Search

Featured Application: Prediction of IAQ in the living room based on IAQ monitoring in the kitchen, as a support for IAQ control in apartments. This study explores the capability of machine learning techniques (MLTs) in predicting IAQ in apartments. Sensor data from kitchen air monitoring were used to determine the conditions in the living room. The analysis was based on several air parameters—temperature, relative humidity, CO2 concentration, and TVOC—recorded in five apartments. Multiple input–multiple output prediction models were built. Linear (multiple linear regression and multilayer perceptron (MLP)) and nonlinear (decision trees, random forest, k-nearest neighbors, and MLP) methods were investigated. Five-fold cross-validation was applied, where four apartments provided data for model training and the remaining one was the source of the test data. The models were compared using performance metrics (R2, MAPE, and RMSE). The naive approach was used as the benchmark. This study showed that linear MLTs performed best. In this case, the coefficients of determination were highest: R2 = 0.94 (T), R2 = 0.94 (RH), R2 = 0.63 (CO2), R2 = 0.84 (TVOC, based on the SGP30 sensor), and R2 = 0.92 (TVOC, based on the SGP30 sensor). The prediction of distinct indoor air parameters was not equally effective. Based on the lowest percentage error, best predictions were attained for indoor air temperature (MAPE = 1.57%), relative humidity (MAPE = 2.97%RH), and TVOC content (MAPE = 0.41%). Unfortunately, CO2 prediction was loaded with high error (MAPE = 20.83%). The approach was particularly effective in open-kitchen apartments, and they could be the target for its application. This research offers a method that could contribute to attaining effective IAQ control in apartments. [ABSTRACT FROM AUTHOR]

This work presents a multisensor device which is intended as an element of IoT for indoor environment (IE) monitoring. It is a portable, small-size, lightweight, energy-efficient direct-reading instrument. The device has an innovative design and construction. It offers real-time measurements of a wide spectrum of physical and chemical quantities (light intensity, temperature, relative humidity, pressure, CO2 concentration, content of volatile organic compounds including formaldehyde, NO2, and particulate matter), data storage (microSD; server as an option), transmission (WiFi; GSM and Ethernet as options), and visualization (smartphone application; PC as an option). Commercial low-cost sensors were utilized, which have been arranged in the individual sensing modules. In the case of gas sensors, dynamic exposure was chosen to ensure a minimum response time. The MQTT protocol was applied for data transmission and communication with other devices, as well as with the user. The multisensor device can collect huge amounts of data about the indoor environment to provide the respective information to the IoT. The device can be configured to control actuators of various auxiliary devices and equipment including external systems used for ventilation, heating, and air conditioning. The prototype is fully operational. The exemplary results of IE monitoring were shown. [ABSTRACT FROM AUTHOR]

High-quality indoor air is essential in open-kitchen restaurants for ensuring a healthy workplace and comfortable conditions for visitors. In this study, indoor air quality interdependence between the kitchen and the dining zones in open-kitchen restaurants was analyzed. The method was based on measurements of selected air parameters using a sensor technique and mutual information (MI) analysis. A long-term approach (based on a several-hour time series) and a short-term approach (based on a several-minute time series) were applied. This study involved four open-kitchen restaurants. The indoor conditions were represented by the temperature, relative humidity, CO2 concentration, and content of the total volatile organic compounds (TVOC) in the air. The MI analyses showed that the long-term co-dependence of the indoor conditions between the kitchen and the dining zones was smaller during business hours (MI = 0.12 ÷ 0.40) compared to night hours (MI = 0.24 ÷ 0.58). The ranking of the long-term MI values for the individual air parameters was MICO2 (0.34) ≅ MIT (0.34) > MIRH (0.28) > MITVOC (0.23). The short-term interdependencies were smaller during night hours (median MI = 0.01 ÷ 0.56) compared to business hours (MI = 0.23 ÷ 0.61). Additionally, the short-term MI was subject to high temporal variability. The ranking of the short-term MI values for the individual air parameters was MICO2 (0.48) > MIT (0.46) > MIRH (0.37) > MITVOC (0.26). Due to the weak and highly variable co-dependence of the air parameters between the kitchen and dining areas, multi-zone monitoring of air parameters with an emphasis on TVOC measurements is recommended to ensure proper indoor conditions in open-kitchen restaurants. The presented approach may be applied to design indoor air quality monitoring and ventilation systems not only in open-kitchen restaurants but also in other interiors with functionally different zones. [ABSTRACT FROM AUTHOR]

