SlideShare une entreprise Scribd logo
1  sur  10
Unsupervised Selection of Mother Wavelets
and Parameter Optimization for Artifact
Removal in Neural Recordings
By
Md Kafiul Islam
Translational System and Signal Processing Group
National University of Singapore
Sequence of Optimization
1) Optimization of Parameter Alpha for Best
Mother Wavelet
2) Optimization of Parameter kA
3) Optimization of Parameter kD
Motivation to Choose Best Wavelet
 To achieve best performance both in terms of artifact removal and signal distortion
2 4 6 8 10
65
70
75
80
85
90
lamda
db2
Best
2 4 6 8 10
12
14
16
18
delSNR
db2
Best
2 4 6 8 10
0.006
0.008
0.01
0.012
0.014
RMSE
db2
Best
2 4 6 8 10
0.5
1
1.5
2
2.5
No. of Trials
PSDDistortion
db2
Best
Comparison of Artifact Removal Performance between Best Mother Wavelet and
Daubechies Wavelet (Filter Length = 4)
2 4 6 8 10
60
70
80
90
lamda
Sym2
Best
2 4 6 8 10
12
14
16
18
20
delSNR
Sym2
Best
2 4 6 8 10
0.008
0.01
0.012
0.014
0.016
RMSE
Sym2
Best
2 4 6 8 10
0.5
1
1.5
2
2.5
3
No. of Trials
PSDDistortion
Sym2
Best
Comparison of Artifact Removal Performance between Best Mother Wavelet
and Symlet Wavelet (Filter Length = 4)
Purpose to Optimize Parameter kD and kA
 To make the selection unsupervised
 To achieve best performance both in terms of artifact removal and signal distortion
1 1.5 2 2.5 3 3.5 4 4.5 5
9
10
11
12
13
14
15 X: 3
Y: 14.5
Parameter k
D
Avg.SNDRImprove
The Maximum Value of Average SNDR Improvement Can be
Achieved Through an Optimized and Unsupervised Selection of
Parameter k_D
0 0.2 0.4 0.6 0.8 1
0
20
40
60
80
100 X: 0.6
Y: 80.97
lamda
0 0.2 0.4 0.6 0.8 1
10
12
14
16
18
X: 0.6
Y: 16.32
delSNR
0 0.2 0.4 0.6 0.8 1
0
1
2
3
X: 0.6
Y: 1.187
PSDDistortion
0 0.2 0.4 0.6 0.8 1
0.005
0.01
0.015
0.02
X: 0.6
Y: 0.009534
RMSE
Parameter k
A
The Best Performance Metrics Can be Achieved Through an Optimized
and Unsupervised Selection of Parameter k_A
Optimization of Parameter α for Best Wavelet
 Wavelet Filter Design (Length = 4)
Low Pass Filter
High Pass Filter
 Criteria for Optimal ‘α’: Options
 Maximize Correlation between Artifactual
Signal and Reconstructed Signal in non-
artifactual regions (i.e. IDi is not artifact index)
 Minimize Correlation between Artifactual
Signal and Reconstructed Signal in artifactual
regions (i.e. IDi is artifact index)
Optimization of Parameter α
• Steps for Optimization Procedure
1) Parameterize the wavelet filters w. r. t. α
2) Sweep α from –π to +π with increment of π/6
3) Compute the filter coef., hα & gα for each α
4) Perform proposed artifact removal process with the
wavelet filters, hα & gα
5) Minimize Correlation between r(n) and r’(n) only in
the artifact-index regions to find optimal alpha,
α_opt1
Or
6) Maximize Correlation between r(n) and r’(n) only in
the non-artifact-index regions to find optimal alpha,
α_opt2
Correlation Value Vs Alpha
-4 -3 -2 -1 0 1 2 3 4
0.35
0.4
0.45
0.5
Minimize ArtifactsCorrelationValue
-4 -3 -2 -1 0 1 2 3 4
0.94
0.96
0.98
1
alpha
Maximize Non-Artifacts
α_opt2 = - 2.618
α_opt1 = - 2.094
Performance Metrics Vs Alpha
-4 -3 -2 -1 0 1 2 3 4
86
87
88
89
lamda
-4 -3 -2 -1 0 1 2 3 4
17.5
18
18.5
19
delSNR
alpha
-4 -3 -2 -1 0 1 2 3 4
1.1
1.15
1.2
1.25
PSDDistortion
-4 -3 -2 -1 0 1 2 3 4
7.6
7.8
8
8.2
8.4
x 10
-3
alpha
RMSE
Optimization of Parameter kA
0.2 0.4 0.6 0.8 1
0
20
40
60
80
100
lamda
0.2 0.4 0.6 0.8 1
8
10
12
14
16
delSNR
Parameter k
A
0.2 0.4 0.6 0.8 1
0
2
4
6
PSDDistortion
0.2 0.4 0.6 0.8 1
0.005
0.01
0.015
0.02
RMSE
Parameter kA
0.2 0.4 0.6 0.8 1
-0.4
-0.2
0
0.2
0.4
Minimize Artifacts
CorrelationValue
0.2 0.4 0.6 0.8 1
0.8
0.85
0.9
0.95
1
Maximize Non-Artifacts
Parameter k
A
kA_opt1 = 1
kA_opt2 = 0.7
Optimization of Parameter kD
1 1.5 2 2.5 3 3.5 4 4.5 5
0.461
0.462
0.463
0.464
Minimize Artifacts
1 1.5 2 2.5 3 3.5 4 4.5 5
0.9934
0.9934
0.9934
0.9934
k
D
Maximize Non-Artifacts
1 2 3 4 5 6
11
12
13
14
15
16
17
k
D
Avg.SNDRImprovement
kD_opt1 = 2.5
kD_opt2 = 5
17 dB SNDR
@ kD_opt1 = 2.5
15.94 dB SNDR
@ kD_opt2 = 5
1 1.5 2 2.5 3 3.5 4 4.5 5
0.8482
0.8482
0.8482
0.8482
PSD dis aft
1 1.5 2 2.5 3 3.5 4 4.5 5
9.9945
9.995
9.9955
x 10
-3
k2
RMSE aft
1 1.5 2 2.5 3 3.5 4 4.5 5
79.687
79.688
79.689
79.69
79.691
79.692
lamda
1 1.5 2 2.5 3 3.5 4 4.5 5
13.4296
13.4298
13.43
13.4302
13.4304
delSNR
k2

