Abstract—
Human activity recognition (HAR) has become a focus of study over the past few years. It is widely used in many fields like health, home safety, security, and energy saving, among others. Research around the health area has evidenced an important increase and a promissory impact on the life quality of a population like the elderly. If we combine sensors and a health condition then we may have a technological solution with methods and techniques that will help us to improve life quality. Smart sensors have become popular. They allow us to monitor data and acquire data in real-time. In HAR, they are used to detect actions and activities like breathing, falling, standing up, or walking. Many commercial solutions use this technology in real-life applications. However, we focused this paper on the Vayaar sensor and the WideFind sensor, two commercial sensors based on ultra-wideband technology, with promising performance, as part of a study developed at the Human Health and Activity Laboratory (H2AL) in the Luleå Tekniska Universitet in Sweden. The study performed a technological and commercial comparison applying machine learning techniques in WEKA for two datasets created with the data gathered from each sensor during an experiment, in which precision and accuracy were analyzed as evaluation parameters of the applied methods. It was identified that random forest (RF) and LogitBoost were the most suitable classifiers to process both WideFind and Vayyar datasets. Random forest had a performance of 85.99% of precision, 85.48% of recall, and 96% of ROC area for the WideFind sensor while LogitBoost had a 69.39% of the performance for precision, 68.89% for recall, and 88.35% of ROC area for the Vayaar sensor.
REFERENCES
Mario, M.-O., Human activity recognition based on single sensor square HV acceleration images and convolutional neural networks, IEEE Sens. J., 2019, vol. 19, no. 4, pp. 1487–1498. https://doi.org/10.1109/JSEN.2018.2882943
Andrade Montoya, P.A., Morejón Bastidas, J.L., and Inga Ortega, E.M., Cobertura máxima de redes de sensores inalámbricos para un sistema de gestión de energía en hogares inteligentes, INGE CUC, 2016, vol. 12, no. 2, pp. 68–78. https://doi.org/10.17981/ingecuc.12.2.2016.07
Uddin, Md.Z., Hassan, M.M., Alsanad, A., and Savaglio, C., A body sensor data fusion and deep recurrent neural network-based behavior recognition approach for robust healthcare, Inf. Fusion, 2019, vol. 55, pp. 105–115. https://doi.org/10.1016/j.inffus.2019.08.004
Ramamurthy, S.R. and Roy, N., Recent trends in machine learning for human activity recognition—A survey, WIREs Data Min. Knowl. Discovery, 2018, vol. 8, no. 4, p. e1254. https://doi.org/10.1002/widm.1254
Sanchez-Comas, A., Synnes, K., and Hallberg, J., Hardware for recognition of human activities: A review of smart home and AAL related technologies, Sensors, 2020, vol. 20, no. 15, p. 4227. https://doi.org/10.3390/s20154227
Sáez Bombín, S., Reconocimiento de actividades físicas con sensores inerciales y Redes Neuronales de Aprendizaje Profundo, Diplom Thesis, Valladolid: Universidad de Valladolid, 2018.
