Abstract
The growth in popularity of smart environments has been quite steep in the last decade and so has the demand for smart health assistance systems. A smart home-based prompting system can enhance these technologies to deliver in-home interventions to users for timely reminders or brief instructions describing the way a task should be carried out for successful completion. This technology is in high demand given the desire of people who have physical or cognitive limitations to live independently in their homes. In this paper, with the introduction of the “PUCK” prompting system, we take an approach to automate prompting-based interventions without any predefined rule sets or user feedback. Unlike other approaches, we use simple off-the-shelf sensors and learn the timing for prompts based on real data that are collected with volunteer participants in our smart home test bed. The data mining approaches taken to solve this problem come with the challenge of an imbalanced class distribution that occurs naturally in the data. We propose a variant of an existing sampling technique, SMOTE, to deal with the class imbalance problem. To validate the approach, a comparative analysis with cost-sensitive learning is performed.
Similar content being viewed by others
References
Bates J, Boote J, Beverley C (2004) Psychosocial interventions for people with a milder dementing illness: a systematic review. J Adv Nurs 45(6):644–658
Boger J, Poupart P, Hoey J, Boutilier C, Fernie G, Mihailidis A (2005) A decision-theoretic approach to task assistance for persons with dementia. In: International joint conference on artificial intelligence, Citeseer, vol 19, p 1293
Boser B, Guyon I, Vapnik V (1992) A training algorithm for optimal margin classifiers. In: Proceedings of the fifth annual workshop on computational learning theory. ACM, pp 144–152
Bureau UC (2010) International database. Table 094. URL http://www.census.gov/population/www/projections/natdet-D1A.html
Chawla N, Bowyer K, Hall L, Kegelmeyer W (2002) Smote: synthetic minority over-sampling technique. J Artif Intell Res 16(1):321–357
Dementia A (ed) (2010) Alzheimer association report: Alzheimer’s disease facts and figures, vol 6
Dietterich T (2000) Ensemble methods in machine learning. Multiple Classifier Systems, pp 1–15
Elkan C (2001) The foundations of cost-sensitive learning. In: International joint conference on artificial intelligence, Citeseer, vol 17, pp 973–978
Freund Y, Schapire R (1996) Experiments with a new boosting algorithm. In: Machine learning-international workshop then conference, Citeseer, pp 148–156
Hand D (1997) Construction and assessment of classification rules
Hastie J, Tibshirani R (2000) Additive logistic regression: a statistical view of boosting. Ann Stat 28(2):337–374
Iba W, Langley P (1992) Induction of one-level decision trees. In: Proceedings of the ninth international conference on machine learning, pp 233–240
Keally M, Zhou G, Xing G (2010) Watchdog: confident event detection in heterogeneous sensor networks. In: 2010 16th IEEE real-time and embedded technology and applications symposium. IEEE, pp 279–288
Kotsiantis S, Pintelas P (2003) Mixture of expert agents for handling imbalanced data sets. Ann Math Comput Teleinform 1(1):46–55
Kubat M, Matwin S (1997) Addressing the curse of imbalanced training sets: one-sided selection. In: Machine learning-international workshop then conference, Citeseer, pp 179–186
Lim M, Choi J, Kim D, Park S (2008) A smart medication prompting system and context reasoning in home environments. In: Networked computing and advanced information management, 2008. NCM’08. Fourth international conference on, IEEE, vol 1, pp 115–118
Matsumoto M, Nishimura T (1998) Mersenne twister: a 623-dimensionally equidistributed uniform pseudo-random number generator. ACM Trans Model Comput Simulat (TOMACS) 8(1):3–30
Maurer U, Smailagic A, Siewiorek D, Deisher M (2006) Activity recognition and monitoring using multiple sensors on different body positions. In: Wearable and implantable body sensor networks, 2006. BSN 2006. International workshop on, IEEE, pp 4–116
