An innovative approach of determining the sample data size for machine learning models: a case study on health and safety management for infrastructure workers

Haoqing Wang; Wen Yi; Yannick Liu; Haoqing Wang; Wen Yi; Yannick Liu

doi:10.3934/era.2022176

Electronic Research Archive

2022, Volume 30, Issue 9: 3452-3462. doi: 10.3934/era.2022176

Previous Article Next Article

Research article Special Issues

An innovative approach of determining the sample data size for machine learning models: a case study on health and safety management for infrastructure workers

1.
Faculty of Business, The Hong Kong Polytechnic University, Hung Hom, Hong Kong
2.
Department of Building and Real Estate, The Hong Kong Polytechnic University, Hung Hom, Hong Kong

Received: 14 June 2022 Revised: 05 July 2022 Accepted: 05 July 2022 Published: 22 July 2022

Numerical experiment is an essential part of academic studies in the field of transportation management. Using the appropriate sample size to conduct experiments can save both the data collecting cost and computing time. However, few studies have paid attention to determining the sample size. In this research, we use four typical regression models in machine learning and a dataset from transport infrastructure workers to explore the appropriate sample size. By observing 12 learning curves, we conclude that a sample size of 250 can balance model performance with the cost of data collection. Our study can provide a reference when deciding on the sample size to collect in advance.
- transportation infrastructure,
- learning curve,
- sample size,
- machine learning,
- health and safety management
Citation: Haoqing Wang, Wen Yi, Yannick Liu. An innovative approach of determining the sample data size for machine learning models: a case study on health and safety management for infrastructure workers[J]. Electronic Research Archive, 2022, 30(9): 3452-3462. doi: 10.3934/era.2022176

Related Papers:

Abstract

Numerical experiment is an essential part of academic studies in the field of transportation management. Using the appropriate sample size to conduct experiments can save both the data collecting cost and computing time. However, few studies have paid attention to determining the sample size. In this research, we use four typical regression models in machine learning and a dataset from transport infrastructure workers to explore the appropriate sample size. By observing 12 learning curves, we conclude that a sample size of 250 can balance model performance with the cost of data collection. Our study can provide a reference when deciding on the sample size to collect in advance.

