{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T12:49:02Z","timestamp":1776084542903,"version":"3.50.1"},"reference-count":52,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2021,1,2]],"date-time":"2021-01-02T00:00:00Z","timestamp":1609545600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Project of Henan Province Science and Technology Research and Development\uff1bProject of National Key Research and Development Project","award":["202102210135 and 2020YFB1712403"],"award-info":[{"award-number":["202102210135 and 2020YFB1712403"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Age-related health issues have been increasing with the rise of life expectancy all over the world. One of these problems is cognitive impairment, which causes elderly people to have problems performing their daily activities. Detection of cognitive impairment at an early stage would enable medical doctors to deepen diagnosis and follow-up on patient status. Recent studies show that daily activities can be used to assess the cognitive status of elderly people. Additionally, the intrinsic structure of activities and the relationships between their sub-activities are important clues for capturing the cognitive abilities of seniors. Existing methods perceive each activity as a stand-alone unit while ignoring their inner structural relationships. This study investigates such relationships by modelling activities hierarchically from their sub-activities, with the overall goal of detecting abnormal activities linked to cognitive impairment. For this purpose, recursive auto-encoders (RAE) and their linear vs. greedy and supervised vs. semi-supervised variants are adopted to model the activities. Then, abnormal activities are systematically detected using RAE\u2019s reconstruction error. Moreover, to apply RAEs for this problem, we introduce a new sensor representation called raw sensor measurement (RSM) that captures the intrinsic structure of activities, such as the frequency and the order of sensor activations. As real-world data are not accessible, we generated data by simulating abnormal behaviour, which reflects on cognitive impairment. Extensive experiments show that RAEs can be used as a decision-supporting tool, especially when the training set is not labelled to detect early indicators of dementia.<\/jats:p>","DOI":"10.3390\/s21010260","type":"journal-article","created":{"date-parts":[[2021,1,3]],"date-time":"2021-01-03T19:54:46Z","timestamp":1609703686000},"page":"260","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Detection of Dementia-Related Abnormal Behaviour Using Recursive Auto-Encoders"],"prefix":"10.3390","volume":"21","author":[{"given":"Damla","family":"Arifoglu","sequence":"first","affiliation":[{"name":"Department of Computer Science, University College London, London WC1E 6BT, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9070-6653","authenticated-orcid":false,"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic and Information, Zhongyuan University of Technology, Zhengzhou 450007, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdelhamid","family":"Bouchachia","sequence":"additional","affiliation":[{"name":"Department of Computing, Bournemouth University, Poole BH12 5BB, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,1,2]]},"reference":[{"key":"ref_1","unstructured":"Statistics, N. (2019). Overview of the UK Population: August 2019."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2017","DOI":"10.1007\/s10489-017-1062-5","article-title":"An improved extreme learning machine model for the prediction of human scenarios in smart homes","volume":"48","author":"Liouane","year":"2018","journal-title":"Appl. Intell."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1007\/s10489-009-0187-6","article-title":"Agent-based execution of personalised home care treatments","volume":"34","author":"Isern","year":"2011","journal-title":"Appl. Intell."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1016\/j.jalz.2011.03.008","article-title":"The diagnosis of mild cognitive impairment due to Alzheimer\u2019s disease: Recommendations from the National Institute on Aging","volume":"7","author":"Albert","year":"2011","journal-title":"Alzheimer Dement."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1016\/j.jalz.2013.02.003","article-title":"2013 Alzheimer\u2019s disease facts and figures","volume":"9","author":"Thies","year":"2013","journal-title":"Alzheimer Dement. J. Alzheimer Assoc."