Computer-aided placement of air quality sensors using adjoint framework and sensor features to localize indoor source emission

Waeytens, Julien; Sadr, Sara

doi:10.1016/j.buildenv.2018.08.012

Cited by 23 publications

(10 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…37 Air quality sensors should be positioned at the breathing zone height or on the ceiling in the middle of the room, and the optimal position needs to take into account the room layout. 70 Thus, finding an appropriate position for a multi-functional sensor is difficult. Existing knowledge of sensor placement focuses on standing or seated participants.…”

Section: Discussionmentioning

confidence: 99%

Supporting dementia care by monitoring indoor environmental quality in a nursing home

Guerra-Santin

Grave

et al. 2023

Indoor and Built Environment

View full text Add to dashboard Cite

The indoor environment quality in care facilities impacts residents’ daily lives. Sensor technology has been proven useful in evaluating the indoor environment of buildings, but the process of using this information to improve residents’ comfort, specifically in the context of nursing homes, is still underdeveloped. Thus, this study focuses on monitoring indoor environmental quality in a nursing home in the Netherlands, supported by professional caregivers’ insights. A campaign was conducted for one year to monitor eight rooms, and a mixed-method approach was used to collect and analyse the data on local weather, building facility operation and proxies’ responses to residents’ comfort. Seventeen care professionals and twenty-two guardians (visitors) answered questions based on their opinions and observation. The results show that the low indoor humidity during heating seasons and high CO2 concentration at night were the main factors leading to environment-related symptoms of residents and care professionals, such as dry eyes. Furthermore, we found that data outliers can help to reveal residents’ occupancy, ventilation habits and activity time, thus showing the application value of environmental sensors in dementia care. We also recommend using non-intrusive sensors for nursing home residents and taking into account room layouts and occupants’ conditions before installing sensors.

show abstract

Section: Discussionmentioning

confidence: 99%

Supporting dementia care by monitoring indoor environmental quality in a nursing home

Guerra-Santin

Grave

et al. 2023

Indoor and Built Environment

View full text Add to dashboard Cite

show abstract

“…The optimal placement of the sensors in enclosed environments was studied utilizing the finite-dimensional Perron–Frobenius concept, 34 in which an adjoint framework and sensor features were used to place the air quality sensors. 35 Ren and Cao 36 provided sensor deployment strategies, such that the placement of sensors along the same main stream plane or parallel to such should be avoided; a better placement would be in or near the ‘well-mix zone (close to outlet region)’ but avoiding the area close to the inlet. In the follow-up study, we will further consider the location of sensors in a single room to improve the reliability of the study.…”

Section: Discussionmentioning

confidence: 99%

Comparison of common machine learning algorithms trained with multi-zone models for identifying the location and strength of indoor pollutant sources

Huang

Gao

Zhang

2020

Indoor and Built Environment

View full text Add to dashboard Cite

The accurate identification of the characteristics of pollutant sources can effectively prevent the loss of human life and property damage caused by the sudden release of harmful chemicals in emergency situations. Machine learning algorithms, artificial neural network (ANN), support vector machine (SVM), k-nearest neighbour (KNN) and naive Bayesian (NB) classification can be used to identify the location of pollutant sources with limited sensor data inputs. In this study, the identification accuracy of the four above-mentioned machine learning algorithms was investigated and compared, considering the different sensor layouts, eigenvector inputs, meteorological parameters and number of samples. The results show that the collection of pollutant concentrations over an extended period of time could improve identification accuracy. Additional sensors were required to reach the same identification accuracy after the introduction of distributed meteorological parameters. Increasing the number of trained samples by a factor of five improved the identification accuracy of KNN by 22% and that of SVM by 1.7%; however, ANN and NB classification remained basically unchanged. When identifying the release mass of the pollutant source, multiple linear, ANN and SVM regression models were adopted. Results show that ANN performs best, whereas SVM provides the least optimal performance.

show abstract

“…The placement of the measuring point is in the center of each floor in the measurement area, it is expected to be able to take the average value of air quality over the entire floor area, by determining the measuring point in the Split Floor Upper-Level area. The minimum height of the measuring instrument is at a height of 0.5 meters from the floor surface [15], and the measuring instrument is placed at that height. Changes in air pollution levels at each different surface height of the parking area (Altitude ±0.00, +5.00, +10.00, +15.00, +20.00, +25.00 Meters)…”

Section: Methodsmentioning

confidence: 99%

Air Quality of a Parking Building in Makassar (A Case Study of Bosowa Tower Parking Building)

Kulle

Hamzah

Mulyadi

2021

EPI-IJE

View full text Add to dashboard Cite

This study aims to determine the level of air quality in the parking building based on the pollution content in it (CO, CO2, HCHO and, VOC), to analyze the effect of the weather, intensity of motorized vehicle traffic, and surface elevation to the air quality. The dependent variable is the level of air pollution. The research sample is the Makassar Bosowa Tower Parking Building, data collection was carried out by direct measurement and observation in 12 days from November 24th till December 17th. The research was done using the comparative method, The data processed using the Mann-Whitney difference test, and the Spearman correlation test using SPSS application. The results showed that the average CO levels had exceeded the limit of good air quality, the average of CO2 levels was still within the limits for good air quality, and the average of HCHO and VOC levels were mostly within the limits for good indoor air quality, according to The Indonesia Minister of Health Regulation Number 1077 in 2011. The result of measurements and tests shows that the changes in the weather do not have a significant effect on the air quality. The amount and the intensity of motorized vehicle traffic affect the air quality, especially during rainy weather.

show abstract

Computer-aided placement of air quality sensors using adjoint framework and sensor features to localize indoor source emission

Cited by 23 publications

References 35 publications

Supporting dementia care by monitoring indoor environmental quality in a nursing home

Supporting dementia care by monitoring indoor environmental quality in a nursing home

Comparison of common machine learning algorithms trained with multi-zone models for identifying the location and strength of indoor pollutant sources

Air Quality of a Parking Building in Makassar (A Case Study of Bosowa Tower Parking Building)

Contact Info

Product

Resources

About