Saputra, Nophaz Hanggara (2022) Identifikasi Kondisi Stres Mental Pada Personil Kepolisian Menggunakan Sinyal EEG Berdasarkan Analisis Fitur Domain Waktu. Masters thesis, Institut Teknologi Sepuluh Nopember.
Text
07111950067009 - Master_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2024. Download (7MB) | Request a copy |
Abstract
Fenomena bunuh diri merupakan fenomena global yang terjadi di dunia bahkan di Indonesia. Hal ini disebabkan adanya komplikasi dari stress yang tinggi dan berat karena faktor ekonomi, masalah keluarga dan lingkungan. Stres tinggi dan berat tidak hanya dialami oleh masyarakat menengah ke bawah, tetapi juga dialami oleh anggota kepolisian di Kepolisian Daerah Jawa Timur. Beban tugas yang berat seperti penanganan unjuk rasa dengan ekskalasi tinggi menjadi salah satu faktor anggota kepolisian mengalami stress tinggi. Pendampingan dan
penyembuhan bersifat psikologis seperti wawancara mendalam, tes asesmen psikologi sudah dilakukan untuk memetakan hambatan psikologis, kelelahan emosi, kebosanan, apatis maupun kondisi stress anggota kepolisian. Penggunaan Electroencephalogram (EEG) merupakan salah satu sinyal fisiologis yang dapat digunakan untuk mengukur dan mengenali stres berdasarkan data aktivitas otak manusia. Dalam penelitian ini, mengenali kondisi stress dan normal berbasis EEG dilakukan dengan menggunakan fitur domain waktu dalam rentang pita frekuensi theta (4 – 8 Hz), Alpha (8 -13 Hz), dan beta (13 – 30 Hz) dari dua saluran yang berbeda yaitu F3 dan F4 dalam sistem 10/20 EEG. Data EEG diperoleh dari 20 partisipan anggota kepolisian (10 kondisi stress dan 10 kondisi normal). Fitur statistik seperti Mean, Standar Deviasi dan Zero Crossing digunakan untuk membedakan antara kondisi stres dan normal. Hasil percobaan menunjukkan bahwa fitur standar deviasi pada sinyal theta dan alfa memberikan nilai akurasi tertinggi dan konsisten pada dua saluran (F3 dan F4). Pada klasifikasi dengan kondisi stres dan normal menggunakan beberapa algoritma, SVM menunjukkan klasifikasi dengan nilai akurasi tetinggi (88,90 %), dibandingkan dengan algoritma lain seperti Random Forest (86,10 %), K-NN (77,80 %), dan Decision Tree (77,80%).
================================================================================================
Suicide is a global phenomenon that occurs worldwide, including in Indonesia. This is due to complications from high and severe stress because of economic factors, family and environmental problems. High and severe stresses are not only experienced by the lower middle class, but also by members of the police in the East Java Regional Police.
The heavy workload, such as handling demonstrations with high escalation, is one of the factors that cause police members to experience high stress. Psychological assistance and healing such as in-depth interviews, psychological assessment tests have been carried out to map the psychological barriers and stressful conditions of police officers. The use of an Electroencephalogram (EEG) is one of the physiological signals that can be used to measure and recognize stress based on data on human brain activity. This research recognized stress. In addition, normal conditions based on EEG was presented using time-domain features in the theta (4-8 hz), alpha (8-13 hz), and beta (13-30 hz) frequency bands from two different channels, namely F3 and F4 in the 10/20 EEG system. EEG data were obtained from 20 members of the police (10 under stress conditions and 10 in normal conditions). Statistical features such as Mean, Standard Deviation, and Zero Crossing are used to distinguish between stress and normal conditions. The experimental results showed that the standard deviation feature on the theta and alpha signal provided the highest accuracy value in two channel (F3 and F4). In the classification of stress and normal conditions using several algorithms, SVM indicates the highest classification accuracy (88.90%), compared to other algorithms such as Random Forest (86.10%), K-NN (77.80%) and Decision Tree (77,80%).
Item Type: | Thesis (Masters) |
---|---|
Uncontrolled Keywords: | identifikasi stres, personil kepolisian, EEG, fitur domain waktu, klasifikasi, Identifying Stres, Police Personnel, EEG, Time Domain Features, Classification |
Subjects: | B Philosophy. Psychology. Religion > BF Psychology T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5102.9 Signal processing. |
Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20101-(S2) Master Thesis |
Depositing User: | Nophaz Hanggara Saputra |
Date Deposited: | 18 Jan 2022 04:46 |
Last Modified: | 02 Nov 2022 02:38 |
URI: | http://repository.its.ac.id/id/eprint/92343 |
Actions (login required)
View Item |