{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T07:10:52Z","timestamp":1763536252665,"version":"build-2065373602"},"reference-count":50,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T00:00:00Z","timestamp":1712707200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Research, Development, and Innovation Fund of Hungary","award":["2019-1.3.1-KK-2019-00007","TKP2021-NKTA-36"],"award-info":[{"award-number":["2019-1.3.1-KK-2019-00007","TKP2021-NKTA-36"]}]},{"name":"Consolidator Researcher Program of \u00d3buda University","award":["2019-1.3.1-KK-2019-00007","TKP2021-NKTA-36"],"award-info":[{"award-number":["2019-1.3.1-KK-2019-00007","TKP2021-NKTA-36"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Diabetes mellitus (DM) is a persistent metabolic disorder associated with the hormone insulin. The two main types of DM are type 1 (T1DM) and type 2 (T2DM). Physical activity plays a crucial role in the therapy of diabetes, benefiting both types of patients. The detection, recognition, and subsequent classification of physical activity based on type and intensity are integral components of DM treatment. The continuous glucose monitoring system (CGMS) signal provides the blood glucose (BG) level, and the combination of CGMS and heart rate (HR) signals are potential targets for detecting relevant physical activity from the BG variation point of view. The main objective of the present research is the developing of an artificial intelligence (AI) algorithm capable of detecting physical activity using these signals. Using multiple recurrent models, the best-achieved performance of the different classifiers is a 0.99 area under the receiver operating characteristic curve. The application of recurrent neural networks (RNNs) is shown to be a powerful and efficient solution for accurate detection and analysis of physical activity in patients with DM. This approach has great potential to improve our understanding of individual activity patterns, thus contributing to a more personalized and effective management of DM.<\/jats:p>","DOI":"10.3390\/s24082412","type":"journal-article","created":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T06:07:46Z","timestamp":1712729266000},"page":"2412","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Physical Activity Detection for Diabetes Mellitus Patients Using Recurrent Neural Networks"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9879-5664","authenticated-orcid":false,"given":"Lehel","family":"D\u00e9nes-Fazakas","sequence":"first","affiliation":[{"name":"Physiological Controls Research Center, University Research and Innovation Center, Obuda University, 1034 Budapest, Hungary"},{"name":"Biomatics and Applied Artificial Intelligence Institute, John von Neumann Faculty of Informatics, Obuda University, 1034 Budapest, Hungary"},{"name":"Doctoral School of Applied Informatics and Applied Mathematics, Obuda University, 1034 Budapest, Hungary"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7260-5557","authenticated-orcid":false,"given":"Barbara","family":"Simon","sequence":"additional","affiliation":[{"name":"Physiological Controls Research Center, University Research and Innovation Center, Obuda University, 1034 Budapest, Hungary"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7225-4521","authenticated-orcid":false,"given":"\u00c1d\u00e1m","family":"Hartv\u00e9g","sequence":"additional","affiliation":[{"name":"Physiological Controls Research Center, University Research and Innovation Center, Obuda University, 1034 Budapest, Hungary"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3188-0800","authenticated-orcid":false,"given":"Levente","family":"Kov\u00e1cs","sequence":"additional","affiliation":[{"name":"Physiological Controls Research Center, University Research and Innovation Center, Obuda University, 1034 Budapest, Hungary"},{"name":"Biomatics and Applied Artificial Intelligence Institute, John von Neumann Faculty of Informatics, Obuda University, 1034 Budapest, Hungary"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6540-6525","authenticated-orcid":false,"given":"\u00c9va-Henrietta","family":"Dulf","sequence":"additional","affiliation":[{"name":"Physiological Controls Research Center, University Research and Innovation Center, Obuda University, 1034 Budapest, Hungary"},{"name":"Biomatics and Applied Artificial Intelligence Institute, John von Neumann Faculty of Informatics, Obuda University, 1034 Budapest, Hungary"},{"name":"Department of Automation, Faculty of Automation and Computer Science, Technical University of