- š Hi, Iām @Shadhil24
Human Activity Recognition (HAR) is considered a valuable research topic in the last few decades. Different types of machine learning models are used for this purpose, What I have done here is that I have created a model using Convolutional Neural Networks in Tensorlfow. Data i've used for training is from my phone itself, taking the x,y,z cordinates of my movements using some application downloaded from playstore. I splitted this data into train,test and validation datasets and trained a model with this. Used sequential model and added layers of CNN which are Conv2D, Flatten,Maxpool2D and DropOuts Trained it in 100 epochs and batch_size is 32.