With the accelerometer dataset, Human activities are analyzed and predicted using the CNN model.
Using the 2D Convolutional Neural Networks, the accelerometer dataset is trained in order to predict the human activities
The dataset in .txt format is loaded into the program and processed to convert into a processable form. Further, it is converted into a DataFrame that can be easily analyzed.
The data is an unbalanced one. It should be balanced in order to avoid bias. Then, the data is encoded using Label Encoder.
The data is standardized using Standard Scaler.
With the function get_frames, frames are created from the dataset.
2D Convolutional Neural Networks are used to train the model and the accuracy of the results is analyzed with confusion matrix and plots.
Submitted by Rajasree Unnithan R (akshaiauh)
Download packets of source code on Coders Packet