Indoor air quality (IAQ) in residential buildings is an issue of increasing importance. IAQ has a serious impact on human wellbeing, performance and health. In order to minimize negative consequences, considerable efforts are made to assure high quality of indoor air. Yet, attention should be payed to the fact that occupants, in particular their activities, heavily influence this component of environment. Therefore, the aim of this work was to develop a method, which allows to characterise the impact of occupant activity on indoor air. The method is based on a semi-quantitative measure called occupant activity impact (OAI) profile. It is individually created for each activity. The profile is prepared using indoor air parameters, which are significantly affected by the activity of occupants. The profile displays how these measurable parameters change due to the occurrence of the activity. The main elements of the method of occupant activity impact characterization are: 1) measurements of multiple indoor air parameters, 2) recording the occurrence of indoor activities, and 3) evaluation of the relation between indoor air parameters and occupant activities. The first task is realized using sensor technique. The second goal is attained by observation. The third aim is achieved using Fisher’s discriminant ratio. The method presented in this work allows to evaluate the character of impact, its range, direction and magnitude. Using an experimental data collected in an exemplary household, we demonstrated that OAI profile is effective in quantifying and analysing the impact of human activity on indoor microclimate. [ABSTRACT FROM AUTHOR]

Occupancy receives considerable attention from building designers and managers. In spite of great importance, its determination is still challenging. Traditional methods have various limitations. Therefore, alternative approaches are developed. The goal of this study is a method which provides information about the total number of occupants inside intermittently occupied space. It is based on the continuous measurements of selected parameters of indoor air and multiclass classification. It was shown that the number of occupants may be successfully determined using time series of CO 2 concentration (MCR = 1.6%, ME = 0.45 person), temperature (MCR = 1.6%, ME = 0.48 person) and relative humidity (MCR = 3.3%, ME = 0.79 person) individually. The data record applied for this purpose should include measurement results from 60 min long period. When using sensor array, this time may be shortened without performance loss. Particularly useful is the combination of temperature and humidity sensors. The analysis revealed that the choice of appropriate classifier is very important. Nonparametric, nonlinear, minimum distance classifier (k-NN) was very effective, while parametric classifier, utilizing linear discriminant functions (LDA) was unsuccessful. The presented method may be also used for determining the duration of occupancy periods. [ABSTRACT FROM AUTHOR]

In this work, we focus on a transient state of sensor as a source of chemical information. This problem deserves attention for many reasons. As an example, utilization of transient states may allow for faster and more accurate information acquisition. We have considered a transient state gas sensor response to test analyte applied for quantitative gas determination. We examined the inflection point which is a promising feature of a signal resulting from transient sensor responses. This particular feature was found to be linearly dependent on the target gas concentration. However, the applicability of inflection point method is dependent on the precision of its determination. It raises a number of issues related to signal regularization. The regularization problem was studied from a theoretical point of view. A number of a-priori estimates for regularization strategies were obtained yielding some practical algorithms for calculating the inflection point in a stable way. Next, they were validated using numerical simulations and real data analysis procedure. This work provides a rigorous mathematical evaluation of the inflection point method and it may contribute to the improvement of gas sensor performance. [ABSTRACT FROM AUTHOR]

The objective of this work was to propose a way of preparing information about in-cabin air quality for the car driver or passenger. It was assumed that information should be objective, relevant, current, complete and useful. The major elements of our concept were: (1) monitoring of selected air parameters inside the cabin, (2) determination of indicators that characterise indoor air, based on measurements, and (3) the method of information extraction. We proposed to realise the first task with a sensor system. The second and third goals were reached by categorisation. The basis for defining categories were ranges of values of measured parameters or their combinations. In a way, the categories were used to quantify indicators of air quality. Shannon entropy and mutual information were applied to find the best categorisation. The concept was investigated using experimental data from car cabin air monitoring in various driving conditions. We conclude that information about air quality in car cabins may be successfully conveyed using the following indicators: thermal conditions – determined based on temperature and relative humidity measurements; air exchange – determined based on CO 2 concentration; and air freshness – determined based on volatile organic compounds (VOCs) content in car cabin air. Each indicator has three categories: bad, intermediate and good. [ABSTRACT FROM AUTHOR]

This work examines the influence of gas sampling method on semiconductor gas sensor response. The problem was investigated with reference to measurements of volatile organic compounds (VOCs) in indoor air, in real conditions. We compared diffusive and dynamic sampling. Based on experimental data, diffusive sampling resulted in smaller and more variable sensor responses. The issue may raise interest among the designers of indoor air monitoring devices based on gas sensors. [ABSTRACT FROM AUTHOR]

The influence of volatile organic compound vapours of TiO2 gas-sensing layers prepared via the sol-gel technique was investigated. The sol-gel-derived layers were tested in the environment of alcohols, aliphatic and aromatic compounds. Specified organic compounds caused reversible changes of the semiconductor film resistance. The response of the titania film was registered as current intensity changes versus time at different sensor operating temperatures. The results suggested that TiO2 films prepared by the sol-gel technique can be used as chemical sensors. [ABSTRACT FROM AUTHOR]