|
|
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.
|
|
|
Advanced scoring of sleep data
Jagošová, Petra ; Novotná, Petra (referee) ; Ronzhina, Marina (advisor)
The master´s thesis is focused on advanced scoring of sleep data, which was performed using deep neural network. Heart rate data and the movement information were used for scoring measured using an Apple Watch smartwatch. After appropriate pre-processing, this data serves as input parameters to the designed networks. The goal of the LSTM network was to classify data into either two groups for sleep and wake or into three groups for wake, Non-REM and REM. The best results were achieved by network doing classification of sleep vs. wake using the accelerometer. The statistical evaluation of this best-designed network reached the values of sensitivity 71,06 %, specificity 57,05 %, accuracy 70,01 % and F1 score 81,42 %.
|
|
|
Smartwatch App for Sports Training and Competitions
Dohnalík, Pavel ; Bartl, Vojtěch (referee) ; Herout, Adam (advisor)
The aim of the work is to create an application for a smart watch, which will allow you to measure races and trainings, or create localization data for this activity. The application is implemented for mobile devices with the Android and iOS operating systems. The Wear OS operating system is supported for smart watches. The thesis describes the theory of programming for mobile operating systems and programming for the operating system Wear OS. The practical part describes the design, implementation and testing. For the implementation of the mobile application as well as for the smart watch application I decided to choose Flutter framework and programming language Dart. The resulting application allow users to measure races and workouts.
|
|
|
Wearables Development Technologies for YSoft SafeQ
Stárek, Jan ; Goldmann, Tomáš (referee) ; Orság, Filip (advisor)
Wearable devices grew in popularity in recent years. This fact contributes to increasing efforts to expand mobile and other applications to wearable devices. Exploring these possibilities, this thesis summarizes information on wearable devices and their typical operating systems, including available tools and restrains these systems offer. Based on the conclusion of theoretical part of this thesis an application for wearable devices is designed and implemented, specifically an application for printers that operate via SafeQ system developed in Y Soft Corporation.
|
|
|
Sleep quality assessment
Benáček, Petr ; Králík, Martin (referee) ; Ronzhina, Marina (advisor)
The topic of this bachelor thesis is an automatic sleep quality assessment using artificial neural network. To assess the quality of sleep were used the movement and heart rate data measured by Apple Watch smartwatch. From these data, statistical variables were calculated. Then were they used as an input to the neural networks. The goal was to automatically identify sleep and wakefulness. In this case, the sensitivity was 89 % and the specificity was 70 %. These values are comparable with other studies. Furthermore, the data were also divided into categories W (wakefulness), NON REM and REM. Parameters evaluating sleep quality, such as TST, % REM or sleep latency, were derived from the output of the neural networks created.
|
|
|
Metronome for the Android Mobile Device
Pomkla, František ; Burget, Radek (referee) ; Bartík, Vladimír (advisor)
The purpose of this project is the implementation of metronome for smartphone with OS Android and smartwatch with OS Tizen. Both applications provide asynchronous functionality of metronome as well as data sharing through Bluetooth connection. These metronome applications should help musicians in music bands. It allows to save specific song's tempo into playlists and than share them via Bluetooth connection with smartwatch application. The smartwatch application produces vibrations instead of click sound. Other smartphone metronome functionality is to scan drum stroke by internal device microphone and compare it with metronome beat. The programming languages C# and Java with SQLite databases were used for implementation.
|
|
|
ECG based human authentication and identification
Waloszek, Vojtěch ; Smital, Lukáš (referee) ; Vítek, Martin (advisor)
In the past years, utilization of ECG for verification and identification in biometry is investigated. The topic is investigated in this thesis. Recordings from ECG ID database from PhysioNet and our own ECG recordings recorded using Apple Watch 4 are used for training and testing this method. Many of the existing methods have proven the possibility of using ECG for biometry, however they were using clinical ECG devices. This thesis investigates using recordings from wearable devices, specifically smart watch. 16 features are extracted from ECG recordings and a random forest classifier is used for verification and identification. The features include time intervals between fiducial points, voltage difference between fiducial points and PR intervals variability in a recording. The average performance of verification model of 14 people is TRR 96,19 %, TAR 84,25 %.
|
|
|
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.
|
|
|
Applications for Wearable Devices based on Android Wear OS
Šmejkal, Petr ; Zeman, Kryštof (referee) ; Hošek, Jiří (advisor)
The semestral project "Application for Android Wear wearables” describes basic principles of the communication network - M2M (machine to machine), H2H (human to human) and D2D (device to device). It is also focused on wearables especially smart watches, available operation systems for smart watches and system Android, Android Wear. In the practical part is described functionality, design and structure of developed application for Android wear smartwatch.
|
|
|
Sleep quality assessment
Dokoupilová, Daniela ; Kozumplík, Jiří (referee) ; Ronzhina, Marina (advisor)
The topic of this bachelor thesis is quality sleep assessment using signals acquired from Apple Watch. From measured signals – heart rate and motion, were extracted parameters for sleep classification using statistical testing. These parameters were later used for training the support vector machine model. The model was first trained to classify Wake and Sleep, then also to classify Wake, REM and NREM stages. The accuracy of Wake/Sleep classification was about 80 %. The accuracy of Wake/REM/NREM classification exceeded 58 %. Finally, sleep quality parameters were calculated and compared to the data rated by a sleep expert. The outcome for Wake/Sleep classification was close to the expert evaluation. The model for Wake/REM/NREM classification was less accurate and differed mainly in parameters concerning Wake stage.
|
guest ::
