Dynamic Time Warping explained using Python and HAR dataset

The Time series classification is a very common task where you will have data from various domains like Signal processing, IoT, human activity, and more and the ultimate aim is to train a specific model so that it can predict the class of any time series with almost perfect accuracy. The given dataset should have labeled time sequences so that our model can predict the class of the time series accurately. One Classic solution to this problem is by using the method of the K Nearest neighbor algorithm. Here in this article, we are going to skip over the usual approach of Euclidean distance and we will use the Dynamic Time Warping or DTW metric. This method does take into consideration that when we are comparing two different time series, they might vary in length and speed.