ms762wu/EMG_Biometrics_2021
2
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity
Structuring and analytics of EMG data from MYO armbands. Work by IAESTE intern Markus Hoff Skudal, summer 2021.
94 Commits 1 Branch 0 Tags 409 MiB
Python 100%
9c030fa2dc
Go to file
Skudalen 9c030fa2dc doc: add first version of the README file
2021-07-07 16:00:33 +02:00
__pycache__ fix: fix indexing of labels in mfcc json 2021-07-07 12:11:46 +02:00
.idea fix: try to implement the NN correctly 2021-07-05 12:43:45 +02:00
.vscode chore: improve code quality 2021-07-06 16:33:35 +02:00
python_speech_features.egg-info fix: add minor changes 2021-06-28 09:59:01 +02:00
.DS_Store feat: add new class DL_data_handler and make sample func 2021-06-30 14:53:44 +02:00
.gitignore feat: clone and import python_speech_features 2021-06-28 10:57:08 +02:00
Handle_emg_data.py fix: fix indexing of labels in mfcc json 2021-07-07 12:11:46 +02:00
mfcc_data.json fix: fix indexing of labels in mfcc json 2021-07-07 12:11:46 +02:00
Neural_Network_Analysis.py feat: get the LSTM running 2021-07-07 15:28:15 +02:00
Present_data.py fix: fix indexing of labels in mfcc json 2021-07-07 12:11:46 +02:00
README.md doc: add first version of the README file 2021-07-07 16:00:33 +02:00
Signal_prep.py fix: change to right naming conventions 2021-07-02 10:26:05 +02:00
Test_functions.py chore: moved presenting functions to Present_data.py 2021-06-25 16:09:51 +02:00

README.md

Analysis of Keystroke EMG data for identification

EMG data handling and Neural Network analysis
Scripts to handle CSV files composed by 2 * 8 EMG sensors(left & right) devided into sessions per subject. The raw data is organised in a CSV_handler object with Handle_emg_data.py. Processing of data can take the further form of: 
* Preprocessing with Signal_prep.py - FFT, MFCC, Wavelet db4
* Storage for Neural Network analysis with DL_handler(Handle_emg_data.py) - combined EMG DataFrame, combined MFCCs DataFrame
* Neural Network analysis in Neural_Network_Analysis.py - LSTM NN, etc.
Technologies used
* Common libs: Numpy, Pandas, Pathlib, Sklearn, Scipy, Matplotlib, Tensorflow, Keras
* Indi libs: Python_speech_features, Pywt
Challanges in the module
* The CSV handlig is for the moment hard-coded to fit the current project due to a very specific file structure and respective naming convention.
* Preprocessing is still limited in Signal_prep.py
* Neural_Network_Analysis.py lacks a more general way to access multiple types of networks