Ir al contenido

Documat

Wearable Sensors and MET Features: The importance of Preprocessing and Understanding the Data

  • Maria Bermudez-Edo [1] Árbol académico ; Daniel Bolaños-Martinez [1] ; Alberto Durán López [1] ; José Luis Garrido [1] Árbol académico ; Maria Jose Rodriguez Fortiz [1]
    1. [1] Universidad de Granada

      Universidad de Granada

      Granada, España

  • Localización: IJIMAI, ISSN-e 1989-1660, Vol. 10, Nº. 1, 2026
  • Idioma: inglés
  • DOI: 10.9781/ijimai.2026.2257
  • Enlaces
  • Resumen

    • Discerning user activities with wearable devices is important to monitor people's behavior and even for developing personalized strategies to prevent some diseases, which has significant implications for healthcare systems. The metabolic equivalent of the task (MET), a measure of the energy cost of physical activities, is a good indicator to discern different activities. However, there is no established formula for calculating the MET. Some works have used several features to approximate the MET, such as the filtered acceleration (ACCfil) or the percentage of the heart rate reserve (%HRR). However, none of them have studied the importance of each of these features in the accuracy of activity classification. This study investigates the impact of different preprocessing techniques on activity recognition accuracy, such as filtering the acceleration to obtain the feature ACCfil. To that end, we performed several experiments with different features and machine learning algorithms to detect the activities. Our results indicate that incorporating features such as ACCfil, HRR, and ratio of unfiltered to filtered acceleration (RUF) improves activity recognition accuracy in some cases up to 166.67%. These features are particularly useful for challenging activities such as stair climbing or household activities. These findings, with their direct implications for developing more accurate activity recognition models with wearable devices, underscore the importance of preprocessing techniques and feature integration.