Contenu connexe

En vedette

Artifact detection and removal
Artifact detection and removalArtifact detection and removal
Artifact detection and removalMd Kafiul Islam
 
Poster Presentation on "Artifact Characterization and Removal for In-Vivo Neu...
Poster Presentation on "Artifact Characterization and Removal for In-Vivo Neu...Poster Presentation on "Artifact Characterization and Removal for In-Vivo Neu...
Poster Presentation on "Artifact Characterization and Removal for In-Vivo Neu...Md Kafiul Islam
 
Poster Presentation on "Artifact Reduction from Scalp EEG for Epilepsy Seizur...
Poster Presentation on "Artifact Reduction from Scalp EEG for Epilepsy Seizur...Poster Presentation on "Artifact Reduction from Scalp EEG for Epilepsy Seizur...
Poster Presentation on "Artifact Reduction from Scalp EEG for Epilepsy Seizur...Md Kafiul Islam
 
Memristors and their potential applications 2012
Memristors and their potential applications 2012Memristors and their potential applications 2012
Memristors and their potential applications 2012Md Kafiul Islam
 
Neural Networks for OCR
Neural Networks for OCRNeural Networks for OCR
Neural Networks for OCRDavid Stark
 
EMBC'13 Poster Presentation on "A Bio-Inspired Cooperative Algorithm for Dist...
EMBC'13 Poster Presentation on "A Bio-Inspired Cooperative Algorithm for Dist...EMBC'13 Poster Presentation on "A Bio-Inspired Cooperative Algorithm for Dist...
EMBC'13 Poster Presentation on "A Bio-Inspired Cooperative Algorithm for Dist...Md Kafiul Islam
 
15 Learnings from the European Innovation Academy 2015
15 Learnings from the European Innovation Academy 201515 Learnings from the European Innovation Academy 2015
15 Learnings from the European Innovation Academy 2015Nikita Lukianets
 
PhD Oral Defense of Md Kafiul Islam on "ARTIFACT CHARACTERIZATION, DETECTION ...
PhD Oral Defense of Md Kafiul Islam on "ARTIFACT CHARACTERIZATION, DETECTION ...PhD Oral Defense of Md Kafiul Islam on "ARTIFACT CHARACTERIZATION, DETECTION ...
PhD Oral Defense of Md Kafiul Islam on "ARTIFACT CHARACTERIZATION, DETECTION ...Md Kafiul Islam
 
Back propagation network
Back propagation networkBack propagation network
Back propagation networkHIRA Zaidi
 
An approach to empirical Optical Character recognition paradigm using Multi-L...
An approach to empirical Optical Character recognition paradigm using Multi-L...An approach to empirical Optical Character recognition paradigm using Multi-L...
An approach to empirical Optical Character recognition paradigm using Multi-L...Abdullah al Mamun
 
Neural Networks
Neural Networks Neural Networks
Neural Networks Eric Su
 
Blood Sugar (Glucose) Measurement, Monitoring and Data Analysis: A Review on ...
Blood Sugar (Glucose) Measurement, Monitoring and Data Analysis: A Review on ...Blood Sugar (Glucose) Measurement, Monitoring and Data Analysis: A Review on ...
Blood Sugar (Glucose) Measurement, Monitoring and Data Analysis: A Review on ...Md Kafiul Islam
 
Igcse biology edexcel 5.10 5.20
Igcse biology edexcel 5.10 5.20Igcse biology edexcel 5.10 5.20
Igcse biology edexcel 5.10 5.20Marc Rodriguez
 
Hand Written Character Recognition Using Neural Networks
Hand Written Character Recognition Using Neural Networks Hand Written Character Recognition Using Neural Networks
Hand Written Character Recognition Using Neural Networks Chiranjeevi Adi
 

En vedette (16)

Artifact detection and removal
Artifact detection and removalArtifact detection and removal
Artifact detection and removal
 
Poster Presentation on "Artifact Characterization and Removal for In-Vivo Neu...
Poster Presentation on "Artifact Characterization and Removal for In-Vivo Neu...Poster Presentation on "Artifact Characterization and Removal for In-Vivo Neu...
Poster Presentation on "Artifact Characterization and Removal for In-Vivo Neu...
 
