vinayakumarr / kalasalingam

IEEE "Invited Talk on Deep Learning" 03/02/2018

Kalasalingam

Please cite the following papers, if you use the code as part of your research

Real-Time Detection of Atrial Fibrillation from Short Time Single Lead ECG Traces Using Recurrent Neural Networks

Instantaneous Heart Rate as a Robust Feature for Sleep Apnea Severity Detection using Deep Learning

Single Sensor Techniques for Sleep Apnea Diagnosis using Deep Learning

Anomaly detection in Phonocardiogram employing Deep learning

Deep models for Phonocardiography (PCG) classification

Atrial Fibrillation: Data set is from https://physionet.org/physiobank/database/afdb/

PCG-physionet: Data set is from https://physionet.org/challenge/2016/

Sleep Apnea: Data set is from https://www.physionet.org/physiobank/database/apnea-ecg/

heartsound - PCG: Data set is from http://www.peterjbentley.com/heartchallenge/

Other supported deep learning papers

Evaluating Shallow and Deep Networks for Secure Shell (SSH)Traffic Analysis

Evaluating Effectiveness of Shallow and Deep Networks to Intrusion Detection System

Deep Android Malware Detection and Classification

Long Short-Term Memory based Operation Log Anomaly Detection

Deep Encrypted Text Categorization

Applying Convolutional Neural Network for Network Intrusion Detection

Secure Shell (SSH) Traffic Analysis with Flow based Features Using Shallow and Deep networks

Applying Deep Learning Approaches for Network Traffic Prediction

Evaluating Shallow and Deep Networks for Ransomware Detection and Classification

Stock Price Prediction Using LSTM, RNN And CNN-Sliding Window Model

Deep Power: Deep Learning Architectures for Power Quality Disturbances Classification

DEFT 2017 - Texts Search @ TALN / RECITAL 2017: Deep Analysis of Opinion and Figurative language on Tweets in French

Deep Stance and Gender Detection in Tweets on Catalan Independence@Ibereval 2017

deepCybErNet at EmoInt-2017: Deep Emotion Intensities in Tweets

Software Installation

sudo apt-get install libatlas-base-dev gfortran python-dev

sudo apt-get install python-pip

sudo pip install --upgrade pip

sudo pip install numpy

sudo pip install scipy

sudo pip install matplotlib

Sudo pip install seaborn

sudo pip install scikit-learn

sudo pip install tensorflow

sudo pip install theano

sudo pip install keras

sudo pip install pandas

sudo pip install h5py

sudo pip install jupyter

sudo pip install ipython

kalasalingam's Issues

Response Variable Is Included in the Training Data!

I think you have included the response variable in the training data. I tried to reproduce your results.
The train accuracy of 99% matched but my test accuracy was only around 70% without including the response in the training data. Can you please comment on my observation. Thanks

Dataset

Hello,
Can you please explain how did u load the sleep apnea datasets in the codes. I mean what exactly do the 'data/train.csv' and 'data/test.csv' files contain and how to find/generate them?

Thank you.