Monard M, Batista G (2002) Learning with skewed class distributions. Adv Logic Artif Intell Robot 173–180
Neill D, Cooper G (2010) A multivariate bayesian scan statistic for early event detection and characterization. Mach Learn 79(3):261–282
Oriani M, Moniz-Cook E, Binetti G, Zanieri G, Frisoni G, Geroldi C, De Vreese L, Zanetti O (2003) An electronic memory aid to support prospective memory in patients in the early stages of Alzheimer’s disease: a pilot study. Aging Mental Health 7(1):22–27
Pineau J, Montemerlo M, Pollack M, Roy N, Thrun S (2003) Towards robotic assistants in nursing homes: challenges and results. Robot Auton Syst 42(3–4):271–281
Platt J (1998) Sequential minimal optimization: a fast algorithm for training support vector machines
Pollack M, Brown L, Colbry D, McCarthy C, Orosz C, Peintner B, Ramakrishnan S, Tsamardinos I (2003) Autominder: an intelligent cognitive orthotic system for people with memory impairment. Robot Auton Syst 44(3–4):273–282
Provost F, Fawcett T, Kohavi R (1998) The case against accuracy estimation for comparing induction algorithms. In: Proceedings of the fifteenth international conference on machine learning, Citeseer, vol 445
Quinlan J (1986) Induction of decision trees. Mach Learn 1(1):81–106
Raskutti B, Kowalczyk A (2004) Extreme re-balancing for svms: a case study. ACM SIGKDD Explor Newslett 6(1):60–69
Rudary M, Singh S, Pollack M (2004) Adaptive cognitive orthotics: combining reinforcement learning and constraint-based temporal reasoning. In: Proceedings of the twenty-first international conference on machine learning, ACM, p 91
Singla G, Cook D, Schmitter-Edgecombe M (2009) Tracking activities in complex settings using smart environment technologies. Int J Biosci Psychiatr Technol (IJBSPT) 1(1):25
Šingliar T, Hauskrecht M (2010) Learning to detect incidents from noisily labeled data. Mach Learn 79(3):335–354
Szewcyzk S, Dwan K, Minor B, Swedlove B, Cook D (2009) Annotating smart environment sensor data for activity learning. Technol Health Care 17(3):161–169
Thomas BL, Crandall AS (2011) A demonstration of PyViz, a flexible smart home visualization tool. In: IEEE international conference on pervasive computing and communications, PerCom ’11 (to appear)
Turney P (2010) Types of cost in inductive concept learning. In: Proceedings of the cost-sensitive learning workshop at the 17th ICML-2000 conference, pp 15–21
Wadley V, Okonkwo O, Crowe M, Ross-Meadows L (2008) Mild cognitive impairment and everyday function: evidence of reduced speed in performing instrumental activities of daily living. Am J Geriatr Psych 16(5):416
Weber J, Pollack M (2007) Entropy-driven online active learning for interactive calendar management. In: Proceedings of the 12th international conference on Intelligent user interfaces. ACM, pp 141–150
Weiss G (2004) Mining with rarity: a unified framework. SIGKDD Explor 6(1):7–14
Weiss G, Provost F (2001) The effect of class distribution on classifier learning: an empirical study. Rutgers University Press, Piscataway
Weiss G, McCarthy K, Zabar B (2007) Cost-sensitive learning vs. sampling: which is best for handling unbalanced classes with unequal error costs. In: International conference on data mining, Citeseer, pp 35–41
Witten I, Frank E (2005) Data mining: practical machine learning tools and techniques. Morgan Kaufmann, Los Altos
Acknowledgments
This work was supported by the United States National Institutes of Health Grant R01EB009675 and National Science Foundation Grant CRI-0852172.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Das, B., Cook, D.J., Schmitter-Edgecombe, M. et al. PUCK: an automated prompting system for smart environments: toward achieving automated prompting—challenges involved. Pers Ubiquit Comput 16, 859–873 (2012). https://doi.org/10.1007/s00779-011-0445-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00779-011-0445-6