Indoor Home Research Articles

A Deep Reinforcement Learning Approach with Visual Semantic Navigation with Memory for Mobile Robots in Indoor Home Context

A Deep Reinforcement Learning Approach with Visual Semantic Navigation with Memory for Mobile Robots in Indoor Home Context

Indoor home environments of Danish children and the socioeconomic position and health of their parents: A descriptive study.

Housing and indoor home environments are associated with the risk of infections and asthma in children. To better understand the determinants and characteristics of these environments, we aimed to describe the associations between parental health and socioeconomic position and housing and indoor home environments of children in Denmark, and the clustering of the factors within these environments. Offspring in the Danish National Birth Cohort (DNBC) whose parents responded to the 11-year follow-up were eligible for inclusion. We included complete cases only. Data on the indoor and housing environments (i.e. variables on housing, sources of gaseous and particle pollution, mould and moisture, and pets) were collected through an online questionnaire responded to by a parent. Data on socioeconomic position were obtained through linkage with registry data on maternal education at offspring birth and household equivalized income at offspring birth. Data on parental health were obtained by linking self-reported data from the 11-year follow-up for mother and father with administrative registry data for the mother. We present descriptive statistics and exploratory factor analyses. A total of 42 723 offspring were included for analyses. The distributions of nearly all indoor and housing environments differed according to educational and income strata, with patterns similar for both education and income. Generally, higher parental educational and income strata had more favorable indoor and housing environments (less secondhand smoking, gas stove use, mould and condensation and higher house ownership, detached house dwellings and newer building age). However, candle use was approximately similar between strata, fireplace use among lower educational and income strata tended towards the extremes (none or daily), and water damage was more common among higher educational and income strata. Parental health was strongly associated with housing and indoor home environment factors - especially parental affective disorders was strongly associated with mould. Four factors were extracted from the exploratory factor analyses, relating primarily in order of extraction to: housing ownership, mould and moisture, candle use and household density. Parental health and socioeconomic position are strongly related to housing and indoor home environments. Additionally, several factors in these environments correlate strongly and cluster together. Observational studies on associations and causal effects of factors in the indoor and housing environments of children on their morbidity, must consider both of these conclusions to arrive at valid estimates and effects.

Inter- and Intra-Individual Variability of Personal Health Risk of Combined Particle and Gaseous Pollutants across Selected Urban Microenvironments

Exposure surrogates, such as air quality measured at a fixed-site monitor (FSM) or residence, are typically used for health estimates. However, people spend various amounts of time in different microenvironments, including the home, office, outdoors and in transit, where they are exposed to different magnitudes of particle and gaseous air pollutants. Health risks caused by air pollution exposure differ among individuals due to differences in activity, microenvironmental concentration, as well as the toxicity of pollutants. We evaluated individual and combined added health risks (AR) of exposure to PM2.5, NO2, and O3 for 21 participants in their daily life based on real-world personal exposure measurements. Exposure errors from using surrogates were quantified. Inter- and intra-individual variability in health risks and key contributors in variations were investigated using linear mixed-effects models and correlation analysis, respectively. Substantial errors were found between personal exposure concentrations and ambient concentrations when using air quality measurements at either FSM or the residence location. The mean exposure errors based on the measurements taken at either the FSM or residence as exposure surrogates was higher for NO2 than PM2.5, because of the larger spatial variability in NO2 concentrations in urban areas. The daily time-integrated AR for the combined PM2.5, NO2, and O3 (TIARcombine) ranged by a factor of 2.5 among participants and by a factor up to 2.5 for a given person across measured days. Inter- and intra-individual variability in TIARcombine is almost equally important. Several factors were identified to be significantly correlated with daily TIARcombine, with the top five factors, including PM2.5, NO2 and O3 concentrations at ‘home indoor’, O3 concentrations at ‘office indoor’ and ambient PM2.5 concentrations. The results on the contributors of variability in the daily TIARcombine could help in targeting interventions to reduce daily health damage related to air pollutants.

