Implementation of Neonatal Seizure Detection using EEG signals for deploying on edge devices including Raspberry Pi.

Overview

NeonatalSeizureDetection

Description

Link: https://arxiv.org/abs/2111.15569

Citation:

@misc{nagarajan2021scalable,
      title={Scalable Machine Learning Architecture for Neonatal Seizure Detection on Ultra-Edge Devices}, 
      author={Vishal Nagarajan and Ashwini Muralidharan and Deekshitha Sriraman and Pravin Kumar S},
      year={2021},
      eprint={2111.15569},
      archivePrefix={arXiv},
      primaryClass={eess.SP}
}

This repository contains code for the implementation of the paper titled "Scalable Machine Learning Architecture for Neonatal Seizure Detection on Ultra-Edge Devices", which has been accepted at the AISP '22: 2nd International Conference on Artificial Intelligence and Signal Processing. A typical neonatal seizure and non-seizure event is illustrated below. Continuous EEG signals are filtered and segmented with varying window lengths of 1, 2, 4, 8, and 16 seconds. The data used here for experimentation can be downloaded from here.

Seizure Event Non-seizure Event

This end-to-end architecture receives raw EEG signal, processes it and classifies it as ictal or normal activity. After preprocessing, the signal is passed to a feature extraction engine that extracts the necessary feature set Fd. It is followed by a scalable machine learning (ML) classifier that performs prediction as illustrated in the figure below.

Pipeline Architecture

Files description

  1. dataprocessing.ipynb -> Notebook for converting edf files to csv files.
  2. filtering.ipynb -> Notebook for filtering the input EEG signals in order to observe the specific frequencies.
  3. segmentation.ipynb -> Notebook for segmenting the input into appropriate windows lengths and overlaps.
  4. features_final.ipynb -> Notebook for extracting relevant features from segmented data.
  5. protoNN_example.py -> Script used for running protoNN model using .npy files.
  6. inference_time.py -> Script used to record and report inference times.
  7. knn.ipynb -> Notebook used to compare results of ProtoNN and kNN models.

Dependencies

If you are using conda, it is recommended to switch to a new environment.

    $ conda create -n myenv
    $ conda activate myenv
    $ conda install pip
    $ pip install -r requirements.txt

If you wish to use virtual environment,

    $ pip install virtualenv
    $ virtualenv myenv
    $ source myenv/bin/activate
    $ pip install -r requirements.txt

Usage

  1. Clone the ProtoNN package from here, antropy package from here, and envelope_derivative_operator package from here.

  2. Replace the protoNN_example.py with protoNN_example.py.

  3. Prepare the train and test data .npy files and save it in a DATA_DIR directory.

  4. Execute the following command in terminal after preparing the data files. Create an output directory should you need to save the weights of the ProtoNN object as OUT_DIR.

        $ python protoNN_example.py -d DATA_DIR -e 500 -o OUT_DIR
    

Authors

Vishal Nagarajan

Ashwini Muralidharan

Deekshitha Sriraman

Acknowledgements

ProtoNN built using EdgeML provided by Microsoft. Features extracted using antropy and otoolej repositories.

References

[1] Nathan Stevenson, Karoliina Tapani, Leena Lauronen, & Sampsa Vanhatalo. (2018). A dataset of neonatal EEG recordings with seizures annotations [Data set]. Zenodo. https://doi.org/10.5281/zenodo.1280684.

[2] Gupta, Ankit et al. "ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices." Proceedings of the 34th International Conference on Machine Learning, Sydney, Australia, PMLR 70.

Owner
Vishal Nagarajan
Undergraduate ML Research Assistant at Solarillion Foundation B.E. (CSE) @ SSNCE
Vishal Nagarajan
A multi-functional library for full-stack Deep Learning. Simplifies Model Building, API development, and Model Deployment.

chitra What is chitra? chitra (चित्र) is a multi-functional library for full-stack Deep Learning. It simplifies Model Building, API development, and M

Aniket Maurya 210 Dec 21, 2022
Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image

NonCuboidRoom Paper Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image Cheng Yang*, Jia Zheng*, Xili Dai, Rui Tang, Yi Ma, Xiao

