Abubaker Elbayoudi
Ahmad Lotfi
ABSTRACT
Analysing changes of the behaviour of an occupant who lives in an Ambient Intelligence (AmI) environment is addressed in this paper. Changes in Activities of Daily Living (ADL) are indicators of the social and health status of the occupant. This research therefore aims to identify trends in ADL and interpret them in a suitable form for carers. It is essential for this purpose to have access to relatively long-term monitoring data of the occupant using appropriate sensory devices. Different trend analysis techniques are investigated and compared. These techniques include; Seasonal Kendall Test (SKT), Simple Moving Mean Average (SMA), and Exponentially Weighted Moving Average (EWMA), which are used to detect trends in the time-series data representing occupancy duration in different areas of a home environment for an elderly person living independently.
- U. N. D. of Economic. World population ageing 2009, volume 295. United Nations Publications, 2010.Google Scholar
- Miles, Laughton E and Dement, William C. Sleep and aging. Sleep, 3(2): 1--220, 1979.Google Scholar
- Manabe, K and Matsui, T and Yamaya, M. Sleep patterns and mortality among elderly patients in a geriatric hospital. Gerontology. Karger Publishers, 46(6): 318--322, 2000.Google Scholar
- Higgins, Julian PT and Green, Sally and others. Cochrane handbook for systematic reviews of interventions. Wiley Online Library, 2008.Google ScholarCross Ref
- Sawsan Mahmoud, Javad Akhlaghinia, Ahmad Lotfi and Caroline Langensiepen. Trend modelling of elderly lifestyle within an occupancy simulator. Computer Modelling and Simulation (UKSim). IEEE, 156--161, 2011. Google ScholarDigital Library
- Soulas, Julie and Lenca, Philippe and Thépaut, André. Unsupervised discovery of activities of daily living characterized by their periodicity and variability. Engineering Applications of Artificial Intelligence. Elsevier, 45, 90--102, 2015. Google ScholarDigital Library
- Rafael-Palou, Xavier and Vargiu, Eloisa and Miralles, Felip. Monitoring People that Need Assistance through a Sensor-based System: Evaluation and First Results. Artificial Intelligence and Assistive Medicine (AIME 2015). CEUR Workshop Proceedings, 1389, 2015.Google Scholar
- Kemp, John and Gaura, Elena and Rednic, Ramona and Brusey, James. Long-term behavioural change detection through pervasive sensing. Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD). IEEE, pages 629--634, 2013. Google ScholarDigital Library
- Alexander, GL and Wilbik, A and Keller, JM and Musterman, K. Generating Sensor Data Summaries to Communicate Change in Elder's Health Status. Applied clinical informatics. Schattauer, 5(1):73, 2014.Google Scholar
- Ros, María and Pegalajar, M. and Delgado, M. and Vila, A. and Anderson, D. and Keller, J. and Popescu, M. Linguistic summarization of long-term trends for understanding change in human behavior. Fuzzy Systems (FUZZ). IEEE, 2080--2087, 2011.Google Scholar
- Forkan, A. R. M. and Khalil, I. and Tari, Z. and Foufou, S. and Bouras, A. A context-aware approach for long-term behavioural change detection and abnormality prediction in ambient assisted living. Pattern Recognition. Elsevier, 48(3):628--641, 2015. Google ScholarDigital Library
- Saives, J. and Pianon, C. and Faraut, G. Activity Discovery and Detection of Behavioral Deviations of an Inhabitant From Binary Sensors. Automation Science and Engineering. IEEE, 12(4):1211--1224, 2015.Google ScholarCross Ref
- Oscar D. Lara and Miguel A. Labrador. A survey on human activity recognition using wearable sensors. Communications Surveys & Tutorials. IEEE, 15(3):1192--1209, 2013.Google ScholarCross Ref
- Ahmed Nabil Belbachir and Mario Drobics and Walter Marschitz. Ambient Assisted Living for ageing wellâĂŞan overview. e & i Elektrotechnik und Informationstechnik, 127(6):200--205, 2010.Google Scholar
- Aggarwal, Jake K and Xia, Lu. Human activity recognition from 3d data: A review. Pattern Recognition Letters. Elsevier, 48:70--80, 2014.Google ScholarCross Ref
- Eunju Kim and S. Helal and D. Cook. Human Activity Recognition and Pattern Discovery. Pervasive Computing. IEEE, 9(1): 48--53, 2010. Google ScholarDigital Library
- Labiba Gillani Fahad, Arshad Ali and Muttukrishnan Rajarajan. Long term analysis of daily activities in a smart home. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), 2013.Google Scholar
- Bruno Lepri, Albert Ali Salah, Fabio Pianesi and Alex Sandy Pentland. Human behavior understanding for inducing behavioral change: Social and theoretical aspects. Constructing Ambient Intelligence. Spring, 82(11):252--263, 2012.Google ScholarCross Ref
- Douglas Ayers and Mubarak Shah. Monitoring human behavior from video taken in an office environment. Image and Vision Computing, 19(12): 833--846, 2001.Google ScholarCross Ref
- McBride, Graham. Validation of models: statistical techniques and data availability. In National Institute of Water and Atmospheric Research. Hamilton, 2000.Google Scholar
- Hirsch, Robert M and Slack, James R. A nonparametric trend test for seasonal data with serial dependence. Water Resources Research. Wiley Online Library, 20(6):727--732, 1984.Google ScholarCross Ref
- Belle, Gerald and Hughes, James P. Nonparametric tests for trend in water quality. Water Resources Research. Wiley Online Library, 20(1):127--136, 1984.Google ScholarCross Ref
- Droke, Clif. Moving averages simplified. Marketplace Books, 2001.Google Scholar
- Roberts, SW. Control chart tests based on geometric moving averages. Technometrics. Taylor & Francis, 1(3): 239--250, 1959.Google ScholarCross Ref
- Holt, Charles C. Forecasting seasonals and trends by exponentially weighted moving averages. International journal of forecasting. Elsevier, 20(1): 5--10, 2004.Google Scholar
- Gardner, Everette S. Exponential smoothing: The state of the art-Part II. International journal of forecasting. Elsevier, 22(4): 637--666, 2006.Google Scholar
- Cox, David R. Prediction by exponentially weighted moving averages and related methods. Journal of the Royal Statistical Society. Series B (Methodological), 414--422, 1961.Google ScholarCross Ref
Index Terms
- Determining Behavioural Trends in an Ambient Intelligence Environment
Recommendations
Trend Analysis Techniques in Forecasting Human Behaviour Evolution
PETRA '17: Proceedings of the 10th International Conference on PErvasive Technologies Related to Assistive EnvironmentsAnalysis of human behaviour changes is a subject of interest for many researchers. This could be obtained considering either short-term or long-term changes. The aim of this study is to find long-term changes (behaviour evolution) in Activities of Daily ...
The human behaviour indicator: A measure of behavioural evolution
Highlights- Introducing behavioural evolution representing progressive changes in activities.
AbstractActivities of daily living (ADL) or activities of daily working (ADW) may be affected by changes in a person’s health or well-being. Measuring progressive changes in one activity or multiple activities is representative of behavioural ...
Interpretation of behaviour evolution in activities of daily living
PETRA '15: Proceedings of the 8th ACM International Conference on PErvasive Technologies Related to Assistive EnvironmentsHuman behaviour can be difficult to interpret even with the sophistication of modern smart homes, yet an understanding of the way people conduct their activities of daily living is essential for any attempts to detect problems. We discuss the key ...
Comments