Claim Missing Document
Check
Articles

Found 15 Documents
Search

KLASIFIKASI SINYAL EEG MENGGUNAKAN SUPPORT VECTOR MACHINE (SVM) UNTUK DETEKSI KEBOHONGAN Kumbara, Bagus; Turnip, Arjon; Waslaluddin, Waslaluddin
ISSN
Publisher : Program Studi Fisika

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Electroencephalogram (EEG) merupakan aktifitas sinyal listrik yang berasal dari elektroda yang dipasangkan pada area otak. Aktifitas sinyal listrik dari otak menyimpan informasi penting yang merupakan sumber informasi utama dalam mendeteksi kebohongan. Support Vector Machine (SVM) digunakan untuk mengklasifikasi siyal EEG untuk mendapatkan hasil deteksi kebohongan. Penelitian ini bertujuan untuk menghasilkan model SVM yang dapat menentukan data EEG untuk subjek berbohong atau tidak. Dalam perekaman EEG, sinyal yang didapat tidak sepenuhnya berasal dari otak namun dapat terkontaminasi oleh sinyal lain seperti EOG, ECG dan EMG. Sehingga untuk mendapatkan informasi yang sesuai, maka dilakukan tahapan pengolahan sinyal digital pada sinyal EEG. Tahapan pengolahan digital meliputi, remove offset, Independent Component Analysis (ICA), Bandpass filter dan Trial data. Sinyal EEG yang bersih digunakan untuk mengetahui informasi yang disembunyikan oleh subjek, misalnya ketika sedang berbohong. Penelitian yang dilakukan menghasilkan model SVM dengan akurasi 75% dan waktu komputasi 0.009 detik, sehingga dapat menentukan data EEG untuk subjek berbohong atau tidak.
DESIGN OF GROUND WATER QUALITY AND CAPACITY MONITORING SYSTEM FOR ASR INFILTRATION WELL USING WIRELESS Alam, Hilman Syaeful; Munandar, Aris; Soetraprawata, Demi; Turnip, Arjon
Teknologi Indonesia Vol 36, No 2 (2013)
Publisher : LIPI Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14203/jti.v36i2.200

Abstract

Design of a monitoring system for the quality and capacity of water absorption wells type Aquifer Storage and Recovery (ASR) using wireless system has been conducted by monitoring changes in well water surface level, the rate of change of fl ow capacity (fl ow rate) and changes in water quality (turbidity). In order to determine the performance of the system, we conducted several tests by placing a sensor and a receiver by two different distances, i.e. the distance of 1 m (short distance) and the actual condition of 35 m (long distance). The results of the system design consist of a wireless monitoring system hardware and data acquisition system software able to display online and in real time. Based on the test results, the value of the total error due to repeatability and linearity for flow rate sensors, water level and turbidity using short-distance wireless systems, are respectively 2.77%, 1.77% and 3.65%. As for the wireless remote system, they are respectively 1.43%, 1.83% and 2.43%. So, the monitoring system of groundwater quality and capacity for infi ltration well using the wireless system can be applied to the actual distance of 35 m, because the error rate due to the infl uence of the distance between the transmitter and the receiver is relatively small, and even better when compared with the short distance ( 1 m).
NEURAL NETWORK TRAINING USING SEQUENTIAL EXTENDED KALMAN FILTER FOR RELIABLE ROAD FRICTION COEFFICIENT ESTIMATION Soetraprawata, Demi; Turnip, Arjon
Teknologi Indonesia Vol 33, No 2 (2010)
Publisher : LIPI Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14203/jti.v33i2.26

