E-happiness physiological indicators of construction workers' productivity: A machine learning approach

Abstract

Worker productivity is a major concern for the construction industry. Many studies assessed the effect of various factors, such as the work environment and worker health, on productivity. Nevertheless, the extent to which an automatic productive assessment can benefit from wearable electronic-based sensor technologies for physiological and psychological tracking purposes has not yet been fully investigated. This work assesses the ability of capturing the effect of construction workers’ happiness on their productivity using physiological signals collected via wearable sensors. Data from both a traditional tracking process (human annotators) and an automated worker physiological signal tracking process that was designed for the purposes of this study were compiled. By considering the traditional tracking process as the baseline for the comparison, this study evaluated the effectiveness of automating happiness tracking as a leading indicator of construction workers’ productivity. The physiological signal data collected included blood volume pulse (BVP), respiration rate (RR), heart rate (HR), galvanic skin response (GSR), and skin temperature (TEMP). These data were obtained from a 4-day field study conducted at a pre-fabricated stone construction factory. The study concluded that a moderate positive correlation exists between a worker’s emotional status and his productivity exists, with a p-value = 5.5 × 10–8 and a Pearson’s coefficient of 0.43.

Keywords

• machine learning
• pervasive computing
• construction productivity
• wearable sensors
• happiness indicators