Variable Step Dynamic Threshold Local Binary Pattern for Classification of Atrial Fibrillation

What is it about?

In this paper, we proposed new methods for feature extraction in machine learning-based classification of atrial fibrillation from ECG signal. The proposed methods do not employ computationally expensive processes such as filtering, wavelet transform, up/downsampling, or beat detection, and can be implemented using only simple addition, division, and compare operations. Our proposed methods achieved one of the best results among published works in atrial fibrillation classification using the same dataset while using less computationally expensive calculations, without significant performance degradation when applied on signals from multiple databases with different sampling frequencies.

Featured Image

Photo by Jair Lázaro on Unsplash

Photo by Jair Lázaro on Unsplash

Why is it important?

The simplicity of methods proposed in this paper can significantly reduce computing resource requirements and improve battery life in a mobile medical devices which needs to detect patterns associated with disease from a biomedical signal. This will allow smaller, more low power and cheaper devices to be produced. The proposed methods are patent pending.