{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,19]],"date-time":"2026-09-19T16:06:19Z","timestamp":1789833979948,"version":"4.0.1"},"reference-count":46,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T00:00:00Z","timestamp":1782518400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministry of University and Research under the framework of PNC \u201cDARE\u2014Digital lifelong prevention project\u201d","award":["PNC0000002\u2014CUP B53C22006450001"],"award-info":[{"award-number":["PNC0000002\u2014CUP B53C22006450001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This paper presents research on a Predictive and Uncertainty Assessment Framework (PUAF), providing a comparative analysis of two prominent methods, Monte Carlo (MC) Dropout and Bootstrap-based models, used in uncertainty estimation techniques of Neural Network predictions of human activity recognition using accelerometer data. Unlike traditional studies that optimize classification accuracy, this work emphasizes uncertainty quantification to enhance model reliability, particularly for critical health-related activities. Among the five activity classes of Sit, Sleep, Walk, Cough and Fall, this work concentrates on the Cough and Fall cases. The study exploits acceleration data from a wearable device positioned on the user\u2019s chest, with features derived from three-axis motion measurements. Synthetic datasets are generated by systematically introducing noise variations, added to the original dataset across all axes, to assess robustness under real-world conditions. Each uncertainty estimation method estimates the probabilities for the five different classes along with the corresponding 95% confidence intervals to quantify the prediction uncertainty. A detailed evaluation is conducted by analyzing the average width of these confidence intervals across different noise levels, identifying the most reliable feature and model combination. Both the MC Dropout and Bootstrap enhance model robustness and uncertainty awareness under noisy sensor conditions. The MC Dropout provides sharper and more sensitive uncertainty estimates, while the Bootstrap yields more stable and better-calibrated predictions. The evaluation using the proposed PUAF demonstrates that each method offers distinct advantages, highlighting the importance of uncertainty quantification for reliable wearable-based HAR systems.<\/jats:p>","DOI":"10.3390\/s26134081","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T05:49:33Z","timestamp":1782712173000},"page":"4081","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Comparative Uncertainty Estimation in Neural Network Analysis of Wearable Sensor Signal for Cough and Fall Detection"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3622-4327","authenticated-orcid":false,"given":"Minh Long","family":"Hoang","sequence":"first","affiliation":[{"name":"Department of Engineering and Architecture, University of Parma, 43124 Parma, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1910-7575","authenticated-orcid":false,"given":"Cesare","family":"Svelto","sequence":"additional","affiliation":[{"name":"Department of Electronics, Information and Bioengineering, Politecnico di Milano, 20133 Milano, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8944-2152","authenticated-orcid":false,"given":"Paolo","family":"Ciampolini","sequence":"additional","affiliation":[{"name":"Department of Engineering and Architecture, University of Parma, 43124 Parma, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0705-527X","authenticated-orcid":false,"given":"Guido","family":"Matrella","sequence":"additional","affiliation":[{"name":"Department of Engineering and Architecture, University of Parma, 43124 Parma, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7399-1827","authenticated-orcid":false,"given":"Giovanni","family":"Chiorboli","sequence":"additional","affiliation":[{"name":"Department of Engineering and Architecture, University of Parma, 43124 Parma, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"93450","DOI":"10.1109\/ACCESS.2024.3422831","article-title":"Simple to Complex, Single to Concurrent Sensor-Based Human Activity Recognition: Perception and Open Challenges","volume":"12","author":"Ankalaki","year":"2024","journal-title":"IEEE Access"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"25579","DOI":"10.1109\/JSEN.2023.3312478","article-title":"An Efficient and Lightweight Deep Learning Model for Human Activity Recognition on Raw Sensor Data in Uncontrolled Environment","volume":"23","author":"Choudhury","year":"2023","journal-title":"IEEE Sens. J."