An energy efficient IoT data compression approach for edge machine learning

Joseph Azar, Abdallah Makhoul, Mahmoud Barhamgi, Raphaël Couturier

Abstract: Highlights•An energy efficient data reduction approach based on a fast error-bounded lossy compressor is proposed.•An edge machine learning model for drivers’ stress detection has been proposed.•The performance of the proposed approach has been tested on a real wearable device.