Time-Use and Spatio-Temporal Variables Influence on Physical Activity Intensity, Physical and Social Health of Travelers

Abstract

Using a multi-dimensional three-week household time-use and activity diary, this study aims to investigate the interaction between time-use and activity travel participation, built environment, leisure-time physical activity, travel parameters, and physical intensity on physical and social health. The relationship between time-use and activity travel participation is complex. Therefore, physical activity (PA) intensity is assumed to intermediate the relationship between endogenuous and exogenous variables. This study use a comprehensive set of data that was collected at a household level for twenty-one (21) consecutive days. A total of 732 individuals and 191 households were recorded, representing 0.029% total population of Bandung Metropolitan Area (BMA). The data analyzed with descriptive and linear regression analysis using Statistical Package for Social Sciences SPSS version 26.0.0 software (IBM: Armonk, NY, USA). An advanced model, such as the hierarchical Structural Equation Model (SEM), is used to validate the relationship between activity patterns and health parameters. The estimated results indicate that a minute increase in public transport mode has an 8.8% positive correlation with physical health and 9.0% with social health. Furthermore, an increase in the one-minute duration of in-home maintenance and out-of-home leisure activities are positively correlated by 2.9% and 3.2%, respectively, with moderate-intensity PA and by 4.5% and 1.8% strenuous-intensity PA. Additionally, high accessibility and availability of basic amenities at a walkable distance and using auxiliary time in social activities are significantly correlated with better physical and social health. Moreover, this study adopted multidisciplinary approaches for better transport policy and a healthier society with a better quality of life.

An Advanced Machine Learning Approach to Predicting Pedestrian Fatality Caused by Road Crashes: A Step toward Sustainable Pedestrian Safety

“…Most of the solutions mentioned above, however, rely heavily on pre-existing assumptions. Machine learning (ML) techniques have more flexibility than traditional statistical models in that they can analyse noisy data, outliers, and missing data, without or with minimal previous assumptions about inputs [12][13][14][15][16][17][18]. In addition, ML methods are notable instances of data-driven techniques that strive to improve the efficiency and precision of accident data processing and forecasting.…”

Real-Time Implementation of a Fully Automated Industrial System Based on IR 4.0 Concept

“…MQTT is a universal transfer protocol that offers an easy and lightweight method of transmitting messages [49]. It uses a bandwidth that allows remote connections to quickly exchange data between clients, thus making it an efficient transfer protocol commonly used in IoT applications [50].…”

On Hyperparameter Optimization of Machine Learning Methods Using a Bayesian Optimization Algorithm to Predict Work Travel Mode Choice

“…ML approaches describe complicated connections between variables by data-driven learning, as opposed to establishing strong assertions beforehand [25]. Numerous studies in the transportation domain have shown that ML approaches are more accurate predictors than traditional statistical techniques [e.g., 19,26,[27][28][29].…”