Step-by-Step Signal Processing with Machine Learning: PCA, ICA, NMF

Signal processing is crucial in many data science tasks. As soon as we start handling audio files, images or even biological measurements, it is useful to know techniques to process such data. In this article, I will introduce three algorithms you can use for two use cases: Principal Components Analysis (PCA) for dimensionality reduction and feature extraction, Independent Components Analysis (ICA) and Nonnegative Matrix Factorization (NMF) for source separation. All three methods have ready-to-use implementations on scikit-learn which are useful for your projects, but for the purpose of this article I will show how you can implement these methods from scratch, using only OpenCV to open and save images, and NumPy to handle matrices. I will provide code snippets throughout the article, and you can find the full code as well as the example datasets on Github.