Poster Presentation on "Artifact Reduction from Scalp EEG for Epilepsy Seizur...
Poster Presentation on "Artifact Reduction from Scalp EEG for Epilepsy Seizur...Poster Presentation on "Artifact Reduction from Scalp EEG for Epilepsy Seizur...
Poster Presentation on "Artifact Reduction from Scalp EEG for Epilepsy Seizur...
 
Memristors and their potential applications 2012
Memristors and their potential applications 2012Memristors and their potential applications 2012
Memristors and their potential applications 2012
 
Neural Networks for OCR
Neural Networks for OCRNeural Networks for OCR
Neural Networks for OCR
 
EMBC'13 Poster Presentation on "A Bio-Inspired Cooperative Algorithm for Dist...
EMBC'13 Poster Presentation on "A Bio-Inspired Cooperative Algorithm for Dist...EMBC'13 Poster Presentation on "A Bio-Inspired Cooperative Algorithm for Dist...
EMBC'13 Poster Presentation on "A Bio-Inspired Cooperative Algorithm for Dist...
 
15 Learnings from the European Innovation Academy 2015
15 Learnings from the European Innovation Academy 201515 Learnings from the European Innovation Academy 2015
15 Learnings from the European Innovation Academy 2015
 
PhD Oral Defense of Md Kafiul Islam on "ARTIFACT CHARACTERIZATION, DETECTION ...
PhD Oral Defense of Md Kafiul Islam on "ARTIFACT CHARACTERIZATION, DETECTION ...PhD Oral Defense of Md Kafiul Islam on "ARTIFACT CHARACTERIZATION, DETECTION ...
PhD Oral Defense of Md Kafiul Islam on "ARTIFACT CHARACTERIZATION, DETECTION ...
 
Back propagation network
Back propagation networkBack propagation network
Back propagation network
 
An approach to empirical Optical Character recognition paradigm using Multi-L...
An approach to empirical Optical Character recognition paradigm using Multi-L...An approach to empirical Optical Character recognition paradigm using Multi-L...
An approach to empirical Optical Character recognition paradigm using Multi-L...
 
Neural Networks
Neural Networks Neural Networks
Neural Networks
 
Blood Sugar (Glucose) Measurement, Monitoring and Data Analysis: A Review on ...
Blood Sugar (Glucose) Measurement, Monitoring and Data Analysis: A Review on ...Blood Sugar (Glucose) Measurement, Monitoring and Data Analysis: A Review on ...
Blood Sugar (Glucose) Measurement, Monitoring and Data Analysis: A Review on ...
 
Igcse biology edexcel 5.10 5.20
Igcse biology edexcel 5.10 5.20Igcse biology edexcel 5.10 5.20
Igcse biology edexcel 5.10 5.20
 
Memristor
MemristorMemristor
Memristor
 
Dsp ppt
Dsp pptDsp ppt
Dsp ppt
 
Hand Written Character Recognition Using Neural Networks
Hand Written Character Recognition Using Neural Networks Hand Written Character Recognition Using Neural Networks
Hand Written Character Recognition Using Neural Networks
 

Similaire à Unsupervised selection of mother wavelets and parameter optimization

FPGA Implementation of a GA
FPGA Implementation of a GAFPGA Implementation of a GA
FPGA Implementation of a GAHocine Merabti
 
Simulation and hardware implementation of Adaptive algorithms on tms320 c6713...
Simulation and hardware implementation of Adaptive algorithms on tms320 c6713...Simulation and hardware implementation of Adaptive algorithms on tms320 c6713...
Simulation and hardware implementation of Adaptive algorithms on tms320 c6713...Raj Kumar Thenua
 
aserra_phdthesis_ppt
aserra_phdthesis_pptaserra_phdthesis_ppt
aserra_phdthesis_pptaserrapages
 
Low Power Reconfigurable ASICs for Wearable Technology Apps
Low Power Reconfigurable ASICs for Wearable Technology AppsLow Power Reconfigurable ASICs for Wearable Technology Apps
Low Power Reconfigurable ASICs for Wearable Technology AppsTriad Semiconductor
 
IIR filter design, Digital signal processing
IIR filter design, Digital signal processingIIR filter design, Digital signal processing
IIR filter design, Digital signal processingAbhishek Thakkar
 
A CMOS 79GHz PMCW radar SOC
A CMOS 79GHz PMCW radar SOCA CMOS 79GHz PMCW radar SOC
A CMOS 79GHz PMCW radar SOCDr. Jianying Guo
 
Discovery Bus: UK QSAR meeting at GSK
Discovery Bus: UK QSAR meeting at GSKDiscovery Bus: UK QSAR meeting at GSK
Discovery Bus: UK QSAR meeting at GSKDavid Leahy
 
Malik - Formal Element Report
Malik - Formal Element ReportMalik - Formal Element Report
Malik - Formal Element ReportJunaid Malik
 