67 Dec 15, 2022
A high performance implementation of HDBSCAN clustering.

HDBSCAN HDBSCAN - Hierarchical Density-Based Spatial Clustering of Applications with Noise. Performs DBSCAN over varying epsilon values and integrates

2.3k Jan 02, 2023
A fuzzing framework for SMT solvers

yinyang A fuzzing framework for SMT solvers. Given a set of seed SMT formulas, yinyang generates mutant formulas to stress-test SMT solvers. yinyang c

Project Yin-Yang for SMT Solver Testing 145 Jan 04, 2023
[CVPR21] LightTrack: Finding Lightweight Neural Network for Object Tracking via One-Shot Architecture Search

LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search The official implementation of the paper LightTra

Multimedia Research 290 Dec 24, 2022
Clean and readable code for Decision Transformer: Reinforcement Learning via Sequence Modeling

Minimal implementation of Decision Transformer: Reinforcement Learning via Sequence Modeling in PyTorch for mujoco control tasks in OpenAI gym

Nikhil Barhate 104 Jan 06, 2023
Simply enable or disable your Nvidia dGPU

EnvyControl (WIP) Simply enable or disable your Nvidia dGPU Usage First clone this repo and install envycontrol with sudo pip install . CLI Turn off y

Victor Bayas 292 Jan 03, 2023
DockStream: A Docking Wrapper to Enhance De Novo Molecular Design

DockStream Description DockStream is a docking wrapper providing access to a collection of ligand embedders and docking backends. Docking execution an

AstraZeneca - Molecular AI 72 Jan 02, 2023
The source code for Adaptive Kernel Graph Neural Network at AAAI2022

AKGNN The source code for Adaptive Kernel Graph Neural Network at AAAI2022. Please cite our paper if you think our work is helpful to you: @inproceedi

11 Nov 25, 2022
7th place solution of Human Protein Atlas - Single Cell Classification on Kaggle

kaggle-hpa-2021-7th-place-solution Code for 7th place solution of Human Protein Atlas - Single Cell Classification on Kaggle. A description of the met

8 Jul 09, 2021
Learning Continuous Image Representation with Local Implicit Image Function

LIIF This repository contains the official implementation for LIIF introduced in the following paper: Learning Continuous Image Representation with Lo

Yinbo Chen 1k Dec 25, 2022
A toolkit for making real world machine learning and data analysis applications in C++

dlib C++ library Dlib is a modern C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real worl

Davis E. King 11.6k Jan 01, 2023
ICON: Implicit Clothed humans Obtained from Normals

ICON: Implicit Clothed humans Obtained from Normals arXiv, December 2021. Yuliang Xiu · Jinlong Yang · Dimitrios Tzionas · Michael J. Black Table of C

Yuliang Xiu 1.1k Dec 30, 2022
Example of a Quantum LSTM

Example of a Quantum LSTM

Riccardo Di Sipio 36 Oct 31, 2022
​ This is the Pytorch implementation of Progressive Attentional Manifold Alignment.

PAMA This is the Pytorch implementation of Progressive Attentional Manifold Alignment. Requirements python 3.6 pytorch 1.2.0+ PIL, numpy, matplotlib C

98 Nov 15, 2022
Group R-CNN for Point-based Weakly Semi-supervised Object Detection (CVPR2022)

Group R-CNN for Point-based Weakly Semi-supervised Object Detection (CVPR2022) By Shilong Zhang*, Zhuoran Yu*, Liyang Liu*, Xinjiang Wang, Aojun Zhou,

Shilong Zhang 129 Dec 24, 2022
LIMEcraft: Handcrafted superpixel selectionand inspection for Visual eXplanations

LIMEcraft LIMEcraft: Handcrafted superpixel selectionand inspection for Visual eXplanations The LIMEcraft algorithm is an explanatory method based on

MI^2 DataLab 4 Aug 01, 2022
An end-to-end machine learning library to directly optimize AUC loss

LibAUC An end-to-end machine learning library for AUC optimization. Why LibAUC? Deep AUC Maximization (DAM) is a paradigm for learning a deep neural n

Andrew 75 Dec 12, 2022
SigOpt wrappers for scikit-learn methods

SigOpt + scikit-learn Interfacing This package implements useful interfaces and wrappers for using SigOpt and scikit-learn together Getting Started In

SigOpt 73 Sep 30, 2022