Skip to content
This repository contains techniques to extract features from time series data.
Branch: master
Clone or download
Latest commit b0d6c08 Jul 29, 2018
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
Accuracy
Data for Users
actions
feature_extraction_scatterplots
features Adding code changes Apr 12, 2018
pca_features
plot_results
.gitignore
DecisionTree.m
HMM.m Added accuracy comment May 4, 2018
ModelEval.m Multi Class SVM Apr 9, 2018
ModelEvalBinary.m
ModelEvalTblKnn.m
ModelEvalTblNb.m
ModelEvalTmpDt.m multi class Decision Tree Apr 21, 2018
ModelEvalTmpNN.m multi class SVM and NN Apr 21, 2018
ModelEvalTmpSVM.m
NN_CONFUSION.png
NN_ROC.png
NNet.m
README.md
SVM.m
SVM_Multi.m
SegmentationUtil.m
Task1.m
action_action_comparison.m Add more plots Apr 13, 2018
csv_reformat.js
data_analysis.m Normalized features Apr 12, 2018
extraction_methods.m
feature_analysis.m
feature_normalization.csv
features.csv Multi Class SVM Apr 9, 2018
normalization.m
package-lock.json
package.json
pca_feature.csv
pca_feature.m
plot_util.m
plots.m
sampler_util.m
user_user_comparison.m

README.md

AMERICAN SIGN LANGUAGE RECOGNITION

This repository contains techniques to extract features from time series data of different american sign languages.

Time Domain Feature Extraction Techniques

  • Means in each of the dimensions
  • Standard Deviation in each of the dimensions
  • Max, Min in each of the dimensions
  • Window Extraction
  • Zero Mean
  • Energy Computation
  • Preemphasis Filter
  • Hamming Window
  • Spectrum Computation (FFT)
  • Mel Frequency Computation
  • Cepstrum Computation
  • Discrete Cosine Transform
  • Lifter (Cepstral Filter)
  • Cepstrum Energy Normalization
  • First and Sec

Frequency Domain Feature Extraction Techniques

  • Max frequency after FFT

Resources:

http://tsfresh.readthedocs.io/en/latest/text/list_of_features.html

#list of Features which can be used: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4401457/table/pone.0124414.t002/?report=objectonly

#related main paper for the above link: #Feature Selection for Wearable Smartphone-Based Human Activity Recognition with Able bodied, Elderly, and Stroke Patients https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4401457/

Related Publications

You can’t perform that action at this time.