Background/Objectives: Activities of Daily Living (ADLs) are crucial for assessing an individual's autonomy, encompassing tasks such as eating, dressing, and moving around, among others. Predicting these activities is part of health monitoring, elderly care, and intelligent systems, improving quality of life, and facilitating early dependency detection, all of which are relevant components of personalized health and social care. However, the automatic classification of ADLs from sensor data remains challenging due to high variability in human behavior, sensor noise, and discrepancies in data acquisition protocols. These challenges limit the accuracy and applicability of existing solutions. This study details the modeling and evaluation of real-time ADL classification models based on batch learning (BL) and stream learning (SL) algorithms. Methods: The methodology followed is the Cross-Industry Standard Process for Data Mining (CRISP-DM). The models were trained with a comprehensive dataset integrating 23 ADL-centric datasets using accelerometers and gyroscopes data. The data were preprocessed by applying normalization and sampling rate unification techniques, and finally, relevant sensor locations on the body were selected. Results: After cleaning and debugging, a final dataset was generated, containing 238,990 samples, 56 activities, and 52 columns. The study compared models trained with BL and SL algorithms, evaluating their performance under various classification scenarios using accuracy, area under the curve (AUC), and F1-score metrics. Finally, a mobile application was developed to classify ADLs in real time (feeding data from a dataset). Conclusions: The outcome of this study can be used in various data science projects related to ADL and Human activity recognition (HAR), and due to the integration of diverse data sources, it is potentially useful to address bias and improve generalizability in Machine Learning models. The principal advantage of online learning algorithms is dynamically adapting to data changes, representing a significant advance in personal autonomy and health care monitoring.

1st Medical Faculty Charles University Prague 12800 Prague Czech Republic

eHealth Competence Center Bavaria Deggendorf Institute of Technology 94469 Deggendorf Germany

Medical Faculty University of Regensburg 93053 Regensburg Germany

Telematics Engineering Research Group Telematics Department Universidad del Cauca Popayán 190002 Colombia

Zobrazit více v PubMed

Blobel B., Ruotsalainen P. Future pHealth Ecosystem-Holistic View on Privacy and Trust. J. Pers. Med. 2023;13:1048. doi: 10.3390/jpm13071048. PubMed DOI PMC

Blobel B., Ruotsalainen P., Lopez D.M., Oemig F. Requirements and Solutions for Personalized Health Systems. In: Blobel B., Goossen W., editors. pHealth 2017. Volume 237. IOS Press; Amsterdam, The Netherlands: Berlin, Germany: Oxford, UK: Tokyo, Japan: Washington, DC, USA: 2017. pp. 3–21. (Series Studies in Health Technology and Informatics). PubMed

Kamal S., Alhasson H.F., Alnusayri M., Alatiyyah M., Aljuaid H., Jalal A., Liu H. Vision Sensor for Automatic Recognition of Human Activities via Hybrid Features and Multi-Class Support Vector Machine. Sensors. 2025;25:200. doi: 10.3390/s25010200. PubMed DOI PMC

Hayat A., Fernando M.D., Bhuyan B.P., Tomar R. Human Activity Recognition for Elderly People Using Machine and Deep Learning Approaches. Information. 2022;13:275. doi: 10.3390/info13060275. DOI

Javeed M., Jalal A. Deep Activity Recognition based on Patterns Discovery for Healthcare Monitoring; Proceedings of the 2023 4th International Conference on Advancements in Computational Sciences (ICACS); Lahore, Pakistan. 20–22 February 2023; Piscataway, NJ, USA: Institute of Electrical and Electronics Engineers Inc.; 2023. DOI

Ray A., Kolekar M.H., Balasubramanian R., Hafiane A. Transfer Learning Enhanced Vision-based Human Activity Recognition: A Decade-long Analysis. Int. J. Inf. Manag. Data Insights. 2023;3:100142. doi: 10.1016/j.jjimei.2022.100142. DOI

Hanzla M., Wahid W., Jalal A. Robust Human Pose Estimation and Action Recognition Over Multi-level Perceptron; Proceedings of the 2024 3rd International Conference on Emerging Trends in Electrical, Control, and Telecommunication Engineering (ETECTE); Lahore, Pakistan. 26–27 November 2024; pp. 1–6. DOI

Ghadi Y.Y., Javeed M., Alarfaj M., Al Shloul T., Alsuhibany S.A., Jalal A., Kamal S., Kim D.-S. MS-DLD: Multi-Sensors Based Daily Locomotion Detection via Kinematic-Static Energy and Body-Specific HMMs. IEEE Access. 2022;10:23964–23979. doi: 10.1109/ACCESS.2022.3154775. DOI

Geravesh S., Rupapara V. Artificial neural networks for human activity recognition using sensor based dataset. Multimed. Tools Appl. 2023;82:14815–14835. doi: 10.1007/s11042-022-13716-z. DOI

Bukht T.F.N., Jalal A., Rahman H. Enhanced Human Interaction Recognition Framework using Pyramid Matching and Deep Neural Network; Proceedings of the 2024 3rd International Conference on Emerging Trends in Electrical, Control, and Telecommunication Engineering (ETECTE); Lahore, Pakistan. 26–27 November 2024; pp. 1–6. DOI