References

[1]	H. Ding, N. N. Sze, Effects of road network characteristics on bicycle safety: a multivariate Poisson-lognormal model, Multimodal Transp., 1 (2022), 1-9. https://doi.org/10.1016/j.multra.2022.100020 doi: 10.1016/j.multra.2022.100020
[2]	Z. Ma, P. Zhang, Individual mobility prediction review: data, problem, method and application, Multimodal Transp., 1 (2022), 1-11. https://doi.org/10.1016/j.multra.2022.100002 doi: 10.1016/j.multra.2022.100002
[3]	X. Z. Simon, Q. Cheng, X. Wu, P. Li, B. Belezamo, J. Lu, et al., A meso-to-macro cross-resolution performance approach for connecting polynomial arrival queue model to volume-delay function with inflow demand-to-capacity ratio, Multimodal Transp., 1 (2022), 1-28. https://doi.org/10.1016/j.multra.2022.100017 doi: 10.1016/j.multra.2022.100017
[4]	W. Yi, H. Wang, Y. Jin, J. Cao, Integrated computer vision algorithms and drone scheduling, Commun. Transp. Res., 1 (2021), 1-4. https://doi.org/10.1016/j.commtr.2021.100002 doi: 10.1016/j.commtr.2021.100002
[5]	X. Lang, D. Wu, W. Mao, Comparison of supervised machine learning methods to predict ship propulsion power at sea, Ocean Eng., 245 (2022), 110387. https://doi.org/10.1016/j.oceaneng.2021.110387 doi: 10.1016/j.oceaneng.2021.110387
[6]	J. Hu, W. Zou, J. Wang, L. Pang, Minimum training sample size requirements for achieving high prediction accuracy with the BN model: a case study regarding seismic liquefaction, Expert Syst. Appl., 185 (2021), 1-13. https://doi.org/10.1016/j.eswa.2021.115702 doi: 10.1016/j.eswa.2021.115702
[7]	C. Ma, X. Wang, L. Xia, X. Cheng, L. Qiu, Effect of sample size and the traditional parametric, nonparametric, and robust methods on the establishment of reference intervals: evidence from real world data. Clin. Biochem., 92 (2021), 67-70. https://doi.org/10.1016/j.clinbiochem.2021.03.006 doi: 10.1016/j.clinbiochem.2021.03.006
[8]	E. Burmeister, L. M. Aitken, Sample size: How many is enough? Aust. Crit. Care, 25 (2012), 271-274. https://doi.org/10.1016/j.aucc.2012.07.002 doi: 10.1016/j.aucc.2012.07.002
[9]	Z. Cui, G. Gong, The effect of machine learning regression algorithms and sample size on individualized behavioral prediction with functional connectivity features, NeuroImage, 178 (2018), 622-637. https://doi.org/10.1016/j.neuroimage.2018.06.001 doi: 10.1016/j.neuroimage.2018.06.001
[10]	H. Taherdoost, Determining sample size; how to calculate survey sample size, Int. J. Econ. Manage. Syst., 2 (2017), 237-239. https://ssrn.com/abstract=3224205
[11]	D. Lakens, Sample size justification, Collabra: Psychol., 8 (2022), 1-28. https://doi.org/10.1525/collabra.33267 doi: 10.1525/collabra.33267
[12]	S. Mao, G. Xiao, J. Lee, L. Wang, Z. Wang, H. Huang, Safety effects of work zone advisory systems under the intelligent connected vehicle environment: a microsimulation approach, J. Intell. Connected Veh., 4 (2021), 16-27. https://doi.org/10.1108/JICV-07-2020-0006 doi: 10.1108/JICV-07-2020-0006
[13]	L. Yue, M. Abdel-Aty, Z. Wang, Effects of connected and autonomous vehicle merging behavior on mainline human-driven vehicle, J. Intell. Connected Veh., 5 (2022), 36-45. https://doi.org/10.1108/JICV-08-2021-0013 doi: 10.1108/JICV-08-2021-0013
[14]	J. Zhu, S. Easa, K. Gao, Merging control strategies of connected and autonomous vehicles at freeway on-ramps: a comprehensive review, J. Intell. Connected Veh., 5 (2022), 99-111. https://doi.org/10.1108/JICV-02-2022-0005 doi: 10.1108/JICV-02-2022-0005
[15]	J. Zhu, I. Tasic, X. Qu, Flow-level coordination of connected and autonomous vehicles in multilane freeway ramp merging areas, Multimodal Transp., 1 (2022), 1-13.