Linear models
Linear modelsLinear models
Linear modelsFAO
 
Boosting the Performance of Nested Spatial Mapping with Unequal Modulation in...
Boosting the Performance of Nested Spatial Mapping with Unequal Modulation in...Boosting the Performance of Nested Spatial Mapping with Unequal Modulation in...
Boosting the Performance of Nested Spatial Mapping with Unequal Modulation in...Ealwan Lee
 
Introduction of 7200 Q-TOF.pdf
Introduction of 7200 Q-TOF.pdfIntroduction of 7200 Q-TOF.pdf
Introduction of 7200 Q-TOF.pdfssuser50b929
 
11. Linear Models
11. Linear Models11. Linear Models
11. Linear ModelsFAO
 
Design consideration and comparative evaluation of swarm intelligence
Design consideration and comparative evaluation of swarm intelligenceDesign consideration and comparative evaluation of swarm intelligence
Design consideration and comparative evaluation of swarm intelligenceShashankPalakurthi
 
Algorithm Selection for Preferred Extensions Enumeration
Algorithm Selection for Preferred Extensions EnumerationAlgorithm Selection for Preferred Extensions Enumeration
Algorithm Selection for Preferred Extensions EnumerationFederico Cerutti
 
DSP MATLAB Projects Research Ideas
DSP MATLAB Projects Research IdeasDSP MATLAB Projects Research Ideas
DSP MATLAB Projects Research IdeasMatlab Simulation
 
Decomposition and Denoising for moment sequences using convex optimization
Decomposition and Denoising for moment sequences using convex optimizationDecomposition and Denoising for moment sequences using convex optimization
Decomposition and Denoising for moment sequences using convex optimizationBadri Narayan Bhaskar
 
Presentació renovables
Presentació renovablesPresentació renovables
Presentació renovablesJordi Cusido
 

Similaire à Unsupervised selection of mother wavelets and parameter optimization (20)

FPGA Implementation of a GA
FPGA Implementation of a GAFPGA Implementation of a GA
FPGA Implementation of a GA
 
Simulation and hardware implementation of Adaptive algorithms on tms320 c6713...
Simulation and hardware implementation of Adaptive algorithms on tms320 c6713...Simulation and hardware implementation of Adaptive algorithms on tms320 c6713...
Simulation and hardware implementation of Adaptive algorithms on tms320 c6713...
 
aserra_phdthesis_ppt
aserra_phdthesis_pptaserra_phdthesis_ppt
aserra_phdthesis_ppt
 
DSP.ppt
DSP.pptDSP.ppt
DSP.ppt
 
Low Power Reconfigurable ASICs for Wearable Technology Apps
Low Power Reconfigurable ASICs for Wearable Technology AppsLow Power Reconfigurable ASICs for Wearable Technology Apps
Low Power Reconfigurable ASICs for Wearable Technology Apps
 
IIR filter design, Digital signal processing
IIR filter design, Digital signal processingIIR filter design, Digital signal processing
IIR filter design, Digital signal processing
 
A CMOS 79GHz PMCW radar SOC
A CMOS 79GHz PMCW radar SOCA CMOS 79GHz PMCW radar SOC
A CMOS 79GHz PMCW radar SOC
 
Discovery Bus: UK QSAR meeting at GSK
Discovery Bus: UK QSAR meeting at GSKDiscovery Bus: UK QSAR meeting at GSK
Discovery Bus: UK QSAR meeting at GSK
 
Malik - Formal Element Report
Malik - Formal Element ReportMalik - Formal Element Report
Malik - Formal Element Report
 
Ad7716
Ad7716Ad7716
Ad7716
 
Shereef_MP3_decoder
Shereef_MP3_decoderShereef_MP3_decoder
Shereef_MP3_decoder
 
Linear models
Linear modelsLinear models
Linear models
 
Boosting the Performance of Nested Spatial Mapping with Unequal Modulation in...
Boosting the Performance of Nested Spatial Mapping with Unequal Modulation in...Boosting the Performance of Nested Spatial Mapping with Unequal Modulation in...
Boosting the Performance of Nested Spatial Mapping with Unequal Modulation in...
 
Introduction of 7200 Q-TOF.pdf
Introduction of 7200 Q-TOF.pdfIntroduction of 7200 Q-TOF.pdf
Introduction of 7200 Q-TOF.pdf
 
11. Linear Models
11. Linear Models11. Linear Models
11. Linear Models
 
Design consideration and comparative evaluation of swarm intelligence
Design consideration and comparative evaluation of swarm intelligenceDesign consideration and comparative evaluation of swarm intelligence
Design consideration and comparative evaluation of swarm intelligence
 
Algorithm Selection for Preferred Extensions Enumeration
Algorithm Selection for Preferred Extensions EnumerationAlgorithm Selection for Preferred Extensions Enumeration
Algorithm Selection for Preferred Extensions Enumeration
 
DSP MATLAB Projects Research Ideas
DSP MATLAB Projects Research IdeasDSP MATLAB Projects Research Ideas
DSP MATLAB Projects Research Ideas
 
Decomposition and Denoising for moment sequences using convex optimization
Decomposition and Denoising for moment sequences using convex optimizationDecomposition and Denoising for moment sequences using convex optimization
Decomposition and Denoising for moment sequences using convex optimization
 