Abstract

The aim of this study is to estimate the vehicle dynamic parameters concerning with road safety (such as, road tire forces, longitudinal and lateral velocities, angular velocity, rolling radius of wheels, side slip, pitch and roll angle, and road friction coeffi cient which are diffi cult to be measured directly in a standard car) using neural network training on the basis of sequential extended Kalman fi lter (SEKF) and the recursive least squares (RLS). For such estimation, a fourteen degree-of-freedom (DOF) nonlinear full-vehicle dynamics model was developed to provide the simulation requirement. The simulation was performed and compared with CarSim (the interpreter for vehicle dynamics) to verify the model, which confi rms the expected results were all the state variables follow the CarSim response well. The simulation results show that the system performs reliably and fastly in estimating the parameters on different road surfaces during various vehicle manoeuvres.
SEQUENTIAL EXTENDED KALMAN FILTER ON EEG EXTRACTION AND CLASSIFICATION Turnip, Arjon; Soetraprawata, Demi; Hariyadi, -; Kusumandari, Dwi Esti
Teknologi Indonesia Vol 36, No 1 (2013)
Publisher : LIPI Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (16.051 KB) | DOI: 10.14203/jti.v36i1.195

Abstract

In this paper, a neural networks training based on Sequential Extended Kalman Filtering (SEKF) analysis for extraction and classifi cation of recorded EEG signal is proposed to improved feature extraction, classifi cation accuracy,and communication rate as well. The robustness of the SEKF against background noises has been evaluated by comparing the separation performance indices of the SEKF with well known algorithms (i.e., BPNN, JADE,and SOBI). A statistically signifi cant improvement was achieved with respect to the rates provided by raw data.
DESIGN OF AN ADAPTIVE INTELLIGENT CONTROLLER IN A SEMI-ACTIVE SUSPENSION SYSTEMS Turnip, Arjon; Soetraprawata, Demi; Hariyadi, -; Kusumandari, Dwi Esti
Teknologi Indonesia Vol 36, No 1 (2013)
Publisher : LIPI Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (16.051 KB) | DOI: 10.14203/jti.v36i1.194

Abstract

In this paper, a semi-active control law consists of two tuneable parameters that are given as the function of the running conditions of the vehicle and an adaptive intelligent controller (AIC) is proposed to obtain the best compromise among confl icting performance indices pertaining to the vehicle suspension system. The proposed AIC method is developed based on the frequency regions. The obtained result indicates that a semi-active suspension system based AIC has a signifi cant potential in improving the ride comfort and the road holding.
An Experiment of Ocular Artifacts Elimination from EEG Signals using ICA and PCA Methods Turnip, Arjon; R. Setiawan, Iwan; Junaidi, Edy; Nguyen, Le Hoa
Journal of Mechatronics, Electrical Power and Vehicular Technology Vol 5, No 2 (2014)
Publisher : Research Centre for Electrical Power and Mechatronics, Indonesian Istitutes of Sciences

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1785.199 KB) | DOI: 10.14203/j.mev.2014.v5.129-138

Abstract

In the modern world of automation, biological signals, especially Electroencephalogram (EEG) is gaining wide attention as a source of biometric information. Eye-blinks and movement of the eyeballs produce electrical signals (contaminate the EEG signals) that are collectively known as ocular artifacts. These noise signals are required to be separated from the EEG signals to obtain the accurate results. This paper reports an experiment of ocular artifacts elimination from EEG signal using blind source separation algorithm based on independent component analysis and principal component analysis. EEG signals are recorded on three conditions, which are normal conditions, closed eyes, and blinked eyes. After processing, the dominant frequency of EEG signals in the range of 12-14 Hz either on normal, closed, and blinked eyes conditions is obtained. 
Autoregressive Integrated Adaptive Neural Networks Classifier for EEG-P300 Classification Soetraprawata, Demi; Turnip, Arjon
Journal of Mechatronics, Electrical Power and Vehicular Technology Vol 4, No 1 (2013)
Publisher : Research Centre for Electrical Power and Mechatronics, Indonesian Istitutes of Sciences

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (494.761 KB) | DOI: 10.14203/j.mev.2013.v4.1-8

