Insect-Wing Structured Microfluidic System for Reservoir Computing
This addresses the need for low-power, high-resilience computing in environments unsuitable for electronics, though it is incremental as it builds on existing reservoir computing concepts.
The study tackled the problem of efficient and adaptive computing by developing a dragonfly-wing inspired microfluidic reservoir computing system, achieving up to 91% classification accuracy with coarse resolution and limited training data.
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.