Presentació renovables
Presentació renovablesPresentació renovables
Presentació renovables
 

Plus de Md Kafiul Islam

EEE400 1st Trimester Progress Presentation on Sleep Disorder Classification
EEE400 1st Trimester Progress Presentation on Sleep Disorder ClassificationEEE400 1st Trimester Progress Presentation on Sleep Disorder Classification
EEE400 1st Trimester Progress Presentation on Sleep Disorder ClassificationMd Kafiul Islam
 
EEE400 1st Trimester Progress Presentation on EEG based Neuro-Marketing
EEE400 1st Trimester Progress Presentation on EEG based Neuro-MarketingEEE400 1st Trimester Progress Presentation on EEG based Neuro-Marketing
EEE400 1st Trimester Progress Presentation on EEG based Neuro-MarketingMd Kafiul Islam
 
Invited talk at IBRO UIU EEG Signal Processing
Invited talk at IBRO UIU EEG Signal ProcessingInvited talk at IBRO UIU EEG Signal Processing
Invited talk at IBRO UIU EEG Signal ProcessingMd Kafiul Islam
 
Study of smart phone sensor based fall detection
Study of smart phone sensor based fall detectionStudy of smart phone sensor based fall detection
Study of smart phone sensor based fall detectionMd Kafiul Islam
 
Presentation slides on Child Tracking System
Presentation slides on Child Tracking SystemPresentation slides on Child Tracking System
Presentation slides on Child Tracking SystemMd Kafiul Islam
 
Poster eog controlled wheelchair new
Poster eog controlled wheelchair newPoster eog controlled wheelchair new
Poster eog controlled wheelchair newMd Kafiul Islam
 
Icasert 2019 pid_230_revised
Icasert 2019 pid_230_revisedIcasert 2019 pid_230_revised
Icasert 2019 pid_230_revisedMd Kafiul Islam
 
Digitization of Infusion Pump
Digitization of Infusion PumpDigitization of Infusion Pump
Digitization of Infusion PumpMd Kafiul Islam
 
Development of a low cost pc-based single-channel eeg monitoring system
Development of a low cost pc-based single-channel eeg monitoring systemDevelopment of a low cost pc-based single-channel eeg monitoring system
Development of a low cost pc-based single-channel eeg monitoring systemMd Kafiul Islam
 
EMG classification using ANN
EMG classification using ANNEMG classification using ANN
EMG classification using ANNMd Kafiul Islam
 
ECG Classification using SVM
ECG Classification using SVMECG Classification using SVM
ECG Classification using SVMMd Kafiul Islam
 
ICDPR@SG 2020 PID_A304_presentation
ICDPR@SG 2020 PID_A304_presentationICDPR@SG 2020 PID_A304_presentation
ICDPR@SG 2020 PID_A304_presentationMd Kafiul Islam
 
EMG controlled Prosthetic Arm
EMG controlled Prosthetic ArmEMG controlled Prosthetic Arm
EMG controlled Prosthetic ArmMd Kafiul Islam
 
Motion Artifact in Ambulatory EEG
Motion Artifact in Ambulatory EEGMotion Artifact in Ambulatory EEG
Motion Artifact in Ambulatory EEGMd Kafiul Islam
 
Exploring smartphone sensors
Exploring smartphone sensorsExploring smartphone sensors
Exploring smartphone sensorsMd Kafiul Islam
 
Presentation on Blood Pressure Monitoring as part of Final Year Project (Part...
Presentation on Blood Pressure Monitoring as part of Final Year Project (Part...Presentation on Blood Pressure Monitoring as part of Final Year Project (Part...
Presentation on Blood Pressure Monitoring as part of Final Year Project (Part...Md Kafiul Islam
 
Senior Project Student's Presentation on Design of EMG Signal Recording System
Senior Project Student's Presentation on Design of EMG Signal Recording SystemSenior Project Student's Presentation on Design of EMG Signal Recording System
Senior Project Student's Presentation on Design of EMG Signal Recording SystemMd Kafiul Islam
 
Senior Project Student's Presentation on Body Temperature Monitoring
Senior Project Student's Presentation on Body Temperature MonitoringSenior Project Student's Presentation on Body Temperature Monitoring
Senior Project Student's Presentation on Body Temperature MonitoringMd Kafiul Islam
 

Plus de Md Kafiul Islam (20)

EEE400 1st Trimester Progress Presentation on Sleep Disorder Classification
EEE400 1st Trimester Progress Presentation on Sleep Disorder ClassificationEEE400 1st Trimester Progress Presentation on Sleep Disorder Classification
EEE400 1st Trimester Progress Presentation on Sleep Disorder Classification
 
EEE400 1st Trimester Progress Presentation on EEG based Neuro-Marketing
EEE400 1st Trimester Progress Presentation on EEG based Neuro-MarketingEEE400 1st Trimester Progress Presentation on EEG based Neuro-Marketing
EEE400 1st Trimester Progress Presentation on EEG based Neuro-Marketing
 
Invited talk at IBRO UIU EEG Signal Processing
Invited talk at IBRO UIU EEG Signal ProcessingInvited talk at IBRO UIU EEG Signal Processing
Invited talk at IBRO UIU EEG Signal Processing
 
