Abstract
This paper proposed automated systems for analyzing elemental processes and for evaluating work skills. The systems use labeled latent Dirichlet allocation (L-LDA) to classify worker motions obtained from sensors into four elemental processes. L-LDA automatically learns characteristic motions, so there is no need to define and identify motion features. The proposed system predicts elemental processes with over 86.9% recall in experiments using the assembly process data. Analyst burden is greatly reduced as compared to systems requiring manual analysis of elemental processes from recorded task data. The system evaluates worker skills based on analyzed time series data for elemental processes in four categories, namely, correctness, stability, speed, and rhythm. As a result, the evaluation system clarifies workers’ strong and weak points in tasks performed in experiments, providing new knowledge that would be unobtainable under conventional evaluation methods. Manufacturing efficiency can be improved by allocating workers based on their strengths, and training efficiency will be improved when workers’ weak areas are revealed.
Similar content being viewed by others
References
Yilmaz OF, Cevikcan E, Durmusoglu MB (2016) Scheduling batches in multi hybrid cell manufacturing system considering worker resources: a case study from pipeline industry. Adv Prod Eng Manag 2016:192–206
Best T (2020) Work measurement in skilled labor environments. https://www.iise.org/uploadedFiles/SHSNew/Tools_and_Resources/Search_by_Category_Details/Work_Measurement_in_Skilled_Labor_Environments.pdf
Ferguson D (2020) “Therbligs: the keys to simplifying work” The Gilbreth Network. https://gilbrethnetwork.tripod.com/therbligs.html
Kotake Y, Wang D, Nakajima H (2018) Evaluating worker’s proficiency from body and eye movements in manufacturing operations. In: 2018 Proc. SMC 2018 Conf., pp 1447–1452
Ju Z, Liu H, Zhu X, Xiong Y (2009) Dynamic grasp recognition using time clustering, Gaussian mixture models and Hidden Markov models. Adv Robot 23(10):1359–1371
Ju Z, Ji X, Li J, Liu H (2017) An integrative framework of human hand gesture segmentation for human robot interaction. IEEE Syst J 11(3):1326–1336
Blei DM, Ng AY, Jordan MI (2003) Latent Dirichlet allocation. J Mach Learn Res 3:993–1022
Maskeri G, Sarkar S, Heafield K (2008) Mining business topics in source code using latent Dirichlet allocation. In: 2008 Proc. ISEC 2008 Conf., pp 113–120
Lukins SK, Kraft NA, Etzkorn LH (2008) Source code retrieval for bug localization using latent Dirichlet allocation. In: 2008 Proc. WCRE 2008 Conf., pp 155–164
Krestel R, Fankhauser P, Nejdl W (2009) Latent dirichlet allocation for tag recommendation. In: 2009 Proc. RecSys 2009 Conf., pp 61–68
Perikos I, Hatzilygeroudis I (2017) Aspect based sentiment analysis in social media with classifier ensembles. In: 2017 Proc. ICIS 2017 Conf., pp 273–278
Shi L, Wu Y, Liu L, Sun X, Jiang L (2018) Event detection and identification of influential spreaders in social media data streams. Big Data Min Anal 1(1):34–46
Alhawarat M, Hegazi M (2018) Revisiting K-means and topic modeling, a comparison study to cluster arabic documents. IEEE Access 6:42740–42749
Guo Y, Shen X, Ge Q, Wang L (2018) Station function discovery: exploring trip records in urban public bike-sharing system. IEEE Access 6:71060–71068
Shoja BM, Tabrizi N (2019) Customer reviews analysis with deep neural networks for E-commerce recommender systems. IEEE Access 7:119121–119130
Canimi KR, Shi L, Griffiths TL (2009) Online inference of topics with latent dirichlet allocation. J Mach Learn Res 5:65–72
