Classifying Mechanical Vibrations using Artificial Neural Networks and Quantum Angle Encoding

Artificial Neural Networks are computing models that have been leading the progress in Machine Learning applications. In parallel, the first quantum computing devices have become available, paving the way for a new paradigm in information processing. Data representation is important for machine learning models. High-dimensional data can be converted to low dimensional codes efficiently by an artificial neural network. Due to quantum properties, a quantum algorithm can also perform this task, leaving only the neural network to perform the classification. In this paper, a quantum angle encoding algorithm is used to encode the vibration data into a binary representation, leaving the artificial neural networks for the classification. The vibration data in converted by applying a rotation on each of the Bloch sphere axes (X, Y and Z). After the rotation is performed, a measurement is made, collapsing the state into a single binary representation (0 or 1). Using the original and the converted data, multiple artificial neural networks topologies were trained to classify the data.