A 12nW Always-On Acoustic Sensing and Object Recognition Microsystem Using Frequency-Domain Feature Extraction and SVM Classification

📋 论文概要

该论文提出了一种仅消耗12nW功率的始终开启声学感知与物体识别微系统，通过频域特征提取和支持向量机（SVM）分类器实现低功耗智能声学检测，解决了超小型IoT设备在持续感知中的功耗瓶颈。

💡 主要创新点

• 实现12nW超低功耗的始终开启声学感知，适用于电池供电的微型IoT设备。
• 采用频域特征提取方法，降低计算复杂度并提升识别效率。
• 集成SVM分类器于微系统中，实现片上物体识别，无需外部处理器。

🏷 关键词

📄 原文摘要

increasingly intelligent and context-aware. Sound is an attractive sensory modality because it is information-rich but not as computationally demanding as alternatives such as vision. New applications of ultra-low power (ULP), ‘always-on’ intelligent acoustic sensing includes agricultural monitoring to detect pests or precipitation, infrastructure health tracking to recognize acoustic symptoms, and security/safety monitoring to identify dangerous conditions. A major impediment for the adoption of always-on, context-aware sensing is power consumption, particularly for ultra-small IoT devices requiring long-term operation without battery replacement. To sustain operation with a 1mm2 solar cell in ambient light (100lux) or achieve a lifetime of 10 years using a button

👥 作者与机构

Seokhyeon Jeong1, Yu Chen1,2, Taekwang Jang1, Julius Tsai3,

David Blaauw1, Hun-Seok Kim1, Dennis Sylvester1 University of Michigan, Ann Arbor, MI Texas A&M University, College Station, TX 3 Invensense, San Jose, CA 1 2 IoT devices are becoming