Low-Power Gesture Recognition Using Convolutional Neural Networks and Ambient Lighting

This paper presents a study focused on developing an efficient signal processing pipeline and identifying suitable machine learning models for real-time gesture recognition using a testbed consisting of an Arduino Nano 33 BLE and three OPT101 photodiodes. Our research aims to address the challenges of limited computational power whilst...

A Low Power System-on-Chip with Memory Stacked on Top of Logic

This work introduces a low-power Cortex-M0+ based computing platform for battery-powered, embedded applications. Voltage stacking is used to save power by recycling charge through a power domain between 0V and Vdd, and a power domain stacked on top of it between Vdd and 2Vdd. The technique enables connecting chips of the future directly to the...

Wireless Indoor Climate Sensor: Implementing the Control Unit at Ultra Low Power

With the completion of the MIST1431 multi sensor IC a demonstrator developed by the Electronic Instrumentation Laboratory of Delft University of Technology and NXP, a demonstrator that shows the capabilities of the MIST chip was needed. This thesis describes the implementation of the control unit, which has to control the MIST chip and wireless...