Equilibrium sorting and moral hazard in residential energy contracts

This paper studies tenant behavior in rental housing when the landlord pays for heating. I develop a model in which renters have heterogeneous preferences for home size and indoor temperature. When energy is costly, renters choose smaller apartments and turn down the heat—or sort into apartments with landlord-pay energy bills. I estimate the model using exogenous variation in energy prices and use a machine-learning algorithm to explore preference heterogeneity. Surprisingly, I find that renters who prefer hotter temperatures do not systematically choose landlord-pay units, though I am unable to rule out sorting on preferences for unobserved home attributes. Eliminating moral hazard by forcing all renters to pay their own bill reduces energy consumption by 25% due to renters turning down the heat (21%) and choosing smaller units (4%). Moral hazard in residential energy contracts costs the United States $836 million per year in welfare losses including $246 million from carbon emissions.

Research on Green Ecological Interior Space Design Based on FPGA and Embedded System

At present, with the development of FPGA technology, FPGA has become an indispensable part of various systems. Based on the idea of modular and standardized design, a simple and standardized design method is found for the construction of FPGA design system. With the attention paid to environmental protection, interior space design also began to pursue green ecology. This paper briefly describes the concept and technical advantages of FPGA and embedded system, analyzes the concept of green ecological interior space design, and introduces the application of FPGA and embedded system in interior space design with examples. Different types of indoor home systems will have different technical applications. FPGA and embedded system are the technical means that interior designers need to learn and understand, Wireless communication technology and Internet of things technology are also of great significance for green ecological interior space design.

3D Instance Segmentation Using Deep Learning on RGB-D Indoor Data

3D object recognition is a challenging task for intelligent and robot systems in industrial and home indoor environments. It is critical for such systems to recognize and segment the 3D object instances that they encounter on a frequent basis. The computer vision, graphics, and machine learning fields have all given it a lot of attention. Traditionally, 3D segmentation was done with hand-crafted features and designed approaches that didn’t achieve acceptable performance and couldn’t be generalized to large-scale data. Deep learning approaches have lately become the preferred method for 3D segmentation challenges by their great success in 2D computer vision. However, the task of instance segmentation is currently less explored. In this paper, we propose a novel approach for efficient 3D instance segmentation using red green blue and depth (RGB-D) data based on deep learning. The 2D region based convolutional neural networks (Mask R-CNN) deep learning model with point based rending module is adapted to integrate with depth information to recognize and segment 3D instances of objects. In order to generate 3D point cloud coordinates (x, y, z), segmented 2D pixels (u, v) of recognized object regions in the RGB image are merged into (u, v) points of the depth image. Moreover, we conducted an experiment and analysis to compare our proposed method from various points of view and distances. The experimentation shows the proposed 3D object recognition and instance segmentation are sufficiently beneficial to support object handling in robotic and intelligent systems.

International Analysis of Sources and Human Health Risk Associated with Trace Metal Contaminants in Residential Indoor Dust.

People spend increasing amounts of time at home, yet the indoor home environment remains understudied in terms of potential exposure to toxic trace metals. We evaluated trace metal (and metalloid) concentrations (As, Cu, Cr, Mn, Ni, Pb, and Zn) and health risks in indoor dust from homes from 35 countries, along with a suite of potentially contributory residential characteristics. The objective was to determine trace metal source inputs and home environment conditions associated with increasing exposure risk across a range of international communities. For all countries, enrichments compared to global crustal values were Zn > Pb > Cu > As > Cr > Ni; with the greatest health risk from Cr, followed by As > Pb > Mn > Cu > Ni > Zn. Three main indoor dust sources were identified, with a Pb-Zn-As factor related to legacy Pb sources, a Zn-Cu factor reflecting building materials, and a Mn factor indicative of natural soil sources. Increasing home age was associated with greater Pb and As concentrations (5.0 and 0.48 mg/kg per year of home age, respectively), as were peeling paint and garden access. Therefore, these factors form important considerations for the development of evidence-based management strategies to reduce potential risks posed by indoor house dust. Recent findings indicate neurocognitive effects from low concentrations of metal exposures; hence, an understanding of the home exposome is vital.

