# Combining Neural Architecture Search and Weight Reshaping for Optimized Embedded Classifiers in Multisensory Glove

## TL;DR

This paper combines neural architecture search and optimization techniques to create efficient classifiers for a multisensory glove, improving accuracy and reducing energy use.

## Contribution

The novel integration of HW-NAS with weight reshaping and quantization techniques for embedded classifiers.

## Key findings

- Optimized models show 75% average reduction in inference time compared to NAS-only baselines.
- Memory usage is reduced by 69% in flash and over 45% in RAM.
- Classification accuracy is improved while maintaining energy efficiency.

## Abstract

Intelligent sensing systems are increasingly used in wearable devices, enabling advanced tasks across various application domains including robotics and human–machine interaction. Ensuring these systems are energy autonomous is highly demanded, despite strict constraints on power, memory and processing resources. To meet these requirements, embedded neural networks must be optimized to achieve a balance between accuracy and efficiency. This paper presents an integrated approach that combines Hardware-Aware Neural Architecture Search (HW-NAS) with optimization techniques—weight reshaping, quantization, and their combination—to develop efficient classifiers for a multisensory glove. HW-NAS automatically derives 1D-CNN models tailored to the NUCLEO-F401RE board, while the additional optimization further reduces model size, memory usage, and latency. Across three datasets, the optimized models not only improve classification accuracy but also deliver an average reduction of 75% in inference time, 69% in flash memory, and more than 45% in RAM compared to NAS-only baselines. These results highlight the effectiveness of integrating NAS with optimization techniques, paving the way towards energy-autonomous wearable systems.