CovidNet: MEl Spectrograms and Machine LEarning

Using deep-learning to diagnose Covid-19 cases from patient audio

Paper and Repository:

Please refer to the paper for in depth information about this project

Description

At the start of 2021, the covid-19 pandemic was in full swing. In response, our junior data science team endeavored to diagnose covid-19 from patient cough audio using deep learning. We used a labeled set of 10,000+ recordings of patients coughing and breathing. Our fundamental approach was to transform the audio recordings in Mel-Spectrograms: 2-dimensional frequency graphs in the Mel scale as shown above. We then used those as inputs to train a convolutional neural network to run in parallel with a Single-Layer Perceptron that used handcrafted features as inputs.

Figure 1: CNN Structure Used

Figure 2: Aggregate Model

Our project went through the full data science pipeline. By wrangling the data, we converted the data into usable training, testing, and validation sets.

Figure 3: Reorganization of Data

Through data exploration, we carefully analyzed the demographic and symptom association of the patients to better understand patterns and better understand feature importance. By looking at previous work, we found promise in using ImageNet for transfer learning to accommodate for our dataset's relatively small size. We documented our work using Github and wrote a final research paper on our project. This project proved to be a valuable experience personally as we had guidance from Dr. Arko Barman to ensure proper procedure and direction.

COVIDNet was my first start-to-finish data science project.