|
|
Advanced methods for sleep quality assessment
Doležalová, Anna ; Králík, Martin (referee) ; Ronzhina, Marina (advisor)
This diploma thesis is focused on advanced sleep assessment using deep learning. Metrics for sleep assessment and their use are described here. There are hearth rate and accelerometer data from Apple Watch used for classification. The basis for the classification was a model composed of 1D convolution networks in combination with recurrent neural network. LSTM and GRU were used as recurrent networks. Models were taught to classify into two, three and five phases. At last the resulting methods are compared.
|
|
| |
|
|
Effect of acquisition site compression in multisite photoplethysmography
Hofrová, Lucie ; Kolář, Radim (referee) ; Janoušek, Oto (advisor)
The theoretical part of the thesis describes the pulse wave's origin, the principle of photoplethysmography, and the influence of vein compression on the morphology of the photoplethysmograph caused by external pressure during PPG signal measurement. Furthermore, the thesis contains the measurement and analysis of the PPG bilateral signal, which is used for the evaluation of whether there are differences between the PPG signal measured on the left or the right side of the human body. A dataset consisting of 10 volunteers was created for evaluation. The practical part contains the algorithm which analysis the PPG signal. Furthermore, normalization and statistical analysis is performed. The results show that external pressure has an effect on pulse wave width analysis and heart rate. When the pressure is high, the ability of pulse wave analysis is impaired.
|
|
|
Device for simultaneous acquisition of PCG and PPG signals
Matoušek, Denis ; Králík, Martin (referee) ; Mézl, Martin (advisor)
This bachelor's thesis deals with the design and implementation of equipment for phonocardiographic and photoplethysmographic measurements. The theoretical part discusses the description of the origin of heart sounds, the place and method of measurement in the framework of phonocardiography. The practical part describes several options for building individual devices with the help of a Raspberry Pi 4 or with the help of measuring technology and a non-soldering field. Subsequently, the best solutions for PPG and PCG data acquisition are selected. 10 volunteers were measured on the final device. The scanned data is processed in the Python environment. Individual measurement results are described, documented, compared, and evaluated against other measurements.
|
|
|
HRV analysis based on PPG signal
Kadlčík, Jindřich ; Hrbotický, Lukáš (referee) ; Smital, Lukáš (advisor)
Heart rate variability analysis has lately gained remarkable popularity as a tool in training optimalization and in prevention of cardiac disease. It is usually based on the ECG signal, the acquisition of which is uncomfortable during activity. Therefore, the option to base the analysis on the PPG signal instead was proposed, but not yet sufficiently studied. This study compiles the necessary information for correct heart rate variability analysis and introduces our own implemented detectors of fiducial points in the PPG signal, and compares their usability for calculation of HRV analysis metrics.
|
|
|
Visualization and analysis of retinal pulsatile phenomena
Plavcová, Daniela ; Odstrčilík, Jan (referee) ; Kolář, Radim (advisor)
Retinal blood flow can be a reflection of the state of the vascular system, but it can also indicate changes in intracranial pressure. For that reason, video sequences are taken from the retina, which can be processed to examine this area. This work deals with the analysis and visualization of pulsations on the retina, representing the change in light attenuation during one hearth cycle, and the search for suitable parameters describing connections and differences between data, whether in the form of signals, images or video sequences.
|
|
|
Advanced sleep quality estimation
Benáček, Petr ; Ředina, Richard (referee) ; Filipenská, Marina (advisor)
This thesis deals with the assessment of sleep quality using modern deep learning methods. The thesis describes metrics for automatic classification of sleep stages. A selected database of sleep data is discussed. Due to the low number of data in the wakefulness phase, different methods of data augmentation are described and implemented. Models based on 1D convolutional networks are the basis for the classification. As a result, models for binary classification and classification of 3 and 4 sleep phases are prepared. Finally, sleep quality metrics are calculated using these models and the results are compared with the literature.
|
|
|
HRV analysis based on PPG signal
Martinů, Žaneta ; Vítek, Martin (referee) ; Smital, Lukáš (advisor)
The thesis deals with the detection of systolic and diastolic peaks of pulse waves in a photoplethysmographic database. The detectors are implemented in MATLAB. The following part of the thesis uses the signal delineation of the photoplethysmographic signal to determine pulse rate variability. The final part of the thesis evaluates the use of pulse rate variability and compares it to the heart rate variability.
|
|
|
Advanced methods for sleep quality assessment
Doležalová, Anna ; Králík, Martin (referee) ; Ronzhina, Marina (advisor)
This diploma thesis is focused on advanced sleep assessment using deep learning. Metrics for sleep assessment and their use are described here. There are hearth rate and accelerometer data from Apple Watch used for classification. The basis for the classification was a model composed of 1D convolution networks in combination with recurrent neural network. LSTM and GRU were used as recurrent networks. Models were taught to classify into two, three and five phases. At last the resulting methods are compared.
|
|
|
PPG signal quality assessment and heart rate estimation
Vargová, Enikö ; Vítek, Martin (referee) ; Němcová, Andrea (advisor)
This work deals with photoplethysmographic (PPG) signals, their processing, quality assessment, estimation of heart rate from PPG signals and the ability to record biological signals with smartphones. The aim of this work is to record PPG signals using a smartphone and reference ECG signals using an ECG recorder. The work also includes the design of two algorithms, one for signal quality assessment and the other for heart rate estimation from PPG signals.
|
guest ::