Cluj-Napoca, Memorandumului Str. 28, 400014 Cluj-Napoca, Romania"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6722-2642","authenticated-orcid":false,"given":"L\u00e1szl\u00f3","family":"Szil\u00e1gyi","sequence":"additional","affiliation":[{"name":"Physiological Controls Research Center, University Research and Innovation Center, Obuda University, 1034 Budapest, Hungary"},{"name":"Biomatics and Applied Artificial Intelligence Institute, John von Neumann Faculty of Informatics, Obuda University, 1034 Budapest, Hungary"},{"name":"Computational Intelligence Research Group, Sapientia Hungarian University of Transylvania, 540485 T\u00eergu Mure\u0219, Romania"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8038-2210","authenticated-orcid":false,"given":"Gy\u00f6rgy","family":"Eigner","sequence":"additional","affiliation":[{"name":"Physiological Controls Research Center, University Research and Innovation Center, Obuda University, 1034 Budapest, Hungary"},{"name":"Biomatics and Applied Artificial Intelligence Institute, John von Neumann Faculty of Informatics, Obuda University, 1034 Budapest, Hungary"}]}],"member":"1968","published-online":{"date-parts":[[2024,4,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Holt, R.I., Cockram, C., Flyvbjerg, A., and Goldstein, B.J. (2017). Textbook of Diabetes, John Wiley & Sons.","DOI":"10.1002\/9781118924853"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e000143","DOI":"10.1136\/bmjsem-2016-000143","article-title":"Update on the effects of physical activity on insulin sensitivity in humans","volume":"2","author":"Bird","year":"2017","journal-title":"BMJ Open Sport Exerc. Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1016\/j.jdiacomp.2016.12.015","article-title":"Fear of hypoglycemia: Influence on glycemic variability and self-management behavior in young adults with type 1 diabetes","volume":"31","author":"Quinn","year":"2017","journal-title":"J. Diabetes Its Complicat."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1016\/S1262-3636(08)73973-9","article-title":"Treatment of diabetes mellitus using an external insulin pump in clinical practice","volume":"34","author":"Jeandidier","year":"2008","journal-title":"Diabetes Metab."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"113","DOI":"10.2147\/DMSO.S29222","article-title":"The impact of brief high-intensity exercise on blood glucose levels","volume":"6","author":"Adams","year":"2013","journal-title":"Diabetes Metab. Syndr. Obes."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1038\/nrendo.2016.162","article-title":"Exercise-stimulated glucose uptake\u2014Regulation and implications for glycaemic control","volume":"13","author":"Sylow","year":"2017","journal-title":"Nat. Rev. Endocrinol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1016\/j.ifacol.2016.07.280","article-title":"The artificial pancreas: A dynamic challenge","volume":"49","author":"Stavdahl","year":"2016","journal-title":"IFAC-PapersOnLine"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1077","DOI":"10.1177\/1932296819869310","article-title":"Artificial pancreas systems and physical activity in patients with type 1 diabetes: Challenges, adopted approaches, and future perspectives","volume":"13","author":"Tagougui","year":"2019","journal-title":"J. Diabetes Sci. Technol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1007\/s004210100436","article-title":"Heart rate as an indicator of the intensity of physical activity in human adolescents","volume":"85","author":"Ekelund","year":"2001","journal-title":"Eur. J. Appl. Physiol."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Crema, C., Depari, A., Flammini, A., Sisinni, E., Haslwanter, T., and Salzmann, S. (2017, January 13\u201315). IMU-based solution for automatic detection and classification of exercises in the fitness scenario. Proceedings of the 2017 IEEE Sensors Applications Symposium (SAS), Glassboro, NJ, USA.","DOI":"10.1109\/SAS.2017.7894068"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"75","DOI":"10.3389\/fphys.2019.00075","article-title":"The key factors in physical activity type detection using real-life data: A systematic review","volume":"10","author":"Allahbakhshi","year":"2019","journal-title":"Front. Physiol."