|
|
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 %.
|
|
|
Drummer's Metronome for Smartphone and Smartwatch
Ondráček, Aleš ; Zemčík, Pavel (referee) ; Herout, Adam (advisor)
The purpose of this thesis is to create a drum metronome smartphone application, which would allow rhythm patterns to be stored in playlists. These would then be used to assist the drummer while playing at rehearsals and at smaller or medium-sized concerts. Key properties of the smartphone application design include the ability to be controlled wirelessly via bluetooth, by a smartwatch application. The final product consists of two interconnected parts: a smartphone metronome application, and a smartwatch control application.
|
|
|
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.
|
|
|
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.
|
|
|
Deployment of Threshold Signatures for Securing Bitcoin Transactions
Tran, Minh ; Dzurenda, Petr
Blockchain technology, especially Bitcoin, has revolutionizedhow we think about and manage financial transactions.However, with the increasing demand and usage of blockchaintechnology, the security of cryptocurrency wallets has become acritical concern. Threshold signatures offer a promising solutionto this problem, allowing multiple parties to sign a transactionwithout revealing their private keys. This article presents an Androidmobile Bitcoin wallet application that uses Schnorr-basedthreshold signatures. The application also deploys smartwatchintegration for enhanced security and usability. This integrationprovides an additional layer of security by requiring physicalconfirmation from the user before approving any transaction.Our implementation provides a secure and efficient platform formanaging Bitcoin assets using threshold signatures while alsoproviding an intuitive and easy-to-use interface for interactingwith the application.
|
|
|
Advanced sleep scoring
Dokoupilová, Daniela ; Novotná, Petra (referee) ; Filipenská, Marina (advisor)
This diploma thesis focuses on classification of sleep stages using a smart watch. Two signals were used – heart rate and acceleration. A model called TinySleepNet composed of convolutional neural network and LSTM was chosen for this task. The model was first trained for the classification of five sleep stages using only heart rate, achieving F1 score of 49%. Acceleration was converted into an SVM vector, on which the second model was trained. Due to the lack of information in the SVM vector, the model was trained only for binary classification of wake/sleep, achieving F1 score of 62.3%. Both SVM and heart rate were combined in the last model. The classification of heart rate and SVM vector into five sleep stages achieved F1 score of 51%. The calculated parameters evaluating sleep quality were then compared with data evaluated by a sleep expert.
|
|
|
Validation of commercially available smartwatches as a human health/activity monitoring tool
Běhunčíková, Vendula ; Janoušek, Oto (referee) ; Němcová, Andrea (advisor)
This master's thesis deals with the topic of health and activity monitoring of individuals using smartwatches. The aim of the thesis was to collect a set of data according to a measurement protocol using various types of smartwatches, along with reference data from the Faros 180 device. The collected data from a total of nine smartwatches was synchronized, and the synchronized heart rate courses were evaluated using the mean absolute error (MAE) metric. The oxygen saturation and blood pressure parameters were statistically evaluated. In the final part of the thesis, the quality of ECG records obtained from the smartwatches and their diagnostic utility were assessed.
|
|
|
Advanced security for blockchain transactions
Tran, Minh ; Člupek, Vlastimil (referee) ; Dzurenda, Petr (advisor)
Blockchain technology, especially Bitcoin, has revolutionized how we think about and manage financial transactions. However, with the increasing demand and usage of blockchain technology, the security of cryptocurrency wallets has become a critical concern. Threshold signatures offer a promising solution to this problem, allowing multiple parties to sign a transaction without revealing their private keys. This article presents an Android mobile Bitcoin wallet application that uses Schnorr-based threshold signatures. The application also deploys smartwatch integration for enhanced security and usability. This integration provides an additional layer of security by requiring physical confirmation from the user before approving any transaction. Our implementation provides a secure and efficient platform for managing Bitcoin assets using threshold signatures while also providing an intuitive and easy-to-use interface for interacting with the application.
|
guest ::
