EcholocationDNN | repository provides the data and codes for the work

EcholocationDNN is a Jupyter Notebook library. EcholocationDNN has no bugs, it has no vulnerabilities, it has a Permissive License and it has low support. You can download it from GitHub.

This repository provides the data and codes for the work done in this link: Insert Link here. The project deals with echolocation using a convolution neural netwrok (CNN) based model. The goal is locate an object in a grid soley using the echo reflections captured from the object by the microphone. The details on the experimental design, data pre-processing, and results are discussed in the document linked above. The idea is to train a supervised DNN model on sample set (x,y) where x is the spectrogram of the echo reflected signal and y is the ground truth location (i.e. (x_gt, y_gt)) of the object. The model is proposed for both single object detection and multi object (i.e 2 objects) detection problem. The ground truth location for two object case would be { (x_1_gt, y_1_gt), (x_2_gt, y_2_gt) }.