Institutional Repository of Vilnius University
Miego EEG apdorojimo informacinės sistemos kūrimas /
Abstract
dc:descriptionThis bachelor thesis presents the development and implementation of an automated sleep elect roencephalogram (EEG) analysis information system [6]. The system utilizes deep learning tech niques in classifying sleep stages and evaluating sleep quality to meet the ever-growing demand for efficient and accurate sleep analytical tools in clinical settings. In general, the main goal was to develop a user-friendly information system that would allow medical professionals to automatically analyze sleep EEG data and provide comprehensive sleep quality reports. This study developed a hybrid deep learning architecture, combining the powers of CNNs for feature extraction and LSTMs for temporal pattern recognition in EEG signals to achieve this goal [3, 1]. The system includes several components: automated preprocessing and noise reduction of EEG signals, classification of sleep stages according to AASM, calculation of the metrics of sleep quality, generation of visual reports about sleep analysis, and evidence-based suggestions for improving the quality of sleep. The experiments were conducted on publicly available sleep EEG datasets. The system was trained and tested on a variety of sleep recordings and achieved high overall classification accura cy for all sleep stages [4]. This included extensive testing of the classification performance and practical clinical applicability of the system.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Jefimovas, Tomas,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD229555348&prefLang=en_US