Putthividhy D, Attias HT, Nagarajan SS (2010) Topic regression multi-modal latent dirichlet allocation for image annotation. In: 2010 Proc. CVPR 2010 Conf., pp 3408–3415
Hoffman MD, Blei DM, Bach F (2010) Online learning for latent dirichlet allocation. In: 2010 Proc. NIPS 2010 Conf., pp 856–864
Zhao B, Zhou H, Li G, Huang Y (2018) ZenLDA: large-scale topic model training on distributed data-parallel platform. Big Data Min Anal 1(1):57–74
Gao Y, Wei X, Zhang X, Zhuang W (2018) A combinational LDA-based topic model for user interest inference of energy efficient IPTV service in smart building. IEEE Access 6:48921–48933
Yu D, Xu D, Wang D, Ni Z (2019) Hierarchical topic modeling of twitter data for online analytical processing. IEEE Access 7:12373–12385
Kanugsukkasem N, Leelanupab T (2019) Financial latent dirichlet allocation (FinLDA): feature extraction in text and data mining for financial time series prediction. IEEE Access 7:71645–71664
Ramge D, Hall D, Nallapati R, Manning CD (2009) Labeled LDA: a supervised topic model for credit attribution in multi-labeled corpora. In: 2009 Proc. EMNLP’09 Conf., pp 248–256
Kular D, Ribeiro E (2016) Discovering spatio-temporal relationships among activities in videos using a relational topic-transition model. In: 2016 Proc. FLAIRS 2016 Conf., pp. 62–67
Faruquie TA, Kalra PK, Banerjee S (2009) Time based activity inference using latent Dirichlet allocation. In: 2009 Proc. BMVC 2009 Conf
Yang S, Yuan C, Hu W, Ding X (2014) A hierarchical model based on latent Dirichlet allocation for action recognition. In: 2014 Proc. ICPR 2014 Conf., pp 2613–2618
Niebles JC, Wang H, Fei-Fei L (2008) Unsupervised learning of human action categories using spatial-temporal words. Int J Comput Vis 79(3):299–318
Li H, Liu J, Zhang S (2011) Hierarchical latent Dirichlet allocation models for realistic action recognition. In: 2011 Proc. ICASSP 2011 Conf., pp 1297–1300
Mori K, Nakajima H, Kotake Y, Wang D, Hata Y (2018) A relationship between product quality and body information of worker and its application to improvement of productivity. In: 2018 Proc. SMC 2018 Conf., pp 1429–1434
Mori K, Nakajima H, Kotake Y, Wang D, Hata Y (2019) Automated analyzing system for recognizing the elemental processes based on the labeled LDA. In: 2019 Proc. ICMLC 2019 Conf., pp 278–282
Mori K, Nakajima H, Kotake Y, Wang D, Hata Y (2019) Automated worker’s skill evaluation system based on the time series elemental processes for improving productivity. In: 2019 Proc. SMC 2019 Conf., pp 1215–1219
Acknowledgements
The authors thank Y. Kotake and D. Wang from Omron Corporation for their helpful discussions and for sharing their dataset with us. This work was supported in part by the Tateisi Science and Technology Foundation (Grant no. 2197012).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
Figures 34, 35, 36, 37, 38, 39 show proposed algorithm as an appendix. These figures are shown based on Python code. Figure 34 shows the algorithm of converting data to text. Figure 35 shows the algorithm of predicting the elemental processes by L-LDA. Figure 36 shows the algorithm of categorizing the processes for each part. Figure 37 shows the algorithm of function “Part0”. Figure 38 shows the algorithm of function “Part1”. Figure 39 shows the algorithm of evaluating the worker skills.
Rights and permissions
About this article
Cite this article
Mori, K., Nakajima, H. & Hata, Y. Automated worker skill evaluation for improving productivity based on labeled LDA. Int. J. Mach. Learn. & Cyber. 12, 1151–1171 (2021). https://doi.org/10.1007/s13042-020-01226-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-020-01226-z