Abstract
Technology development and digital techniques provide wide opportunities to develop automatic systems. With the help of automated assessment systems, fall prediction for elders or persons with walking disabilities can be identified. Instead of conventional manual video assessment, the prediction accuracy can be improved if the person's gait model is analyzed. Various gait analysis models are evolved in the recent era that uses support vector machine, artificial neural network, and backpropagation neural network for analysis. However, analyzing gait energy images for fall prediction is addressed in limited research works. Considering this research gap this research work proposed a gait-based fall prediction model using a deep learning approach and identifies the early fall of persons with walking disabilities. Gait energy image is used as input for the proposed deep convolutional neural network (DCNN) to predict the early fall. The proposed DCNN model attains a classification accuracy of 99.1% and prediction ratio of 98.64% which is much better than conventional ResNet 50 and CNN method-based gait analysis. Few other parameters, such as specificity, sensitivity, and detection accuracy, are also analyzed to validate the proposed model performance.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Alamoudi R, Alamoudi M (2020) Development of linear regression models to estimate the margin of stability based on spatio-temporal gait parameters. IEEE Access 8:19853–19859
Anwary AR, Hongnian Yu, Vassallo M (2019) Gait evaluation using procrustes and euclidean distance matrix analysis. IEEE J Biomed Health Inform 23(5):2021–2029
El-Alfy H, Mitsugami I, Yagi Y (2018) Gait recognition based on normal distance maps. IEEE Trans Cybern 48(5):1526–1539
Jarchi D, Pope J, Lee TKM, Tamjidi L, Mirzaei A, Sanei S (2018) A review on accelerometry-based gait analysis and emerging clinical applications. IEEE Rev Biomed Eng 11:177–194
Karuppusamy P (2021) Building detection using two-layered novel convolutional neural networks. J Soft Comput Paradigm (JSCP) 3(01):29–37
Lefeber N, Degelaen M, Truyers C, Safin I, Beckwée D (2019) Validity and reproducibility of inertial physilog sensors for spatiotemporal gait analysis in patients with stroke. IEEE Trans Neural Syst Rehabil Eng 27(9):1865–1874
Li G, Liu T, Yi J (2018) Wearable sensor system for detecting gait parameters of abnormal gaits: a feasibility study. IEEE Sens J 18(10):4234–4241
Ma H, Liao W-H (2017) Human gait modeling and analysis using a semi-markov process with ground reaction forces. IEEE Trans Neural Syst Rehabil Eng 25(6):597–607
Mani N, Haridoss P, George B (2021) A wearable ultrasonic-based ankle angle and toe clearance sensing system for gait analysis. IEEE Sens J 21(6):8593–8603
Meng L, Martinez-Hernandez U, Childs C, Dehghani-Sanij AA, Buis A (2019) A practical gait feedback method based on wearable inertial sensors for a drop foot assistance device. IEEE Sens J 19(24):12235–12243
Neha Sharma A. Sampath Dakshina Murthy T. Karthikeyan B. Omkar Lakshmi Jagan et al. Gait diagnosis using fuzzy logic with wearable tech for prolonged disorders of diabetic cardiomyopathy, Materials Today: Proceedings, https://doi.org/10.1016/j.matpr.2020.10.623.
