BioNetExplorer: Architecture-Space Exploration of Bio-Signal Processing Deep Neural Networks for Wearables
This work addresses the need for low-overhead, hardware-aware DNNs in wearable edge devices for applications like arrhythmia and seizure detection, offering incremental improvements in efficiency and customization.
The authors tackled the problem of designing efficient deep neural networks for bio-signal processing in wearable devices by proposing BioNetExplorer, a framework that uses genetic algorithms to explore architectures under hardware constraints, resulting in a 9x reduction in exploration time, up to 30MB storage savings with minimal quality loss, and up to 53x compression with less than 0.2% quality loss.
In this work, we propose the BioNetExplorer framework to systematically generate and explore multiple DNN architectures for bio-signal processing in wearables. Our framework adapts key neural architecture parameters to search for an embedded DNN with a low hardware overhead, which can be deployed in wearable edge devices to analyse the bio-signal data and to extract the relevant information, such as arrhythmia and seizure. Our framework also enables hardware-aware DNN architecture search using genetic algorithms by imposing user requirements and hardware constraints (storage, FLOPs, etc.) during the exploration stage, thereby limiting the number of networks explored. Moreover, BioNetExplorer can also be used to search for DNNs based on the user-required output classes; for instance, a user might require a specific output class due to genetic predisposition or a pre-existing heart condition. The use of genetic algorithms reduces the exploration time, on average, by 9x, compared to exhaustive exploration. We are successful in identifying Pareto-optimal designs, which can reduce the storage overhead of the DNN by ~30MB for a quality loss of less than 0.5%. To enable low-cost embedded DNNs, BioNetExplorer also employs different model compression techniques to further reduce the storage overhead of the network by up to 53x for a quality loss of <0.2%.