},{"key":"ref_6","first-page":"121","article-title":"Aging changes","volume":"9","author":"Wild","year":"2010","journal-title":"Geraotechnology"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1007\/s12652-015-0270-2","article-title":"A review of smart homes in healthcare","volume":"6","author":"Amiribesheli","year":"2015","journal-title":"J. Ambient. Intell. Humaniz. Comput."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Dawadi, P., Cook, D., and Schmitter-Edgecombe, M. (2014, January 13\u201317). Smart Home-based Longitudinal Functional Assessment. Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct Publication, Washington, DC, USA.","DOI":"10.1145\/2638728.2638813"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Riboni, D., Bettini, C., Civitarese, G., Janjua, Z.H., and Helaoui, R. (2015, January 23\u201327). Fine-grained recognition of abnormal behaviours for early detection of mild cognitive impairment. Proceedings of the 2015 IEEE International Conference on Pervasive Computing and Communications (PerCom), St. Louis, MO, USA.","DOI":"10.1109\/PERCOM.2015.7146521"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"121","DOI":"10.3233\/JAD-130272","article-title":"Detecting the Effect of Alzheimer\u2019s Disease on Everyday Motion Behaviour","volume":"38","author":"Kirste","year":"2014","journal-title":"J. Alzheimer Dis."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1097\/WAD.0000000000000069","article-title":"Comparison of an electronic and paper-based Montreal Cognitive Assessment tool","volume":"29","author":"Snowdon","year":"2015","journal-title":"Alzheimer Dis. Assoc. Disord."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1897","DOI":"10.1212\/WNL.0000000000002582","article-title":"Leisure-time physical activity associates with cognitive decline: The Northern Manhattan Study","volume":"86","author":"Willey","year":"2016","journal-title":"Neurology"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1108\/IJPCC-01-2015-0002","article-title":"Activities of daily life recognition using process representation modelling to support intention analysis","volume":"11","author":"Naeem","year":"2015","journal-title":"Int. J. Pervasive Comput. Commun."},{"key":"ref_14","unstructured":"Socher, R., Manning, C.D., and Ng, A.Y. (2010, January 10). Learning continuous phrase representations and syntactic parsing with recursive neural networks. Proceedings of the NIPS-2010 Deep Learning and Unsupervised Feature Learning Workshop, Whistler, BC, Canada."},{"key":"ref_15","unstructured":"Socher, R., Pennington, J., Huang, E.H., Ng, A.Y., and Manning, C.D. (2011, January 27\u201331). Semi-supervised Recursive Autoencoders for Predicting Sentiment Distributions. Proceedings of the Conference on Empirical Methods in Natural Language Processing, Edinburgh, UK."},{"key":"ref_16","unstructured":"Socher, R., Huval, B., Bhat, B., Manning, C.D., and Ng, A.Y. (2012, January 3\u20136). Convolutional-recursive Deep Learning for 3D Object Classification. Proceedings of the 25th International Conference on Neural Information Processing Systems, NIPS\u201912, Lake Tahoe, NV, USA."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1016\/j.pmcj.2009.06.008","article-title":"Fast Track Article: Assessing Everyday Life Behavioral Rhythms for the Older Generation","volume":"5","author":"Virone","year":"2009","journal-title":"Pervasive Mob. Comput."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1109\/TITB.2011.2113352","article-title":"Detection of abnormal living patterns for elderly living alone using support vector data description","volume":"15","author":"Lee","year":"2011","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"628","DOI":"10.1016\/j.patcog.2014.07.007","article-title":"A context-aware approach for long-term behavioural change detection and abnormality prediction in ambient assisted living","volume":"48","author":"Forkan","year":"2015","journal-title":"Pattern Recognit."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1016\/j.eswa.2016.02.030","article-title":"Detecting and exploring deviating behaviour of smart home residents","volume":"55","author":"Verikas","year":"2016","journal-title":"Expert Syst. Appl."