Abstract
Human activity recognition evolves around classifying and analyzing workers’ actions quantitatively using convolutional neural networks on the time-series data provided by inertial measurement units and motion capture systems. However, this requires expensive training datasets since each warehouse scenario has slightly different settings and activities of interest. Here, transfer learning promises to shift the knowledge a deep learning method gained on existing reference data to new target data. We benchmark interpretable and non-interpretable transfer learning for human activity recognition on the LARa order-picking dataset with AndyLab and RealDisp as domain-related and domain-foreign reference datasets. We find that interpretable transfer learning via the recently proposed probabilistic rule stacking learner, which does not require any labeled data on the target dataset, is possible if the labels are sufficiently semantically related. The success depends on the proximity of the reference and target domains and labels. Non-interpretable transfer learning via fine-tuning can be applied even if there is a major domain-shift between the datasets and reduces the amount of labeled data required on the target dataset.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Agresti, A.: An Introduction to Categorical Data Analysis. John Wiley, Hoboken (2018)
Atzmon, Y., Chechik, G.: Probabilistic AND-OR attribute grouping for zero-shot learning. In: Conference on Uncertainty in Artificial Intelligence (2018)
Avsar, H., Altermann, E., Reining, C., Rueda, F.M., Fink, G.A., ten Hompel, M.: Benchmarking annotation procedures for multi-channel time series HAR dataset. In: 2021 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events, pp. 453–458 (2021)
Banos, O., Toth, M.A., Damas, M., Pomares, H., Rojas, I.: Dealing with the effects of sensor displacement in wearable activity recognition. Sensors 14(6), 9995–10023 (2014)
Calzavara, M., Glock, C.H., Grosse, E.H., Persona, A., Sgarbossa, F.: Analysis of economic and ergonomic performance measures of different rack layouts in an order picking warehouse. Comput. Ind. Eng. 111, 527–536 (2017)
Chen, C., Jafari, R., Kehtarnavaz, N.: A survey of depth and inertial sensor fusion for human action recognition. Multimed. Tools Appl. 76(3), 4405–4425 (2017)
Cheng, H.T., Sun, F.T., Griss, M., Davis, P., Li, J., You, D.: NuActiv: recognizing unseen new activities using semantic attribute-based learning. In: 11th Annual Conference on Mobile Systems, Applications, and Services, pp. 361–374 (2013)
Daduna, J.R.: Automated and autonomous driving in freight transport - opportunities and limitations. In: Lalla-Ruiz, E., Mes, M., Voß, S. (eds.) ICCL 2020. LNCS, vol. 12433, pp. 457–475. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59747-4_30
Ding, N., Deng, J., Murphy, K.P., Neven, H.: probabilistic label relation graphs with Ising models. In: Proceedings of the 2015 IEEE International Conference on Computer Vision, pp. 1161–1169 (2015)
Feldhorst, S., Aniol, S., ten Hompel, M.: Human Activity Recognition in der Kommissionierung - Charakterisierung des Kommissionierprozesses als Ausgangsbasis für die Methodenentwicklung. Logistics J. 2016(10) (2016)
Grosse, E.H., Calzavara, M., Glock, C.H., Sgarbossa, F.: Incorporating human factors into decision support models for production and logistics: current state of research. IFAC-PapersOnLine 50(1), 6900–6905 (2017)
Grosse, E.H., Glock, C.H., Neumann, W.P.: Human factors in order picking system design: a content analysis. IFAC-PapersOnLine 48(3), 320–325 (2015)
Guo, L., Lei, Y., Xing, S., Yan, T., Li, N.: Deep convolutional transfer learning network: a new method for intelligent fault diagnosis of machines with unlabeled data. IEEE Trans. Industr. Electron. 66(9), 7316–7325 (2018)
Huang, H., Pouls, M., Meyer, A., Pauly, M.: Travel time prediction using tree-based ensembles. In: Lalla-Ruiz, E., Mes, M., Voß, S. (eds.) ICCL 2020. LNCS, vol. 12433, pp. 412–427. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59747-4_27
