45
Wearable BioSignal Interface by Thanakrit Lersmethasakul

Wearable BioSignal Interface

Embed Size (px)

DESCRIPTION

- To study the behavior and properties of bio-electric signals. - Develop a system to identify and recognize patterns of signals on a portable computer.

Citation preview

Page 1: Wearable BioSignal Interface

Wearable BioSignal Interfaceby Thanakrit Lersmethasakul

Page 2: Wearable BioSignal Interface

Content

1. Objective

2. Literature Survey

3. System Scenario

4. Experiment

Page 3: Wearable BioSignal Interface

1. Objective

- To study the behavior and properties of bio-electric signals.

- Develop a system to identify and recognize patterns of signals on a portable computer.

- Can be used to control the device.

Page 4: Wearable BioSignal Interface

2. Literature Survey

1. Studying the Use of Fuzzy Inference Systems for Motor Imagery Classification.2. System of Communication and Control Based on the Thought.3. BioSig: The Free and Open Source Software Library for Biomedical Signal Processing.4. Forearm EMG Pattern Recognition for Multifunction Myoelectric Control System.5. EEG Based Brain Computer Interface.6. A Review of Classification Algorithms for EEG-based Brain-

Computer Interfaces.7. Artificial Speech Synthesizer Control by Brain-Computer Interface

Page 5: Wearable BioSignal Interface

2.1 Studying the Use of Fuzzy Inference Systems for Motor Imagery Classification [1]

- Brain-Computer Interfaces with CFIS. (Chiu's Fuzzy Inference System)

- 3 steps processing(1) Clustering of training data - Subtractive

clustering algorithm.

(2) Generation of the fuzzy rules - Gaussian membership function.

(3) Fuzzy rule optimization - Gradient Descent Formulas

Page 6: Wearable BioSignal Interface

- Detection - Bipolar Electrodes - Feature Extraction - beta and alpha bands (C3β, C3α, C4β, C4α)- Hand-Made Fuzzy Rules (HMFR)- Classifier Comparison - Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), Linear Classifier (LC)

Table 1 Accuracy(%) and Mutual Information (MI) of Classifiers [1]

Page 7: Wearable BioSignal Interface

Table 2 Fuzzy rules automatically extracted by CFIS for subject [1]

Table 3 Hand-made fuzzy rules used to classify motor imagery data [1]

Page 8: Wearable BioSignal Interface

2. System of Communication and Control Based on the Thought [2]

- Accuracy in classify 70%

- Autoregressive Adaptive Parameter Feature Extraction

- Neural Network Classifier

- Movement patterns of left and right hand

Page 9: Wearable BioSignal Interface

Figure 1 System workflow [2]

Page 10: Wearable BioSignal Interface

3. BioSig: The Free and Open Source Software Library for Biomedical Signal Processing [3]

- Open source application for Biomedical Signal Processing.

- Used in research of Neuroinformatics, Brain-Computer Interfaces, Neurophysiology, Psychology, Cardiovascular Systems and Sleep Research.

Page 11: Wearable BioSignal Interface

- Data Acquisition, Artifact Processing, Quality Control, Feature Extraction, Classification, Modeling and Data Visualization.

- Electroencephalogram (EEG), Electrocardiogram (ECG), Electrooculogram (EOG), Electromyogram (EMG).

Page 12: Wearable BioSignal Interface

Figure 2 Architecture of the BioSig toolbox and its elements [3]

Page 13: Wearable BioSignal Interface

Figure 4 Elements of a brain computer interface [3]

Page 14: Wearable BioSignal Interface

4. Forearm EMG Pattern Recognition for Multifunction Myoelectric Control System [4]

Figure 5 Multifunction myoelectric control system [4]

Page 15: Wearable BioSignal Interface

Figure 6 EMG signals from muscle movement, posture and hand gestures. [4]

Page 16: Wearable BioSignal Interface

Figure 7 Processing [4]

Page 17: Wearable BioSignal Interface

5. EEG Based Brain Computer Interface [5]

- Test with 1 hidden layer-50 neurons, 1 hidden layer-100 neurons, 2 hidden layers-50 neurons and 2 hidden layers-100 neurons Neural Network.

- Left movement with eyes closed, Right movement with eyes closed and Left movement with eyes open are example patterns

Page 18: Wearable BioSignal Interface

Figure 8 Functional Model of a BCI System [5]

Page 19: Wearable BioSignal Interface

Figure 9 Nihon Kohden Neurofax-21 channel Electroencephalograph [5]

Page 20: Wearable BioSignal Interface

Figure 10 Planning for Left movement with eyes closed [5]

Page 21: Wearable BioSignal Interface

Conclusion

- Movement can easily be identified and observed by EEG.

- Analytical thought process is still almost impossible to classify, since emotions can’t be predicted via scalp EEG.

- The more the number of neurons or layers the better the classification is but at cost of memory and processing power.

