Abstract
It is very challenging for amputees to walk and adapt to uneven surfaces. It is essential to classify different gait surfaces so that intelligent prostheses can be designed for automatic gait adjustment. In this study, supervised machine learning algorithms are used for the gait classification of uneven surfaces. Gait pattern plays a significant role in human movement. Inertia measuring unit (IMU) sensor data is used, which is mounted on the right shank body part. Acceleration data in the x-direction is used for the gait classification of uneven surfaces. Nine different surfaces, namely data slope down, slope up, stair down, stair up, bank right, bank left, cobble stone, grass, and flat even, are studied. Fourteen features, namely mean, RMS, kurtosis, standard deviation, crest factor, skewness, shape indicator, clearance indicator, min, impulse indicator, range, max, margin factor, and energy, are extracted from the data. Supervised machine learning algorithms namely K-Nearest Neighbour (KNN), support vector machine (SVM), Ensemble classifier and Neural network (NN) are employed for gait classification. A maximum gait classification accuracy of 87% is obtained for the subspace discriminant ensemble classifier.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Goujon-Pillet H, Drevelle X, Bonnet X, Villa C, Martinet N, Sauret C, Bascou J, Loiret I, Djian F, Rapin N (2014) APSIC: “Training and fitting amputees during situations of daily living.” IRBM 35:60–65
Labarrière F, Thomas E, Calistri L, Optasanu V, Gueugnon M, Ornetti P, Laroche D (2020) Machine learning approaches for activity recognition and/or activity prediction in locomotion assistive devices a systematic review. Sensors 20:1–30
Johansson JL, Sherrill DM, Riley PO, Bonato P, Herr H (2005) A clinical comparison of variable-dam** and mechanically passive prosthetic knee devices. Am J Phys Med Rehabil 84:563–575
Au SK, Weber JA, Herr HM (2009) Powered ankle foot prosthesis improves walking metabolic economy. IEEE Trans Robot 25:51–66
Chauhan P, Singh AK, Raghuwanshi NK (2022) The state of art review on prosthetic feet and its significance to imitate the biomechanics of human ankle-foot. Mater Today Proc 62:6364–6370
Tedesco S, Barton J, O’Flynn B (2017) A review of activity trackers for senior citizens: research perspectives, commercial landscape and the role of the insurance industry. Sensors 17(6):1–39
Chauhan P, Singh AK, Raghuwanshi NK, Rathore R (2023) Experimental investigation of gait parameters and stability analysis for unilateral transtibial amputee. Sadhana 48:271
Chen Y-P, Yang J-Y, Liou S-N, Lee G-Y, Wang JeenShing (2008) Online classifier construction algorithm for human activity detection using a tri-axial accelerometer. Appl Math Comput 205(2):849–860
Reenalda J, Maartens E, Homan, L, Buurke JJ (2016) Continuous three dimensional analysis of running mechanics during a marathon by means of inertial magnetic measurement units to objectify changes in running mechanics. J Biomech 49(14):3362–3367
Lim S, D’Souza C (2019) Statistical prediction of load carriage mode and magnitude from inertial sensor derived gait kinematics. Appl Ergon 76:1–11
Muller A, Pontonnier C, Robert-Lachaine X, Dumont G, Plamondon A (2020) Motion- based prediction of external forces and moments and back loading during manual material handling tasks. Appl Ergon 82:1–6
Hu B, Li S, Chen Y, Kavi R, Coppola S (2021) Applying deep neural networks and inertial measurement unit in recognising irregular walking differences in the real world. Appl Ergon 96:1–9
Fairhurst SR, Koehler-McNicholas SR, Slater BC, Nickel EA, Koester KA, Voss GO, Ferguson JE (2017)Improving automatic control of an ankle-foot prosthesis using machine learning algorithms. Front Biomed Devices. 40672:1–2
Johnny DF, Natlie B, Edward DL: Gait phase detection from thigh kinematics using machine learning techniques. In: Proceedings of the IEEE international symposium on medical measurements and applications, pp 263–268
Ferdous W, Rezaul KB, Chris JH, Saman H, David CA (2015) Classification of parkinson’s disease gait using spatial-temporal gait features. IEEE J Biomed Health Inform 19:1794–1802
Elham D, Babak T, Alex M (2016) Automated classification of pathological gait after stroke using ubiquitous sensing technology. In: Proceedings of the 38th annual international conference of the ieee engineering in medicine and biology society, pp 6150–6153
Manap HH, Tahir NM, Yassin AIM (2011) Statistical analysis of parkinson disease gait classification using artificial neural network. In: Proceedings of the IEEE international symposium on signal processing and information technology, pp 60–65
Lee SS, Choi ST, Choi SI (2019) Classification of gait type based on deep learning using various sensors with smart insole. Sensors 19(8):1–15
Lee SM, Yoon SM, Cho H, Human activity recognition from accelerometer data using Convolutional Neural Network. In: Proceedings of the IEEE international conference on big data and smart computing, pp 131–134
Wu J, Wang J, Liu L (2007) Feature extraction via KPCA for classification of gait patterns. Hum Mov Sci 26:393–411
Chen L, Yang P, Xu X, Zu L, Guo X (2008) Above-knee prosthesis control based on posture recognition by support vector machine. IEEE conference on robotics, automation and mechatronics, pp 307–312
Kasnesis, P., Patrikakis, C. Z., & Venieris, I. S. PerceptionNet: “A deep convolutional neural network for late sensor fusion”. In Intelligent Systems and Applications: Proceedings of the 2018 Intelligent Systems Conference, Volume 1, pp. 101–119, (2019).
Ai Q, Zhang Y, Qi W, Liu Q, Chen K (2017) Research on lower limb motion recognition based on fusion of EMG and accelerometer signals. Symmetry 9(8):1–19
Wang J, Cao D, Wang J, Liu C (2021) Action recognition of lower limbs based on surface electromyography weighted feature method. Sensors 21(18):1–17
Luo Y, Coppola SM, Dixon PC, Li S, Dennerlein JT, Hu B (2020) A database of human gait performance on irregular and uneven surfaces collected by wearable sensors. Scientific data 7(1):1–9
Ranawat NS, Prakash J, Miglani A, Kankar PK (2023) Performance evaluation of LSTM and Bi-LSTM using non-convolutional features for blockage detection in centrifugal pump. Eng Appl Artif Intell 122:1–24
Ranawat NS, Miglani A, Kankar PK (2023) Blockage detection in centrifugal pump using butterfly optimization-based feature selection. Mapan 38:499–509
Ranawat NS, Kankar PK, Miglani A (2020) Fault diagnosis in centrifugal pump using support vector machine and artificial neural network. J Eng Res EMSME 99:99–111
Ranawat NS, Prakash J, Miglani A, Kankar PK (2023) Fuzzy recurrence plots for shallow learning-based blockage detection in a centrifugal pump using pre-trained image recognition models. ASME J Comput Inf Sci Eng 23(5):1–13
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chauhan, P., Raghuwanshi, N.K., Singh, A.K. (2024). Implementation of Supervised Machine Learning Algorithms for Gait Alteration Classification of the Human Foot. In: Raghavendra, G., Deepak, B.B.V.L., Gupta, M. (eds) Recent Advances in Mechanical Engineering, Volume 1. ICMech-REC 2023. Lecture Notes in Mechanical Engineering. Springer, Singapore. https://doi.org/10.1007/978-981-97-0918-2_37
Download citation
DOI: https://doi.org/10.1007/978-981-97-0918-2_37
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-0917-5
Online ISBN: 978-981-97-0918-2
eBook Packages: EngineeringEngineering (R0)