Replication Data for: Low Cost Gunshot Detection using Deep Learning on the Raspberry Pi

This dataset contains replication data for the paper titled \"Low Cost Gunshot Detection using Deep Learning on the Raspberry Pi\" published at the 2019 IEEE International Conference on Big Data (Big Data) in Los Angeles, California. The dataset consists of the WAV files used to train, validate, and test our models, the models themselves, and the cached NumPy features and labels arrays we ultimately used to train our models. Our GitHub repository linked in the \"Related Material\" metadata section below provides more details on how we parsed through these files to create our training, validation, and testing datasets and how we used them to construct our models. Our cached NumPy feature array (originally 32GB in size) was split into 15 subarrays of roughly 2.1GB each. These subarrays can, in alphanumeric order by filename, be concatenated together to reproduce our original feature array which directly corresponds to the provided NumPy labels array (index by index).