  • Referencias bibliográficas
    • [1] J. F. Sallis, D. Adlakha, A. Oyeyemi, D. Salvo, “An international physical activity and public health research agenda to inform coronavirus...
    • [2] M. Izquierdo, R. Merchant, J. Morley, S. Anker, I. Aprahamian, H. Arai, M. Aubertin-Leheudre, R. Bernabei, E. Cadore, M. Cesari, others,...
    • [3] K. Ito, Y. Suzuki, T. Sakaguchi, K. Fujiwara, Y. Nishii, H. Yasui, O. Taguchi, O. Hataji, “Physical Activity Using a Wearable Device as...
    • [4] N. Aguilar-Farias, W. J. Brown, T. L. Skinner, G. G. Peeters, “Metabolic equivalent values of common daily activities in middle-age and...
    • [5] A. Davoudi, M. T. Mardini, D. Nelson, F. Albinali, S. Ranka, P. Rashidi, T. M. Manini, others, “The effect of sensor placement and number...
    • [6] F. Tokmak, T. Koivisto, O. Lahdenoja, T. Vasankari, S. Jaakkola, K. E. J. Airaksinen, “Mechanocardiography detects improvement of systolic...
    • [7] M. Sevil, M. Rashid, Z. Maloney, I. Hajizadeh, S. Samadi, M. R. Askari, N. Hobbs, R. Brandt, M. Park, L. Quinn, others, “Determining physical...
    • [8] F. Tokmak, B. Semiz, “Unveiling the Relationships Between Seismocardiogram Signals, Physical Activity Types and Metabolic Equivalent of...
    • [9] V. Dentamaro, V. Gattulli, D. Impedovo, F. Manca, “Human activity recognition with smartphone-integrated sensors: A survey,” Expert Systems...
    • [10] A. Uphill, K. L. Kendall, A. Fogarty, S. Guppy, H. Brown, T. Zomer, S. Parker, G. G. Haff, “Validity of Apple Watch, Garmin Forerunner...
    • [11] M. L. Danielsson, M. Vergeer, G. Plasqui, J. K. Baumgart, “Accuracy of the Apple Watch Series 4 and Fitbit Versa for Assessing Energy...
    • [12] M. Jetté, K. Sidney, G. Blümchen, “Metabolic equivalents (METS) in exercise testing, exercise prescription, and evaluation of functional...
    • [13] U. Verma, P. Tyagi, M. Kaur, “Artificial intelligence in human activity recognition: a review,” International Journal of Sensor Networks,...
    • [14] M. Nakanishi, S. Izumi, S. Nagayoshi, H. Kawaguchi, M. Yoshimoto, T. Shiga, T. Ando, S. Nakae, C. Usui, T. Aoyama, others, “Estimating...
    • [15] C. Lützner, H. Voigt, I. Roeder, S. Kirschner, J. Lützner, “Placement makes a difference: accuracy of an accelerometer in measuring step...
    • [16] D. R. Witt, R. A. Kellogg, M. P. Snyder, J. Dunn, “Windows into human health through wearables data analytics,” Current Opinion in Biomedical...
    • [17] N. M. Remillard, W. Hoogkamer, G. Layec, J. Sirard, “Validation of Exercise and Postexercise Energy Expenditure Estimates Using Hip and...
    • [18] J. Xie, D. Wen, L. Liang, Y. Jia, L. Gao, J. Lei, others, “Evaluating the validity of current mainstream wearable devices in fitness...
    • [19] A. Shcherbina, C. M. Mattsson, D. Waggott, H. Salisbury, J. W. Christle, T. Hastie, M. T. Wheeler, E. A. Ashley, “Accuracy in wrist-worn,...
    • [20] K. Ohkawara, Y. Oshima, Y. Hikihara, K. Ishikawa-Takata, I. Tabata, S. Tanaka, “Real-time estimation of daily physical activity intensity...
    • [21] N. Koizumi, H. Ogata, Y. Negishi, H. Nagayama, M. Kaneko, K. Kiyono, N. Omi, “Energy Expenditure of Disaster Relief Operations...",...
    • [23] I. M. Pires, F. Hussain, G. Marques, N. M. Garcia, “Comparison of machine learning techniques for the identification of human activities...
    • [24] Ç. B. Erda, I. Atasoy, K. Açici, H. O, “Integrating features for accelerometerbased activity recognition,” Procedia Computer Science,...
    • [25] A. K. Panja, A. Rayala, A. Agarwala, S. Neogy, C. Chowdhury, “A hybrid tuple selection pipeline for smartphone based Human Activity Recognition,”...
    • [26] A. Poli, G. Cosoli, L. Scalise, S. Spinsante, “Impact of wearable measurement properties and data quality on ADLs classification accuracy,”...
    • [27] O. Barut, L. Zhou, Y. Luo, “Multitask LSTM model for human activity recognition and intensity estimation using wearable sensor data,”...
    • [28] T. Stewart, A. Narayanan, L. Hedayatrad, J. Neville, L. Mackay, S. Duncan, “A Dual-Accelerometer System for Classifying Physical Activity...
    • [29] J. Lu, X. Zheng, M. Sheng, J. Jin, S. Yu, “Efficient human activity recognition using a single wearable sensor,” IEEE Internet of Things...
    • [30] F. M. Garcia-Moreno, M. J. Rodriguez-Fortiz, P. Barnaghi, M. Bermudez- Edo, “Modelling time-series data generation with diffusion models...
    • [31] E. Ferrara, “Large language models for wearable sensor-based human activity recognition, health monitoring, and behavioral modeling:...
    • [32] N. Gupta, S. K. Gupta, R. K. Pathak, V. Jain, P. Rashidi, J. S. Suri, “Human activity recognition in artificial intelligence framework:...
    • [33] P. Kumar, S. Chauhan, L. K. Awasthi, “Human activity recognition (har) using deep learning: Review, methodologies, progress and future...
    • [34] S. Zhang, Y. Li, S. Zhang, F. Shahabi, S. Xia, Y. Deng, N. Alshurafa, “Deep learning in human activity recognition with wearable sensors:...
    • [35] M. Liandana, D. P. Hostiadi, G. A. Pradipta, “A New Approach for Human Activity Recognition (HAR) Using A Single Triaxial Accelerometer...
    • [36] N. M. Obiri, K. Van Laerhoven, “A Survey of LoRaWAN-integrated Wearable Sensor Networks for Human Activity Recognition: Applications,...
    • [37] Y. Li, G. Yang, Z. Su, S. Li, Y. Wang, “Human activity recognition based on multienvironment sensor data,” Information Fusion, vol. 91,...
    • [38] L. Liu, Y. Sun, X. Ge, “A Hybrid Multi-Person Fall Detection Scheme Based on Optimized YOLO and ST-GCN,” International Journal of Interactive...
    • [39] C. Contoli, V. Freschi, E. Lattanzi, “Energy-aware human activity recognition for wearable devices: A comprehensive review,” Pervasive...
    • [40] M. Heydarian, T. E. Doyle, “rWISDM: Repaired WISDM, a Public Dataset for Human Activity Recognition,” arXiv preprint arXiv:2305.10222,...
    • [41] M. Arshad, F. H. Jaskani, M. A. Sabri, F. Ashraf, M. Farhan, M. Sadiq, H. Raza, “Hybrid machine learning techniques to detect real time...
    • [42] D. Micucci, M. Mobilio, P. Napoletano, “Unimib shar: A dataset for human activity recognition using acceleration data from smartphones,”...
    • [43] G. Vavoulas, C. Chatzaki, T. Malliotakis, M. Pediaditis, M. Tsiknakis, “The mobiact dataset: Recognition of activities of daily living...
    • [44] N. Sikder, A.-A. Nahid, “KU-HAR: An open dataset for heterogeneous human activity recognition,” Pattern Recognition Letters, vol. 146,...
    • [45] S. Gashi, C. Min, A. Montanari, S. Santini, F. Kawsar, “A multidevice and multimodal dataset for human energy expenditure estimation...
    • [46] S. Chan, Y. Hang, C. Tong, A. Acquah, A. Schonfeldt, J. Gershuny, A. Doherty, “CAPTURE-24: A large dataset of wrist-worn activity tracker...
    • [47] D. M. Karantonis, M. R. Narayanan, M. Mathie, N. H. Lovell, B. G. Celler, “Implementation of a real-time human movement classifier using...
    • [48] S. Ö. Arik, T. Pfister, “Tabnet: Attentive interpretable tabular learning,”vol. 35, no. 8, pp. 6679–6687, 2021, doi: https://doi.org/10.1609/aaai.v35i8.16826
    • [49] X. Huang, A. Khetan, M. Cvitkovic, Z. Karnin, “Tabtransformer: Tabular data modeling using contextual embeddings,” arXiv preprint arXiv:2012.06678,...
Fundación Dialnet

Mi Documat

Opciones de artículo

Opciones de compartir

Opciones de entorno