The reason for this is that it is easier to design and implement in the classroom than game-based learning (GBL). Instead of developing special educational games, gamification can be implemented simply by using some game design elements provided by publicly available digital gamification tools. However, choosing the right gamification tools and their game design elements is not an easy task for teachers. This paper describes a new classification for gamification and its application in the evaluation of popular digital gamification tools. Reviewing the characteristics of these tools can help teachers not only in selecting these tools, but also in independently evaluating other tools. The classification described is the first step in developing the future technological-pedagogical framework for the design and implementation of gamified activities in schools. © 2024 University of Split, FESB.

关键词： Game design

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition from Video Frame Sequence using Face Mesh and Pre-Trained Models of Convolutional Neural Network 24

Emotion Recognition from Video Frame Sequence using Face Mes...

引用

24th International Seminar on Intelligent Technology and Its Applications, ISITIA 2023

作者： Adi, Derry Pramono Yuniarno, Eko Mulyanto Wulandari, Diah Puspito Institut Teknologi Sepuluh Nopember Faculty of Intelligent Electrical and Informatics Technology Dept. of Electrical Engineering Surabaya Indonesia Institut Teknologi Sepuluh Nopember Faculty of Intelligent Electrical and Informatics Technology Dept. of Electrical Engineering Dept. of Computer Engineering Surabaya Indonesia Institut Teknologi Sepuluh Nopember Faculty of Intelligent Electrical and Informatics Technology Dept. of Computer Engineering Surabaya Indonesia

ISBN: (纸本)9798350313956

Emotions are a collection of subjective cognitive experiences and psychological and physiological characteristics that express a wide range of feelings, thoughts, and behaviors in human interaction. Emotions can be represented through several means, such as facial expressions, tone of voice, and behavior. Deep Learning (DL) research has focused on incorporating facial expressions. Images with facial expressions are commonly used as data input for the DL model. Unfortunately, most DL models in Facial Emotion Recognition (FER) use static images. This method does not take into consideration all conceivable facial expressions. The static image of facial expressions is insufficient for recognizing emotions, but a sequential image from a video is required. In this study, we extract MediaPipe's face mesh feature, the state-of-the-art multidimensional expression key points embedded in the video image sequence. Furthermore, we feed sequence image data into the pre-trained Convolutional Neural Network (CNN) model. The data we used is from The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) with the emotion classes of 'Anger,' 'Fearful,' 'Happy,' and 'Sad.' For this specific FER task, we found that the best pre-trained CNN model achieved 92.8% accuracy (using the VGG-19 model), with the fastest runtime of ∼2.3 seconds (achieved using the SqueezeNet model). © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Identification of obtaining incorrect values from the GSR sensor during skin resistance measurements 7

Identification of obtaining incorrect values from the GSR se...

引用

7th International Conference on Information and Computer Technologies, ICICT 2024

作者： Koprda, Stefan Magdin, Martin Sasik, Matus Balogh, Zoltan Fodor, Kristian Molnar, Gyorgy University In Nitra Faculty Of Natural Sciences And Informatics Constantine The Philosopher Department Of Informatics Nitra Slovakia Óbuda University Kandó Kálmán Faculty Of Electrical Engineering Budapest Hungary

ISBN: (纸本)9798350385625

The paper deals with the analysis of problematic values from the galvanic skin response (GSR) sensor obtained during the conducted research aimed at the correlation of physiological functions and emotional state of a person through the measurement of skin response. The experiment involved primary school students who were monitored during various activities. Skin response data was systematically recorded and sent to a central database using the Arduino UNO platform. The study identified the dynamics of skin response in relation to emotional state and various activities. However, technical problems were identified during the experiment, in particular the recurrent non-standard occurrence of zero values. These were analyzed and addressed through sensor calibration. The integration of the GSR sensor with the Arduino UNO and subsequent optimization of the power supply resulted in stable and reliable operation of the sensor. The improved data quality confirms the success of the corrective measures. © 2024 IEEE.

关键词： Physiological models

来源：评论

学校读者我要写书评

暂无评论

Phonetic Analysis of Queen Elizabeth's Christmas Messages 17

Phonetic Analysis of Queen Elizabeth's Christmas Messages

引用

17th IEEE International Scientific Conference on informatics, informatics 2024

作者： Pozdilek, Martin Pozdilkova, Alena University of Pardubice Faculty of Electrical Engineering and Informatics Studentská 95 PardubiceI 530 02 Czech Republic

ISBN: (纸本)9798350387674

Our article aims to analyse the Christmas messages of Queen Elizabeth II and find the words that were said with the most significant emphasis or voice intensity. It will be measured using energy per second. The phonetic analysis will be used, and words with the most significant energy will be found. Energy is a critical parameter that determines the intensity of the voice. Energy is defined as the sum of the samples' squares within the word's length. A logarithm function will be used to provide a better range of energy values. Data analysis using edge detection and neural networks interprets their common characteristics. So, what about Queen Elizabeth II she wanted to emphasise in her Christmas speeches. © 2024 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Formation Control Design of Fixed-wing UAVs Based on Model Reference Adaptive Control

Periodica Polytechnica Electrical Engineering and Computer S...

引用

Periodica Polytechnica electrical engineering and Computer Science 2025年第1期69卷 43-52页

作者： Lantos, Bela Kimathi, Stephen Department of Control Engineering and Information Technology Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Műegyetem rkp. 3. BudapestH-1111 Hungary Department of Electrical and Electronic Engineering Dedan Kimathi University of Technology P.O.B. 10143 Dedan Kimathi Nyeri10100 Kenya

Formation control is currently a popular field of research due to the increasing application areas of unmanned aerial vehicles. Of concern is the stability of unmanned aerial vehicles (UAVs) formation while tracking especially under the influence of disturbances, and model parameter uncertainty. Since formation of the UAV formation while tracking, especially flying involves a mutual cooperation, consensus-based techniques are more suited such that a group of UAVs are collectively coordinated to perform some tasks. In this paper, a leader–follower formation control of homogeneous fixed wing UAVs based on model reference adaptive control with an integral error control compensation is presented. Model reference adaptive control is powerful and effective for handling uncertain and varying dynamics. This proposed distributed composite control strategy with a directed graph topology, although model-dependent can be effective to suppress disturbances affecting the vehicles, while achieving consensus-based tracking of a reference path. The numerical simulation results given show the applicability of this proposed control strategy. © 2025 Budapest University of Technology and Economics. All rights reserved.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Automatic Speech Liveness Detection 22

Automatic Speech Liveness Detection

引用

22nd International Conference on Emerging eLearning Technologies and Applications, ICETA 2024

作者： Haluška, Renát Kupcová, Eva Pleva, Matúš Hric, František Technical University of Košice Faculty of Electrical Engineering and Informatics Department of Electronics and Multimedia Communications Kosice Slovakia

ISBN: (纸本)9798331527716

This paper addresses the growing challenge of detecting deepfake audio, which can mimic or alter speech using advanced machine learning techniques like GAN sand RNNs. Such audio manipulation poses risks in biometric security and fraud. The study focuses on developing detection methods using acoustic features such as Mel-Frequency Cepstral Coefficients (MFCCs) and zero-crossing rate (ZCR). Two neural network models were tested, with the best achieving accuracy in identifying synthetic audio. The results highlight the need for advanced detection algorithms to keep pace with evolving deepfake technologies, enhancing biometric and digital security systems. © 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

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：