Yuzhong Shen

Dr. Yuzhong Shen

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 December 2022 in Buildings
Verified
Journal Article
Open access
PDF file
SYShiyi Yin
Shiyi Yin
YWYaoping Wu
Yaoping Wu
YSYuzhong Shen
Yuzhong Shen
SRSteve Rowlinson
Steve Rowlinson
Different sets of drivers underlie different safety behaviors, and uncovering such complex patterns helps formulate targeted measures to cultivate safety behaviors. Machine learning can explore such complex patterns among safety behavioral data. This paper aims to develop a classification framework for construction personnel’s safety behaviors with machine learning algorithms, including logistics regression (LR), support vector machine (SVM), random forest (RF), and categorical boosting (CatBoost). The classification framework has three steps, i.e., data collection and preprocessing, modeling and algorithm implementation, and optimal model acquisition. For illustrative purposes, five common safety behaviors of a random sample of Hong Kong-based construction personnel are used to validate the classification framework. To achieve high classification performance, this paper employed a combinative strategy, consisting of feature selection, synthetic minority over-sampling technique (SMOTE), one-hot encoding, standard scaler and classifiers to classify safety behaviors, and multi-objective slime mould algorithm (MOSMA) to optimize parameters in the classifiers. Results suggest that the combinative strategy of CatBoost–MOSMA achieves the highest classification performance with the maximum average scores, including area under the curve of receiver characteristic operator (AUC) ranging from 0.84 to 0.92, accuracy ranging from 0.80 to 0.86, and F1-score ranging from 0.79 to 0.86. From the optimal model, a unique set of important features was identified for each safety behavior, and ten out of the 46 input indicators were found important for all five safety behaviors. Based on the findings, this study advocates using the machine learning strategy of CatBoost–MOSMA in future construction safety behavior research and makes concrete and targeted suggestions to cultivate different construction safety behaviors.

8 November 2023 in Sustainability
Verified
Journal Article
Open access
PDF file
YSYuzhong Shen
Yuzhong Shen
YLYadi Li
Yadi Li
CJChuanjing Ju
Chuanjing Ju
HAHassan Ashraf
Hassan Ashraf
ZHZhen Hu
Zhen Hu
Shoeb Ahmed MemonShoeb Ahmed Memon
Shoeb Ahmed Memon
Organizational climate is the ascribed psychological meaning and significance associated with the procedures, policies, and practices that are recognized and rewarded in the workplace and, hence, mediate the effects of environmental stimuli on individuals’ responses. Safety climate is a specific organizational climate, i.e., organizational climate for safety. Previous research claimed that organizational climate provides a foundation for safety climate, but without elaboration on the foundational mechanisms. This paper attempts to fill this knowledge gap. As organizational climate is a multi-dimensional phenomenon, this paper chooses two dimensions: perceived organizational support (POS) and participative decision making (PaDM). Drawing on an interactive approach to forming climate perceptions, this paper introduces two interactive constructs—leader–member exchange (LMX) and team-member exchange (TMX)—and establishes a multiple mediation model depicting the foundational effect of organizational climate on safety climate. A random sample of 292 Hong Kong-based construction personnel is used to validate the model. The results show that both POS and PaDM are positively associated with perceived safety climate (β1 = 0.175, p < 0.01; β2 = 0.502, p < 0.005), both LMX and TMX fully mediate the effect of PaDM on safety climate (effect sizes are 0.146 and 0.076, respectively), and only LMX partially mediates the effect of POS on safety climate (effect size is 0.131). This study sheds light on the foundational effects of organizational climate on safety climate. POS can improve the quality of reciprocal exchange about safety matters between construction personnel and their supervisors and hence raise construction personnel’s awareness of the priority of safety. PaDM can improve the quality of reciprocal exchange about safety matters vertically and horizontally and hence have construction personnel aware of the importance of safety. In practice, this paper suggests that project managers recognize and reward construction personnel’s contributions in a timely manner, genuinely care about their well-being, and take their suggestions seriously in making decisions. In this way, the quality of both vertical and horizontal exchange about safety matters improves, and a sound and positive safety climate ensues.

16 May 2025 in Safety and Health at Work
Verified
Journal Article
Open access
ZHZhen Hu
Zhen Hu
SLSiyuan Li
Siyuan Li
CHChangquan He
Changquan He
YSYuzhong Shen
Yuzhong Shen
ZHZhong Heng
Zhong Heng
SLSiyi Li
Siyi Li
This study provides a comprehensive overview of the research progress on construction safety resilience and sets up a three-subdimension concept framework (structural resilience, psychological resilience, and managerial resilience) with the theory of engineering resilience. With a three-step review method based on document metrics analysis and scientific measurements, this study screened 1,018 related articles published on the Web of Science, and 168 articles were finally selected as research samples. The VOSviewer software was used to analyze the number of publications, the journals, and the keyword co-occurrence. The software-generated visual graphics and tables were described and summarized. The results show that the existing research on construction safety resilience mainly focuses on three streams: structural resilience, psychological resilience, and managerial resilience. Previous studies on structural resilience mostly focus on the physical aspect of a construction project, while the research on psychological and managerial resilience mainly relates with the personal and managerial aspects of a construction project, respectively. The differences, influencing factors, and measuring methods for these three research streams on construction safety resilience were also explored. Future studies could distinguish them more clearly with their definitions, measurements, and relationships. This study helps to clarify the framework of construction safety resilience and provides a theoretical basis for the evaluation and development of resilient construction safety management, which may be beneficial for future studies on construction safety resilience.

