Skip to content

Latest commit

 

History

History
50 lines (42 loc) · 2.58 KB

README.md

File metadata and controls

50 lines (42 loc) · 2.58 KB

SigPy

SigPy is a python framework and GUI for using machine-learning methods to analyse gastro-intestinal (GI) electrophysiological data.GI recordings first undergo preprocessing steps including band-pass filtering and normalisation. Pre-labelled slow-wave activity is used to train a convolutional neural network (CNN). New data loaded into SigPy can then apply this CNN onto this new data and automate the marking process of GI slow-waves. Once the recordings have labelled the slow wave events, SigPy enables detailed analyses of slow wave dynamics including through the production of animations displaying the propagation of slow-waves. SigPy also allows exporting of data into a format compatible with the Gastro-intestinal Electrical Mapping Suite (GEMS) MATLAB toolbox to perform other slow wave related analyses.

Software requirements

In Linux Variants

Install PqQT5 or PyQT4: sudo apt-get install python-qt4 Install PIP: sudo apt-get install python-pip Install scientific python libraries: sudo apt-get install python-numpy python-scipy python-matplotlib Install graphviz: sudo apt-get install graphviz

In window

Install Anaconda from https://www.anaconda.com/download/#download From Anaconda Prompt:

conda install pip

Installing and running

pip install -r requirements.txt

Run by: python main_SigPy.py

Prerequisites

numpy>=1.13.1 PySide>=1.2.4 pyqtgraph>=0.10.0 scipy>=0.19.1 theano>=0.9.0 keras>=2.1.4 matplotlib>=2.0.2 scikit-learn==0.19.1 h5py==2.7.1 pydot==1.2.4 graphviz==0.8.2 hyperas==0.4 hyperopt==0.1

Built With

  • PyQt - PyQt is a set of Python v2 and v3 bindings for The Qt Company's Qt application framework and runs on all platforms supported by Qt including Windows, OS X, Linux, iOS and Android.
  • PyQtGraph - PyQtGraph is a pure-python graphics and GUI library built on PyQt4 / PySide and numpy.
  • Theano - Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently.
  • Keras - Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano. It was developed with a focus on enabling fast experimentation.
  • Numpy - NumPy is the fundamental package for scientific computing with Python.

Authors

  • Shameer Sathar - Design, Conceptualisation, Algorithm Development, Visualisation Techniques
  • Terry Mayne - Bug Fixes, compatibility with GEMS