Novelty detection algorithms to help identify abnormal activities in the daily lives of elderly people
Keywords:
Activities of Daily Living, Machine Learning Algorithms, Novelty DetectionAbstract
The population’s life expectancy is increasing, and this scenario will bring challenges to be faced in the coming decades to provide healthy and inclusive aging. At this stage of life, several common health conditions, chronic illnesses, and disabilities affect the individual’s physical and mental health and prevent him from carrying out Activities of Daily Living. In this context, this article presents a comparative study between some Machine Learning algorithms used to identify behavioral abnormalities based on ADL (Activities of Daily Living), through the Novelty Detection technique. ADL data were used to create a model that defines the baseline behavior of an elderly person, and new observations, to verify significant changes in behavior, are classified as outliers or abnormal. The Local Outlier Factor, One-class Support Vector Machine, Robust Covariance, and Isolation Forest algorithms were analyzed, and the Local Outlier Factor obtained the best result, reaching a precision and F1-Score of 96%.
Downloads
References
WHO – World Health Organization, 2021. Aging and Health. Accessed on: November 16th, 2022 [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/ageing-andhealth.
WHO – World Health Organization, 2017. 10 Facts on Ageing and Health. Accessed on: January 10th,2023. [Online] Available: https://www.who.int/news-room/factsheets/detail/10-facts-on-ageing-and-health.
NCOA - National Council on Aging, 2021. Chronic Conditions for Older Adults. Accessed on January 3rd, 2023. [Online] Available: https://www.ncoa.org/article/the-top-10-most-common-chronic-conditions-in-older-adults.
JCHS – Join Center for Housing Studies of Harvard University, 2016. Accessed on February 12th, 2023. [Online] Available: https://www.jchs.harvard.edu/research-areas/reports/projections-and-implications-housing-growing-populationolder-households.
UN - United Nations, 2022. Aging and disability. Accessed on December 18th, 2022. [Online] Available: https://www.un.org/development/desa/disabilities/disability-andageing.
R. M., Gomathi and M. Nithya. “Human activity recognition with smartphones using machine learning process”. Proc. Of International Conference on Computer Communication and Informatics (ICCCI), Hammamet, Tunisia, 2022, pp. 1-10. DOI: 10.1109/ICCCI54379.2022.9740773.
D. Arifoglu and A. Bouchachia, “A. Detection of abnormal behavior for dementia sufferers using Convolutional Neural Networks”. Artificial intelligence in medicine, v. 94, p. 88-95, 2019. DOI: 10.1016/j.artmed.2019.01.005.
S. W. Yahaya, A. Lotfi, A. and M. Mahmud, “Detecting anomaly and its sources in activities of daily living”. SN Computer Science, v. 2, n. 1, p. 1-18, 2021. DOI: 10.1007/s42979-020-00418-2.
B. Ouafae, L. Oumaima, R. Mariam and L. Abdelouahid, "Novelty Detection Review State of Art and Discussion of New Innovations in The Main Application Domains,"2020 1st International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET), Meknes, Morocco, 2020, pp. 1-7, DOI 10.1109/IRASET48871.2020.9092147.
V. R. Leithardt, D. Nunes, A. G. Rossetto, C. O. Rolim, Geyer C. F., J. S. Silva, “Privacy Management Solution in Ubiquitous Environments Using Percontrol”. Journal of Ubiquitous Systems & Pervasive Networks, v.5, n.2, p. 21-28, 2014. DOI: 10.5383/JUSPN.05.02.004.
A. Howedi A., Lotfi and A. Pourabdollah, “An entropy-based approach for anomaly detection in activities of daily living in the presence of a visitor”. Entropy, v. 22, n. 8, p. 845, 2020. DOI: 10.3390/e22080845.
S. O. P Pinto and V. S. Sobreiro, “Literature review: Anomaly detection approaches on digital business financial systems”. Digital Business, v. 2, Issue 2, 2022, 100038, ISSN 2666-9544. DOI: /10.1016/j.digbus.2022.100038.
M. Fahim and A. Sillitti, "Anomaly Detection, Analysis and Prediction Techniques in IoT Environment: A Systematic Literature Review," in IEEE Access, vol. 7, pp. 81664-81681, 2019, DOI: 10.1109/ACCESS.2019.2921912.
T. Sureda Riera, J. R. Bermejo Higuera J. Bermejo Higuera, J. J. Martínez Herraiz, J. A. Sicilia Montalvo. “Prevention and Fighting against Web Attacks through Anomaly Detection Technology. A Systematic Review”. Sustainability. 2020; 12 (12): 4945. DOI: 10.3390/su12124945.
