A Rapid Pipeline for Training and Deploying ML Models on WeBe Band

2026-09-24

AI Summary

This study addresses the prolonged machine learning development cycles and tight hardware coupling caused by resource constraints on edge devices by proposing WeBe Band, an automated workflow. By integrating Piccolo AI, this method combines AutoML, hardware-aware quantization, automatic firmware generation, and over-the-air (OTA) deployment to establish a system-level closed loop spanning model generation, compilation, and on-device deployment. Rather than pursuing novel architectural innovations, this work validates performance trade-offs between classical models and lightweight neural networks on microcontrollers through real-time profiling. The proposed approach effectively decouples software and hardware dependencies, significantly enhancing iteration efficiency for edge AI development.

Abstract

Developing optimized machine-learning algorithms for edge devices with limited computational and memory resources is challenging, time-consuming, and highly dependent on device-specific constraints. In this work, we streamline an edge ML workflow to enable rapid development, optimization, and deployment of machine-learning (ML) models directly on the WeBe Band, a wrist-worn wearable device designed for multimodal physiological data monitoring. The proposed system automatically generates hardware-efficient ML models that can be easily integrated into the WeBe core firmware, supporting AutoML, hardware-aware quantization, and performance profiling to build models that meet desired latency targets while remaining compatible with device memory and power limitations. The proposed framework tightly integrates the open-source Piccolo AI ecosystem with an automated pipeline that generates deployable firmware artifacts, performs hardware-aware model compilation, and supports over-the-air (OTA) deployment. The system supports multiple lightweight model classes, including classical machine-learning algorithms and neural networks, and provides built-in on-device profiling tools to evaluate inference latency and memory footprint under realistic execution conditions. Experimental results demonstrate clear trade-offs between model complexity and deployability on a microcontroller, showing that classical models offer strong real-time performance while lightweight neural networks require careful resource management. Rather than proposing new learning architectures, the current work mainly focuses on system-level automation, deployability, and enabling researchers and developers to rapidly iterate on models and evaluate them directly on target hardware. Although demonstrated on the WeBe Band platform, the workflow is designed to be extensible to other ML-powered edge devices.

Problem

• Edge ML
• Resource-constrained devices
• Model deployment
• Wearable devices
• Hardware-aware optimization

Innovation

• Edge ML
• AutoML
• Hardware-aware quantization
• OTA deployment
• System-level automation