Study of smart phone sensor based fall detection
Study of smart phone sensor based fall detectionStudy of smart phone sensor based fall detection
Study of smart phone sensor based fall detection
 
Presentation slides on Child Tracking System
Presentation slides on Child Tracking SystemPresentation slides on Child Tracking System
Presentation slides on Child Tracking System
 
TENSYMP presentation
TENSYMP presentationTENSYMP presentation
TENSYMP presentation
 
Poster eog controlled wheelchair new
Poster eog controlled wheelchair newPoster eog controlled wheelchair new
Poster eog controlled wheelchair new
 
Icasert 2019 pid_230_revised
Icasert 2019 pid_230_revisedIcasert 2019 pid_230_revised
Icasert 2019 pid_230_revised
 
Digitization of Infusion Pump
Digitization of Infusion PumpDigitization of Infusion Pump
Digitization of Infusion Pump
 
Development of a low cost pc-based single-channel eeg monitoring system
Development of a low cost pc-based single-channel eeg monitoring systemDevelopment of a low cost pc-based single-channel eeg monitoring system
Development of a low cost pc-based single-channel eeg monitoring system
 
EMG classification using ANN
EMG classification using ANNEMG classification using ANN
EMG classification using ANN
 
Real-time Vein Imaging
Real-time Vein ImagingReal-time Vein Imaging
Real-time Vein Imaging
 
ECG Classification using SVM
ECG Classification using SVMECG Classification using SVM
ECG Classification using SVM
 
ICDPR@SG 2020 PID_A304_presentation
ICDPR@SG 2020 PID_A304_presentationICDPR@SG 2020 PID_A304_presentation
ICDPR@SG 2020 PID_A304_presentation
 
EMG controlled Prosthetic Arm
EMG controlled Prosthetic ArmEMG controlled Prosthetic Arm
EMG controlled Prosthetic Arm
 
Motion Artifact in Ambulatory EEG
Motion Artifact in Ambulatory EEGMotion Artifact in Ambulatory EEG
Motion Artifact in Ambulatory EEG
 
Exploring smartphone sensors
Exploring smartphone sensorsExploring smartphone sensors
Exploring smartphone sensors
 
Presentation on Blood Pressure Monitoring as part of Final Year Project (Part...
Presentation on Blood Pressure Monitoring as part of Final Year Project (Part...Presentation on Blood Pressure Monitoring as part of Final Year Project (Part...
Presentation on Blood Pressure Monitoring as part of Final Year Project (Part...
 
Senior Project Student's Presentation on Design of EMG Signal Recording System
Senior Project Student's Presentation on Design of EMG Signal Recording SystemSenior Project Student's Presentation on Design of EMG Signal Recording System
Senior Project Student's Presentation on Design of EMG Signal Recording System
 
Senior Project Student's Presentation on Body Temperature Monitoring
Senior Project Student's Presentation on Body Temperature MonitoringSenior Project Student's Presentation on Body Temperature Monitoring
Senior Project Student's Presentation on Body Temperature Monitoring
 

Dernier

PE 459 LECTURE 2- natural gas basic concepts and properties
PE 459 LECTURE 2- natural gas basic concepts and propertiesPE 459 LECTURE 2- natural gas basic concepts and properties
PE 459 LECTURE 2- natural gas basic concepts and propertiessarkmank1
 
School management system project Report.pdf
School management system project Report.pdfSchool management system project Report.pdf
School management system project Report.pdfKamal Acharya
 
Wadi Rum luxhotel lodge Analysis case study.pptx
Wadi Rum luxhotel lodge Analysis case study.pptxWadi Rum luxhotel lodge Analysis case study.pptx
Wadi Rum luxhotel lodge Analysis case study.pptxNadaHaitham1
 
kiln thermal load.pptx kiln tgermal load
kiln thermal load.pptx kiln tgermal loadkiln thermal load.pptx kiln tgermal load
kiln thermal load.pptx kiln tgermal loadhamedmustafa094
 
Online food ordering system project report.pdf
Online food ordering system project report.pdfOnline food ordering system project report.pdf
Online food ordering system project report.pdfKamal Acharya
 
Hospital management system project report.pdf
Hospital management system project report.pdfHospital management system project report.pdf
Hospital management system project report.pdfKamal Acharya
 
Work-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptxWork-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptxJuliansyahHarahap1
 
GEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLE
GEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLEGEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLE
GEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLEselvakumar948
 
Generative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPTGenerative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPTbhaskargani46
 
Unleashing the Power of the SORA AI lastest leap
Unleashing the Power of the SORA AI lastest leapUnleashing the Power of the SORA AI lastest leap
Unleashing the Power of the SORA AI lastest leapRishantSharmaFr
 
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdfAldoGarca30
 
Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptx
Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptxOrlando’s Arnold Palmer Hospital Layout Strategy-1.pptx
Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptxMuhammadAsimMuhammad6
 
Employee leave management system project.
Employee leave management system project.Employee leave management system project.
Employee leave management system project.Kamal Acharya
 
