中文

基于弹性节点硬件的事件检测时间序列数据自动收集与标注方法

机器学习 2024-07-17 v1 人工智能

摘要

近期物联网技术的发展凸显了利用传感器数据有效理解环境背景的重要性。本文引入一种新型嵌入式系统,旨在在物联网设备上自动对传感器数据进行标注,从而提升数据收集方法的效率。我们 presented an integrated hardware and software solution equipped with specialized labeling sensors that streamline the capture and labeling of diverse types of sensor data. 通过在本地实现轻量级标注方法的处理,本系统最小化了数据传输需求,减少了对外部资源的依赖。实验验证采用收集的数据及卷积神经网络模型,通过4折交叉验证实现了最高达91.67%的高分类准确率。这些结果表明,该系统具备收集带有正确标签的音频和振动数据的稳健能力。

关键词

引用

@article{arxiv.2407.11042,
  title  = {An Automated Approach to Collecting and Labeling Time Series Data for Event Detection Using Elastic Node Hardware},
  author = {Tianheng Ling and Islam Mansour and Chao Qian and Gregor Schiele},
  journal= {arXiv preprint arXiv:2407.11042},
  year   = {2024}
}

备注

This paper is accepted by the 4th Workshop on Collaborative Technologies and Data Science in Smart City Applications (CODASSCA 2024)