Issue No. 05 - May (2018 vol. 51)
Jagmohan Chauhan , Aalto University
Suranga Seneviratne , University of Sydney
Yining Hu , Data61 and University of New South Wales
Archan Misra , Singapore Management University
Aruna Seneviratne , University of New South Wales
Youngki Lee , Singapore Management University
Recurrent neural networks (RNNs) have shown promising results in audio and speech-processing applications. The increasing popularity of Internet of Things (IoT) devices makes a strong case for implementing RNN-based inferences for applications such as acoustics-based authentication and voice commands for smart homes. However, the feasibility and performance of these inferences on resource-constrained devices remain largely unexplored. The authors compare traditional machine-learning models with deep-learning RNN models for an end-to-end authentication system based on breathing acoustics.
audio acoustics, home automation, Internet of Things, learning (artificial intelligence), recurrent neural nets
J. Chauhan, S. Seneviratne, Y. Hu, A. Misra, A. Seneviratne and Y. Lee, "Breathing-Based Authentication on Resource-Constrained IoT Devices using Recurrent Neural Networks," in Computer, vol. 51, no. 5, pp. 60-67, 2018.