Efficient Edge Analytics: Addressing Cyber-Physical MASINT with Machine Learning on Audio at the Edge
Date of Award
Doctor of Philosophy (PhD)
Computer Engineering and Sciences
Carlos E. Otero
Munevver M. Subasi
Samuel P. Kozaitis
With the growth of the Internet of Things and the rise of Big Data, data processing and machine learning applications are being moved to cheap and low size, weight, and power (SWaP) devices at the edge, often in the form of mobile phones, embedded systems, or microcontrollers. The field of Cyber-Physical Measurements and Signature Intelligence (MASINT) makes use of these devices to analyze and exploit data in ways not otherwise possible, which results in increased data quality, increased security, and decreased bandwidth. However, methods to train and deploy models at the edge are limited, and models with sufficient accuracy are often too large for the edge device. Therefore, there is a clear need for techniques to create efficient AI/ML at the edge. This work presents training techniques for audio models in the field of environmental sound classification at the edge. Specifically, we design and train CNNs, first, to classify office sounds in audio clips. Then, we design and train Transformers to classify office sounds in audio clips. Results show that a BERT-based Transformer, trained on Mel spectrograms, can outperform a CNN using 99.85% fewer parameters. Our final model outperforms the state-of-the-art MFCC-based CNN on the office sounds dataset, using just over 6,000 parameters – small enough to run on a microcontroller.
Elliott, David, "Efficient Edge Analytics: Addressing Cyber-Physical MASINT with Machine Learning on Audio at the Edge" (2020). Theses and Dissertations. 733.