M. P. de Freitas, V. A. Piai, R. H. Farias, A. M. R. Fernandes, A. G. de Moraes Rossetto, V. R. Q. Leithardt, “Artificial Intelligence of Things Applied to Assistive Technology: A Systematic Literature Review”. Sensors. 2022; 22(21):8531. DOI: 10.3390/s22218531.
M. Koutli, N. Theologou, A. Tryferidis, D. Tzovaras, “Abnormal Behavior Detection for Elderly People Living Alone Leveraging IoT Sensors”. Proc. of IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE), 2019, pages 922-926DO 922-926. DOI: 10.1109/BIBE.2019.00173.
S. Yahaya, A. Lotfi, M. Mahmud, “A Consensus Novelty Detection Ensemble Approach for Anomaly Detection in Activities of Daily Living”. Applied Soft Computing. Volume 83, 2019, 105613, ISSN 1568-4946. DOI: 10.1016/j.asoc.2019.105613.
Z. Zhang, S. Ishida, S. Tagashira, A. Fukuda, “A. Danger-Pose Detection System Using Commodity Wi-Fi for Bathroom Monitoring”. Sensors. 2019; 19(4):884. DOI: 10.3390/s19040884.
D. Zekri, T. Delot, M. Thilliez, S. Lecomte, M. Desertot, “A Framework for Detecting and Analyzing Behavior Changes of Elderly People over Time Using Learning Techniques”. Sensors. 2020; 20(24):7112. DOI: 10.3390/s20247112.
A. Howedi, L. Ahmad and P. Amir, “An Entropy-Based Approach for Anomaly Detection in Activities of Daily Living in the Presence of a Visitor”. Entropy. 2020, 22, no. 8: 845. DOI: 10.3390/e22080845.
A. Omar, A. Raed, S. Terence, M. Xiaogang, “A Review of Local Outlier Factor Algorithms for Outlier Detection in Big Data Streams”. Big Data Cogn. Comput. 2021, 5(1), 1. DOI: 10.3390/bdcc5010001.
C., Zhangyu, Z., Chengming, D., Jianwei. “Outlier detection using isolation forest and local outlier factor”. Proc. of the Conference on Research in Adaptive and Convergent Systems (RACS ’19). Association for Computing Machinery, 2019, New York, NY, USA, 161–168. DOI: 10.1145/3338840.3355641.
C. C. Aggarwal. Outlier Analysis. Berlim, Germany: Springer; 2nd ed., 2017. ISBN: 978-3-319-47578-3.
X. Tao, Y. Peng, F. Zhao, P. Zhao, Y. Wang, Y. “A parallel algorithm for network traffic anomaly detection based on Isolation Forest”. International Journal of Distributed Sensor Networks, v. 14, n. 11, 2018, DOI: 10.1177/1550147718814471.
P. Skelsey, “Forecasting risk of crop disease with anomaly detection algorithms”. Phytopathology R, v. 111, n. 2, p. 321-332, 2021. DOI:10.1094/PHYTO-05-20-0185-R.
I. A. Bozdog, T. Daniel-Nicusor, M. Antal, C. Antal, T. Cioara, I. Anghel, I. Salomie, "Human Behavior and Anomaly Detection using Machine Learning and Wearable Sensors,"2021 IEEE 17th International Conference on Intelligent Computer Communication and Processing (ICCP), Cluj-Napoca, Romania, 2021, pp. 383-390, DOI: 10.1109/ICCP53602.2021.9733684.
eHealth Monitoring Open Data Project, 2018. Accessed on: November 22nd, 2022. [Online] Available: https://sourceforge.net/projects/ehealthmonitoringproject/.
CASAS: Center of Advanced Studies in Adaptive System. Accessed on December 13th, 2022. [Online] Available at: http://casas.wsu.edu/datasets/.
DaLiAc – Daily Life Activities. Accessed on December 1st, 2022. [Online] Available at: https://www.mad.tf.fau.de/research/activitynet/daliac-daily-lifeactivities/.
ADLs: Activities of Daily Living (ADLs) Recognition Using Binary Sensors Version 1.0. Accessed on January 10th, 2023. [Online] Available: https://archive.ics.uci.edu/ml/datasets/Activities+of+Daily+Living+(ADLs)+Recognition+Using+Binary+Sensors.
H. Mshali, T. Lemlouma, and D. Magoni, "Analysis of dependency evaluation models for eHealth services," 2014 IEEE Global Communications Conference, Austin, TX, USA, 2014, pp. 2429-2435, DOI: 10.1109/GLOCOM.2014.7037172.
R.R. de Lima, A. M. R. Fernandes, J. R. Bombasar, B.A. da Silva, P. Crocker, V. R. Q. Leithardt, “An Empirical Comparison of Portuguese and Multilingual BERT Models for Auto-Classification of NCM Codes in International Trade”. Big Data and Cognitive Computing. 2022; 6(1):8 DOI:10.3390/bdcc6010008.