Vellido, A., The importance of interpretability and visualization in machine learning for applications in medicine and health care, Neural Comput. Appl., 2019, vol. 32, no. 24, pp. 18069–18083. https://doi.org/10.1007/s00521-019-04051-w
Ordóñez, F.J. and Roggen, D., Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition, Sensors, 2016, vol. 16, no. 1, p. 115. https://doi.org/10.3390/s16010115
Synnes, K., Lilja, M., Nyman, A., Espinilla, M., Cleland, I., Comas, A.G.S., Comas-Gonzalez, Z., Hallberg, J., Karvonen, N., Morais, W.O.D., Cruciani, F., and Nugent, C., H2Al—The human health and activity laboratory, Proceedings, 2018, vol. 2, no. 19, p. 1241. https://doi.org/10.3390/proceedings2191241
Persson, J., Johansson, G., Arvidsson, I., Östlund, B., Holgersson, C., Persson, R., and Rydenfält, C., A framework for participatory work environment interventions in home care–Success factors and some challenges, BMC Health Services Res., 2020, vol. 22, no. 1, p. 345. https://doi.org/10.1186/s12913-022-07710-2
Rocha, J.A., Piñeres-Espitia, G., Butt, S.A., De-La-Hoz-Franco, E., Tariq, M.I., Sinito, D.C., and Comas-González, Z., Human activity recognition through wireless body sensor networks (WBSN) applying data mining techniques, Advances in Intelligent Data Analysis and Applications, Pan, JS., Balas, V.E., and Chen, C.M., Eds., Smart Innovation, Systems and Technologies, vol. 253, Singapore: Springer, 2022, pp. 327–339. https://doi.org/10.1007/978-981-16-5036-9_31
Zhou, Yi., Vongsa, D., Zhou, Yi., Cheng, Z., and Jing, L., A healthcare system for detection and analysis of daily activity based on wearable sensor and smartphone, 2015 IEEE 12th Intl Conf on Ubiquitous Intelligence and Computing and 2015 IEEE 12th Intl Conf on Autonomic and Trusted Computing and 2015 IEEE 15th Intl Conf on Scalable Computing and Communications and Its Associated Workshops (UIC-ATC-ScalCom), Beijing, 2015, IEEE, 2015, pp. 1109–1114. https://doi.org/10.1109/uic-atc-scalcom-cbdcom-iop.2015.203
Al-Khafajiy, M., Baker, T., Chalmers, C., Asim, M., Kolivand, H., Fahim, M., and Waraich, A., Remote health monitoring of elderly through wearable sensors, Multimedia Tools Appl., 2019, vol. 78, no. 17, pp. 24681–24706. https://doi.org/10.1007/s11042-018-7134-7
Guan, Q., Li, C., Guo, X., and Shen, B., Infrared signal based elderly fall detection for in-home monitoring, 2017 9th Int. Conf. on Intelligent Human-Machine Systems and Cybernetics (IHMSC), Hangzhou, China, 2017, IEEE, 2017, vol. 1, pp. 373–376. https://doi.org/10.1109/ihmsc.2017.91
Diraco, G., Leone, A., and Siciliano, P., A radar-based smart sensor for unobtrusive elderly monitoring in ambient assisted living applications, Biosensors, 2017, vol. 7, no. 4, p. 55. https://doi.org/10.3390/bios7040055
Wang, Ya., Liu, Q., and Fathy, A.E., CW and pulse–Doppler radar processing based on FPGA for human sensing applications, IEEE Trans. Geosci. Remote Sensing, 2013, vol. 51, no. 5, pp. 3097–3107. https://doi.org/10.1109/tgrs.2012.2217975
Du, H., Jin, T., He, Yu., Song, Yo., and Dai, Yo., Segmented convolutional gated recurrent neural networks for human activity recognition in ultra-wideband radar, Neurocomputing, 2020, vol. 396, pp. 451–464. https://doi.org/10.1016/j.neucom.2018.11.109
Qi, F., Liang, F., Liu, M., Lv, H., Wang, P., Xue, H., and Wang, J., Position-information-indexed classifier for improved through-wall detection and classification of human activities using UWB bio-radar, IEEE Antennas Wireless Propag. Lett., 2019, vol. 18, no. 3, pp. 437–441. https://doi.org/10.1109/lawp.2019.2893358
Qi, F., Li, Z., Liang, F., Lv, H., An, Q., and Wang, J., A novel time-frequency analysis method based on HHT for finer-grained human activity using SFCW radar, 2016 Progress in Electromagnetic Research Symposium (PIERS), Shanghai, 2016, IEEE, 2016, pp. 2536–2539.