Novel Insights From Interviewer Assessments of Personal Attributes, Home Environment, and Residential Context in NSHAP.

This study was aimed to describe the interviewer-assessed measures present in the 2015/2016 Round of National Social Life, Health, and Aging Project (NSHAP), outline strengths of interviewer-assessed measures, and explore how interviewer assessments in the domains of home environment and personal characteristics are associated with older adult health. Data come from the 2015/2016 Round of the NSHAP. We provide descriptive results from the interviewer assessments of personal attributes, indoor home environment, and outdoor residential context. We present an illustrative analysis of reports of falls, a health outcome that might be predicted by characteristics assessed by the interviewer, and we suggest directions for further research. Interviewer assessments collected in NSHAP are useful as proxy measures and can be used in combination with respondent's reports and ecological measures to generate insights into healthy aging.

The role of artificial photo backgrounds of shelter dogs on pet profile clicking and the perception of sociability.

With the increasing prevalence of technology, the internet is often the first step for potential pet owners searching for an adoptable dog. However, best practices for the online portrayal of shelter and foster dogs remain unclear. Different online photo backgrounds appearing on adoption websites for shelter dogs may impact adoption speed by influencing viewer interest. Online clicking behaviour on pet profiles and human-directed sociability, broadly defined, has been previously linked to increased adoption likelihood. Therefore, the objective of this study was to determine the relationship between photo backgrounds of shelter dogs and online clicking as well as perceived human-directed sociability. In a virtual experiment, 680 participants were asked to rank the sociability and friendliness of four different adoptable dogs on a scale from 0–10. The photo background of each dog was digitally altered and randomly assigned to four experimental background conditions: 1) outdoor, 2) home indoor, 3) in-kennel, and 4) plain coloured. As a proxy for adoption interest, a link to the dog’s adoption profile was presented on each slide and the clicking behaviour of participants on this link was recorded. Mixed logistic regression and Poisson models revealed that background did not affect participants’ link-clicking behaviour (chisq = 3.55, df = 3, p = .314) nor perceptions of sociability (statistic = 6.19, df = 3, p = .103). Across all backgrounds, only 4.74% of presented slides culminated in participant link-clicking. Sociability scores also did not predict link clicking. Assessment of participant-related factors and dog ID revealed that link-clicking and sociability scores of photographs were influenced by differences between dogs themselves and unaffected by participants’ awareness of study hypotheses. We conclude that artificial background types did not affect participant responses. The results demonstrate the importance of empirical data in making marketing decisions in animal shelters. Understanding which aspects of online marketing materials impact viewer interest will provide guidance for both animal shelter personnel and foster families to improve the speed of adoption of the animals in their care.

Association between prenatal exposure to indoor air pollution and autistic-like behaviors among preschool children.

Indoor air pollution is a recognized risk factor for a range of negative health outcomes. This study aimed to investigate the association between maternal prenatal exposure to indoor air pollution and the presence of autistic-like behaviors among preschool children. Data were obtained from the Longhua Child Cohort Study in 2017, in which we enrolled a total of 65317 preschool children. Associations between maternal exposure to four sources of indoor air pollution (e.g., cooking, environmental tobacco smoke (ETS), mosquito coils, and home decoration) during pregnancy and preschool children's autistic traits were analyzed using multivariate logistic regression. Our results showed that maternal exposure to indoor air pollution from four different sources during pregnancy was associated with the presence of children's autistic-like behaviors. There was dose-response relationship between the accumulative exposure to the four different indoor air pollution sources and the risk of autistic-like behaviors. Furthermore, we found a significant additive interaction between prenatal exposure to both cooking and mosquito coil incense on the risk of autistic-like behaviors. Maternal prenatal exposure to the indoor air pollution from four sources might increase with the risk of autistic-like behaviors being present among preschool children, with an additive interaction effect between some pollution sources.