[16]	Y. Du, Q. Meng, S. Wang, H. Kuang, Two-phase optimal solutions for ship speed and trim optimization over a voyage using voyage report data, Transp. Res. Part B Methodol., 122 (2019), 88-114. https://doi.org/10.1016/j.trb.2019.02.004 doi: 10.1016/j.trb.2019.02.004
[17]	R. Yan, S. Wang, Y. Du, Development of a two-stage ship fuel consumption prediction and reduction model for a dry bulk ship, Transp. Res. Part E Logist. Transp. Rev., 138 (2020), 1-22. https://doi.org/10.1016/j.tre.2020.101930 doi: 10.1016/j.tre.2020.101930
[18]	R. Yan, S. Wang, J. Cao, D. Sun, Shipping domain knowledge informed prediction and optimization in port state control, Transp. Res. Part B Methodol., 149 (2021), 52-78. https://doi.org/10.1016/j.trb.2021.05.003 doi: 10.1016/j.trb.2021.05.003
[19]	W. Yi, S. Wang, Mixed-integer linear programming on work-rest schedule design for construction sites in hot weather, Comput.-Aided Civ. Infrastruct. Eng., 32 (2017), 429-439. https://doi.org/10.1111/mice.12267 doi: 10.1111/mice.12267
[20]	Y. Li, Y. Lu, J. Chen, A deep learning approach for real-time rebar counting on the construction site based on YOLOv3 detector, Autom. Constr., 124 (2021), 1-14. https://doi.org/10.1016/j.autcon.2021.103602 doi: 10.1016/j.autcon.2021.103602
[21]	A. Shehadeh, O. Alshboul, R. Mamlook, O. Hamedat, Machine learning models for predicting the residual value of heavy construction equipment: an evaluation of modified decision tree, LightGBM, and XGBoost regression, Autom. Constr., 129 (2021), 1-16. https://doi.org/10.1016/j.autcon.2021.103827 doi: 10.1016/j.autcon.2021.103827
[22]	X. Qu, S. Wang, D. Niemeier, On the urban-rural bus transit system with passenger-freight mixed flow, Commun. Transp. Res., 2 (2022), 1-3. https://doi.org/10.1016/j.commtr.2022.100054 doi: 10.1016/j.commtr.2022.100054
[23]	K. Wang, S. Wang, L. Zhen, X. Qu, Cruise service planning considering berth availability and decreasing marginal profit, Transp. Res. Part B Methodol., 95 (2017), 1-18. https://doi.org/10.1016/j.trb.2016.10.020 doi: 10.1016/j.trb.2016.10.020
[24]	L. Zhen, Y. Hu, S. Wang, G. Laporte, Y. Wu, Fleet deployment and demand fulfillment for container shipping liners, Transp. Res. Part B Methodol., 120 (2019), 15-32. https://doi.org/10.1016/j.trb.2018.11.011 doi: 10.1016/j.trb.2018.11.011
[25]	L. Wu, Y. Adulyasak, J. F. Cordeau, S. Wang, Vessel service planning in seaports, Oper. Res., 2022. https://doi.org/10.1287/opre.2021.2228. doi: 10.1287/opre.2021.2228
[26]	L. Zhen, Y. Wu, S. Wang, G. Laporte, Green technology adoption for fleet deployment in a shipping network, Transp. Res. Part B Methodol., 139 (2020), 388-410. https://doi.org/10.1016/j.trb.2020.06.004 doi: 10.1016/j.trb.2020.06.004
[27]	J. Qi, S. Wang, H. Psaraftis, Bi-level optimization model applications in managing air emissions from ships: a review, Commun. Transp. Res., 1 (2021), 1-5. https://doi.org/10.1016/j.commtr.2021.100020 doi: 10.1016/j.commtr.2021.100020
[28]	S. Wang, H. N. Psaraftis, J. Qi, Paradox of international maritime organization's carbon intensity indicator, Commun. Transp. Res., 1 (2021), 1-5. https://doi.org/10.1016/j.commtr.2021.100005 doi: 10.1016/j.commtr.2021.100005
[29]	S. Wang, L. Zhen, D. Zhuge, Dynamic programming algorithms for selection of waste disposal ports in cruise shipping, Transp. Res. Part B Methodol., 108 (2018), 235-248. https://doi.org/10.1016/j.trb.2017.12.016 doi: 10.1016/j.trb.2017.12.016
[30]	S. Wang, D. Zhuge, L. Zhen, C. Y. Lee, Liner shipping service planning under sulfur emission regulations, Transp. Sci., 55 (2021), 491-509. https://doi.org/10.1287/trsc.2020.1010 doi: 10.1287/trsc.2020.1010
[31]	S. Wang, J. Qi, G. Laporte, Optimal subsidy design for shore power usage in ship berthing operations, Nav. Res. Logist., 69 (2022), 566-580. https://doi.org/10.1002/nav.22029 doi: 10.1002/nav.22029