Page 22: Wearable BioSignal Interface

Table 4 Some of classifier properties [6]

6. A Review of Classification Algorithms for EEG-based Brain-Computer Interfaces [6]

Page 23: Wearable BioSignal Interface

7. Artificial Speech Synthesizer Control by Brain-Computer Interface[7]

- Invasive EEG with Neurotrophic Electrode.

- Gyrus Precentral (a prominent structure in the parietal lobe of the human brain).

- Kalman filter-based decoder in Speech Synthesizer

Page 24: Wearable BioSignal Interface

Figure 11 Schematic of the brain-machine interface for real-time synthetic speech production [7]

Page 25: Wearable BioSignal Interface

2. System Scenario

Page 26: Wearable BioSignal Interface

4.1 EMG Signal Classification with Autoregresive Model and Backpropagation Neural Network.

(1) Detection

4. Experiment

Figure 12 Cyberlink Brainfinger [8]

Page 27: Wearable BioSignal Interface

Figure 13 Middle of bicep muscle [9]

Page 28: Wearable BioSignal Interface

Figure 14 EMG signal detection by Cyberlink Brainfinger.

Page 29: Wearable BioSignal Interface

Motionless

Fold

Contract

Twist-In

Twist-Out

Sway-Front

Sway-Back

Page 30: Wearable BioSignal Interface

Fold

Twist-In Twist-Out

Sway-Front Sway-Back

Contract

Page 31: Wearable BioSignal Interface

(2) Feature Extraction - AR – Coefficients with Least Mean Square- Convergence constant (µ) = 0.001 [10]- Autoregressive order = 4

Figure 15 Autoregressive process

Page 32: Wearable BioSignal Interface

(3) Classification- Backpropagation Neural Network- Learning rate = 0.5- Error = 0.3

Figure 16 Backpropagation Neural Network process

Page 33: Wearable BioSignal Interface

Figure 17 BioSign on UMPC

Page 34: Wearable BioSignal Interface

Conclusion

- Low accuracy (Error = 0.3).

- NN structure is not good enough.

- Training data is too little.

Page 35: Wearable BioSignal Interface

4.2 Finding appropriate NN architecture with WEKA

- Calculate and keep AR-coefficients data

Figure 18 AR-coefficients calculation with LMS method.

Page 36: Wearable BioSignal Interface

Figure 19 ARFF format file.

Page 37: Wearable BioSignal Interface

Figure 20 Preprocess on Weka.

Page 38: Wearable BioSignal Interface

Figure 21 Classify on Weka.

Learning Rate = 0.3Momentum = 0.2

Page 39: Wearable BioSignal Interface

Table 5 7-patterns classification result.(motionless, contract, fold, sway_back, sway_front, twist_in, twist_out)

Page 40: Wearable BioSignal Interface

Table 6 6-patterns classification result.(contract, fold, sway_back, sway_front, twist_in, twist_out)

Page 41: Wearable BioSignal Interface

Table 7 4-patterns classification result.(contract, fold, sway_back, twist_in)

Page 42: Wearable BioSignal Interface

Figure 22 Neural Network (28 - Hidden Layers)

Page 43: Wearable BioSignal Interface

- Portable EEG brainwave headset- TGAM1 module, with TGAT1 ASIC- Automatic wireless computer pairing- Neuroscience defined EEG power spectrum (Alpha, Beta, etc.)

Page 44: Wearable BioSignal Interface

Reference

1. Lotte Fabien, L´ecuyer Anatole, Lamarche Fabrice and Arnaldi Bruno, “Studying the Use of Fuzzy Inference Systems for Motor Imagery Classification.”, IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol.15, No.2, June 2007.

2. R.Gonzalez, "System of Communication and Control Based on the Thought", 2010.3. Carmen Vidaurre, Tilmann H. Sander and Alois Schl, “BioSig: The Free and Open Source Software Library for Biomedical Signal Processing”, Computational Intelligence and Neuroscience, Volume 2011.4. Angkoon Phinyomark, "Forearm EMG Pattern Recognition for Multifunction Myoelectric Control System", 12th RGA-Ph.D. Congress.5. Syed M. Saddique and Laraib Hassan Siddiqui. “EEG Based Brain Computer Interface”.

Journal of Software, vol.4, no.6, August 2009.6. F.Lotte, M.Congedo, A.Lecuyer, F.Lamarche and B.Arnaldi. “A Review of Classification

Algorithms for EEG-based Brain-Computer Interfaces”. Journal of Neural Engineering 4, 2007.

7. Syed M. Saddique and Laraib Hassan Siddiqui. “EEG Based Brain Computer Interface”. Journal of Software, vol.4, no.6, August 2009.

Page 45: Wearable BioSignal Interface

5. Cyberlink Brainfinger, http://www.brainfingers.com6. Carlo J. De Luca,2002. ”Surface Electromyography: Detection and Recording”. by DelSys

Incorporated.7. Hefftner G., Zucchini W., and Jaros G.,1988. "The Eletromyogram (EMG) as a Control

Signal for Functional Neuromuscular Stimulation. Part I: Autoregressive Modeling as a Means of EMG Signature Discrimination". IEEE Transactions on Biomedical Engeneering, 35(34), pp.230–237.