Klasifikasi Sinyal Eeg Motor Imagery Tangan Kanan Dan Kiri Berdasarkan Fitur Common Spatial Pattern (CSP) Menggunakan Multilayer Perceptron Backpropagation (MLP-BP)

Synatria, Subekti (2021) Klasifikasi Sinyal Eeg Motor Imagery Tangan Kanan Dan Kiri Berdasarkan Fitur Common Spatial Pattern (CSP) Menggunakan Multilayer Perceptron Backpropagation (MLP-BP). Undergraduate Thesis thesis, Institut Teknologi Telkom Purwokerto.

	Text COVER.pdf Download (1MB)
	Text ABSTRACT.pdf Download (85kB)
	Text ABSTRAK.pdf Download (5kB)
	Text BAB I.pdf Download (285kB)
	Text BAB II.pdf Download (2MB)
	Text BAB III.pdf Download (754kB)
	Text BAB IV.pdf Restricted to Registered users only Download (1MB) | Request a copy
	Text BAB V.pdf Download (190kB)
	Text DAFTAR PUSTAKA.pdf Download (270kB)
	Text LAMPIRAN.pdf Restricted to Registered users only Download (1MB) | Request a copy

Abstract

The number of people with disabilities is increasing, so that bionic technology is needed as a substitute for motor work functions such as the Brain Computer Interface (BCI) in the classification of Electroencephalogical (EEG) signals. This study aims to determine the level of accuracy and the best system model in the classification of right and left hand imagery motor based on the characteristics of the EEG channel. The system design in this study consists of wave channel selection using a Finite Impulse Response (FIR) Filter, Common Spatial Pattern (CSP) feature extraction, and Multilayer Perceptron Back-Propagation (MLP-BP) classification. This study uses a secondary dataset from BCI Competition IV (2b) with 9 research subjects. The scenario is carried out by testing using 1 dataset with several variations in the number of hidden layer nodes on each wave channel. The variations are 8, 16, and 24 nodes. The variations are 8, 16 and 24 nodes. Based on the test, the accuracy value is the highest average accuracy of the 10 K-Fold experiments. Accuracy in scenario 8 hidden layer nodes is 68.5%, hidden layer 16 nodes is 68.5%, and hidden layer 24 nodes is 68.7%. The best results from the 3 scenarios were using 24 nodes. Meanwhile, the alpha channel was the best channel from the scenario. Keywords : bci, eeg, csp, fir, mlp-bp, motor imagery

Actions (login required)

View Item