Dennis Harnandi
Universitas Kristen Maranatha

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Classification of Electroencephalogram Signal Sleeping Condition Output EEG Digital Tools Laboratory Clinical Neurophysiology Immanuel Hospital with Support Vector Machine Ratnadewi Ratnadewi; Dedeh Supantini; Decky Gunawan; Dennis Harnandi; Diana Chandrasasmita
International Journal of Artificial Intelligence Research Vol 6, No 2 (2022): Desember 2022
Publisher : International Journal of Artificial Intelligence Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v6i2.447

Abstract

Sleep Disorders like insomnia is one of the main health problems. Sleep deficiencies can increase the risk of diabetes, hypertension and cognitive disorders and behavior. The brain produces electrical signals, when someone is doing any activity such as moving, waking up, sleeping, etc. This electrical signal can be recorded using an electroencephalogram (EEG). In this study, brain signals are read with EEG Digital Laboratory of Clinical Neurophysiology Imanuel Hospital. The EEG signal results will be classified using Machine Learning Support Vector Machine (SVM). EEG signal data was obtained from Immanuel Hospital in Bandung. Conditions to be classified are the condition of waking, drowsiness (stage-1), and sleep (stage-2). Extraction of features using discrete wavelet transform Daubechies DB4. The decomposition level used in this study is Level-1 and Level-2. Based on the tests that have been carried out, the best parameter values obtained are C 10, Gamma 1, and Kernel Poly. Based on these parameters, the accuracy value was 78.8% for level-1, and 76.6% for level-2.