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Cescon, M., Choudhary, D., Pinsker, J.E., Dadlani, V., Church, M.M., Kudva, Y.C., Doyle, F.J., and Dassau, E. (2021). Activity detection and classification from wristband accelerometer data collected on people with type 1 diabetes in free-living conditions. Comput. Biol. Med., 135.","DOI":"10.1016\/j.compbiomed.2021.104633"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"205","DOI":"10.3389\/fendo.2014.00205","article-title":"Autonomic neuropathy in diabetes mellitus","volume":"5","author":"Verrotti","year":"2014","journal-title":"Front. Endocrinol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"251","DOI":"10.14797\/mdcj-14-4-251","article-title":"Cardiac autonomic neuropathy in diabetes mellitus","volume":"14","author":"Agashe","year":"2018","journal-title":"Methodist Debakey Cardiovasc. J."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"e3301","DOI":"10.1002\/dmrr.3301","article-title":"The relationship between glycaemic variability and cardiovascular autonomic dysfunction in patients with type 1 diabetes: A systematic review","volume":"36","author":"Helleputte","year":"2020","journal-title":"Diabetes\/Metab. Res. Rev."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Vijayan, V., Connolly, J.P., Condell, J., McKelvey, N., and Gardiner, P. (2021). Review of Wearable Devices and Data Collection Considerations for Connected Health. Sensors, 21.","DOI":"10.3390\/s21165589"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Liang, L., Kong, F.W., Martin, C., Pham, T., Wang, Q., Duncan, J., and Sun, W. (2017). Machine learning\u2013based 3-D geometry reconstruction and modeling of aortic valve deformation using 3-D computed tomography images. Int. J. Numer. Methods Biomed. Eng., 33.","DOI":"10.1002\/cnm.2827"},{"key":"ref_18","first-page":"749","article-title":"Explainable machine-learning predictions for the prevention of hypoxaemia during surgery","volume":"2","author":"Lundberg","year":"2018","journal-title":"Int. J. Numer. Methods Biomed. Eng."},{"key":"ref_19","first-page":"183","article-title":"Morphology-based vs unsupervised word clustering for training language models for Serbian","volume":"16","author":"Ostrogonac","year":"2019","journal-title":"Acta Polytech. Hung. J. Appl. Sci."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"229","DOI":"10.12700\/APH.17.3.2020.3.12","article-title":"Classification of Special Web Reviewers Based on Various Regression Methods","volume":"17","author":"Mach","year":"2020","journal-title":"Acta Polytech. Hung."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"167","DOI":"10.12700\/APH.21.2.2024.2.9","article-title":"Semantic Composition of Data Analytical Processes","volume":"21","year":"2024","journal-title":"Acta Polytech. Hung."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"A193","DOI":"10.2337\/db18-738-P","article-title":"Predicting Future Glucose Fluctuations Using Machine Learning and Wearable Sensor Data","volume":"67","author":"Hayeri","year":"2018","journal-title":"Diabetes"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Daskalaki, E., Diem, P., and Mougiakakou, S.G. (2016). Model-free machine learning in biomedicine: Feasibility study in type 1 diabetes. PLoS ONE, 11.","DOI":"10.1371\/journal.pone.0158722"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"e11030","DOI":"10.2196\/11030","article-title":"Data-Driven Blood Glucose Pattern Classification and Anomalies Detection: Machine-Learning Applications in Type 1 Diabetes","volume":"21","author":"Woldaregay","year":"2019","journal-title":"J. Med. Internet Res."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e10775","DOI":"10.2196\/10775","article-title":"Artificial intelligence for diabetes management and decision support: Literature review","volume":"20","author":"Contreras","year":"2018","journal-title":"J. Med. Internet Res."},{"key":"ref_26","first-page":"1","article-title":"Learning representations by back-propagating errors","volume":"5","author":"Rumelhart","year":"1988","journal-title":"Cogn. Model."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1482","DOI":"10.1177\/19322968221102183","article-title":"Detection of Meals and Physical Activity Events From Free-Living Data of People with Diabetes","volume":"17","author":"Askari","year":"2022","journal-title":"J. Diabetes Sci. Technol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1007\/s42452-021-04427-5","article-title":"Recurrent neural networks with long term temporal dependencies in machine tool wear diagnosis and prognosis","volume":"3","author":"Zeng","year":"2021","journal-title":"SN Appl. Sci."