12 July 2023 in Preprints.org
Verified
Preprint
Open access
PDF file
YSYuzhong Shen
Yuzhong Shen
YLYadi Li
Yadi Li
CJChuanjing Ju
Chuanjing Ju
HAHassan Ashraf
Hassan Ashraf
ZHZhen Hu
Zhen Hu
Shoeb Ahmed MemonShoeb Ahmed Memon
Shoeb Ahmed Memon
Organizational climate is the ascribed psychological meanings and significance associated with the procedures, policies and practices that are recognized and rewarded in the workplace, and hence mediates the effects of environmental stimuli on individuals’ response. Safety climate is a specific organizational climate, i.e., organizational climate for safety. Previous research claimed that organizational climate provides foundation for safety climate, but without elaboration on the foundational mechanisms. This paper attempts to fill up this knowledge gap. As organizational climate is a multi-dimensional phenomenon, this paper chooses two dimensions, i.e., perceived organizational support (POS) and participative decision-making (PaDM), for illustrative purposes. Drawing on an interactive approach to forming climate perceptions, this paper introduces two interactive constructs, i.e., leader-member exchange (LMX) and team member exchange (TMX), and establishes a multiple mediation model depicting the foundational effect of organizational climate on safety climate. A random sample of Hong Kong based construction personnel is used to validate the model. The results show that both POS and PaDM are positively associated with perceived safety climate, both LMX and TMX fully mediate the effect of PaDM on safety climate, and only LMX partially mediates the effect of POS on safety climate. This study sheds light on the foundational effects of organizational climate on safety climate. POS can improve the quality of reciprocal exchange about safety matters between construction personnel and their supervisors, and hence raise construction personnel’s awareness of the priority of safety. PaDM can improve the quality of reciprocal exchange about safety matters vertically and horizontally, and hence have construction personnel aware the importance of safety. In practice, this paper suggests that project managers timely recognize and reward construction personnel’s contribution, genuinely cares about their well-being, and take their suggestions seriously in making decisions. In this way, the quality of both vertical and horizontal exchange about safety matters improves, and a sound and positive safety climate ensues.

30 April 2025 in WORK: A Journal of Prevention, Assessment & Rehabilitation
Verified
Journal Article
Closed access
ZHZhen Hu
Zhen Hu
ZHZhong Heng
Zhong Heng
CHChangquan He
Changquan He
YSYuzhong Shen
Yuzhong Shen
SLSiyuan Li
Siyuan Li
SLSiyi Li
Siyi Li
Background: The construction industry has been struggling with high rates of accident and fatality. Safety climate helps construction firms build up safety capability and has received enormous attention from the academia and practitioners. However, it still lacks the systematic review on safety climate in construction workplace, especially from the perspective of organizational-level factors. Objective: This study attempts to explore the latest research progress and future research directions of safety climate in construction workplace from the multilevel perspective. Methods: This study adopted a three-step literature review approach including bibliometric review, scientometric analysis, and qualitative discussion. The journals, keywords, co-authorship network, and co-citation network were examined. Results: Three research mainstreams of safety climate in construction workplace (i.e., assessment, individual-level factors, and organizational-level factors) were identified in the co-occurrence network of the keywords. Co-authorship analysis reveals that Dongping Fang, Albert P. C. Chan, and Helen Lingard were the top three prolific authors in this domain. Six groups existed in the co-authorship network and 3 clusters were found in the co-citation network. Conclusions: It is necessary to develop adaptive methods and dimensions for measuring safety climate in construction workplace. More individual-level factors of safety climate in construction workplace should be further explored. The interactions and influencing mechanism between the organizational- and individual-level factors need to be further clarified. This study may benefit both the academic community and safety policymakers by highlighting the critical factors of safety climate and providing the directions for initiating future studies related with safety climate in construction workplace.

20 December 2024 in Buildings
Verified
Journal Article
Open access
PDF file
ZHZhen Hu
Zhen Hu
ZHZhong Heng
Zhong Heng
LSLi Siyuan
Li Siyuan
SLSiyi Li
Siyi Li
YSYuzhong Shen
Yuzhong Shen
ZXZhizhou Xu
Zhizhou Xu
Physical symptoms plague construction workers and pose threats to safety performance and productivity. Following the resilience engineering (RE) principles, recent construction safety management practices enhance construction workers’ safety capability and safety management system resilience. This paper established an exploratory structural model explaining how construction workers’ safety capability alleviates their physical and psychological symptoms through safety management system resilience. To validate and estimate the structural model, 741 valid responses from construction workers based in Shanghai, China were obtained. Given no established scales for the constructs in the model, a cross-validation procedure, consisting of exploratory and confirmatory factor analysis and path analysis, was performed. The results showed that although neither safety capability nor safety management system resilience has direct negative impacts on physical symptoms, they can reduce physical symptoms via alleviating psychological symptoms. Furthermore, safety capability can reduce psychological and physical symptoms via safety management system resilience. This paper therefore suggests that cultivating construction workers’ safety capability would be the first step in implementing resilience engineering principles in construction. The continuous implementation of cost-effective and tailored resilience training programs are suggested to enhance construction workers’ safety capability. Safety management systems are suggested to improve with the fostering of a just culture and emerging technologies.