Abstract
Human activity recognition and fall detection have been popular research topics because of its wide area of application. Traditional activity recognition methods have complex feature extraction steps. We propose a new feature extraction method based on linear prediction analysis(LPA) to reduce computational complexity involved with engineering features. The feature extraction method we propose establishes a link between human activity and the signal system and regards acceleration signals as the output of the human activity. Using the relationship between the human activity and the output signal, linear predictive analysis can isolate information about human activity and transform it into a compact representation through linear prediction coefficients (LPC). In order to verify the effectiveness of the method, we design an activity recognition system based on linear prediction analysis and feature extraction. At the same time, we study the performance of the combination of linear prediction coefficients and time domain features. We use data from the public dataset SCUT-NAA, which contains ten different activities, and another public dataset, which records people falling. A random forest classification algorithm based on ensemble learning is used for activity recognition and fall detection. The results show that the combined vector of linear prediction coefficient and time domain activity amplitude feature obtained a 93% accuracy rate and the system evaluation index F1 of 0.92 on the SCUT-NAA dataset. Additionally, we achieved an accuracy rate of 97% in fall detection.
Similar content being viewed by others
References
Aggarwal J, Ryoo M (2011) Human activity analysis: a review. ACM Comput Surv 43:16–43. https://doi.org/10.1145/1922649.1922653
Andrey I (2017) Real-time human activity recognition from accelerometer data using Convolutional Neural Networks. Appl. Soft Comput. 62:62–922. https://doi.org/10.1016/j.asoc.2017.09.027
Ashqar H, Almannaa M, Elhenawy M, Rakha H, House L (2018) Smartphone transportation mode recognition using a hierarchical machine learning classifier and pooled features from time and frequency domains. IEEE transactions on intelligent transportation systems PP:1-9. doi:https://doi.org/10.1109/TITS.2018.2817658
Attal F, Mohammed S, Dedabrishvili M, Chamroukhi F, Oukhellou L, Amirat Y (2015) Physical human activity recognition using wearable sensors. Sensors 15:31314–31338. https://doi.org/10.3390/s151229858
Chelli A, Pätzold M (2019) A machine learning approach for fall detection and daily living activity recognition. IEEE Access 7:38670–38687. https://doi.org/10.1109/ACCESS.2019.2906693
Ermes M, Pärkkä J, Mäntyjärvi J, Korhonen I (2008) Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions. IEEE transactions on information technology in biomedicine : a publication of the IEEE Engineering in Medicine and Biology Society 12:20–26. https://doi.org/10.1109/TITB.2007.899496
Gao L, Bourke A, Nelson J (2014) Evaluation of accelerometer based multi-sensor versus single-sensor activity recognition systems. Med. Eng. Phys. 36:36–785. https://doi.org/10.1016/j.medengphy.2014.02.012
Guo M, Wang Z, Yang N, Li Z, An T (2019) A multisensor multiclassifier hierarchical fusion model based on entropy weight for human activity recognition using wearable inertial sensors. IEEE Transactions on Human-Machine Systems 49(1):105–111. https://doi.org/10.1109/THMS.2018.2884717
Hassan MM, Uddin MZ, Mohamed A, Almogren A (2018) A robust human activity recognition system using smartphone sensors and deep learning. Futur Gener Comput Syst 81:307–313. https://doi.org/10.1016/j.future.2017.11.029
Hsu Y-L, Yang S-C, Chang H-C, Lai H-C (2018) Human daily and sport activity recognition using a wearable inertial sensor network. IEEE access PP:1-1. doi:https://doi.org/10.1109/ACCESS.2018.2839766
Jansi R, Amutha R (2018) Sparse representation based classification scheme for human activity recognition using smartphones. Multimed. Tools Appl. 78:78–11045. https://doi.org/10.1007/s11042-018-6662-5
Kim Y, Son Y, Kim W, Jin B, Yun M (2018) Classification of Children’s sitting postures using machine learning algorithms. Appl Sci 8:1280. https://doi.org/10.3390/app8081280
