forearm surface electromyography activity detection noise detection, identification and...
TRANSCRIPT
Forearm Surface Electromyography
Activity Detection
Noise Detection, Identification and Quantification
Signal Enhancement
• Make myoelectric forearm prostheses more useable
• So far– Onset detection– Noise reduction
Aim of research
• Introduction to myoelectric signals, prostheses and control
• Onset and activity detection• Carleton University’s CleanEMG - Noise
detection, identification, quantification• Signal enhancement
Today
Myoelectric signals and prostheses
Forearm Prosthesis Control
• None (passive)– Realistic looking– Has a few basic uses
• Body powered– User shrugs to open and close claw– Proprioception– Limited orientation
• Myoelectric– Pick up muscle signals and interpret
them into open and close commands– Mostly claw/pincer-type– First commercial limb in 1964
What myoelectric prostheses are not
• No sensory feedback– No proprioception– One gesture at a time
• Not part of your body• Doff every night to charge• Takes a while to don the socket
every morning
• Not as dextrous as natural hands- No direct control of fingers
• Made by Touch Bionics in Livingston• Individually articulated fingers• Motors stall when ‘enough’ grip has been
applied– Monitored by microprocessor
• Clever re-use of open/close to allow more gestures
• Can ‘pulse’ the motors to increase grip
The iLimbState-of-the-Art Forearm Prostheses
The iLimb andiLimb Digits
• iLimb shares limitations with all modern commercial myoelectric prostheses:– Amplitude-based commands do not directly
relate to desired gesture• Not all users can do all ‘double impulse’-type
commands
– Cannot address individual fingers– Manual thumb rotation for pinch and grip– Limited battery life – a day of normal use
Limitations of myoelectric prostheses
The Myoelectric Signal
Examples of typical sEMG signal
Multi-channelraw sEMG signal(live or recorded)
Sample Filter Windowing
Dimensionality reductionClassifierMajority vote
Class label stream
Feature extraction
Generic Pattern Recognition System
Onset/activity detection
One-Dimensional Local Binary Patterns for Surface EMG Activity Detection
• For image analysis• Spatiotemporal LBP for video analysis
2-D Local Binary Patterns
http://www.scholarpedia.org/article/File:LBP.jpg
• Take windows of signal
• Calculate LBP codes within window
• Form normalised histogram
One-Dimensional (1-D) Local Binary Patterns
Sample number
n
x[n]
0 0 1 1 0 020 21 22 23 24 25
= 12 in decimal
1-D LBP Activity Detection
𝑤 [ 𝑗 ] 𝑥 [𝑛 ]
LBP code calculation
‘Inactivity’ bins
Activity bins> Inactivity bins
YESActivity
NONo
activity
‘Activity’ bins
x[n]
1-D LBP histogram calculation
• Test on a synthetic signal (bandlimited Gaussian noise with AWGN 6dB)
1-D LBP Bin Behaviour
• Test on single gesture of real EMG recording
1-D LBP bin behaviour
• Once activity is detected, pattern recognition can be started
• Can sum the LBP codes from multiple channels within a window to get a single decision
1-D LBP Activity Detection
Placement at Carleton University, Ottawa, Canada
CleanEMG
• Access to an expert to manually identify and/or mitigate noise is not always possible
• EMG can be contaminated with several types of noise
• For each type, do some or all of these:– Detect– Identify– Quantify– Mitigate
Carleton University’s CleanEMG
• Power line (50Hz or 60Hz)• ECG• Clipping• Quantisation• Amplifier saturation
Also• Baseline wander• RF
Types of EMG noise
• Signal to Quantisation Noise Ratio• Signal to ECG Ratio• Effective Number of Bits• Signal to Motion Artefact Ratio• Power line Power (Least Squares
Identification)
Features
SQNRSNR (ECG)ENOBSMR
• Contaminants can be mistaken for each other if a single feature type is used– Motion artefact and ECG– Clipping and quantisation
• Training a classifier should help to address this
Why a classifier?
• Improved Prof Chan’s and Graham Fraser’s CleanEMG Matlab code
• Trained classifiers to identify contaminants using artificially-contaminated real and synthetic EMG– Indicated that detection and identification are
harder for signals with higher SNR
Work done at Carleton
• The techniques lead to improvements in classification accuracy for noisy data– Data Set 1 (Recorded at Strathclyde) – a little,
especially Channel 2– Data Set 2 (Prof Chan’s) – improved– Data Set 3 (Italian) – improvement in some
subjects
• Classification accuracy is improved for noisy data
Classification accuracy
PR system with a new stageRaw sEMG signal (measured or recorded)
Sample Filter Data Windowing
Dimensionality ReductionClassifierMedian Filter
(Majority Vote)
Class label
Feature Extraction
Onset Detection
Noise Detection, Identification, Quantification,
Mitigation