BioNetExplorer: Architecture-Space Exploration of Bio-Signal Processing Deep Neural Networks for Wearables

Bharath Srinivas Prabakaran, Asima Akhtar, Semeen Rehman, Osman Hasan, Muhammad Shafique

Research output: Contribution to journalArticlepeer-review


Deep Learning (DL) has been shown to be highly effective in solving various problems across numerous applications and domains, such as autonomous driving and image recognition. Due to the advent of DL, plenty of research works have explored the applicability of DL, more specifically Deep Neural Networks (DNNs), to solve pattern recognition and computer vision challenges. More recently, researchers have focused on the topic of automated generation and exploration of DNN architectures, which tend to mostly focus on image recognition or visual datasets, primarily, due to the computer vision-related DL advancements. In this work, we propose the BioNetExplorer framework to systematically generate and explore multiple DNN architectures for bio-signal processing in wearable devices. Our framework varies key neural architecture parameters to search for an embedded DNN architecture with a low hardware overhead, which can be deployed in wearable edge devices to analyze the bio-signal data and to extract the relevant information, such as arrhythmia and seizure. Furthermore, BioNetExplorer reduces the exploration time by deploying genetic algorithms, such as NSGA-II, SPEA-2, etc. Our framework also enables hardware-aware DNN architecture search 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, attributed towards ventricular fibrillation, due to genetic predisposition or a pre-existing heart condition. The use of genetic algorithms reduces the exploration time, on average, by 9×, 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 53× for a quality loss of < 0.2%.

Original languageEnglish (US)
JournalIEEE Internet of Things Journal
StateAccepted/In press - 2021


  • Bio-signals
  • Biological system modeling
  • Computer architecture
  • Convolution
  • Deep Neural Networks
  • DNN
  • Efficiency.
  • Electrocardiography
  • Embedded Systems
  • Exploration
  • Hardware
  • Healthcare
  • Long Short Term Memory
  • LSTM
  • Monitoring
  • Performance
  • Quantization (signal)
  • Wearable computers
  • Wearables

ASJC Scopus subject areas

  • Signal Processing
  • Information Systems
  • Hardware and Architecture
  • Computer Science Applications
  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'BioNetExplorer: Architecture-Space Exploration of Bio-Signal Processing Deep Neural Networks for Wearables'. Together they form a unique fingerprint.

Cite this