Ústav automatizace inženýrských úloh a informatiky

Browse

Now showing 1 - 5 of 29

Building Execution Plan as an effective document for Building Information Modelling
(Elsevier B.V, 2024-07-29) Sudakova, Katsiaryna; Remeš, Josef; Tichá, Alena
The use of Building Information Modelling (BIM) technology is recently becoming an increasingly influential factor in the successful completion of construction projects. Providing a wide range of technical enhancements to the design process (for example software for 3D modelling), BIM also offers a wide range of tools for managing construction projects. The goal of Building Information Modelling is to eliminate gaps in data transmission between different stages of the life cycle of a construction project. In this context, BEP, or BIM Execution Plan, is an essential document in the BIM concept. It functions as a tool for managing a project, both from the human resources perspective, such as meeting deadlines, and from the perspective of preserving and transferring graphical and non-graphical data of the project. Furthermore, it provides a detailed plan for building design, construction, and facility management, helping to ensure that all stakeholders are in line with the project’s goals. This article examines BEP as it evolves throughout various life cycle stages, from initial design and planning to construction and final delivery, exploring its potential in facility management.
Virtual reality exposure effect in acrophobia: psychological and physiological evidence from a single experimental session
(Springer Nature, 2024-07-15) Varšová, Kristína; Szitás, Dagmar; Janoušek, Oto; Jurkovičová, Lenka; Bartošová, Kateřina; Juřík, Vojtěch
In recent years, virtual reality (VR) has gained attention from researchers in diverse fields, particularly in therapy of phobias. Currently, virtual reality exposure therapy therapy (VRET) is considered a promising cognitive-behavioral therapy technique. However, specific psychological and physiological responses of VR users to virtual exposure in such a context are still only vaguely explored. In this experimental study, we mapped VR exposure in a height environment in people with a moderate fear of heights–acrophobia. Thirty-six participants were divided into experimental and control groups–with and without psychological guidance during exposure. Participants' subjective level of anxiety was examined, and objective physiological response was captured via heart rate variability (HRV) measurement. Psychological assessments recorded an anticipated rise in participant anxiety following exposure to height; nevertheless, no distinctions were observed in self-reported anxiety concerning psychological guidance. Notably, objective physiological measures revealed that VR exposure prompts physiological responses akin to real-world scenarios. Moreover, based on the analysis of heart rate variability, participants who received psychological guidance were identified as better at compensating for anxiety compared to those without such support. These findings support VRET as a promising tool for psychotherapy and advocate for psychological guidance as beneficial in reducing anxiety and managing stress during exposure. The results may help improve our understanding of anxiety during exposure to phobic stimuli.
Calibration of pedestrian ingress model based on CCTV surveillance data using machine learning methods
(Public Library of Science, 2024-01-18) Floriánová, Martina; Uhlík, Ondřej; Apeltauer, Tomáš
Machine learning methods and agent-based models enable the optimization of the operation of high capacity facilities. In this paper, we propose a method for automatically extracting and cleaning pedestrian traffic detector data for subsequent calibration of the ingress pedestrian model. The data was obtained from the waiting room traffic of a vaccination center. Walking speed distribution, the number of stops, the distribution of waiting times, and the locations of waiting points were extracted. Of the 9 machine learning algorithms, the random forest model achieved the highest accuracy in classifying valid data and noise. The proposed microscopic calibration allows for more accurate capacity assessment testing, procedural changes testing, and geometric modifications testing in parts of the facility adjacent to the calibrated parts. The results show that the proposed method achieves state-of-the-art performance on a violent-flows dataset. The proposed method has the potential to significantly improve the accuracy and efficiency of input model predictions and optimize the operation of high-capacity facilities.
Neural Network-Based Train Identification in Railway Switches and Crossings Using Accelerometer Data
(Hindawi, 2020-11-24) Krč, Rostislav; Podroužek, Jan; Floriánová, Martina; Vukušič, Ivan; Plášek, Otto
This paper aims to analyse possibilities of train type identification in railway switches and crossings (S&C) based on accelerometer data by using contemporary machine learning methods such as neural networks. That is a unique approach since trains have been only identified in a straight track. Accelerometer sensors placed around the S&C structure were the source of input data for subsequent models. Data from four S&C at different locations were considered and various neural network architectures evaluated. The research indicated the feasibility to identify trains in S&C using neural networks from accelerometer data. Models trained at one location are generally transferable to another location despite differences in geometrical parameters, substructure, and direction of passing trains. Other challenges include small dataset and speed variation of the trains that must be considered for accurate identification. Results are obtained using statistical bootstrapping and are presented in a form of confusion matrices.
Machine Learning-Based Node Characterization for Smart Grid Demand Response Flexibility Assessment
(MDPI, 2021-03-09) Krč, Rostislav; Floriánová, Martina; Podroužek, Jan; Apeltauer, Tomáš; Stupka, Václav; Pitner, Tomáš
As energy distribution systems evolve from a traditional hierarchical load structure towards distributed smart grids, flexibility is increasingly investigated as both a key measure and core challenge of grid balancing. This paper contributes to the theoretical framework for quantifying network flexibility potential by introducing a machine learning based node characterization. In particular, artificial neural networks are considered for classification of historic demand data from several network substations. Performance of the resulting classifiers is evaluated with respect to clustering analysis and parameter space of the models considered, while the bootstrapping based statistical evaluation is reported in terms of mean confusion matrices. The resulting meta-models of individual nodes can be further utilized on a network level to mitigate the difficulties associated with identifying, implementing and actuating many small sources of energy flexibility, compared to the few large ones traditionally acknowledged.

Browse

Recent Submissions