The Decision Supports for Male Migrant Workers’ Physical Features at Different Stages of Physical Exercise Behavior by Association Rules Based Data Mining Technology

Abstract With the adjustment of agricultural and rural economic structure, rapid industrialization and urbanization, more than a third of rural labor transferred to non-agricultural industries in China. Guangzhou was one of the major areas introducing many rural labor forces. Migrant workers became a huge group of workers. The health state of migrant workers was directly related to economic development. In fact, the health state of migrant workers was not optimistic in China. Migrant workers, as a special group, has become the “bottleneck” or the “blind spot” for extensively and deeply developing the National Fitness Program. The study aimed at providing decision supports for the health promotion of the migrant workers. Methods: 435 healthy male migrant workers (20~40 years old) were recruited on Guangzhou, China. The physical data was acquainted by Chinese Nation Adults’ Physical Health Standard. Physical Exercise Behavior Stages Questionnaire was the classification standard of exercise behavior change stage (EBCS). Association rules-based data mining technology was applied in this study to find out the potential links between physical features and EBCS on migrant workers, analyze their physical conditions at different EBCS, and provide health promotion decision supports for migrant workers. Results: Results showed that migrant workers displayed different physical features at different EBCS. The decision supports health promotion for migrant workers should be different at each different EBCS. Conclusions: The decision supports of health promotion for migrant workers were mainly included controlling and managing an appropriate body weight, especially at the pre-contemplation stage (PCS), being alert to the increased risk of hypertension at PCS, preparation stage (PS) and maintenance stage (MS), increasing their flexibility at PCS, and preventing the decline of cardiopulmonary function at PS.

[1]  B H Marcus,et al.  Assessing motivational readiness and decision making for exercise. , 1992, Health psychology : official journal of the Division of Health Psychology, American Psychological Association.

[2]  J. Sundquist,et al.  Interactive Effects of Physical Fitness and Body Mass Index on the Risk of Hypertension. , 2016, JAMA internal medicine.

[3]  S. Prince,et al.  Workplace physical activity interventions and moderate-to-vigorous intensity physical activity levels among working-age women: a systematic review protocol , 2014, Systematic Reviews.

[4]  J. Prochaska,et al.  Stages and processes of self-change of smoking: toward an integrative model of change. , 1983, Journal of consulting and clinical psychology.

[5]  S. Bakken,et al.  A Data Mining Approach for Examining Predictors of Physical Activity Among Urban Older Adults. , 2015, Journal of gerontological nursing.

[6]  James O Prochaska,et al.  Stages of change. , 2011, Journal of clinical psychology.

[7]  M. Mahmoodi,et al.  Physical Activity Status and Position of Governmental Employees in Changing Stage Based on the Trans-Theoretical Model in Hamadan, Iran , 2015, Global journal of health science.

[8]  Ryan E Rhodes,et al.  Physical activity: Health impact, prevalence, correlates and interventions , 2017, Psychology & health.

[9]  S. Prince,et al.  Impact of Workplace Physical Activity Interventions on Physical Activity and Cardiometabolic Health Among Working-Age Women: A Systematic Review and Meta-Analysis , 2017, Circulation. Cardiovascular quality and outcomes.

[10]  F. Sohrabi,et al.  Application of the Trans-Theoretical Model (TTM) to Exercise Behavior among Female College Students. , 2007, Journal of research in health sciences.

[11]  Sergei V Kalinin,et al.  Constraining Data Mining with Physical Models: Voltage- and Oxygen Pressure-Dependent Transport in Multiferroic Nanostructures. , 2015, Nano letters.