Frances Cleary

Frances Cleary, Witawas Srisa-an, Beatriz Gil et al.

On garment intelligence influenced by artificial neural networks and neuromorphic computing is emerging as a research direction in the e-textile sector. In particular, bio inspired Spiking Neural Networks mimicking the workings of the brain show promise in recent ICT research applications. Taking such technological advancements and new research directions driving forward the next generation of e-textiles and smart materials, we present a wearable micro Brain capable of event driven artificial spiking neural network computation in a fabric based environment. We demonstrate a wearable Brain SNN prototype with multi-layer computation, enabling scalability and flexibility in terms of modifications for hidden layers to be augmented to the network. The wearable micro Brain provides a low size, weight and power artificial on-garment intelligent wearable solution with embedded functionality enabling offline adaptive learning through the provision of interchangeable resistor synaptic weightings. The prototype has been evaluated for fault tolerance, where we have determine the robustness of the circuit when certain parts are damaged. Validations were also conducted for movements to determine if the circuit can still perform accurate computation.

Frances Cleary, David Henshall, Sasitharan Balasubramaniam

E-textiles has received tremendous attention in recent years due to the capability of integrating sensors into a garment to provide high precision sensing of the human body. Besides sensing, a number of solutions for e-textile garments have also integrated wireless interfaces allowing these sensing data to be transmitted and also sensors that allow users to provide instructions through touching. While this has provided a new level of sensing that can result in unprecedented applications, there has been little attention placed on on-body computing for e-textiles. Facilitating computing on e-textiles can result in a new form of On-body Edge Computing, where sensor information are processed very close to the body before being transmitted to an external device or wireless access point. This form of computing can provide new security and data privacy capabilities and at the same time provide opportunities for new energy harvesting mechanisms to process the data through the garment. This paper proposes this concept through embroidered Programmable Logic Array (PLA) integrated into e-textiles. In the way that PLAs have programmable logic circuits by interconnecting different AND, NOT and OR gates, we propose e-textile based gates that are sewn into a garment and connected through conductive thread stitching. Two designs are proposed and this includes Single and Multi-Layered PLA. Experimental validations have been conducted at the individual gates as well as the entire PLA circuits to determine the voltage utilization as well as logic computing reliability. Our proposed approach can usher in a new form of On-Body Edge Computing for e-textile garments for future wearable technologies