Insect-Wing Structured Microfluidic System for Reservoir Computing

TL;DR

This paper presents a bio-inspired microfluidic reservoir computing system using a dragonfly-wing design, capable of high-accuracy pattern classification with low power and resilience, suitable for environments where traditional electronics fail.

Contribution

It introduces a novel microfluidic reservoir computing architecture inspired by insect wings, demonstrating effective pattern classification with minimal training data.

Findings

Achieved up to 91% classification accuracy.

Operates effectively with coarse resolution and limited training data.

Demonstrates viability of fluid-based reservoir computing systems.

Abstract

As the demand for more efficient and adaptive computing grows, nature-inspired architectures offer promising alternatives to conventional electronic designs. Microfluidic platforms, drawing on biological forms and fluid dynamics, present a compelling foundation for low-power, high-resilience computing in environments where electronics are unsuitable. This study explores a hybrid reservoir computing system based on a dragonfly-wing inspired microfluidic chip, which encodes temporal input patterns as fluid interactions within the micro channel network. The system operates with three dye-based inlet channels and three camera-monitored detection areas, transforming discrete spatial patterns into dynamic color output signals. These reservoir output signals are then modified and passed to a simple and trainable readout layer for pattern classification. Using a combination of raw reservoir outputs and synthetically generated outputs, we evaluated system performance, system clarity, and data efficiency. The results demonstrate consistent classification accuracies up to $91\%$, even with coarse resolution and limited training data, highlighting the viability of the microfluidic reservoir computing.