Multi-Sensor Platform for Predictive Air Quality Monitoring

Abstract

Air quality monitoring is a very important aspect of providing safe indoor conditions, and carbon dioxide (CO2) is one of the pollutants that most affects people’s health. An automatic system able to accurately forecast CO2 concentration can prevent a sudden rise in CO2 levels through appropriate control of heating, ventilation and air-conditioning (HVAC) systems, avoiding energy waste and ensuring people’s comfort. There are several works in the literature dedicated to air quality assessment and control of HVAC systems; the performance maximisation of such systems is typically achieved using a significant amount of data collected over a long period of time (even months) to train the algorithm. This can be costly and may not respond to a real scenario where the habits of the house occupants or the environment conditions may change over time. To address this problem, an adaptive hardware–software platform was developed, following the IoT paradigm, with a high level of accuracy in forecasting CO2 trends by analysing only a limited window of recent data. The system was tested considering a real case study in a residential room used for smart working and physical exercise; the parameters analysed were the occupants’ physical activity, temperature, humidity and CO2 in the room. Three deep-learning algorithms were evaluated, and the best result was obtained with the Long Short-Term Memory network, which features a Root Mean Square Error of about 10 ppm with a training period of 10 days.

Prototype of Monitoring Transportation Pollution Spikes through the Internet of Things Edge Networks

“…Furthermore, the findings of this research shed light on the considerable impact of memory consumption when utilizing this system, as demonstrated in Paper [37]. Papers [41][42][43][44][45] presented various suggestions for addressing air pollution in smart cities, and this research offers a concrete solution to these proposals, marking a significant contribution to the field.…”

“…Furthermore, the findings of this research shed light on the considerable impact of memory consumption when utilizing this system, as demonstrated in Paper [37]. Papers [41][42][43][44][45] presented various suggestions for addressing air pollution in smart In Figure 16, the data extracted from the PM2.5 sensor paint a compelling picture, revealing a substantial presence of spikes within the dataset. The dataset contains over 2000 instances of elevated values for PM2.5, surpassing the established threshold of 35 micrograms per cubic meter, as indicated in Table 2.…”

“…The authors of paper [41] introduced an adaptive hardware-software platform for predictive air quality monitoring, explicitly focusing on carbon dioxide (CO2) concentrations. The aim was to forecast CO2 trends accurately to prevent sudden increases and enable heating, ventilation, and air conditioning (HVAC) systems to control indoor conditions effectively while avoiding energy waste.…”

Study on Sensor Fault-Tolerant Control for Central Air-Conditioning Systems Using Bayesian Inference with Data Increments

“…Statistics show that building energy consumption has exceeded one-third of the total global energy consumption [ 1 , 2 , 3 ], and 60% is consumed by building energy systems (for ventilation, heating, and cooling). With the development of the economy and the improvement in living standards, people have a higher and higher demand for indoor air environments [ 4 , 5 ]. The application of HVAC systems in buildings is also becoming increasingly widespread [ 6 , 7 , 8 ].…”

A Resilient LoRa-Based Solution to Support Pervasive Sensing

“…However, as IoT evolves, network connectivity, security, and privacy challenges become prominent. Given IoT's potential to generate massive volumes of data, it is critical to develop networks that can support reliable, secure, and efficient data exchange [1][2][3].…”