SMART SYSTEM UNTUK KLASIFIKASI TINGKAT STRES DENGAN METODE KOHONEN NEURAL NETWORK MENGGUNAKAN NEUROSKY MINDWAVE
| Main Author: | Himawan, Arif Danang Yunindra |
|---|---|
| Format: | Thesis NonPeerReviewed Book |
| Bahasa: | eng |
| Terbitan: |
, 2018
|
| Subjects: | |
| Online Access: |
http://eprints.umm.ac.id/39032/1/PENDAHULUAN.pdf http://eprints.umm.ac.id/39032/2/BAB%201.pdf http://eprints.umm.ac.id/39032/3/BAB%202.pdf http://eprints.umm.ac.id/39032/4/BAB%203.pdf http://eprints.umm.ac.id/39032/5/BAB%204.pdf http://eprints.umm.ac.id/39032/6/BAB%205.pdf http://eprints.umm.ac.id/39032/7/Lampiran.pdf http://eprints.umm.ac.id/39032/ |
Daftar Isi:
- Stress can affect the final grade students in completing the thesis in a timely manner. In previous researchers have researched to determine the level of student stress by recording data EEG (Electroencephalogram) signal using Neurosky Mindwave control device. The Fuzzy method used has weaknesses in the rule base system and no appropriate test equipment is used to compare the results of the method. Kohonen Neural Network is one of the artificial neural network to be an alternative to be able to classify (clustering) a person's stress level based on learning from training data and test the output with Likert Scales test equipment. The Kohonen Neural Network method result 3 clusters with high stress level on attention value 58-98, and meditation 19-51 in Cluster 1, then with moderate stress level in attention value range 60-88 and meditation value 50-78 in Cluster 2, and low stress level in the range of attention value 19-50 and meditation value 25-62 in Cluster 3. Test results with Likert Scales there is a matching output of 45% of the 20 new data.