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Hoang, M.L., Carratu, M., Ugwiri, M.A., Paciello, V., and Pietrosanto, A. (2020, January 7\u20139). A New Technique for Optimization of Linear Displacement Measurement Based on MEMS Accelerometer. Proceedings of the 2020 International Semiconductor Conference (CAS), Sinaia, Romania.","DOI":"10.1109\/CAS50358.2020.9268038"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Hoang, M.L., and Pietrosanto, A. (2020, January 7\u20139). An Effective Method on Vibration Immunity for Inclinometer Based on MEMS Accelerometer. Proceedings of the 2020 International Semiconductor Conference (CAS), Sinaia, Romania.","DOI":"10.1109\/CAS50358.2020.9267997"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Hoang, M.L., Carrat\u00f9, M., Paciello, V., and Pietrosanto, A. (2023). Fusion Filters between the No Motion No Integration Technique and Kalman Filter in Noise Optimization on a 6DoF Drone for Orientation Tracking. Sensors, 23.","DOI":"10.3390\/s23125603"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Hoang, M.L., Pietrosanto, A., Iacono, S.D., and Paciello, V. (2020, January 25\u201328). Pre-Processing Technique for Compass-Less Madgwick in Heading Estimation for Industry 4.0. Proceedings of the 2020 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Dubrovnik, Croatia.","DOI":"10.1109\/I2MTC43012.2020.9128969"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Hoang, M.L., Carratu, M., Paciello, V., and Pietrosanto, A. (2020, January 20\u201323). A New Orientation Method for Inclinometer Based on MEMS Accelerometer Used in Industry 4.0. Proceedings of the 2020 IEEE 18th International Conference on Industrial Informatics (INDIN), Warwick, UK.","DOI":"10.1109\/INDIN45582.2020.9442189"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"115859","DOI":"10.1016\/j.sna.2024.115859","article-title":"A Novel Design of a MEMS Resonant Accelerometer with Adjustable Sensitivity","volume":"379","author":"Zhang","year":"2024","journal-title":"Sens. Actuators A Phys."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"e39789","DOI":"10.2196\/39789","article-title":"Wearable Neck Surface Accelerometers for Occupational Vocal Health Monitoring: Instrument and Analysis Validation Study","volume":"6","author":"Lei","year":"2022","journal-title":"JMIR Form. Res."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Hoang, M.L., Matrella, G., and Ciampolini, P. (2024). Comparison of Machine Learning Algorithms for Heartbeat Detection Based on Accelerometric Signals Produced by a Smart Bed. Sensors, 24.","DOI":"10.3390\/s24061900"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Hoang, M.L., Carratu, M., Paciello, V., and Pietrosanto, A. (2021, January 17\u201320). Noise Attenuation on IMU Measurement For Drone Balance by Sensor Fusion. Proceedings of the 2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Glasgow, UK.","DOI":"10.1109\/I2MTC50364.2021.9460041"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"7755","DOI":"10.1109\/JSEN.2026.3656322","article-title":"Stagewise Optimization Framework for Fall Direction Recognition From Wearable Sensor Data Based on Machine Learning","volume":"26","author":"Hoang","year":"2026","journal-title":"IEEE Sens. J."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1016\/j.aej.2024.01.030","article-title":"A Multi-Channel Hybrid Deep Learning Framework for Multi-Sensor Fusion Enabled Human Activity Recognition","volume":"91","author":"Zhang","year":"2024","journal-title":"Alex. Eng. J."