Qi, F., Lv, H., Liang, F., Li, Z., Yu, X., and Wang, J., MHHT-based method for analysis of micro-Doppler signatures for human finer-grained activity using through-wall SFCW radar, Remote Sensing, 2017, vol. 9, no. 3, p. 260. https://doi.org/10.3390/rs9030260
He, Y., Molchanov, P., Sakamoto, T., Aubry, P., Le Chevalier, F., and Yarovoy, A., Range-Doppler surface: A tool to analyse human target in ultra-wideband radar, IET Radar, Sonar Navig., 2015, vol. 9, no. 9, pp. 1240–1250. https://doi.org/10.1049/iet-rsn.2015.0065
Bouchard, K., Maitre, J., Bertuglia, C., and Gaboury, S., Activity recognition in smart homes using UWB radars, Procedia Comput. Sci., 2020, vol. 170, pp. 10–17. https://doi.org/10.1016/j.procs.2020.03.004
Sharma, S., Mohammadmoradi, H., Heydariaan, M., and Gnawali, O., Device-free activity recognition using ultra-wideband radios, 2019 Int. Conf. on Computing, Networking and Communications (ICNC), Honolulu, Hawaii, 2019, IEEE, 2020, pp. 1029–1033. https://doi.org/10.1109/iccnc.2019.8685504
Wang, Y., Zhou, J., Tong, J., and Wu, X., UWB-radar-based synchronous motion recognition using time-varying range–Doppler images, IET Radar, Sonar Navig., 2019, vol. 13, no. 12, pp. 2131–2139. https://doi.org/10.1049/iet-rsn.2019.0240
Rana, S.P., Dey, M., Brown, R., Siddiqui, H.U., and Dudley, S., Remote vital sign recognition through machine learning augmented UWB, 12th Eur. Conf. on Antennas and Propagation (EuCAP 2018), London, 2018, Institution of Engineering and Technology, 2018, vol. 2018. https://doi.org/10.1049/cp.2018.0978
Caroppo, A., Leone, A., Rescio, G., Diraco, G., and Siciliano, P., Multi-sensor platform for detection of anomalies in human sleep patterns, Sensors. CNS 2016, Andò, B., Baldini, F., Di Natale, C., Marrazza, G., and Siciliano, P., Eds., Lecture Notes in Electrical Engineering, vol. 431, Cham: Springer, 2018, pp. 276–285. https://doi.org/10.1007/978-3-319-55077-0_36
Piltaver, R., Cvetkovic, B., and Kaluža, B., Denoising human-motion trajectories captured with ultra-wideband real-time location system, Informatica, 2015, vol. 39, no. 3, pp. 311–322.
Diraco, G., Leone, A., and Siciliano, P., Radar sensing technology for fall detection under near real-life conditions, 2nd IET Int. Conf. on Technologies for Active and Assisted Living (TechAAL 2016), London, 2016, Institution of Engineering and Technology, 2016, vol. 2016, no. 4, pp. 1–6. https://doi.org/10.1049/ic.2016.0054
García-Restrepo, J., Ariza-Colpas, P.P., Butt-Aziz, S., Piñeres-Melo, M.A., Naz, S., and De-La-Hoz-Franco, E., Evaluating techniques based on supervised learning methods in casas kyoto dataset for human activity recognition, Computer Information Systems and Industrial Management, Saeed, K., Dvorský, J., Nishiuchi, N., and Fukumoto, M., Eds., Lecture Notes in Computer Science, vol. 14164, Cham: Springer, 2023, pp. 253–269. https://doi.org/10.1007/978-3-031-42823-4_19
Persson, J., Johansson, G., Arvidsson, I., Östlund, B., Holgersson, C., Persson, R., and Rydenfält, C., A framework for participatory work environment interventions in home care–Success factors and some challenges, BMC Health Services Res., 2020, vol. 22, no. 1, p. 345. https://doi.org/10.1186/s12913-022-07710-2
Patricia, A.-C.P., Enrico, V., Shariq, B.A., De La Hoz Franco, E., Alberto, P.-M.M., Isabel, O.-C.A., Tariq, M.I., Restrepo, J.K.G., and Fulvio, P., Machine learning applied to datasets of human activity recognition: Data analysis in health care, Curr. Med. Imaging Rev., 2023, vol. 19, no. 1, pp. 46–64. https://doi.org/10.2174/1573405618666220104114814
