Abstract
Wearable inertial measurement units (IMU) enable large-scale multicenter studies of everyday gait analysis in patients with rare neurodegenerative diseases such as cerebellar ataxia. To date, the quantity of sensors used in such studies has involved a trade-off between data quality and clinical feasibility. Here, we apply machine learning techniques to potentially reduce the number of sensors required for real-life gait analysis from three sensors to a single sensor on the hip. We trained 1D-CNNs on constrained walking data from individuals with cerebellar ataxia and healthy controls to generate synthetic foot data and predict gait features from a single sensor and tested them in free walking conditions, including the everyday life of unseen subjects. We compare 14 stride-based gait features (e.g. stride length) with three sensors (two on the feet and one on the hip) with our approach estimating the same features based on raw IMU-data from a single sensor placed on the hip. Leveraging layer-wise relevance propagation (LRP) and transfer learning, we determine driving elements of the input signals to predict individuals’ gait features. Our approach achieved a relative error (\(< 5\%\)) similar to the state of the art three-sensor approach. Thus, machine learning-assisted one-sensor systems can reduce the complexity and cost of gait analysis in upcoming clinical studies while maintaining clinical meaningful effect sizes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anders, C.J., Neumann, D., Samek, W., Müller, K.R., Lapuschkin, S.: Software for dataset-wide xai: From local explanations to global insights with Zennit, CoRelAy, and ViRelAy. CoRR abs/2106.13200 (2021)
APDM: Mobility lab whitepaper (2015). https://apdm.wpengine.com/wp-content/uploads/2015/05/02-Mobility-Lab-Whitepaper.pdf
Buckley, E., Mazzà, C., McNeill, A.: A systematic review of the gait characteristics associated with cerebellar ataxia. Gait Posture 60, 154–163 (2018)
Cuturi, M., Blondel, M.: Soft-DTW: a differentiable loss function for time-series. In: International Conference on Machine Learning (2017)
Czech, M., et al.: The impact of reducing the number of wearable devices on measuring gait in Parkinson disease: noninterventional exploratory study. JMIR Rehabil. Assist. Technol. 7(2), e17986 (2020)
Ghanekar, S.D., Kuo, S.H., Staffetti, J.S., Zesiewicz, T.A.: Current and emerging treatment modalities for spinocerebellar ataxias. Expert Rev. Neurother. 22(2), 101–114 (2022). pMID: 35081319
Goyal, P., Ribeiro, V.J., Saran, H., Kumar, A.: Strap-down pedestrian dead-reckoning system. In: International Conference on Indoor Positioning and Indoor Navigation (IPIN), 2011. pp. 1–7. IEEE/Institute of Electrical and Electronics Engineers Incorporated (2011)
Hannink, J., Kautz, T., Pasluosta, C.F., Gasmann, K.G., Klucken, J., Eskofier, B.M.: Sensor-based gait parameter extraction with deep convolutional neural networks. IEEE J. Biomed. Health Inf. 21(1), 85–93 (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1026–1034 (2015)
Hossain, M.S.B., Dranetz, J., Choi, H., Guo, Z.: DeepBBWAE-Net: a CNN-RNN based deep superlearner for estimating lower extremity sagittal plane joint kinematics using shoe-mounted IMU sensors in daily living. IEEE J. Biomed. Health Inf. 26(8), 3906–3917 (2022)
Ilg, W., et al.: the ESMI consortium: digital gait biomarkers allow to capture 1-year longitudinal change in spinocerebellar ataxia type 3. Mov. Disord. 37(11), 2295–2301 (2022)
Ilg, W., et al.: Real-life gait assessment in degenerative cerebellar ataxia: toward ecologically valid biomarkers. Neurology 95(9), e1199–e1210 (2020)
Jabri, S., Carender, W., Wiens, J., Sienko, K.H.: Automatic ML-based vestibular gait classification: examining the effects of IMU placement and gait task selection. J. Neuroeng. Rehabil. 19(1), 132 (2022)
Joyce, M.R., et al.: Quality of life changes following the onset of cerebellar ataxia: symptoms and concerns self-reported by ataxia patients and informants. Cerebellum (London, England) 21(4), 592–605 (2022)
Kadirvelu, B., et al.: A wearable motion capture suit and machine learning predict disease progression in Friedreich’s ataxia. Nat. Med. 29(1), 86–94 (2023)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. CoRR abs/1412.6980 (2014)
Letzgus, S., Wagner, P., Lederer, J., Samek, W., Müller, K.R., Montavon, G.: Toward explainable AI for regression models. IEEE Signal Process. Mag. 39(4), 40–58 (2022). https://arxiv.org/pdf/2112.11407v2
Maghoumi, M., Taranta, E.M., LaViola, J.: DeepNAG: deep non-adversarial gesture generation. In: 26th International Conference on Intelligent User Interfaces, pp. 213–223 (2021)
Müller, M.: Dynamic Time Warping, pp. 69–84. Springer, Berlin (2007). https://doi.org/10.1007/978-3-540-74048-3_4
Morris, R., Stuart, S., McBarron, G., Fino, P.C., Mancini, M., Curtze, C.: Validity of mobility lab (version 2) for gait assessment in young adults, older adults and Parkinson’s disease. Physiol. Meas. 40(9), 095003 (2019)
Pascanu, R., Mikolov, T., Bengio, Y.: On the difficulty of training recurrent neural networks (2012)
Ruano, L., Melo, C., Silva, M.C., Coutinho, P.: The global epidemiology of hereditary ataxia and spastic paraplegia: a systematic review of prevalence studies. Neuroepidemiology 42(3), 174–183 (2014)
Thierfelder, A., et al.: Real-life turning movements capture subtle longitudinal and preataxic changes in cerebellar ataxia. Mov. Disord.: Official J. Mov. Disord. Soc. 37(5), 1047–1058 (2022)
Acknowledgments
The authors thank the International Max Planck Research School for Intelligent Systems (IMPRS-IS) for supporting Jens Seemann. This work was supported by Else Kröner-Fresenius-Stiftung: Project ClinbrAIn. Further support was received by the European Research Council ERC 2019-SYG under EU Horizon 2020 research and innovation programme (grant agreement No. 856495, RELEVANCE). ChatGPT generated the part of the title ‘One Hip Wonder’ given the abstract and the prompt to generate a fun title.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Seemann, J., Loris, T., Weber, L., Synofzik, M., Giese, M.A., Ilg, W. (2023). One Hip Wonder: 1D-CNNs Reduce Sensor Requirements for Everyday Gait Analysis. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14263. Springer, Cham. https://doi.org/10.1007/978-3-031-44204-9_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-44204-9_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44203-2
Online ISBN: 978-3-031-44204-9
eBook Packages: Computer ScienceComputer Science (R0)