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Yu, Z., and Yan, W.Q. (2020, January 25\u201327). Human Action Recognition Using Deep Learning Methods. Proceedings of the 2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ), Wellington, New Zealand.","DOI":"10.1109\/IVCNZ51579.2020.9290594"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ifacol.2022.11.152","article-title":"Deep-Learning-Based Human Activity Recognition Using Wearable Sensors","volume":"55","author":"Nouriani","year":"2022","journal-title":"IFAC-PapersOnLine"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhang, S., Li, Y., Zhang, S., Shahabi, F., Xia, S., Deng, Y., and Alshurafa, N. (2022). Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances. Sensors, 22.","DOI":"10.3390\/s22041476"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"106035","DOI":"10.1109\/ACCESS.2025.3573937","article-title":"A Review of Developments and Metrology in Machine Learning and Deep Learning for Wearable IoT Devices","volume":"13","author":"Hoang","year":"2025","journal-title":"IEEE Access"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"S20","DOI":"10.1016\/j.gaitpost.2024.08.040","article-title":"Del Deep Learning Algorithms for the Recognition of Human Movements in Work Activities","volume":"114","author":"Palazzo","year":"2024","journal-title":"Gait Posture"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e57097","DOI":"10.2196\/57097","article-title":"Recognition of Daily Activities in Adults with Wearable Inertial Sensors: Deep Learning Methods Study","volume":"12","year":"2024","journal-title":"JMIR Med. Inform."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"6008104","DOI":"10.1109\/LSENS.2023.3326126","article-title":"Enhanced Complex Human Activity Recognition System: A Proficient Deep Learning Framework Exploiting Physiological Sensors and Feature Learning","volume":"7","author":"Choudhury","year":"2023","journal-title":"IEEE Sens. Lett."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"107441","DOI":"10.1016\/j.compbiomed.2023.107441","article-title":"Application of Uncertainty Quantification to Artificial Intelligence in Healthcare: A Review of Last Decade (2013\u20132023)","volume":"165","author":"Seoni","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2530","DOI":"10.1109\/TBME.2019.2963816","article-title":"Personalizing Activity Recognition Models Through Quantifying Different Types of Uncertainty Using Wearable Sensors","volume":"67","author":"Akbari","year":"2020","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_23","unstructured":"Huo, Z., PakBin, A., Chen, X., Hurley, N., Yuan, Y., Qian, X., Wang, Z., Huang, S., and Mortazavi, B. (2020). Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"343346","DOI":"10.1016\/j.aca.2024.343346","article-title":"Enhancing Decision Confidence in AI Using Monte Carlo Dropout for Raman Spectra Classification","volume":"1332","author":"Contreras","year":"2024","journal-title":"Anal. Chim. Acta"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1109\/TIM.2016.2627260","article-title":"Choosing Bootstrap Method for the Estimation of the Uncertainty of Traffic Noise Measurements","volume":"66","author":"Liguori","year":"2017","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Hoang, M.L., Nkembi, A.A., and Pham, P.L. (2023). Real-Time Risk Assessment Detection for Weak People by Parallel Training Logical Execution of a Supervised Learning System Based on an IoT Wearable MEMS Accelerometer. Sensors, 23.","DOI":"10.3390\/s23031516"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zeevi, T., Shwartz-Ziv, R., LeCun, Y., Staib, L.H., and Onofrey, J.A. (2025, January 11\u201315). Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.01933"},{"key":"ref_28","first-page":"1008010","article-title":"Bootstrap Method for Uncertainty Evaluation in Critical Dimension Small-Angle X-Ray Scattering","volume":"73","author":"Yang","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_29","unstructured":"Carreno-Medrano, P., Kuli\u0107, D., and Burke, M. (2022). Adapting Neural Models with Sequential Monte Carlo Dropout. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Basiri, S., Ollila, E., and Koivunen, V. (2014, January 2\u20135). Fast and Robust Bootstrap in Analysing Large Multivariate Datasets. Proceedings of the 2014 48th Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, USA.","DOI":"10.1109\/ACSSC.2014.7094385"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Milan\u00e9s-Hermosilla, D., Trujillo Codorni\u00fa, R., L\u00f3pez-Baracaldo, R., Sagar\u00f3-Zamora, R., Delisle-Rodriguez, D., Villarejo-Mayor, J.J., and N\u00fa\u00f1ez-\u00c1lvarez, J.R. (2021). Monte Carlo Dropout for Uncertainty Estimation and Motor Imagery Classification. Sensors, 21.","DOI":"10.3390\/s21217241"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"054002","DOI":"10.1088\/1361-6560\/abe04f","article-title":"A Comparison of Monte Carlo Dropout and Bootstrap Aggregation on the Performance and Uncertainty Estimation in Radiation Therapy Dose Prediction with Deep Learning Neural Networks","volume":"66","author":"Nguyen","year":"2021","journal-title":"Phys. Med. Biol."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Miu, T., Missier, P., and Plotz, T. (2015, January 26\u201328). Bootstrapping Personalised Human Activity Recognition Models Using Online Active Learning. Proceedings of the 2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing, Liverpool, UK.","DOI":"10.1109\/CIT\/IUCC\/DASC\/PICOM.2015.170"},{"key":"ref_34","unstructured":"Reyes-Ortiz, J., Anguita, D., Ghio, A., Oneto, L., and Parra, X. (2024, May 06). Human Activity Recognition Using Smartphones [Dataset]. Available online: https:\/\/archive.ics.uci.edu\/dataset\/240\/human+activity+recognition+using+smartphones."},{"key":"ref_35","unstructured":"WISDM (2025, February 05). Lab WISDM: WIreless Sensor Data Mining. Available online: https:\/\/www.cis.fordham.edu\/wisdm\/dataset.php."},{"key":"ref_36","unstructured":"Weiss, G. (2025, February 08). WISDM Smartphone and Smartwatch Activity and Biometrics Dataset. Available online: https:\/\/archive.ics.uci.edu\/dataset\/507\/wisdm+smartphone+and+smartwatch+activity+and+biometrics+dataset."},{"key":"ref_37","unstructured":"M5STACK (2024, November 15). M5StickC ESP32-PICO Mini IoT Development Kit. Available online: https:\/\/shop.m5stack.com\/products\/stick-c?srsltid=AfmBOoohU6hCEuJXfBeCX6FgbLDfF1aAgbrv9oolNHdX0FRo6WHovrcC&variant=43982750843137."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Ad\u0131n, V., Zhang, Y., Oelmann, B., and Bader, S. (2023, January 22\u201325). Tiny Machine Learning for Damage Classification in Concrete Using Acoustic Emission Signals. Proceedings of the 2023 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Kuala Lumpur, Malaysia.","DOI":"10.1109\/I2MTC53148.2023.10175972"},{"key":"ref_39","first-page":"1031","article-title":"Grid Search Hyperparameter Tuning in Additive Manufacturing Processes","volume":"35","author":"Ogunsanya","year":"2023","journal-title":"Manuf. Lett."},{"key":"ref_40","unstructured":"Agarap, A.F. (2018). Deep Learning Using Rectified Linear Units (ReLU). arXiv."},{"key":"ref_41","unstructured":"Ian, G., Yoshua, B., and Aaron, C. (2016). Deep Learning, MIT Press."},{"key":"ref_42","unstructured":"Yarin, G., and Zoubin, G. (2015). Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1007\/S0033312300003379","article-title":"B. Efron and R. J. Tibshirani (1993). An Introduction to the Bootstrap. New York: Chapman & Hall, xvi + 436 pp. ISBN 0-412-0423t-2, $50.00","volume":"63","author":"Markus","year":"1998","journal-title":"Psychometrika"},{"key":"ref_44","unstructured":"Maja, P. (2025). Understanding Model Calibration\u2014A Gentle Introduction and Visual Exploration of Calibration and the Expected Calibration Error (ECE). arXiv."},{"key":"ref_45","unstructured":"Chuan, G., Geoff, P., Yu, S., and Kilian, Q.W. (2017). On Calibration of Modern Neural Networks. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1145\/1964897.1964918","article-title":"Activity Recognition Using Cell Phone Accelerometers","volume":"12","author":"Kwapisz","year":"2011","journal-title":"ACM SIGKDD Explor. Newsl."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4081\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T05:56:23Z","timestamp":1782712583000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4081"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,27]]},"references-count":46,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26134081"],"URL":"https:\/\/doi.org\/10.3390\/s26134081","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,27]]}}}