Improving Indoor Occupancy Detection Accuracy of the SLEEPIR Sensor Using LSTM Models
Improving Indoor Occupancy Detection Accuracy of the SLEEPIR Sensor Using LSTM Models
复制标题
使用 LSTM 模型提高 SLEEPIR 传感器的室内占用检测精度
DOI：
10.1109/jsen.2023.3287565
复制
发表时间：
2023
影响因子：
4.3
通讯作者：
Wang, Ya
中科院分区：
文献类型：
--
作者：
Chen, Zhangjie;Wang, Mingyi;Wang, Ya
我们最近开发了一个同步的低能量电子斩波被动红外（SLEEPIR）传感器节点来检测静止和移动的乘员。它使用液晶快门来调制传统被动红外（PIR）传感器接收的红外信号，从而使其能够检测静止的乘员。然而，SLEEPIR传感器的检测精度很容易受到红外环境干扰的影响。为了解决这个问题，在本文中，我们提出了两种长短期记忆（LSTM）模型来过滤红外环境干扰，称为基线LSTM（Base.LSTM）和统计LSTM（Stat.LSTM）。它们使用传感器节点原始输出和统计特征作为各自的输入。为了比较，我们提出了两个其他模型：占用状态开关检测（SSD）算法，直接使用一个预定的阈值电压值来分类的占用状态及其状态变化;和多层感知（MLP）分类器与统计特征输入（Stat.ML）。为了验证它们的检测性能，我们设计了不同环境设置下的两个测试场景：1）日常占用测试和2）EDGE案例测试。第一个场景旨在尽可能多地在实验室和公寓房间中恢复复杂的现实环境。第二种方案旨在验证它们在不同环境温度下的检测精度。该场景还考虑了不同的占用姿势，例如躺下。实验结果表明，在两种测试场景中，两种LSTM模型的检测准确率（95%）都优于SSD（约82%-94%）和Stat.ML（约80%-90%）。
We recently developed a synchronized low-energy electronically chopped passive infrared (SLEEPIR) sensor node to detect stationary and moving occupants. It uses a liquid crystal shutter to modulate the infrared signal received by a traditional passive infrared (PIR) sensor and thus enables its capability to detect stationary occupants. However, the detection accuracy of the SLEEPIR sensor can be easily influenced by infrared environmental disturbances. To address this problem, in this article, we propose two long short-term memory (LSTM) models to filter infrared environmental disturbance, named baseline LSTM (Base.LSTM) and statistical LSTM (Stat.LSTM). They use the sensor node raw output and statistical features as their respective input. For comparison, we propose two other models: the occupancy state switch detection (SSD) algorithm that directly uses a predetermined threshold voltage value to classify the occupancy state and its status change; and the multilayer perception (MLP) classifier with statistical feature inputs (Stat.ML). To validate their detection performance, we designed two testing scenarios in different environment settings: 1) daily occupancy tests and 2) EDGE case tests. The first scenario intends to restore complex real-life environmental situations as much as possible in the lab and apartment rooms. The second scenario aims to verify their detection accuracy under different environmental temperatures. This scenario also considers different occupancy postures, such as lying down. Experimental results show that the detection accuracy of both LSTM models (95%) in both testing scenarios outperforms that of the SSD (around 82%–94%) and the Stat.ML (around 80%–90%).
登录
查看更多内容
影响因子：
6
作者：
Christ, Maximilian;Braun, Nils;Kempa-Liehr, Andreas W.
通讯作者：
Kempa-Liehr, Andreas W.
使用 LSTM 神经网络和迁移学习进行占用率预测
DOI：
--
发表时间：
2020
期刊：
International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology
影响因子：
--
作者：
Piyapat Leeraksakiat;W. Pora
通讯作者：
W. Pora
使用粒子过滤器和 SLEEPIR 传感器系统估计室内占用情况
影响因子：
4.3
作者：
Emad-ud-Din, Muhammad;Chen, Zhangjie;Wu, Libo;Shen, Qijie;Wang, Ya
通讯作者：
Wang, Ya
影响因子：
7.4
作者：
Zhuang, Chaoqun;Choudhary, Ruchi;Mavrogianni, Anna
通讯作者：
Mavrogianni, Anna
用于住宅建筑占用检测的集成传感器数据处理
影响因子：
6.7
作者：
Chenli Wang;Jun Jiang;Thomas P. Roth;Cuong Nguyen;Yuhong Liu;Hohyun Lee
通讯作者：
Hohyun Lee