[32]	S. Wang, R. Yan, A global method from predictive to prescriptive analytics considering prediction error for "Predict, then optimize" with an example of low-carbon logistics, Cleaner Logist. Supply Chain, 4 (2022), 1-3. https://doi.org/10.1016/j.clscn.2022.100062 doi: 10.1016/j.clscn.2022.100062
[33]	R. Yan, S. Wang, Integrating prediction with optimization: models and applications in transportation management, Multimodal Transp., 1 (2022), 1-5. https://doi.org/10.1016/j.multra.2022.100018 doi: 10.1016/j.multra.2022.100018
[34]	R. Yan, S. Wang, L. Zhen, G. Laporte, Emerging approaches applied to maritime transport research: past and future, Commun. Transp. Res., 1 (2021), 1-14. https://doi.org/10.1016/j.commtr.2021.100011 doi: 10.1016/j.commtr.2021.100011
[35]	A. P. Chan, W. Yi, D. W. Chan, D. P. Wong, Using the thermal work limit as an environmental determinant of heat stress for construction workers, J. Manage. Eng., 29 (2013), 414-423.
[36]	A. P. Chan, W. Yi, D. P. Wong, M. C. Yam, D. W. Chan, Determining an optimal recovery time for construction rebar workers after working to exhaustion in a hot and humid environment, Build. Environ., 58 (2012), 163-171. https://doi.org/10.1016/j.buildenv.2012.07.006 doi: 10.1016/j.buildenv.2012.07.006
[37]	M. Flores-Sosa, E. León-Castro, J. M. Merigó, R. R. Yager, Forecasting the exchange rate with multiple linear regression and heavy ordered weighted average operators, Knowl.-Based Syst., 248 (2022), 108863. https://doi.org/10.1016/j.knosys.2022.108863 doi: 10.1016/j.knosys.2022.108863
[38]	Q. H. Luu, M. F. Lau, S. P. Ng, T. Y. Chen, Testing multiple linear regression systems with metamorphic testing, J. Syst. Software, 182 (2021), 1-21. https://doi.org/10.1016/j.jss.2021.111062 doi: 10.1016/j.jss.2021.111062
[39]	G. C. McDonald, Ridge regression, Wiley Interdiscip. Rev. Comput. Stat., 1 (2009), 93-100. https://doi.org/10.1002/wics.14 doi: 10.1002/wics.14
[40]	G. Smith, F. Campbell, A critique of some ridge regression methods, J. Am. Stat. Assoc., 75 (1980), 74-81. https://wwwtandfonline.53yu.com/doi/abs/10.1080/01621459.1980.10477428
[41]	C. R. Genovese, J. Jin, L. Wasserman, Z. Yao, A comparison of the lasso and marginal regression, J. Mach. Learn. Res., 13 (2012), 2107-2143.
[42]	S. Wang, B. Ji, J. Zhao, W. Liu, T. Xu, Predicting ship fuel consumption based on LASSO regression, Transp. Res. Part D: Transp. Environ., 65 (2018), 817-824. https://doi.org/10.1016/j.trd.2017.09.014 doi: 10.1016/j.trd.2017.09.014
[43]	W. J. Fu, Penalized regressions: the bridge versus the lasso, J. Comput. Graphical Stat. , 7 (1998), 397-416. https://wwwtandfonline.53yu.com/doi/abs/10.1080/10618600.1998.10474784
[44]	V. Cherkassky, Y. Ma, Practical selection of SVM parameters and noise estimation for SVM regression, Neural Networks, 17 (2004), 113-126. https://doi.org/10.1016/S0893-6080(03)00169-2 doi: 10.1016/S0893-6080(03)00169-2
[45]	W. C. Hong, Y. Dong, L. Y. Chen, S. Y. Wei, SVR with hybrid chaotic genetic algorithms for tourism demand forecasting, Appl. Soft Comput., 11 (2011), 1881-1890. https://doi.org/10.1016/j.asoc.2010.06.003 doi: 10.1016/j.asoc.2010.06.003
[46]	D. Li, M. Qiu, J. Jiang, S. Yang, The application of an optimized fractional order accumulated grey model with variable parameters in the total energy consumption of Jiangsu Province and the consumption level of Chinese residents, Electron. Res. Arch., 30 (2022), 798-812. https://doi.org/10.3934/era.2022042 doi: 10.3934/era.2022042
[47]	X. Li, L. Kang, Y. Liu, Y. Wu, Distributed Bayesian posterior voting strategy for massive data, Electron. Res. Arch., 30 (2022), 1936-1953. https://doi.org/10.3934/era.2022098 doi: 10.3934/era.2022098

Reader Comments

Your name:*

Email:*
© 2022 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)