Abstract

Brain Computer Interface has a potency to be applied in mechatronics apparatus and vehicles in the future. Compared to the other techniques, EEG is the most preferred for BCI designs. In this paper, a new adaptive neural network classifier of different mental activities from EEG-based P300 signals is proposed. To overcome the over-training that is caused by noisy and non-stationary data, the EEG signals are filtered and extracted using autoregressive models before passed to the adaptive neural networks classifier. To test the improvement in the EEG classification performance with the proposed method, comparative experiments were conducted using Bayesian Linear Discriminant Analysis. The experiment results show that the all subjects achieve a classification accuracy of 100%.
The Performance of EEG-P300 Classification using Backpropagation Neural Networks Turnip, Arjon; Soetraprawata, Demi
Journal of Mechatronics, Electrical Power and Vehicular Technology Vol 4, No 2 (2013)
Publisher : Research Centre for Electrical Power and Mechatronics, Indonesian Istitutes of Sciences

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (276.701 KB) | DOI: 10.14203/j.mev.2013.v4.81-88

Abstract

Electroencephalogram (EEG) recordings signal provide an important function of brain-computer communication, but the accuracy of their classification is very limited in unforeseeable signal variations relating to artifacts. In this paper, we propose a classification method entailing time-series EEG-P300 signals using backpropagation neural networks to predict the qualitative properties of a subject’s mental tasks by extracting useful information from the highly multivariate non-invasive recordings of brain activity. To test the improvement in the EEG-P300 classification performance (i.e., classification accuracy and transfer rate) with the proposed method, comparative experiments were conducted using Bayesian Linear Discriminant Analysis (BLDA). Finally, the result of the experiment showed that the average of the classification accuracy was 97% and the maximum improvement of the average transfer rate is 42.4%, indicating the considerable potential of the using of EEG-P300 for the continuous classification of mental tasks.
An Experiment of Ocular Artifacts Elimination from EEG Signals using ICA and PCA Methods Arjon Turnip; Iwan R. Setiawan; Edy Junaidi; Le Hoa Nguyen
Journal of Mechatronics, Electrical Power and Vehicular Technology Vol 5, No 2 (2014)
Publisher : National Research and Innovation Agency

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14203/j.mev.2014.v5.129-138

Abstract

In the modern world of automation, biological signals, especially Electroencephalogram (EEG) is gaining wide attention as a source of biometric information. Eye-blinks and movement of the eyeballs produce electrical signals (contaminate the EEG signals) that are collectively known as ocular artifacts. These noise signals are required to be separated from the EEG signals to obtain the accurate results. This paper reports an experiment of ocular artifacts elimination from EEG signal using blind source separation algorithm based on independent component analysis and principal component analysis. EEG signals are recorded on three conditions, which are normal conditions, closed eyes, and blinked eyes. After processing, the dominant frequency of EEG signals in the range of 12-14 Hz either on normal, closed, and blinked eyes conditions is obtained. 
Autoregressive Integrated Adaptive Neural Networks Classifier for EEG-P300 Classification Demi Soetraprawata; Arjon Turnip
Journal of Mechatronics, Electrical Power and Vehicular Technology Vol 4, No 1 (2013)
Publisher : National Research and Innovation Agency

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14203/j.mev.2013.v4.1-8

Abstract

Brain Computer Interface has a potency to be applied in mechatronics apparatus and vehicles in the future. Compared to the other techniques, EEG is the most preferred for BCI designs. In this paper, a new adaptive neural network classifier of different mental activities from EEG-based P300 signals is proposed. To overcome the over-training that is caused by noisy and non-stationary data, the EEG signals are filtered and extracted using autoregressive models before passed to the adaptive neural networks classifier. To test the improvement in the EEG classification performance with the proposed method, comparative experiments were conducted using Bayesian Linear Discriminant Analysis. The experiment results show that the all subjects achieve a classification accuracy of 100%.