Tamil Call Girls Bhayandar WhatsApp +91-9930687706, Best Service
Tamil Call Girls Bhayandar WhatsApp +91-9930687706, Best ServiceTamil Call Girls Bhayandar WhatsApp +91-9930687706, Best Service
Tamil Call Girls Bhayandar WhatsApp +91-9930687706, Best Servicemeghakumariji156
 
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...Arindam Chakraborty, Ph.D., P.E. (CA, TX)
 
Hostel management system project report..pdf
Hostel management system project report..pdfHostel management system project report..pdf
Hostel management system project report..pdfKamal Acharya
 
Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...
Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...
Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...drmkjayanthikannan
 
Computer Lecture 01.pptxIntroduction to Computers
Computer Lecture 01.pptxIntroduction to ComputersComputer Lecture 01.pptxIntroduction to Computers
Computer Lecture 01.pptxIntroduction to ComputersMairaAshraf6
 

Dernier (20)

PE 459 LECTURE 2- natural gas basic concepts and properties
PE 459 LECTURE 2- natural gas basic concepts and propertiesPE 459 LECTURE 2- natural gas basic concepts and properties
PE 459 LECTURE 2- natural gas basic concepts and properties
 
School management system project Report.pdf
School management system project Report.pdfSchool management system project Report.pdf
School management system project Report.pdf
 
Wadi Rum luxhotel lodge Analysis case study.pptx
Wadi Rum luxhotel lodge Analysis case study.pptxWadi Rum luxhotel lodge Analysis case study.pptx
Wadi Rum luxhotel lodge Analysis case study.pptx
 
kiln thermal load.pptx kiln tgermal load
kiln thermal load.pptx kiln tgermal loadkiln thermal load.pptx kiln tgermal load
kiln thermal load.pptx kiln tgermal load
 
Integrated Test Rig For HTFE-25 - Neometrix
Integrated Test Rig For HTFE-25 - NeometrixIntegrated Test Rig For HTFE-25 - Neometrix
Integrated Test Rig For HTFE-25 - Neometrix
 
Online food ordering system project report.pdf
Online food ordering system project report.pdfOnline food ordering system project report.pdf
Online food ordering system project report.pdf
 
Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7
Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7
Call Girls in South Ex (delhi) call me [🔝9953056974🔝] escort service 24X7
 
Hospital management system project report.pdf
Hospital management system project report.pdfHospital management system project report.pdf
Hospital management system project report.pdf
 
Work-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptxWork-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptx
 
GEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLE
GEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLEGEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLE
GEAR TRAIN- BASIC CONCEPTS AND WORKING PRINCIPLE
 
Generative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPTGenerative AI or GenAI technology based PPT
Generative AI or GenAI technology based PPT
 
Unleashing the Power of the SORA AI lastest leap
Unleashing the Power of the SORA AI lastest leapUnleashing the Power of the SORA AI lastest leap
Unleashing the Power of the SORA AI lastest leap
 
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
 
Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptx
Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptxOrlando’s Arnold Palmer Hospital Layout Strategy-1.pptx
Orlando’s Arnold Palmer Hospital Layout Strategy-1.pptx
 
Employee leave management system project.
Employee leave management system project.Employee leave management system project.
Employee leave management system project.
 
Tamil Call Girls Bhayandar WhatsApp +91-9930687706, Best Service
Tamil Call Girls Bhayandar WhatsApp +91-9930687706, Best ServiceTamil Call Girls Bhayandar WhatsApp +91-9930687706, Best Service
Tamil Call Girls Bhayandar WhatsApp +91-9930687706, Best Service
 
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
 
Hostel management system project report..pdf
Hostel management system project report..pdfHostel management system project report..pdf
Hostel management system project report..pdf
 
Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...
Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...
Unit 4_Part 1 CSE2001 Exception Handling and Function Template and Class Temp...
 
Computer Lecture 01.pptxIntroduction to Computers
Computer Lecture 01.pptxIntroduction to ComputersComputer Lecture 01.pptxIntroduction to Computers
Computer Lecture 01.pptxIntroduction to Computers
 