Associations Among Home Indoor Environmental Quality Factors and Worker Health While Working From Home During COVID-19 Pandemic

Abstract The outbreak of SARS-CoV-2 virus forced office workers to conduct their daily work activities from home over an extended period. Given this unique situation, an opportunity emerged to study the satisfaction of office workers with indoor environmental quality (IEQ) factors of their houses where work activities took place and associate these factors with mental and physical health. We designed and administered a questionnaire that was open for 45 days during the COVID-19 pandemic and received valid data from 988 respondents. The results show that low satisfaction with natural lighting, glare, and humidity predicted eye-related symptoms, while low satisfaction with noise was a strong predictor of fatigue or tiredness, headaches or migraines, anxiety, and depression or sadness. Nose- and throat-related symptoms and skin-related symptoms were only uniquely predicted by low satisfaction with humidity. Low satisfaction with glare uniquely predicted an increase in musculoskeletal discomfort. Symptoms related to mental stress, rumination, or worry were predicted by low satisfaction with air quality and noise. Finally, low satisfaction with noise and indoor temperature predicted the prevalence of symptoms related to trouble concentrating, maintaining attention, or focus. Workers with higher income were more satisfied with humidity, air quality, and indoor temperature and had better overall mental health. Older individuals had increased satisfaction with natural lighting, humidity, air quality, noise, and indoor temperature. Findings from this study can inform future design practices that focus on hybrid home-work environments by highlighting the impact of IEQ factors on occupant well-being.

How Work From Home Has Affected the Occupant's Well-Being in the Residential Built Environment: An International Survey Amid the Covid-19 Pandemic

Abstract This paper presents the results from an international survey that investigated the impacts of the built environment on occupant well-being during the corona virus disease 2019 (COVID-19) pandemic when most professionals were forced to work from home (WFH). The survey was comprised of 81 questions focusing on the respondent's profiles, residences, home indoor environmental quality, health, and home working experiences. A total of 1460 responses were collected from 35 countries, and 1137 of them were considered complete for the analysis. The results suggest that home spatial layout has a significant impact on occupant well-being during WFH since home-life distractions and noises due to the lack of a personal workspace are likely to prevent productive work. Lack of scenic views, inadequate daylighting, and poor acoustics were also reported to be detrimental to occupant productivity and the general WFH experience. It is also revealed from this survey that temperature, relative humidity, and indoor air quality generally have higher satisfaction ratios compared with the indoor lighting and acoustic conditions, and the home layout. Hence, home design for lighting, acoustics, and layout should also receive greater attention in the future.

Greening home: caring for plants indoors

ABSTRACT Plants are widely advocated as beneficial for indoor, urban environments; however, research into how people live with indoor plants in their homes remains limited. This article begins to investigate indoor plant keeping and how it is experienced and valued. Empirically, the article draws on exploratory qualitative research undertaken with houseplant keepers within the inner suburbs of Melbourne (Australia). The research shows that indoor plants are valued in diverse ways that orient around instrumental contributions of plants, caring practices within people’s homes, and extended sensibilities relating to wider social and ecological dynamics. By attending to plants as part of indoor home places, this analysis expands the empirical focus of human–plant geographies and provides future research directions to further productive conversations between urban greening and human geography.

Recognizing occupant presence status in residential buildings from environment sensing data by data mining approach

Actual information of occupant presence is an essential input for the simulation of building energy use and home automation system. Previous studies installed motion sensors, cameras, environment sensor networks or smart meters to detect the occupant presence status directly or indirectly in offices. These approaches would raise the household cost and privacy concerns when were applied to residential buildings. Recently, home indoor environment monitors are becoming a part of daily life with the population of smart home products, and massive indoor environment data in the residential buildings could be collected remotely. Therefore, we conducted an experiment in three bedrooms that were already installed with home indoor environment monitors, based on the hypothesis that information of occupant presence could be extracted from indoor environment data by appropriate data mining approach. Two algorithms were designed in the experiment for the data mining, where one recognized the presence status directly from the environment data, and the other indirectly from the usage information of light and AC that were recognized from illuminance, air temperature and relative humidity. Results showed that it was difficult to develop an algorithm that performed well both on the training and testing datasets when we expected to directly mine the occupant presence from indoor environment parameters, but the performance could be greatly improved when we added the bridge information of light and AC operations into the algorithm, and then the recognition accuracy could be improved higher than 92% in all the three rooms.

