Power-efficient gesture sensing for edge devices: mimicking fourier transforms with spiking neural networks

• Published in: Applied intelligence (Dordrecht, Netherlands) Vol. 53; no. 12; pp. 15147 - 15162
• Main Authors: Arsalan, Muhammad, Santra, Avik, Issakov, Vadim
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.06.2023; Springer Nature B.V
• Subjects: Artificial Intelligence; Computer Science; Continuous wave radar; Fast Fourier transformations; Fourier transforms; Machines; Manufacturing; Mechanical Engineering; Neural networks; Portable equipment; Power consumption; Power management; Processes; Spiking; NengoDL; Neuromorphic hardware; Gesture sensing; Nengo; Human computer interface; Spiking neural networks
• ISSN: 0924-669X; 1573-7497
• DOI: 10.1007/s10489-022-04258-w

One of the key design requirements for any portable/mobile device is low power. To enable such a low powered device, we propose an embedded gesture detection system that uses spiking neural networks (SNNs) applied directly to raw ADC data of a 6 0 G H z frequency modulated continuous wave radar. SNNs can facilitate low power systems because they are sparse in time and space and are event-driven. The proposed system, as opposed to earlier state-of-the-art methods, relies solely on the target’s raw ADC data, thus avoiding the overhead of performing slow-time and fast-time Fourier transforms (FFTs) processing. The proposed architecture mimics the discrete Fourier transformation within the SNN itself avoiding the need for FFT accelerators and makes the FFT processing tailored to the specific application, in this case gesture sensing. The experimental results demonstrate that the proposed system is capable of classifying 8 different gestures with an accuracy of 9 8 . 7 % . This result is comparable to the conventional approaches, yet it offers lower complexity, lower power consumption and faster computations comparable to the conventional approaches.