Biau, G. and Scornet, E., A random forest guided tour, TEST, 2016, vol. 25, no. 2, pp. 197–227. https://doi.org/10.1007/s11749-016-0481-7
Tehrany, M.S., Jones, S., Shabani, F., Martínez-Álvarez, F., and Tien Bui, D., A novel ensemble modeling approach for the spatial prediction of tropical forest fire susceptibility using LogitBoost machine learning classifier and multi-source geospatial data, Theor. Appl. Climatology, 2019, vol. 137, nos. 1–2, pp. 637–653. https://doi.org/10.1007/s00704-018-2628-9
Friedman, J., Hastie, T., and Tibshirani, R., Additive logistic regression: A statistical view of boosting (with discussion and a rejoinder by the authors), Ann. Stat., 2000, vol. 28, no. 2, pp. 337–407. https://doi.org/10.1214/aos/1016218223
Sarker, I.H., Deep cybersecurity: A comprehensive overview from neural network and deep learning perspective, SN Comput. Sci., 2021, vol. 2, no. 3, p. 154. https://doi.org/10.1007/s42979-021-00535-6
Weerasuriya, A.U., Zhang, X., Lu, B., Tse, K.T., and Liu, C.H., A Gaussian process-based emulator for modeling pedestrian-level wind field, Building Environ., 2021, vol. 188, p. 107500. https://doi.org/10.1016/j.buildenv.2020.107500
Sun, P., Reid, M.D., and Zhou, J., An improved multiclass LogitBoost using adaptive-one-vs-one, Mach. Learn., 2014, vol. 97, no. 3, pp. 295–326. https://doi.org/10.1007/s10994-014-5434-3
Butt, S.A., Khalid, A., and Ali, A., A software development for medical with a multiple decision taking functionalities, Adv. Eng. Software, 2022, vol. 174, p. 103294. https://doi.org/10.1016/j.advengsoft.2022.103294
Schwarzenbach, H., Da Silva, A.M., Calin, G., and Pantel, K., Data normalization strategies for microRNA quantification, Clin. Chem., 2015, vol. 61, no. 11, pp. 1333–1342. https://doi.org/10.1373/clinchem.2015.239459
Ernesto, E., Johan, M., Dixon, S., Emiro, D.-L.-H.-F., Inirida, A., and Carlos, H., Neural networks as tool to improve the intrusion detection system, Computer Information Systems and Industrial Management, Saeed, K. and Dvorský, J., Eds., Lecture Notes in Computer Science, vol. 12883, Cham: Springer, 2021, pp. 124–139. https://doi.org/10.1007/978-3-030-84340-3_10
Funding
This research has been supported under the REMIND project Marie Sklodowska-Curie EU Framework for Research and Innovation Horizon 2020, under grant agreement no. 734355 Project REMIND.
Author information
Authors and Affiliations
Contributions
Authors contributed as follows:
Conceptualization—Zhoe Comas-González (Z.C.), Kåre Synnes (K.S.),
Andres Sanchez-Comas (A.S.), Aurelian Joliet (A.J.) and Emiro Delahoz-Franco (E.D.);
Methodology—Z.C., K.S. and Johan Mardini (J.M.); Data set creation—Z.C. and A.J.;
Formal analysis—Z.C., E.D. and J.M.;
Data curation—Z.C., Diego Molina-Estren (D.M.), J.M. and Daniela Ospino-Balcázar (D.O.);
Writing—original draft preparation, Z.C., A.S. and J.M;
Writing—review and editing, Z.C., Gabiel Piñeres-Espitia (G.P.) and A.S.;
Project administration—K.S. and E.D.
Corresponding authors
Ethics declarations
The authors of this work declare that they have no conflicts of interest.
Additional information
Publisher’s Note.
Allerton Press remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Comas-González, Z., Mardini, J., Butt, S.A. et al. Sensors and Machine Learning Algorithms for Location and POSTURE Activity Recognition in Smart Environments. Aut. Control Comp. Sci. 58, 33–42 (2024). https://doi.org/10.3103/S0146411624010048
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0146411624010048