The global concern regarding the monitoring of construction workers' activities necessitates an efficient means of continuous monitoring for timely action recognition at construction sites. This ...paper introduces a novel approach-the multi-scale graph strategy-to enhance feature extraction in complex networks. At the core of this strategy lies the multi-feature fusion network (MF-Net), which employs multiple scale graphs in distinct network streams to capture both local and global features of crucial joints. This approach extends beyond local relationships to encompass broader connections, including those between the head and foot, as well as interactions like those involving the head and neck. By integrating diverse scale graphs into distinct network streams, we effectively incorporate physically unrelated information, aiding in the extraction of vital local joint contour features. Furthermore, we introduce velocity and acceleration as temporal features, fusing them with spatial features to enhance informational efficacy and the model's performance. Finally, efficiency-enhancing measures, such as a bottleneck structure and a branch-wise attention block, are implemented to optimize computational resources while enhancing feature discriminability. The significance of this paper lies in improving the management model of the construction industry, ultimately aiming to enhance the health and work efficiency of workers.
In this article, we ask whether macro-level changes during the first year of the COVID-19 pandemic relate to changes in the levels of discrimination against women and Black job-seekers at the point ...of hire. We develop three main hypotheses: that discrimination against women and Black job-seekers increases due to a reduction in labor demand; that discrimination against women decreases due to the reduced supply of women employees and applicants; and that discrimination against Black job-seekers decreases due to increased attention toward racial inequities associated with the Black Lives Matter protests during the summer of 2020. We test these hypotheses using a correspondence audit study collected over two periods, before and during the early COVID-19 pandemic, for one professional occupation: accountants. We find that White women experience a positive change in callbacks during the pandemic, being preferred over White men, and this change is concentrated in geographic areas that experienced relatively larger decreases in women's labor supply. Black women experience discrimination pre-pandemic but receive similar callbacks to White men during the pandemic. In contrast to both White and Black women, discrimination against Black men is persistent before and during the pandemic. Our findings are consistent with the prediction of gender-specific changes in labor supply being associated with gender-specific changes in hiring discrimination during the COVID-19 pandemic. More broadly, our study shows how hiring decision-making is related to macro-level labor market processes.
Although well theorized at the individual level, previous research has neglected the role of national context in shaping overall levels of nonwork–work and work–nonwork interference. This study fills ...this gap by examining how a national context of gender empowerment affects the likelihood of experiencing nonwork–work and work–nonwork interference at the individual and national levels. Controlling for individual-level differences in the distribution of job demands and resources, results from our multilevel models indicate that women’s empowerment has significant net gender and parenthood effects on nonwork–work interference. By contrast, gender empowerment equally structures work–nonwork interference for these groups. Our results highlight the need to investigate interference bidirectionally and in a multilevel context.
This article examines how rumors impact democracy and transparency in a cooperative workplace. Although literature on rumors generally analyzes them as negative to workplace culture, the author ...argues that rumors constitute a critical aspect of democratic participation. Drawing on long-term ethnographic fieldwork in a worker-recuperated business in Argentina, the author shows how members use rumors to incite deliberation, participate in decision-making, question organizational policy, and oversee managerial authority. Although informal communication at work can create uncertainty, confusion, and concerns about efficiency, the author finds that rumors can also increase worker influence, encourage organizational accountability, and ultimately protect against the consolidation of power.
Purpose> Construction action recognition is essential to efficiently manage productivity, health and safety risks. These can be achieved by tracking and monitoring construction work. This study aims ...to examine the performance of a variant of deep convolutional neural networks (CNNs) for recognizing actions of construction workers from images of signals of time-series data. Design/methodology/approach> This paper adopts Inception v1 to classify actions involved in carpentry and painting activities from images of motion data. Augmented time-series data from wearable sensors attached to worker's lower arms are converted to signal images to train an Inception v1 network. Performance of Inception v1 is compared with the highest performing supervised learning classifier, k-nearest neighbor (KNN). Findings> Results show that the performance of Inception v1 network improved when trained with signal images of the augmented data but at a high computational cost. Inception v1 network and KNN achieved an accuracy of 95.2% and 99.8%, respectively when trained with 50-fold augmented carpentry dataset. The accuracy of Inception v1 and KNN with 10-fold painting augmented dataset is 95.3% and 97.1%, respectively. Research limitations/implications> Only acceleration data of the lower arm of the two trades were used for action recognition. Each signal image comprises 20 datasets. Originality/value> Little has been reported on recognizing construction workers' actions from signal images. This study adds value to the existing literature, in particular by providing insights into the extent to which a deep CNN can classify subtasks from patterns in signal images compared to a traditional best performing shallow network.