Lara O, Labrador M (2013) A survey on human activity recognition using wearable sensors. Communications Surveys & Tutorials, IEEE 15:1192–1209. https://doi.org/10.1109/SURV.2012.110112.00192
Lu W, Fan F, Chu J, Jing P, Su Y (2018) Wearable computing for internet of things: a discriminant approach for human activity recognition. IEEE internet of things journal PP:1-1. doi:https://doi.org/10.1109/JIOT.2018.2873594
Morales J, Akopian D (2017) Physical activity recognition by smartphones, a survey. Biocybernetics and Biomedical Engineering 37:388–400. https://doi.org/10.1016/j.bbe.2017.04.004
Nazabal A, Garcia-Moreno P, Artés Rodríguez A, Ghahramani Z (2015) Human activity recognition by combining a small number of classifiers. IEEE journal of biomedical and health informatics 20:1342–1351. https://doi.org/10.1109/JBHI.2015.2458274
Ojetola O, Gaura E, Brusey J (2015) Data set for fall events and daily activities from inertial sensors. doi:https://doi.org/10.1145/2713168.2713198
Pärkkä J, Ermes M, Korpipää P, Mäntyjärvi J, Peltola J, Korhonen I (2006) Activity classification using realistic data from wearable sensors. IEEE transactions on information technology in biomedicine : a publication of the IEEE Engineering in Medicine and Biology Society 10:119–128. https://doi.org/10.1109/TITB.2005.856863
Poppe R (2010) Poppe, R.: a survey on vision-based human action recognition. Image and vision computing 28(6), 976-990. Image Vis Comput 28:976–990. https://doi.org/10.1016/j.imavis.2009.11.014
Preece S, Goulermas J, Kenney L, Howard D (2009) A comparison of feature extraction methods for the classification of dynamic activities from accelerometer data. Biomedical Engineering, IEEE Transactions on 56:871–879. https://doi.org/10.1109/TBME.2008.2006190
Ramasamy Ramamurthy S, Roy N (2018) Recent trends in machine learning for human activity recognition-a survey. Wiley interdisciplinary reviews: data mining and knowledge discovery:e1254. doi:https://doi.org/10.1002/widm.1254
Roh J, Park H-J, Lee K, Hyeong J, Kim S, Lee B (2018) Sitting posture monitoring system based on a low-cost load cell using machine learning. Sensors (Basel, Switzerland) 18. doi:https://doi.org/10.3390/s18010208
SanSegundo R, Cordoba R, Ferreiros J, D'Haro L (2016) Frequency Features and GMM-UBM approach for Gait-based Person Identification using Smartphone Inertial Signals. Pattern Recogn. Lett. 73:73–67. https://doi.org/10.1016/j.patrec.2016.01.008
San-Segundo R, Blunck H, Moreno-Pimentel J, Stisen A, Gil-Martín M (2018) Robust human activity recognition using smartwatches and smartphones. Eng Appl Artif Intell 72:190–202. https://doi.org/10.1016/j.engappai.2018.04.002
Tao D, Guo Y, Song M, Li Y-T, Yu Z, Tang Y (2016) Person re-identification by dual-regularized KISS metric learning. IEEE Trans Image Process 25:1–1. https://doi.org/10.1109/TIP.2016.2553446,2738
Vanrell SR, Milone DH, Rufiner HL (2018) Assessment of Homomorphic analysis for human activity recognition from acceleration signals. IEEE J. Biomed. Health Inform. 22(4):1001–1010. https://doi.org/10.1109/JBHI.2017.2722870
Wang Z, Wu D, Chen J, Ghoneim A, Hossain MA (2016) A Triaxial accelerometer-based human activity recognition via EEMD-based features and game-theory-based feature selection. IEEE Sensors J 16(9):3198–3207
Wang J, Huang Z, Zhang W, Patil A, Patil K, Zhu T, Shiroma E, Schepps M, Harris T (2016) Wearable sensor based human posture recognition. doi:https://doi.org/10.1109/BigData.2016.7841004
Xue Y, Jin L (2010) A naturalistic 3D acceleration-based activity dataset & benchmark evaluations. doi:https://doi.org/10.1109/ICSMC.2010.5641790
Acknowledgements
We would like to thank the HCII-LAB of South China University of Technology for providing us with the SCUT-NAA dataset(http://www.hcii-lab.net/data/scutnaa). We would also like to thank Coventry University for providing us with the fall detection dataset (http://cogentee.coventry.ac.uk/datasets/fall_adl_data.zip).
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.
Rights and permissions
About this article
Cite this article
Li, R., Li, H. & Shi, W. Human activity recognition based on LPA. Multimed Tools Appl 79, 31069–31086 (2020). https://doi.org/10.1007/s11042-020-09150-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-09150-8