Modeling daily in-home activities using machine learning techniques

Activity-based modeling for travel demand forecasting have mainly focused on out-of-home activities. However, out-of-home (OH) and in-home (IH) activities are closely related decisions. For example, individuals working-from-home for longer duration are less likely to make commute trips to the workplace. Furthermore, COVID-19 has forced individuals to replace their OH with IH activities, which further indicates the need for in-home activity modelling. To address the inter-dependencies and better predict travel demand, efforts are required to model in-home activities. This paper develops machine learning (ML) models to investigate in-home activities. We have considered in-home activities in the four thematic categories: sleeping, leisure and discretionary, household and personal maintenance, and mandatory activities. Models were developed for: 1) activity participation and 2) activity duration. The former is focused on modeling what type of in-home activities individuals would perform during a typical weekday, where the latter models the duration for each in-home activity. Several machine learning models were applied, including artificial neural network (ANN), regression trees (RT), Ensembles, support vector machine (SVM), k-nearest neighbor (KNN), and Gaussian process regression (GPR). For each technique, we seek the best model by fine-tuning the modeling architecture. We also compared the prediction speed of the models to understand how they would perform in practice. The results of the participation models had an overall accuracy above 95%, where the activity duration models had an R2 between 0.74 and 0.94. This research demonstrates how machine learning models are robust and can be adopted to accurately predict activity participation and duration.

Gender-dependent impact of COVID-19 lockdown on metabolic and psychological aspects.

The first COVID-19 lockdown resulted in enforced quarantine of heavily affected areas with social isolation and related measures by several governments to slow the spread of the disease. The general population experienced several mental and lifestyle changes. Herein, we aimed to evaluate the metabolic and psychological effects induced by lifestyle changes during COVID-19 self-isolation among an Apulian overweight/obese cohort with metabolic disturbances. The study assessed anthropometric data (weight, abdominal circumferences), dietary habits (adherence to the Mediterranean diet, junk food score), lifestyle habits (i.e., smoking, and physical activity), levels of stress and anxiety, and depression. Subjects underwent bioumoral exams before and after self-isolation to monitor glycemic and lipid profiles. A total of 245 subjects (M:F = 118:127) have been included in the study. After lockdown, the number of obese subjects significantly increased in both sexes, and was higher in females than in males (P < 0.0001). Glycemic and lipid profiles worsened, with higher levels of insulinemia, lower levels of HDL cholesterol, and higher levels of triglycerides in females than in males. Adherence to the Mediterranean diet and consumption of junk foods were altered in both groups, especially in females. Psychological aspects were significantly higher in females than in males. Finally, work activities and familial status strongly affected the metabolic and psychological profile. In conclusion, COVID-19 self-isolation induced changes in lifestyle and dietary habits with psychological distress and detrimental effects on metabolic patterns, which were more pronounced in female gender.

Effects of the COVID-19 lockdown and recovery on People's mobility and air quality in the United Arab Emirates using satellite and ground observations.

The stringent COVID-19 lockdown measures in 2020 significantly impacted people's mobility and air quality worldwide. This study presents an assessment of the impacts of the lockdown and the subsequent reopening on air quality and people's mobility in the United Arab Emirates (UAE). Google's community mobility reports and UAE's government lockdown measures were used to assess the changes in the mobility patterns. Time-series and statistical analyses of various air pollutants levels (NO2, O3, SO2, PM10, and aerosol optical depth-AOD) obtained from satellite images and ground monitoring stations were used to assess air quality. The levels of pollutants during the initial lockdown (March to June 2020) and the subsequent gradual reopening in 2020 and 2021 were compared with their average levels during 2015-2019. During the lockdown, people's mobility in the workplace, parks, shops and pharmacies, transit stations, and retail and recreation sectors decreased by about 34%-79%. However, the mobility in the residential sector increased by up to 29%. The satellite-based data indicated significant reductions in NO2 (up to 22%), SO2 (up to 17%), and AOD (up to 40%) with small changes in O3 (up to 5%) during the lockdown. Similarly, data from the ground monitoring stations showed significant reductions in NO2 (49% - 57%) and PM10 (19% - 64%); however, the SO2 and O3 levels showed inconsistent trends. The ground and satellite-based air quality levels were positively correlated for NO2, PM10, and AOD. The data also demonstrated significant correlations between the mobility and NO2 and AOD levels during the lockdown and recovery periods. The study documents the impacts of the lockdown on people's mobility and air quality and provides useful data and analyses for researchers, planners, and policymakers relevant to managing risk, mobility, and air quality.

How residential energy consumption has changed due to COVID-19 pandemic? An agent-based model.

Integrating occupant behavior with residential energy use for detailed energy quantification has attracted research attention. However, many of the available models fail to capture unseen behavior, especially in unprecedented situations such as COVID-19 lockdowns. In this study, we adopted a hybrid approach consisting of agent-based simulation, machine learning and energy simulation techniques to simulate the urban energy consumption considering the occupants' behavior. An agent-based model is developed to simulate the in-home and out-of-home activities of individuals. Separate models were developed to recognize physical characteristics of residential dwellings, including heating equipment, source of energy, and thermostat setpoints. The developed modeling framework was implemented as a case study for the Central Okanagan region of British Columbia, where alternative COVID-19 scenarios were tested. The results suggested that during the pandemic, the daily average in-home-activity duration (IHD) increased by approximately 80%, causing the energy consumption to increase by around 29%. After the pandemic, the average daily IHD is expected to be higher by approximately 32% compared with the pre-pandemic situation, which translates to an approximately 12% increase in energy consumption. The results of this study can help us understand the implications of the imposed COVID-19 lockdown with respect to energy usage in residential locations.

COVID-19 Lockdown and the Impact on Mobility, Air Quality, and Utility Consumption: A Case Study from Sharjah, United Arab Emirates

This study presents an analysis of the impact of COVID-19 lockdown on people’s mobility trends, air quality, and utility consumption in Sharjah, United Arab Emirates (UAE). Records of lockdown and subsequent easing measures, infection and vaccination rates, community mobility reports, remotely sensed and ground-based air quality data, and utility (electricity, water, and gas) consumption data were collected and analyzed in the study. The mobility trends reflected the stringency of the lockdown measures, increasing in the residential sector but decreasing in all other sectors. The data showed significant improvement in air quality corresponding to the lockdown measures in 2020 followed by gradual deterioration as the lockdown measures were eased. Electricity and water consumption increased in the residential sector during the lockdown;however, overall utility consumption did not show significant changes. The changes in mobility were correlated with the relevant air quality parameters, such as NO2, which in turn was highly correlated to O3. The study provides data and analysis to support future planning and response efforts in Sharjah. Furthermore, the methodology used in the study can be applied to assess the impacts of COVID-19 or similar events on people’s mobility, air quality and utility consumption at other geographical locations.