An Explainable Tiny-Fast Kolmogorov–Arnold Network for Gesture-Based Air Handwriting Recognition of Tifinagh Letters in Resource-Constrained IoT Device

Abstract

Air handwriting recognition has emerged as a promising solution for touchless human-computer interaction, particularly in the context of Internet of Things (IoT) systems and wearable devices, where traditional input modalities are often infeasible. However, despite extensive research on Latin, Arabic, and Chinese scripts, no prior work has explored real-time air-written recognition of Tifinagh characters a historically and culturally significant script used by Amazigh communities in North Africa. To address this gap, we present the first end-to-end air handwriting recognition framework for the Tifinagh alphabet, designed specifically for constrained IoT environments. At the core of our system is XTiny-FastKAN, a novel, interpretable TinyML model based on a fast variant of the Kolmogorov–Arnold Network (KAN), optimized for ultra-low-latency inference and minimal memory consumption. The system captures inertial motion signals using a consumer-grade IMU, applies a rasterization-based preprocessing pipeline, and uses temporal saliency mapping for explainable predictions. Our quantized model achieves a recognition accuracy of 96.6%, with a memory footprint of just 35 KB and an inference time of 0.04 ms, enabling real-time execution on microcontroller-class IoT hardware. This work not only fills a critical gap in the digitization of underrepresented languages but also contributes a deployable, energy-efficient, and explainable edge AI solution aligned with the growing demands of TinyML in IoT ecosystems. Our codes and dataset are available at https://github.com/Ism-ail11/XTiny-FastKAN.