Ústav telekomunikací

Browse

Now showing 1 - 5 of 411

Computer-Aided Diagnosis of Graphomotor Difficulties Utilizing Direction-Based Fractional Order Derivatives
(Springer, 2024-11-27) Gavenčiak, Michal; Mucha, Ján; Mekyska, Jiří; Galáž, Zoltán; Šafárová, Katarína; Faúndez Zanuy, Marcos
Children who do not sufficiently develop graphomotor skills essential for handwriting often develop graphomotor disabilities (GD), impacting the self-esteem and academic performance of the individual. Current examination methods of GD consist of scales and questionaries, which lack objectivity, rely on the perceptual abilities of the examiner, and may lead to inadequately targeted remediation. Nowadays, one way to address the factor of subjectivity is to incorporate supportive machine learning (ML) based assessment. However, even with the increasing popularity of decision-support systems facilitating the diagnosis and assessment of GD, this field still lacks an understanding of deficient kinematics concerning the direction of pen movement. This study aims to explore the impact of movement direction on the manifestations of graphomotor difficulties in school-aged. We introduced a new fractional-order derivative-based approach enabling quantification of kinematic aspects of handwriting concerning the direction of movement using polar plot representation. We validated the novel features in a barrage of machine learning scenarios, testing various training methods based on extreme gradient boosting trees (XGBboost), Bayesian, and random search hyperparameter tuning methods. Results show that our novel features outperformed the baseline and provided a balanced accuracy of 87 % (sensitivity = 82 %, specificity = 92 %), performing binary classification (children with/without graphomotor difficulties). The final model peaked when using only 43 out of 250 novel features, showing that XGBoost can benefit from feature selection methods. Proposed features provide additional information to an automated classifier with the potential of human interpretability thanks to the possibility of easy visualization using polar plots.
The Problem of Integrating Digital Twins into Electro-Energetic Control Systems
(MDPI, 2024-09-18) Bohačík, Antonín; Fujdiak, Radek
The use of digital twins (DTs) in the electric power industry and other industries is a hot topic of research, especially concerning the potential of DTs to improve processes and management. This paper aims to present approaches to the creation of DTs and models in general. It also examines the key parameters of these models and presents the challenges that need to be addressed in the future development of this field. Our analysis of the DTs and models discussed in this paper is carried out on the basis of identified key characteristics, which serve as criteria for an evaluation and comparison that sets the basis for further investigation. A discussion of the findings shows the potential of DTs and models in different sectors. The proposed recommendations are based on this analysis, and aim to support the further development and use of DTs. Research into DTs represents a promising sector with high potential. However, several key issues and challenges need to be addressed in order to fully realize their benefits in practice.
UAV-BS Integration with Urban Infrastructure: An Energy Efficiency Perspective
(IEEE, 2024-11-04) Kirubakaran, Balaji; Vikhrova, Olga; Andreev, Sergey; Hošek, Jiří
The integration of uncrewed aerial vehicles (UAVs) with fifth-generation (5G) cellular networks has been a prominent research focus in recent years and continues to attract significant interest in the context of sixth-generation (6G) wireless networks. UAVs can serve as aerial wireless platforms to provide on-demand coverage, mobile edge computing, and enhanced sensing and communication services. However, UAV-assisted networks present new opportunities and challenges due to the inherent size, weight, and power constraints of UAVs, their controllable mobility, and the line-ofsight (LoS) characteristics of communication channels. This article discusses these opportunities and challenges from the viewpoint of mobile network operators (MNOs), and offers a novel perspective on efficiently utilizing modern city infrastructures for UAV deployment in typical urban scenarios. In these scenarios, UAV-mounted base stations (UAV-BSs) can significantly improve service continuity and network energy efficiency. We compare system performance in terms of user satisfaction and energy efficiency between conventional UAV deployment, which follows demand dynamics, and an alternative approach where UAVs land on urban infrastructure equipped with charging stations. To identify the preferred UAV locations, while considering the limited availability of such stations and environmental dynamics, we employ a data-driven genetic algorithm. This algorithm closely approximates the true optimal locations subject to a moderate computational budget.
Indirect Assessment of Hyperechogenicity of Substantia Nigra Utilizing Sleep-based Biomarkers
(Institute of Electrical and Electronics Engineers Inc., 2024-01-03) Mikulec, Marek; Mekyska, Jiří; Galáž, Zoltán
Transcranial sonography of the substantia nigra (TCS-SN) may serve as a suitable test for screening groups at a high risk of developing Lewy body diseases (LBDs) such as Parkinson's disease or dementia with Lewy bodies. Although one of the most prominent early markers of these neurodegenerative disorders is the idiopathic rapid eye movement (REM) sleep behavior disorder, the relationship between TCS-SN and sleep alterations has not been fully explored. The aim of this study is to investigate whether sleep-based biomarkers could be used to stratify subjects into three groups with different echogenic areas of the substantia nigra. To achieve this goal, we enrolled 93 participants who underwent TCS-SN and 7-night actigraphy. Additionally, participants completed a sleep diary and the REM sleep behavior disorder screening questionnaire. To assess the severity of pathological echogenicity, we employed a machine learning algorithm utilizing the XGBoost algorithm. The results show that a multimodal assessment of sleep was able to predict the outcomes of TCS-SN with a balanced accuracy of 96 %. Overall, these findings underscore the potential of a comprehensive approach to model the results of TCS-SN and its implications for the prodromal diagnosis of LBDs.
Dreadnought guitar top plate innovation
(Studio D Akustika, 2024-10-10) Jirásek, Ondřej
This paper describes the innovation of Dreadnought guitars, especially braces on top plate The goal was to increase the dynamic range of the instruments, not only in strength but also in spectral spread The prolongation of tones in the Sustain and Release phases was also important Mechanical and acoustic properties of instruments from Furch Guitars’ production were measured (Chladni figures, frequency response), numerical simulation of innovated top plate in program ANSYS was prepared (by the matrix) and the changes in organisation of ribs were proposed as following The new samples of innovated Dreadnought guitars were produced by the factory, again measured, analysed and evaluated.

Browse

Recent Submissions