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"D\u00e9nes-Fazakas, L., Szil\u00e1gyi, L., Tasic, J., Kov\u00e1cs, L., and Eigner, G. (2020, January 5\u20137). Detection of physical activity using machine learning methods. Proceedings of the 2020 IEEE 20th International Symposium on Computational Intelligence and Informatics (CINTI), Budapest, Hungary.","DOI":"10.1109\/CINTI51262.2020.9305845"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"D\u00e9nes-Fazakas, L., Siket, M., Szil\u00e1gyi, L., Kov\u00e1cs, L., and Eigner, G. (2022). Detection of Physical Activity Using Machine Learning Methods Based on Continuous Blood Glucose Monitoring and Heart Rate Signals. Sensors, 22.","DOI":"10.3390\/s22218568"},{"key":"ref_31","unstructured":"(2020, January 21). TensorFlow Core v2.4.0. Available online: https:\/\/www.tensorflow.org\/api_docs."},{"key":"ref_32","unstructured":"(2020, January 21). Scikit-Learn User Guide. Available online: https:\/\/scikit-learn.org\/0.18\/_downloads\/scikit-learn-docs.pdf."},{"key":"ref_33","unstructured":"(2020, January 21). NumPy Documentation. Available online: https:\/\/numpy.org\/doc\/."},{"key":"ref_34","unstructured":"(2020, January 21). Pandas Documentation. Available online: https:\/\/pandas.pydata.org\/docs\/."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Razvan Bunescu, C.M., and Shubrook, J. (2013, January 4\u20137). Blood Glucose Prediction Using Physiological Models and Support Vector Regression. Proceedings of the 2013 12th International Conference on Machine Learning and Applications, Miami, FL, USA.","DOI":"10.1109\/ICMLA.2013.30"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Cho, K., van Merrienboer, B., Bahdanau, D., and Bengio, Y. (2014, January 25\u201329). Learning Phrase Representations using RNN Encoder\u2013Decoder for Statistical Machine Translation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar.","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"Schuster","year":"1997","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"Framewise phoneme classification with bidirectional LSTM and other neural network architectures","volume":"18","author":"Graves","year":"2005","journal-title":"Neural Netw."},{"key":"ref_40","unstructured":"Ioffe, S., and Szegedy, C. (2015). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1004988","DOI":"10.3389\/fncom.2022.1004988","article-title":"GAPCNN with HyPar: Global Average Pooling convolutional neural network with novel NNLU activation function and HYBRID parallelism","volume":"16","author":"Habib","year":"2022","journal-title":"Front. Comput. Neurosci."},{"key":"ref_42","unstructured":"Agarap, A.F. (2018). Deep learning using rectified linear units (relu). arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Kouretas, I., and Paliouras, V. (2019, January 13\u201315). Simplified Hardware Implementation of the Softmax Activation Function. Proceedings of the 2019 8th International Conference on Modern Circuits and Systems Technologies (MOCAST), Thessaloniki, Greece.","DOI":"10.1109\/MOCAST.2019.8741677"},{"key":"ref_44","unstructured":"Kingma, D.P., and Ba, J. (2017). Adam: A Method for Stochastic Optimization. arXiv."},{"key":"ref_45","unstructured":"Gordon-Rodriguez, E., Loaiza-Ganem, G., Pleiss, G., and Cunningham, J.P. (2020). Uses and Abuses of the Cross-Entropy Loss: Case Studies in Modern Deep Learning. arXiv."},{"key":"ref_46","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press. Available online: http:\/\/www.deeplearningbook.org."},{"key":"ref_47","first-page":"9971669","article-title":"SuperPruner: Automatic Neural Network Pruning via Super Network","volume":"2021","author":"Liu","year":"2021","journal-title":"Sci. Program."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"65","DOI":"10.12700\/APH.18.1.2021.1.5","article-title":"EEG-based Speech Activity Detection","volume":"18","year":"2021","journal-title":"Acta Polytech. Hung."},{"key":"ref_49","unstructured":"G\u00e9ron, A. (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, O\u2019Reilly Media."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Czmil, A., Czmil, S., and Mazur, D. (2019). A Method to Detect Type 1 Diabetes Based on Physical Activity Measurements Using a Mobile Device. Appl. Sci., 9.","DOI":"10.3390\/app9122555"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/8\/2412\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:25:30Z","timestamp":1760106330000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/8\/2412"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,10]]},"references-count":50,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2024,4]]}},"alternative-id":["s24082412"],"URL":"https:\/\/doi.org\/10.3390\/s24082412","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2024,4,10]]}}}