Dataset for IoT-based Indoor Air Quality Management System for Intelligent Education Environments

One of the leading causes of early health detriment is the increasing levels of air pollution in major cities and eventually in indoor spaces. Monitoring the air quality effectively in closed spaces like educational institutes and hospitals can improve both the health and the life quality of the occupants. In this paper, we propose an efficient Indoor Air Quality (IAQ) monitoring and management system, which uses a combination of cutting-edge technologies to monitor and predict major air pollutants like CO2, PM2.5, TVOCs, and other factors like temperature and humidity. The aim is to create an intelligent environment for IAQ. The data is captured and monitored using an Internet of Things network of sensors, manufactured by ourselves, in different lecture rooms at the university. The obtained data is then processed and correlated in real time using a complex event processing engine and analyzed by machine/deep learning algorithms. A long short-term memory neural network is proposed to forecast IAQ. Then a decision tree regressor is used to identify the relationships between temperature, humidity and different pollutants like CO2 and PM2.5.

城市乃至室内空间的空气污染水平持续攀升，是早期健康损害的主要诱因之一。对学校、医院等封闭空间的空气质量开展有效监测，可提升场所内人员的健康水平与生活质量。本文提出一种高效的室内空气质量（Indoor Air Quality, IAQ）监测与管理系统，该系统结合前沿技术，可对二氧化碳（CO₂）、PM2.5、总挥发性有机化合物（TVOCs）等主要空气污染物，以及温度、湿度等环境参数进行监测与预测，旨在构建智能化室内空气质量管控环境。本研究在大学的多间教室内部署自研传感器组成的物联网（Internet of Things, IoT）网络，采集并监测相关数据。所获取的数据随后将通过复杂事件处理引擎进行实时处理与关联分析，并借助机器学习/深度学习算法开展分析。研究提出采用长短期记忆神经网络（Long Short-Term Memory, LSTM）实现室内空气质量预测，随后采用决策树回归器分析温度、湿度与二氧化碳、PM2.5等污染物之间的关联关系。

搜集汇总

背景与挑战

背景概述

该数据集专注于物联网（IoT）在智能教育环境中的室内空气质量（IAQ）管理，通过传感器网络监测CO2、PM2.5、TVOCs等污染物以及温湿度数据，并利用复杂事件处理（CEP）和机器学习算法（如LSTM和决策树回归）进行实时分析和预测。数据集包含IoT流定义、CEP事件模式、智能合约、LSTM分析代码和复杂事件数据，支持相关论文的研究，旨在改善教育机构的室内环境质量，适用于人工智能、物联网和机器学习领域的应用。