Park JS, Lee CM, Koo S-M, Kim CH (2020) Gait phase detection using force sensing resistors. IEEE Sens J 20(12):6516–6523
Prateek GV, Skog I, McNeely ME, Duncan RP, Earhart GM, Nehorai A (2018) Modeling, detecting, and tracking freezing of gait in parkinson disease using inertial sensors. IEEE Trans Biomed Eng 65(10):2152–2161
Ranganathan, G. (2021) A study to find facts behind preprocessing on deep learning algorithms. J Innovative Image Process (JIIP) 3, no. 01: 66
Ren P, Tang S, Fang F, Luo L, Lei Xu, Bringas-Vega ML, Yao D, Kendrick KM, Valdes-Sosa PA (2017) Gait rhythm fluctuation analysis for neurodegenerative diseases by empirical mode decomposition. IEEE Trans Biomed Eng 64(1):52–60
Rohan A, Rabah M, Hosny T, Kim S-H (2020) Human pose estimation-based real-time gait analysis using convolutional neural network. IEEE Access 8:191542–191550
Sampath Dakshina MurthyKarthikeyan AT, Jagan BOL, Kumari CU (2020) Novel deep neural network for individual re recognizing physically disabled individuals. Mater Today: Proceed 33:4323–4328
Sampath Dakshina Murthy A, Karthikeyan T, Vinothkanna R (2019) A novel hidden Markov model-based adaptive dynamic time warping (HMDTW) gait analysis for identifying physically challenged persons. Soft Comput.
Sampath Dakshina Murthy A, Karthikeyan T, Vinoth Kanna R (2019) A wireless IOT system towards gait detection technique using FSR sensor and wearable IOT devices. International Journal of Intelligent Unmanned Systems , ISSN: 2049–6427
Sampath Dakshina Murthy A, Karthikeyan T, Omkar Lakshmi Jagan B (2020) Clinical model machine learning for gait observation cardiovascular disease diagnosis. Int J Pharm. https://doi.org/10.31838/ijpr/2020.12.04.460
Shuangqun Li Wu, Liu HM (2019) Attentive spatial-temporal summary networks for feature learning in irregular gait recognition. IEEE Trans Multimed 21(9):2361–2375
Singh JP, Jain S, Arora S, Singh UP (2018) Vision-based gait recognition: a survey. IEEE Access 6:70497–70527
Slijepcevic D, Zeppelzauer M, Gorgas A-M, Schwab C, Schüller M, Baca A, Breiteneder C, Horsak B (2018) Automatic classification of functional gait disorders. IEEE J Biomed Health Inform 22(5):1653–1661
Smys, S., and Jennifer S. Raj. (2021) Analysis of Deep Learning Techniques for Early Detection of Depression on Social Media Network-A Comparative Study. J Trends Comput Sci Smart Technol (TCSST) 3, no. 01: 24–39.
Song M, Kim J (2018) An ambulatory gait monitoring system with activity classification and gait parameter calculation based on a single foot inertial sensor. IEEE Trans Biomed Eng 65(4):885–893
Tran L, Choi D (2020) Data augmentation for inertial sensor-based gait deep neural network. IEEE Access 8:12364–12378
Tran L, Hoang T, Nguyen T, Kim H, Choi D (2021) Multi-model long short-term memory network for gait recognition using window-based data segment. IEEE Access 9:23826–23839
Wang W, Ackland DC, McClelland JA, Webster KE, Halgamuge S (2018) Assessment of gait characteristics in total knee arthroplasty patients using a hierarchical partial least squares method. IEEE J Biomed Health Inform 22(1):205–214
Weitao Xu, Lan G, Lin Qi, Khalifa S, Hassan M, Bergmann N, Wen Hu (2019) KEH-Gait: using kinetic energy harvesting for gait-based user authentication systems. IEEE Trans Mob Comput 18(1):139–152
Zhang H, Guo Yi, Zanotto D (2020) Accurate ambulatory gait analysis in walking and running using machine learning models. IEEE Trans Neural Syst Rehabil Eng 28(1):191–202
Zou C, Huang R, Cheng H, Qiu J (2021) Learning gait models with varying walking speeds. IEEE Robot Automation Lett 6(1):183–190
Acknowledgements
Authors have no funding support to study and introduce the article.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
No animals and humans are involved.
Informed consent
We use our own content.
Additional information
Communicated by Joy Iong-Zong Chen.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Sampath Dakshina Murthy, A., Karthikeyan, T. & Vinoth Kanna, R. Gait-based person fall prediction using deep learning approach. Soft Comput 26, 12933–12941 (2022). https://doi.org/10.1007/s00500-021-06125-1
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-021-06125-1