Comprehensive Design Review Team 14 BMW Brainwave Manipulated
Comprehensive Design Review Team 14: BMW Brainwave Manipulated Wagon Electrical and Computer Engineering
Team 14 Members Zijian Chen CSE Tiffany Jao CSE Faculty Advisor: Qiangfei Xia Man Qin EE Electrical and Computer Engineering Xueling Zhao EE ‹#›
Outline ▪ System Review ▪ Demo Overview ▪ CDR Demo ▪ FPR Deliverables Electrical and Computer Engineering ‹#›
Previous Block Diagram TX Arduino Module Neurosky headset Bluetooth v 3. 0 Think. Gear Packet Computer C# Application Signal Processing Arduino/ USB serial Write Database Command Algorithm XBEE: TX User Interface Man Qin Zijian Chen Robotic Car Motor Arduino XBEE: RX Xueling Zhao Tiffany Jao Electrical and Computer Engineering Power Supply ‹#›
Revised Block Diagram EEG data Proprietary wireless 2. 4 GHz Emotiv EPOC headset C# Application Signal Processing Computer (training)Alpha, beta power (real time) Alpha, beta power (training)Alpha, beta power Bayesian Classifier Database (Training Data) command User Interface Man Qin Zijian Chen Xueling Zhao Tiffany Jao Robotic Car Electrical and Computer Engineering Arduino Bluetooth HC 05 ‹#›
Current Control ▪ Control using eye open/close • Alpha and beta power • Alpha power increases when close eyes ▪ Use sensor around occipital lobe- visionary processing • O 1 Electrical and Computer Engineering ‹#›
Signal Processing: FFT ▪ Input: Raw EEG data from headset ▪ C# library ▪ Visualize raw EEG data in frequency domain ▪ 1 second frame - 128 samples ▪ 0. 5 second overlapping window ▪ Output: calculated alpha and beta total power Ø Alpha wave : 8 – 12 Hz Ø Beta wave: 13 -30 Hz Electrical and Computer Engineering ‹#›
Before FFT: Raw EEG Data Voltage vs Time Eye-Closed Voltage vs Time Voltage (u. V) Eye-Open Voltage vs Time(Sec) Fig 1. (a) Time(Sec) Fig 1. (b) These two graphs are not meaningful as they are not indicting any information. Electrical and Computer Engineering ‹#›
After FFT: Power vs Frequency Eye-Closed Power vs Frequency Power(Watt) Eye-Open Power vs Frequency(Hz) Fig 2. (a) Spike within alpha range Frequency(Hz) Fig 2. (b) A dominant spike is observed in Fig 2. (b) Eye-Closed. Electrical and Computer Engineering ‹#›
FFT: Alpha and Beta Power Comparison Eye-Open vs Eye-Closed Beta Power Level Alpha Open Closed Fig 3. Alpha power increases obviously, while Beta power stays in similar level Fig 3. Electrical and Computer Engineering ‹#›
Naïve Bayes Classifier ▪ Probabilistic classifier based on applying Bayes’ theorem. Bayes Theorem: ▪ Why Naive Bayes Classifier : • Provide strong machine learning ability to adapt patterns • Run faster that other classifier, Need O(1) run time. • High accuracy for classification with small size of training set. Electrical and Computer Engineering ‹#›
Naïve Bayes Classifier ▪ How to Use ? average of closed-eye alpha, beta Find. Reference Point() (Alpha, Beta, Trigger) Real Time Data (alpha, beta) Database Analysis. Training. Set() (Training) Update probability classify() compare probability of trigger on and off Electrical and Computer Engineering output (true/false) ‹#›
Remote Robotic Car ▪ HC-5 Bluetooth Module ▪ Arduino Uno Electrical and Computer Engineering ‹#›
Remote Robotic Car ▪ Power L 298 N Motor Driver Board Digital Input From Arduino ▪ Power Supply Powered by 6 AA batteries which have total voltage of 9 v. Output to motor Electrical and Computer Engineering ‹#›
Remote Robotic Car HC-5 bluetooth module Electrical and Computer Engineering Arduino L 298 N Motor Driver Board 6 AA Batteries power 2 Motors ‹#›
Graphical User Interface - Training Electrical and Computer Engineering ‹#›
Graphical User Interface - Control Electrical and Computer Engineering ‹#›
Outline ▪ System Review ▪ Demo Overview ▪ CDR Demo ▪ FPR Deliverables Electrical and Computer Engineering ‹#›
Demo Overview ▪ Utilize the brainwave to control the robotic car • forward/stop What’s working Issues • Data retrieval from Emotiv • 1 second delay between car and the software • real time signal processing • Wireless interference • Bayesian classifier distinguished eye open/close state • misclassified result • Software interfacing with robotic car Electrical and Computer Engineering ‹#›
Outline ▪ System Review ▪ Demo Overview ▪ CDR Demo ▪ FPR Deliverables Electrical and Computer Engineering ‹#›
Outline ▪ System Review ▪ Demo Overview ▪ CDR Demo ▪ FPR Deliverables Electrical and Computer Engineering ‹#›
Proposed FPR Deliverables • Minimize the amount of misclassified command • filter outlier in training set • Ability to classify another command • Turning • Minimize delay Electrical and Computer Engineering ‹#›
Thank you Questions? Electrical and Computer Engineering ‹#›
BACKUP SLIDE Electrical and Computer Engineering ‹#›
Naïve Bayes Classifier ▪ Find Reference Point ▪ Get the average alpha and beta from training set ▪ Remove unusual-high alpha or beta data ▪ Use to determine if alpha or beta is high or low Electrical and Computer Engineering ‹#›
Naïve Bayes Classifier ▪ Analysis. Tranning. Set() ▪ Update Probability Table base on Training Set ▪ P(H_Alpha|Trigger) P(H_Alpha|NO_Trigger) P(L_Alpha|NO_Trigger) P(H_Beta|NO_Trigger) P(L_Beta|NO_Trigger) Electrical and Computer Engineering ‹#›
Naïve Bayes Classifier ▪ Classify ▪ Calculate probability of trigger on ▪ on ← argmax P(Y = t)∏P(Xi|Y = t) ▪ Calculate probability of trigger off ▪ off ← argmax P(Y = NO_t)∏P(Xi|Y = NO_t) ▪ Compare on and off ▪ return classified result Electrical and Computer Engineering ‹#›
Why changes the headset? ▪ It is needed to have more than 1 sensor for accurate measurement ▪ 2 references sensor Electrical and Computer Engineering ‹#›
FFT 1 -sec frame vs 2 -sec frame Electrical and Computer Engineering ‹#›
- Slides: 29