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...

Towards a low-cost air-written character recognition system: Designing an embedded machine learning system to recognise the first 10 letters of the Latin alphabet

This study introduces a novel system that leverages three photodiodes and ambient light to identify air-written characters on a resource-constrained device. Through experimentation, suitable methods of data preprocessing, machine learning and model compression were selected to recognize the first 10 characters of the Latin alphabet. The final...

AI on Low-Cost Hardware: Software Subgroup

Artificial Intelligence has become a dominant part of our lives, however, complex artificial intelligence models tend to use a lot of energy, computationally complex operations, and a lot of memory resources. Therefore, it excluded a whole class of hardware in its applicability. Namely, relatively resource-constrained low-cost hardware. This...

µLightDigit: A TinyML System for Contactless Digit Recognition using Ambient Light

This thesis describes the design and implementation of µLightDigit, which is the second iteration of the LightDigit project: a contactless air-writing system based on ambient light detection with embedded deep learning using only simple photodiodes. The system is able to classify digits 0–9 written in the air by detecting the dynamic hand shadow...

Recognising Gestures Using Ambient Light and Convolutional Neural Networks: Adapting Convolutional Neural Networks for Gesture Recognition on Resource-constrained Microcontrollers

This paper presents how a convolutional neural network can be constructed in order to recognise gestures using photodiodes and ambient light. A number of candidates are presented and evaluated, with the most performant being adopted for in-depth analysis. This network is then compressed in order to be ran on an Arduino Nano 33 BLE...

The application of differentiable programming frameworks to computational fluid dynamics

In recent years many automatic differentiable programming frameworks have been developed in which numerical programs can be differentiated through automatic differentiation (AD). Examples of these frameworks are Theano, TensorFlow and Pytorch. These frameworks are widely used in Machine Learning. AD also finds applications in the field of...

Evaluating and Improving Large-Scale Machine Learning Frameworks

Given the increasing popularity of Machine Learning, and the ever increasing need to solve larger and more complex learning challenges, it is unsurprising that numerous distributed learning strategies have been brought forward in recent years, along with many large scale Machine Learning frameworks. It is however unclear how well these...

Thermosphere Modelling using Machine Learning: Artificial Neural Networks to forecast thermospheric densities and generalise beyond the properties of an acceleration data set using the Swarm satellites as study case

The Low Earth Orbit (LEO) region has been attractive to many space agencies and organisations because of its ease of access and the ideal opportunity for remote sensing. Due to the low altitudes, a satellite's orbital state is highly affected by the atmospheric drag force acting on the satellite's body. The largest variation in this drag force...