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"480","DOI":"10.3414\/ME0592","article-title":"Assessing the quality of activities in a smart environment","volume":"48","author":"Cook","year":"2009","journal-title":"Methods Inf. Med."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Hammerla, N., Fisher, J., Andras, P., Rochester, L., Walker, R., and Plotz, T. (2015, January 25\u201330). PD Disease State Assessment in Naturalistic Environments Using Deep Learning. Proceedings of the twenty-ninth AAAI conference on artificial intelligence, Austin, TX, USA.","DOI":"10.1609\/aaai.v29i1.9484"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Janjua, Z.H., Riboni, D., and Bettini, C. (2016, January 4\u20138). Towards Automatic Induction of Abnormal Behavioral Patterns for Recognizing Mild Cognitive Impairment. Proceedings of the 31st Annual ACM Symposium on Applied Computing, Pisa, Italy.","DOI":"10.1145\/2851613.2851687"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/j.neucom.2016.05.110","article-title":"Modeling interaction in multi-resident activities","volume":"230","author":"Benmansour","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Tong, Y., Chen, R., and Gao, J. (2015). Hidden State Conditional Random Field for Abnormal Activity Recognition in Smart Homes. Entropy, 17.","DOI":"10.3390\/e17031358"},{"key":"ref_26","unstructured":"Arifoglu, D., and Bouchachia, A. (2017, January 24\u201326). Activity Recognition and Abnormal Behaviour Detection with Recurrent Neural Networks. Proceedings of the 14th International Conference on Mobile Systems and Pervasive Computing, Leuven, Belgium."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1016\/j.artmed.2019.01.005","article-title":"Detection of abnormal behaviour for dementia sufferers using Convolutional Neural Networks","volume":"94","author":"Arifoglu","year":"2019","journal-title":"Artif. Intell. Med."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Arifoglu, D., and Bouchachia, A. (2019, January 11\u201315). Abnormal Behaviour Detection for Dementia Sufferers via Transfer Learning and Recursive Auto-Encoders. Proceedings of the 2019 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), Kyoto, Japan.","DOI":"10.1109\/PERCOMW.2019.8730744"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.engappai.2019.103401","article-title":"Detecting indicators of cognitive impairment via Graph Convolutional Networks","volume":"89","author":"Arifoglu","year":"2020","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1017\/S135561771200149X","article-title":"Naturalistic assessment of everyday activities and prompting technologies in mild cognitive impairment","volume":"4","author":"Seelye","year":"2013","journal-title":"J. Int. Neuropsychol. Soc."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1302","DOI":"10.1109\/TSMC.2013.2252338","article-title":"Automated Cognitive Health Assessment Using Smart Home Monitoring of Complex Tasks","volume":"43","author":"Dawadi","year":"2013","journal-title":"IEEE Trans. Syst. Man, Cybern. Syst."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Nikamalfard, H., Zheng, H., Wang, H., Jeffers, P., Mulvenna, M., McCullagh, P., Martin, S., Wallace, J., Augusto, J., and Carswell, W. (2012, January 5\u20137). Knowledge discovery from activity monitoring to support independent living of people with early dementia. Proceedings of the 2012 IEEE-EMBS International Conference on Biomedical and Health Informatics, Hong Kong, China.","DOI":"10.1109\/BHI.2012.6211735"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Wallace, B., Goubran, R., Knoefel, F., Petriu, M., and McAvoy, A. (2014, January 1\u20134). Design of games for measurement of cognitive impairment. Proceedings of the IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI), Valencia, Spain.","DOI":"10.1109\/BHI.2014.6864318"},{"key":"ref_34","unstructured":"Pl\u00f6tz, T., Hammerla, N., and Olivier, P. (2011, January 16\u201322). Feature Learning for Activity Recognition in Ubiquitous Computing. Proceedings of the 22th International Joint Conference on Artificial Intelligence, Catalonia, Spain."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Ord\u00f3\u00f1ez, F.J., and Roggen, D. (2016). Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition. Sensors, 16.","DOI":"10.3390\/s16010115"},{"key":"ref_36","unstructured":"Hammerla, N.Y., Halloran, S., and Pl\u00f6tz, T. (2016, January 9\u201315). Deep, Convolutional, and Recurrent Models for Human Activity Recognition Using Wearables. Proceedings of the 25th International Joint Conference on Artificial Intelligence, IJCAI\u201916, New York, NY, USA."},{"key":"ref_37","unstructured":"Charissa, A., and Sung-Bae, C. (2015, January 24\u201326). Evaluation of deep convolutional neural network architectures for human activity recognition with smartphone sensors. Proceedings of the KIISE Korea Computer Congress, Jeju, Korea."},{"key":"ref_38","first-page":"10","article-title":"Research on Healthy Anomaly Detection Model Based on Deep Learning from Multiple Time-Series Physiological Signals","volume":"2016","author":"Wang","year":"2016","journal-title":"Sci. Program."},{"key":"ref_39","unstructured":"Paulus, R., Socher, R., and Manning, C.D. (2014, January 8\u201313). Global Belief Recursive Neural Networks. Proceedings of the 27th International Conference on Neural Information Processing Systems, Montreal, QC, Canada."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Zhou, C., and Paffenroth, R.C. (2017, January 13\u201317). Anomaly Detection with Robust Deep Autoencoders. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD \u201917, Halifax, NS, Canada.","DOI":"10.1145\/3097983.3098052"},{"key":"ref_41","unstructured":"Schreyer, M., Sattarov, T., Borth, D., Dengel, A., and Reimer, B. (2017). Detection of Anomalies in Large Scale Accounting Data using Deep Autoencoder Networks. arXiv."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Van Kasteren, T., Englebienne, G., and Kr\u00f6se, B.J.A. (2011). Human Activity Recognition from Wireless Sensor Network Data: Benchmark and Software. Act. Recognit. Pervasive Intell. Environ., 165\u2013186.","DOI":"10.2991\/978-94-91216-05-3_8"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/j.neucom.2016.12.049","article-title":"Unsupervised Learning of Sensor Topologies for Improving Activity Recognition in Smart Environments","volume":"234","author":"Twomey","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/MC.2012.328","article-title":"CASAS: A Smart Home in a Box","volume":"46","author":"Cook","year":"2013","journal-title":"Computer"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.1109\/TASE.2015.2471842","article-title":"Activity Discovery and Detection of Behavioral Deviations of an Inhabitant From Binary Sensors","volume":"12","author":"Saives","year":"2015","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1755","DOI":"10.1007\/s12652-017-0645-7","article-title":"A tailored smart home for dementia care","volume":"9","author":"Amiribesheli","year":"2018","journal-title":"J. Ambient. Intell. Humaniz. Comput."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Amiribesheli, M., and Bouchachia, A. (2015, January 15\u201317). Smart Homes Design for People with Dementia. Proceedings of the 2015 International Conference on Intelligent Environments, Prague, Czech Republic.","DOI":"10.1109\/IE.2015.33"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/0004-3702(90)90005-K","article-title":"Recursive Distributed Representations","volume":"46","author":"Pollack","year":"1990","journal-title":"Artif. Intell."},{"key":"ref_49","unstructured":"Fran\u00e7ois, C. (2020, October 21). Keras. Available online: https:\/\/github.com\/fchollet\/keras."},{"key":"ref_50","unstructured":"Theano Development Team (2016). Theano: A Python framework for fast computation of mathematical expressions. arXiv."},{"key":"ref_51","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A Method for Stochastic Optimization. arXiv."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1007\/s12652-016-0367-2","article-title":"Learning movement patterns of the occupant in smart home environments: An unsupervised learning approach","volume":"8","author":"Zhang","year":"2017","journal-title":"J. Ambient. Intell. Humaniz. Comput."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/1\/260\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:06:27Z","timestamp":1760159187000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/1\/260"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,2]]},"references-count":52,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,1]]}},"alternative-id":["s21010260"],"URL":"https:\/\/doi.org\/10.3390\/s21010260","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,2]]}}}