Personal Exposure to PM2.5 In-Utero and Birthweight in the MADRES Pregnancy Cohort

BACKGROUND AND AIM: In-utero exposure to particulate matter with aerodynamic diameter less than 2.5µm (PM2.5) in the 3rd trimester has been linked with low birth weight and childhood obesity risk, especially in Hispanic populations. However, previous results have been mixed, likely due to measurement error introduced by estimating personal exposure from ambient data. We investigated the effect of total personal PM2.5 exposure on birthweight and whether it differed by indoor vs outdoor origin in the MADRES cohort study. METHODS: Personal PM2.5 exposure was measured in 206 pregnant women in the 3rd trimester using 48-hour integrated, filter-based sampling. Linear regression was used to test the association between personal PM2.5 exposure and birthweight, adjusting for gestational age, parity, race, maternal age, diabetes, and smoking. Interactions of PM2.5 with indoor sources, home ventilation or time spent indoors tested whether the effect of total PM2.5 on birthweight varied by predominant origin of PM2.5. RESULTS:Participants were predominately Hispanic (79.8%) with mean (SD) gestational age of 39.0 (1.5) weeks, age of 28.2 (6.0) years, and pre-pregnancy BMI of 28.8 (6.8) kg/m2. Mean 48 hour 3rd trimester PM2.5 exposure was 24.5 (41.3) µg/m3 and mean birthweight 3,292.9 (493.2) grams. Total personal PM2.5 was not associated with birthweight (β= 0.28, 95% CI: -1.93 – 2.49, per 1-unit increase in PM2.5). However, the effect of PM2.5 varied by window opening (none or little of the time: 3.09 (-0.67, 6.86) vs most or all of the time: -1.48 (-4.22, 1.27), interaction p=0.052) and marginally by time spent indoors per day (12 hrs: -1.28 (-4.50, 1.95), 13-18 hrs: 1.19 (-4.02, 6.39), 19+ hrs: 3.32 (-0.86, 7.49), interaction p=0.234). CONCLUSIONS:While we did not find a significant association between total prenatal personal PM2.5 exposure and birthweight, we did find evidence that outdoor source contributions to personal PM2.5 exposure were more strongly associated with lower birthweight. KEYWORDS: air pollution, particular matter, birth outcomes, pregnancy outcomes, epidemiology

Ag nanoparticles-functionalized dumbbell-shaped In2O3 derived from MIL-68(In) with excellent sensitivity to formaldehyde

Formaldehyde, as a pollutant gas produced by indoor home decoration, threatens human health to Tablea large extent, so it is necessary to detect formaldehyde gas at low concentrations. The dumbbell-shaped indium oxide (In2O3) prepared with MIL-68(In) as the precursor was modified by Ag nanoparticles, and a series of characterization and analysis were performed on it. Field-emission scanning electronic microscope (FESEM) and transmission electron microscope (TEM) results showed that the Ag nanoparticles are successfully grown on the surface of In2O3. X-ray photoelectron spectroscopy (XPS) analysis confirmed the presence of Ag nanoparticles. The gas-sensing results showed that to 20 ppm formaldehyde, In2O3/Ag showed the highest response (29.9) at 160 °C, and the sensor showed high and rapid response-recovery, good reproducibility, and remarkable stability. This work proves that loading Ag is a feasible method to improve the performance of In2O3 based gas sensor.

