|
|
Wireless data logger for environmental monitoring - server-side
Bártek, Jiří ; Kolářová, Jana (referee) ; Sekora, Jiří (advisor)
This work describes the design and implementation of the server-side component, which is part of a comprehensive task for measuring temperature in medical storage spaces and sending the measured temperature at specified time intervals. The created device will receive the measured data and subsequently send it to an e-mail address. The introductory part deals with the legislation related to the storage of medicines and further provides the reader with theoretical information about the used devices and protocols. The next section of the work introduces the implementation of the device and software solution. The outcome of the work is a device capable of communicating with another microcontroller and sending the received data to a selected e-mail address for subsequent archiving.
|
|
|
Wireless data logger for environmental monitoring - client-side
Štopl, Vlastimil ; Kolářová, Jana (referee) ; Sekora, Jiří (advisor)
The aim of this work is to design a client-server device for automatic recording of environmental temperature for the storage of pharmaceuticals. This work focuses on the client part. The theoretical section includes relevant legislation for pharmaceutical storage and definitions of the Internet of Things. The practical part comprises the actual system design of the device and its implementation. The chosen control unit is the ESP8266 microcontroller in conjunction with the DS18B20 sensor.
|
|
|
Upper limb movement analysis
Toláš, Štěpán ; Sekora, Jiří (referee) ; Kolářová, Jana (advisor)
This master's thesis investigates the use of inertial measurement units (IMUs) for the analysis of upper limb movements with a focus on their use in rehabilitation. Using accelerometers, gyroscopes and magnetometers, IMUs provide comprehensive data on limb orientation and dynamics. A pilot study was conducted to appropriately process the available data, develop a measurement protocol and an application to visualize the movement data.
|
|
|
Segmentation of Electrocardiographic Signals Using Deep Learning Methods
Hejč, Jakub ; Černý, Martin (referee) ; Halámek, Josef (referee) ; Kolářová, Jana (advisor)
The thesis deals with deep learning methods for the segmentation of surface and intracardiac electrocardiographic recording with focus on atrial activity. The theoretical part introduces current segmentation aproaches of electrocardiographic signals. Issues related to the development of deep learning models in context of standard ECG databases were also discussed. We proposed a pipeling for processing multimodal electrophysiology data from interventional procedures in order to build reliable training datasets. A deep model for segmentation of intracardiac recordings based on a modified residual architecture was proposed. A series of experiments was conducted to evaluate the effect of both model and dataset properties on segmentation quality. The annotation methodology of recordings with atrial fibrillation proved to be a crucial factor. Properties of loss function and type of data augmentation were revealed as secondary important parameters. A novel P wave segmentation method for incomplete references was proposed in the thesis. The approach was inspired by the deep contrast learning. It was modified to distinguish local segments of signals at different levels of abstraction of the extracted feature maps. Results were analyzed using standard quality metrics and post-hoc visual analysis. In some cases, a statistical comparison of experiments for different settings was performed. The results of the work showed that it is possible to use intracardiac signals for embedding a vector representation of local atrial activation into deep models.
|
|
|
Measurement and anaysis of electrocardiograms
Zimáková, Jana ; Vítek, Martin (referee) ; Kolářová, Jana (advisor)
The aim of my barchelor’s thesis was to become familiar with the methology of measurement of electrocardiographic signals, their description and subsequent analysis. During the measurement I used a computer system Biopac and program Matlab. The work is divided into three parts. The first part is focused on general problems of the heart activity, the generation, measurement and description of ECG curves. The second part is devoted to a description of the systém Biopac – recovery, procedure for the measurement and results measured sleep and stress ECG. The third part describes the actual processing of measured signals in Matlab.
|
|
|
Auditory evoked potentials and its sensing
Němečková, Pavla ; Svačinová, Jana (referee) ; Kolářová, Jana (advisor)
This thesis deals recording evoked potentials. The TruTrace EMG was used for the recording and data was collected from 10 volunteers. For a better understanding of this is issue, is explained auditory system, recording methods, stimulation pulses and stimulation headphones at first. The main goal of the thesis is to compare the current averaging method with the newly created method. The results from both methods were compared based on their standard error of the mean. Bayesian averaging, new method, was more successful in 65 % than the pre-set rejection method.
|
|
|
Influence of physical load to electrical activity of muscles
Kadeřábek, Jan ; Sekora, Jiří (referee) ; Kolářová, Jana (advisor)
This bachelor’s thesis describes influence of physical load on electrical activity of muscles. In each of bachelor’s thesis chapters are analyzed questions of measurement EMG signals and their elaboration, include statistic attestation of influence physical load on electrical activity of muscles. EMG signals were received from group of 10 students and in program acqKnowledge, were taken off parameters for statistic elaboration. In created program were due to time and frequency analysis calculated parameters of EMG records, which can also describe influence of physical load. Accomplishments of this project are the tables with measured data, their graphs, statistics attestation of influence physical load on electrical activity of muscles and program, which can do time and frequency analysis of measured records. On significance level 10% was verified hypothesis, that physical load influence electrical activity of muscles.
|
|
|
Recognition of isolated words
Ondruška, Jiří ; Švrček, Martin (referee) ; Kolářová, Jana (advisor)
Human speech recognition in biometric systems is an actual problem, which science intensively deals with. One of most used methods is the method of hidden Markovov’s models. Attention in isolated words recognition is focused on characteristic speech signal parameters obtaining, enabling most clear identification due to hiddem Markov model application. This work concentrates on biometric systems, its methods, and then is focused on isolated words recognition problems. The hidden Markov model recognition system with usage of some Matlab functions is designed. Concept focuses on characteristic speech signal parameters obtaining, code book making through vector quantization, words model training and finally probability of concrete model and obtained word similarity evaluation. Ratio for one speaker's spoken words recognition reaches 40%.
|
|
|
The radio therapy process planning
Slavíček, Tomáš ; Kolářová, Jana (referee) ; Hrozek, Jan (advisor)
This thesis aims to bring reader to the problems of radiotherapy, to give him an overview of basic principles and methods used to treat patients with cancer by ionizing radiation. The first part is devoted to the physical description of radiation and means of quantification. Interactions of radiation with matter are discussed next following with characterization of radiation effects on living cells and tissues. In the next part there is a description of the devices used in the treatment by ionizing radiation and an explanation of the various acts of patient's preparation from the target localization to irradiation. The final chapter describes created program with a graphical environment, which includes the key elements of commercial planning systems for the creation of the irradiation plan. This program uses real CT images and provides the user a basic idea of creating radiotherapeutic plan. The user has several functions for creating and optimizing the plan. The output of the program is a graphical representation of the spatial distribution of dose in the patient's body.
|
|
|
Medical standing devices
Vadják, Šimon ; Ronzhina, Marina (referee) ; Kolářová, Jana (advisor)
This bachelor‘s thesis deals with patient verticalization and medical standing devices, which we use for this purpose. These findings are particularly important for rehabilitation and nursing care and also for the development of new standing devices. The bachelor‘s thesis describes the basic con¬cepts of human motor skills, the effect of changing position on the human organism, an overview of medical standing devices and their comparison. Thesis deals with comparison of the technical pa¬rameters of two standing devices more closely, standing device BALANCE Trainer and STOJ. The final part is devoted to measuring blood pressure using the noninvasive, continuous method of measuring at a group of wheelchair users during verticalization. I created a program with a graphical interface which allows measured data to load, display and measure, in numerical compu-ting environment MATLAB (version 7.9.0-R2009B). The results were statistically tested in the same numerical computing environment.
|
guest ::
RSS feed.