PulseAugur
EN
LIVE 10:24:37

MAUPITI enables on-device learning for low-power infrared sensors

Researchers have developed MAUPITI, a novel on-device learning system for low-resolution infrared sensors. This system utilizes a smart multi-pixel IR sensor with a RISC-V microcontroller, enabling pose and gesture recognition under strict memory and power constraints. By employing a prototype-based Nearest Class Mean classifier, MAUPITI achieves accuracy comparable to conventional methods while allowing for continuous adaptation on the device. AI

IMPACT Enables privacy-preserving, adaptive AI capabilities in resource-constrained embedded systems.

RANK_REASON Academic paper detailing a new on-device learning system for infrared sensors.

Read on Hugging Face Daily Papers →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

MAUPITI enables on-device learning for low-power infrared sensors

COVERAGE [2]

  1. arXiv cs.LG TIER_1 English(EN) · Beatrice Alessandra Motetti, Tanguy Dugas du Villard, Matteo Risso, Alessio Burrello, Francesco Daghero, Enrico Macii, Massimo Poncino, Marco Castellano, Alfio Basile, Daniele Jahier Pagliari ·

    MAUPITI: On-Device Prototype-Based Learning on a Smart Infrared Sensor

    arXiv:2608.07192v1 Announce Type: new Abstract: Low-resolution infrared (IR) array sensors represent an interesting solution for privacy-preserving human sensing in embedded systems. In this letter, we describe a smart multi-pixel IR sensor integrating a 16$\times$16 thermal MOSF…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    MAUPITI: On-Device Prototype-Based Learning on a Smart Infrared Sensor

    Low-resolution infrared (IR) array sensors represent an interesting solution for privacy-preserving human sensing in embedded systems. In this letter, we describe a smart multi-pixel IR sensor integrating a 16$\times$16 thermal MOSFET (TMOS) array and a RISC-V microcontroller ext…