Towards healthy and cost-effective indoor environment management in smart homes: A deep reinforcement learning approach

Indoor environmental quality is an important issue since people spend most of their time indoors. This paper aims to develop an autonomous indoor environment management approach to ensure a healthy indoor environment with minimized energy cost via the optimal control of ventilation system and heating/cooling system in smart homes. Due to the uncertainties of weather conditions, electricity price and home occupancy, as well as the complex interaction between indoor air quality and indoor thermal environment, it is challenging to develop an efficient control strategy. To address this challenge, the indoor environment management problem is formulated as a Markov decision process, and then a deep reinforcement learning control strategy, which combines double deep Q network with prioritized experience replay mechanism, is proposed to solve the Markov decision process. The proposed approach can make adaptive control decisions based on the current observations without requiring any forecast information of system uncertainties. Control performance under different scenarios show the proposed approach has good adaptability to the variation of weather conditions, electricity prices, home occupancy patterns and indoor temperature requirements. Moreover, the proposed approach is compared with a double deep Q network-based approach and a model predictive control-based approach. Comparison results show that the proposed approach reduces the average daily energy cost by 3.51% and 8.56% in winter scenarios and 4.05%, 7.88% in summer scenarios while achieving the smallest indoor air quality and temperature violations.

Air quality, Environment and Respiratory Outcomes in Bronchopulmonary Dysplasia, the AERO-BPD cohort study: design and adaptation during the SARS-CoV-2 pandemic

IntroductionAlmost half of all school-age children with bronchopulmonary dysplasia (BPD) have asthma-like symptoms and more suffer from lung function deficits. While air pollution and indoor respiratory irritants are known to...

The reliability and validity of a physical activity and sedentary behaviour home audit tool for children aged 2–5 years

ObjectivesTo test the reliability and validity of a physical activity and sedentary behaviour home environment audit tool for young children (2–5 years old). DesignCross-sectional. MethodsParents of children aged 2–5 years were recruited through online methods (i.e., social media and blogs). Reliability of the SPACES home audit tool was assessed using self-reported surveys (n = 55) completed on two separate occasions, approximately 12 days apart. Validity of the home audit tool was assessed in a separate sample via home observations by researchers conducted after parents completed the self-report survey (n = 21). The audit tool measured indoor and outdoor home environment characteristics hypothesised to influence young children's physical activity and sedentary behaviour. Data were analysed using intraclass correlations (ICCs) and Kappas. ResultsThe majority of items demonstrated acceptable reliability and validity (80.4% and 53.4%, respectively). Size of the child's bedroom showed substantial agreement for reliability (ICC = 0.85), and slight agreement for validity (ICC = 0.23). Physical activity equipment items within the indoor environment showed slight to moderate agreement for reliability (ICC = 0.32–0.68) and slight agreement for validity (ICC = 0.15–0.35). Screen time equipment showed substantial agreement for reliability (ICC = 0.83) and fair for validity (ICC = 0.38). Outdoor items (e.g., backyard size, availability and condition of physical activity equipment, outdoor features) showed substantial agreement for reliability and validity (ICC = 0.84–0.95). ConclusionsThe home audit tool was found to be reliable and valid for many items. This tool could be used in future research to understand the impact of the home environment on young children's physical activity and sedentary behaviour.

Analysis of spatial factors, time-activity and infiltration on outdoor generated PM2.5 exposures of school children in five European cities

Atmospheric particles are a major environmental health risk. Assessments of air pollution related health burden are often based on outdoor concentrations estimated at residential locations, ignoring spatial mobility, time-activity patterns, and indoor exposures. The aim of this work is to quantify impacts of these factors on outdoor-originated fine particle exposures of school children.We apply nested WRF-CAMx modelling of PM2.5 concentrations, gridded population, and school location data. Infiltration and enrichment factors were collected and applied to Athens, Kuopio, Lisbon, Porto, and Treviso. Exposures of school children were calculated for residential and school outdoor and indoor, other indoor, and traffic microenvironments. Combined with time-activity patterns six exposure models were created. Model complexity was increased incrementally starting from residential and school outdoor exposures.Even though levels in traffic and outdoors were considerably higher, 80–84% of the exposure to outdoor particles occurred in indoor environments. The simplest and also commonly used approach of using residential outdoor concentrations as population exposure descriptor (model 1), led on average to 26% higher estimates (15.7 μg/m3) compared with the most complex model (# 6) including home and school outdoor and indoor, other indoor and traffic microenvironments (12.5 μg/m3). These results emphasize the importance of including spatial mobility, time-activity and infiltration to reduce bias in exposure estimates.