This dataset has been collected by Edge Impulse team to demonstrate how to perform Sensor Fusion Classification leveraging Neural Networks Embeddings.

Sensor fusion refers to the process of combining data from different types of sensors to give more information to the neural network. To extract meaningful information from this data, you can use the same DSP block, multiples DSP blocks, or use neural networks embeddings.

You can have a look at this tutorial for more information to see how to use this dataset.

This dataset combines audio data and accelerometer data.

Recommended Impulse

• Feature extraction: Audio Embeddings ( Spectrogram + Convolution Neural Network Embeddings) + Spectral Analysis (accelerometer)
• Learning block: Classification using a fully-connected network