Unsupervised selection of mother wavelets and parameter optimization

  • 1. Unsupervised Selection of Mother Wavelets and Parameter Optimization for Artifact Removal in Neural Recordings By Md Kafiul Islam Translational System and Signal Processing Group National University of Singapore
  • 2. Sequence of Optimization 1) Optimization of Parameter Alpha for Best Mother Wavelet 2) Optimization of Parameter kA 3) Optimization of Parameter kD
  • 3. Motivation to Choose Best Wavelet  To achieve best performance both in terms of artifact removal and signal distortion 2 4 6 8 10 65 70 75 80 85 90 lamda db2 Best 2 4 6 8 10 12 14 16 18 delSNR db2 Best 2 4 6 8 10 0.006 0.008 0.01 0.012 0.014 RMSE db2 Best 2 4 6 8 10 0.5 1 1.5 2 2.5 No. of Trials PSDDistortion db2 Best Comparison of Artifact Removal Performance between Best Mother Wavelet and Daubechies Wavelet (Filter Length = 4) 2 4 6 8 10 60 70 80 90 lamda Sym2 Best 2 4 6 8 10 12 14 16 18 20 delSNR Sym2 Best 2 4 6 8 10 0.008 0.01 0.012 0.014 0.016 RMSE Sym2 Best 2 4 6 8 10 0.5 1 1.5 2 2.5 3 No. of Trials PSDDistortion Sym2 Best Comparison of Artifact Removal Performance between Best Mother Wavelet and Symlet Wavelet (Filter Length = 4)
  • 4. Purpose to Optimize Parameter kD and kA  To make the selection unsupervised  To achieve best performance both in terms of artifact removal and signal distortion 1 1.5 2 2.5 3 3.5 4 4.5 5 9 10 11 12 13 14 15 X: 3 Y: 14.5 Parameter k D Avg.SNDRImprove The Maximum Value of Average SNDR Improvement Can be Achieved Through an Optimized and Unsupervised Selection of Parameter k_D 0 0.2 0.4 0.6 0.8 1 0 20 40 60 80 100 X: 0.6 Y: 80.97 lamda 0 0.2 0.4 0.6 0.8 1 10 12 14 16 18 X: 0.6 Y: 16.32 delSNR 0 0.2 0.4 0.6 0.8 1 0 1 2 3 X: 0.6 Y: 1.187 PSDDistortion 0 0.2 0.4 0.6 0.8 1 0.005 0.01 0.015 0.02 X: 0.6 Y: 0.009534 RMSE Parameter k A The Best Performance Metrics Can be Achieved Through an Optimized and Unsupervised Selection of Parameter k_A
  • 5. Optimization of Parameter α for Best Wavelet  Wavelet Filter Design (Length = 4) Low Pass Filter High Pass Filter  Criteria for Optimal ‘α’: Options  Maximize Correlation between Artifactual Signal and Reconstructed Signal in non- artifactual regions (i.e. IDi is not artifact index)  Minimize Correlation between Artifactual Signal and Reconstructed Signal in artifactual regions (i.e. IDi is artifact index)
  • 6. Optimization of Parameter α • Steps for Optimization Procedure 1) Parameterize the wavelet filters w. r. t. α 2) Sweep α from –π to +π with increment of π/6 3) Compute the filter coef., hα & gα for each α 4) Perform proposed artifact removal process with the wavelet filters, hα & gα 5) Minimize Correlation between r(n) and r’(n) only in the artifact-index regions to find optimal alpha, α_opt1 Or 6) Maximize Correlation between r(n) and r’(n) only in the non-artifact-index regions to find optimal alpha, α_opt2
  • 7. Correlation Value Vs Alpha -4 -3 -2 -1 0 1 2 3 4 0.35 0.4 0.45 0.5 Minimize ArtifactsCorrelationValue -4 -3 -2 -1 0 1 2 3 4 0.94 0.96 0.98 1 alpha Maximize Non-Artifacts α_opt2 = - 2.618 α_opt1 = - 2.094
  • 8. Performance Metrics Vs Alpha -4 -3 -2 -1 0 1 2 3 4 86 87 88 89 lamda -4 -3 -2 -1 0 1 2 3 4 17.5 18 18.5 19 delSNR alpha -4 -3 -2 -1 0 1 2 3 4 1.1 1.15 1.2 1.25 PSDDistortion -4 -3 -2 -1 0 1 2 3 4 7.6 7.8 8 8.2 8.4 x 10 -3 alpha RMSE
  • 9. Optimization of Parameter kA 0.2 0.4 0.6 0.8 1 0 20 40 60 80 100 lamda 0.2 0.4 0.6 0.8 1 8 10 12 14 16 delSNR Parameter k A 0.2 0.4 0.6 0.8 1 0 2 4 6 PSDDistortion 0.2 0.4 0.6 0.8 1 0.005 0.01 0.015 0.02 RMSE Parameter kA 0.2 0.4 0.6 0.8 1 -0.4 -0.2 0 0.2 0.4 Minimize Artifacts CorrelationValue 0.2 0.4 0.6 0.8 1 0.8 0.85 0.9 0.95 1 Maximize Non-Artifacts Parameter k A kA_opt1 = 1 kA_opt2 = 0.7
  • 10. Optimization of Parameter kD 1 1.5 2 2.5 3 3.5 4 4.5 5 0.461 0.462 0.463 0.464 Minimize Artifacts 1 1.5 2 2.5 3 3.5 4 4.5 5 0.9934 0.9934 0.9934 0.9934 k D Maximize Non-Artifacts 1 2 3 4 5 6 11 12 13 14 15 16 17 k D Avg.SNDRImprovement kD_opt1 = 2.5 kD_opt2 = 5 17 dB SNDR @ kD_opt1 = 2.5 15.94 dB SNDR @ kD_opt2 = 5 1 1.5 2 2.5 3 3.5 4 4.5 5 0.8482 0.8482 0.8482 0.8482 PSD dis aft 1 1.5 2 2.5 3 3.5 4 4.5 5 9.9945 9.995 9.9955 x 10 -3 k2 RMSE aft 1 1.5 2 2.5 3 3.5 4 4.5 5 79.687 79.688 79.689 79.69 79.691 79.692 lamda 1 1.5 2 2.5 3 3.5 4 4.5 5 13.4296 13.4298 13.43 13.4302 13.4304 delSNR k2