Kirchhof, M., Schmid, L., Reining, C., ten Hompel, M., Pauly, M.: pRSL: interpretable multi-label stacking by learning probabilistic rules. In: Uncertainty in Artificial Intelligence. PMLR (2021). (in press)
Kirchhof, M.: GitHub repository for this article (2021). https://github.com/mkirchhof/rslAppl
de Koster, R., Le-Duc, T., Roodbergen, K.J.: Design and control of warehouse order picking: a literature review. Eur. J. Oper. Res. 182(2), 481–501 (2007)
Krüger, A., Feldmann, F., Pauly, M., ten Hompel, M.: Einsatzmöglichkeiten maschineller Lernverfahren in einer dezentral organisierten Lagerverwaltung auf Basis intelligenter Behälter. Logistics J. Proc. 2020(12) (2020)
Kull, M., Perello Nieto, M., Kängsepp, M., Silva Filho, T., Song, H., Flach, P.: Beyond temperature scaling: obtaining well-calibrated multi-class probabilities with Dirichlet calibration. Adv. Neural. Inf. Process. Syst. 32, 12316–12326 (2019)
Liu, L., Zhou, T., Long, G., Jiang, J., Zhang, C.: Attribute propagation network for graph zero-shot learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34(04), pp. 4868–4875 (2020)
Maurice, P., et al.: Human movement and ergonomics: an industry-oriented dataset for collaborative robotics. Int. J. Robot. Res. 38(14), 1529–1537 (2019)
Rueda, F.M., Grzeszick, R., Fink, G.A., Feldhorst, S., Ten Hompel, M.: Convolutional neural networks for human activity recognition using body-worn sensors. Informatics 5(2), 26 (2018)
Niemann, F., et al.: LARa: creating a dataset for human activity recognition in logistics using semantic attributes. Sensors 20(15), 4083 (2020)
Ordóñez, F., Roggen, D.: Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. Sensors 16(1), 115 (2016)
Reining, C., Niemann, F., Rueda, F.M., Fink, G.A., ten Hompel, M.: Human activity recognition for production and logistics - a systematic literature review. Information 10(8), 245 (2019)
Reining, C., Rueda, F.M., Niemann, F., Fink, G.A., ten Hompel, M.: Annotation performance for multi-channel time series HAR dataset in logistics. In: 2020 IEEE International Conference on Pervasive Computing and Communications Workshops, pp. 1–6 (2020)
Ribeiro, P.M.S., Matos, A.C., Santos, P.H., Cardoso, J.S.: Machine learning improvements to human motion tracking with IMUs. Sensors 20(21), 6383 (2020)
Roggen, D., et al.: Collecting complex activity datasets in highly rich networked sensor environments. In: Seventh International Conference on Networked Sensing Systems (INSS), pp. 233–240 (2010)
Rueda, F.M., Fink, G.: From human pose to on-body devices for human-activity recognition. In: 26th International Conference on Pattern Recognition (ICPR), pp. 10066–10073 (2021)
Schaub, K., Caragnano, G., Britzke, B., Bruder, R.: The European assembly worksheet. Theor. Issues Ergon. Sci. 14(6), 616–639 (2013)
Vicon: Full Body Modeling with Plug-in Gate (2017). https://docs.vicon.com/display/Nexus26/Full+body+modeling+with+Plug-in+Gait. Accessed 16 Mar 2021
Xian, Y., Lampert, C.H., Schiele, B., Akata, Z.: Zero-shot learning - a comprehensive evaluation of the good, the bad and the ugly. IEEE Trans. Pattern Anal. Mach. Intell. 41(9), 2251–2265 (2018)
Yordanova, K., et al.: Challenges in Annotation of useR Data for UbiquitOUs Systems: Results from the 1st ARDUOUS Workshop (2018). arXiv:1803.05843
Zhang, A., et al.: Transfer learning with deep recurrent neural networks for remaining useful life estimation. Appl. Sci. 8(12), 2416 (2018)
Zhang, A., Lipton, Z.C., Li, M., Smola, A.J.: Dive into Deep Learning (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Kirchhof, M., Schmid, L., Reining, C., Hompel, M.t., Pauly, M. (2021). Chances of Interpretable Transfer Learning for Human Activity Recognition in Warehousing. In: Mes, M., Lalla-Ruiz, E., Voß, S. (eds) Computational Logistics. ICCL 2021. Lecture Notes in Computer Science(), vol 13004. Springer, Cham. https://doi.org/10.1007/978-3-030-87672-2_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-87672-2_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87671-5
Online ISBN: 978-3-030-87672-2
eBook Packages: Computer ScienceComputer Science (R0)