Ferrari A., Micucci D., Mobilio M., Napoletano P. Deep learning and model personalization in sensor-based human activity recognition. J. Reliab. Intell. Environ. 2023;9:27–39. doi: 10.1007/s40860-021-00167-w. DOI

Javeed M., Mudawi N.A., Alabduallah B.I., Jalal A., Kim W. A Multimodal IoT-Based Locomotion Classification System Using Features Engineering and Recursive Neural Network. Sensors. 2023;23:4716. doi: 10.3390/s23104716. PubMed DOI PMC

Uribe G., Lopez D.M., Blobel B. Towards Automated Biomedical Ontology Harmonization. In: Blobel B., Sauermann S., Mense A., editors. pHealth 2014. Volume 200. IOS Press; Amsterdam, The Netherlands: Berlin, Germany: Oxford, UK: Tokyo, Japan: Washington, DC, USA: 2014. pp. 62–68. (Series Studies in Health Technology and Informatics). PubMed

Ceron J., Lopez D.M. Human activity recognition supported on indoor localization: A Systematic Review. In: Blobel B., Yang B., editors. pHealth 2018. Volume 249. IOS Press; Amsterdam, The Netherlands: Berlin, Germany: Oxford, UK: Tokyo, Japan: Washington, DC, USA: 2018. pp. 93–101. (Series Studies in Health Technology and Informatics). PubMed

Reiss A., Stricker D. Creating and benchmarking a new dataset for physical activity monitoring; Proceedings of the Pr ceedings of the 5th International Conference on Pervasive Technologies Related to Assistive Environments; Heraklion, Greece. 6–8 June 2012; pp. 1–8.

Lima W.S., Bragança H.L., Souto E.J. NOHAR-NOvelty discrete data stream for Human Activity Recognition based on smartphones with inertial sensors. Expert Syst. Appl. 2021;166:114093. doi: 10.1016/j.eswa.2020.114093. DOI

Miranda L., Viterbo J., Bernardini F. Advances in Soft Computing. Springer; Berlin/Heidelberg, Germany: 2020. Impact of Memory Control on Batch Learning in Human Activity Recognition Scenario in Comparison to Data Stream Learning; pp. 145–157.

Bifet A., Gavalda R., Holmes G., Pfahringer B. Machine Learning for Data Streams: With Practical Examples in MOA. MIT Press; Cambridge, MA, USA: 2018.

Amezzane I., Fakhri Y., Aroussi M.E., Bakhouya M. Comparative Study of Batch and Stream Learning for Online Smartphone-based Human Activity Recognition. In: Ben Ahmed M., Boudhir A., Younes A., editors. Innovations in Smart Cities Applications Edition 2. SCA 2018. Springer; Cham, Switzerland: 2018. Lecture Notes in Intelligent Transportation and Infrastructure.

Wirth R. CRISP-DM: Towards a Standard Process Model for Data Mining; Proceedings of the Fourth International Conference on the Practical Application of Knowledge Discovery and Data Mining; Virtual Event. 6–10 July 2020; pp. 29–39.

Final Dataset (A Comprehensive Dataset for Activities of Daily Living (ADL) Research by Unifying and Processing Multiple Data Sources) [(accessed on 22 September 2024)]. Available online: https://www.kaggle.com/datasets/dgomez216/unin-dataset-trabajo-de-grado.

Peccatiello R.B., Gondim J.J.C., Garcia L.P.F. Applying One-Class Algorithms for Data Stream-Based Insider Threat Detection. IEEE Access. 2023;11:70560–70573. doi: 10.1109/ACCESS.2023.3293825. DOI

Reyes-Ortiz J.L., Anguita D., Oneto L., Parra X. Smartphone-Based Recognition of Human Activities and Postural Transitions. UCI Mach. Learn. Repos. 2015 doi: 10.24432/C54G7M. DOI

Vaizman Y., Ellis K., Lanckriet G. Recognizing detailed human context in the wild from smartphones and smartwatches. IEEE Pervasive Comput. 2017;16:62–74. doi: 10.1109/MPRV.2017.3971131. DOI

Reiss A. PAMAP2 Physical Activity Monitoring. UCI Mach. Learn. Repos. 2012:567–572. doi: 10.24432/C5NW2H. DOI

Saha S.S., Rahman S., Rasna M.J., Islam A.M., Ahad A.R. DU-MD: An open-source human action dataset for ubiquitous wearable sensors; Proceedings of the 2018 Joint 7th International Conference on Informatics, Electronics and Vision and 2nd International Conference on Imaging, Vision and Pattern Recognition, ICIEV-IVPR; Kitakyushu, Japan. 25–29 June 2018; Piscataway, NJ, USA: Institute of Electrical and Electronics Engineers Inc.; 2018. pp. 567–572. DOI

Flutter Documentation. [(accessed on 25 October 2024)]. Available online: https://flutter.dev/

Flask Documentation. [(accessed on 25 October 2024)]. Available online: https://flask.palletsprojects.com/en/stable/

Amazon Web Services. [(accessed on 25 October 2024)]. Available online: https://aws.amazon.com/es/

Arlot S., Celisse A. A survey of cross-validation procedures for model selection. Stat. Surv. 2010;4:40–79. doi: 10.1214/09-SS054. DOI