Abstract
Activity recognition requires further research to enable a multitude of human-centric applications in the smart home environment. Currently, the major challenges in activity recognition include the domination of major activities over minor activities, their non-deterministic nature and the lack of availability of human-understandable output. In this paper, we introduce a novel Evolutionary Ensembles Model (EEM) that values both minor and major activities by processing each of them independently. It is based on a Genetic Algorithm (GA) to handle the non-deterministic nature of activities. Our evolutionary ensemble learner generates a human-understandable rule profile to ensure a certain level of confidence for performed activities. To evaluate the EEM, we performed experiments on three different real world datasets. Our experiments show significant improvement of 0.6 % to 0.28 % in the F-measures of recognized activities compared to existing counterparts. It is expected that EEM would be a practical solution for the activity recognition problem due to its understandable output and improved accuracy.
Similar content being viewed by others
References
Parisa RC, Diane JH, Lawrence B, Maureen S (2011) Discovering activities to recognize track in a smart environment. IEEE Trans Knowl Data Eng 23(4):527–539
Munguia TE, Intille SS, Larson K (2004) Activity recognition in the home setting using simple and ubiquitous sensors, PERVASIVE
Pavan T, Chellappa R, Subrahmanian VS, Udrea O (2008) Machine recognition of human activities: a survey. IEEE Trans Circuits Syst Video Technol 18(11):1473–1488
Vinh LT, Lee S, Xuan HL, Hung QN, Hyoung K, Manhyung H, Lee YK (2011) Semi-Markov conditional random fields for accelerometer-based activity recognition. Appl Intell 35(2):226–241
Kasteren T, Noulas A, Englebienne G, Krose B (2008) Accurate activity recognition in a home setting. In: Proceedings of the 10th international conference on ubiquitous computing, New York, 2008
Shi LD, Shi YH, Gao Y, Shan L, Bin Y (2011) XCSC: a nove approach to clustering with extended classifier system. Int J Neural Syst 21(1):79–93
Bull L, Studley M, Bagnall A, Whittley I (2007) Learning classifier system ensembles with rule-sharing. IEEE Trans Evol Comput 11(4):496–502
Kuncheva LI, Jain LC (2000) Designing classifier fusion systems by genetic algorithms. IEEE Trans Evol Comput 4(4):327–336
Kim KJ, Cho SB (2008) An evolutionary algorithm approach to optimal ensemble classifiers for DNA microarray data analysis. IEEE Trans Evol Comput 12(3):377–388
Folino G, Pizzuti C, Spezzano G (2010) An ensemble-based evolutionary framework for coping with distributed intrusion detection. Genet Program Evol Mach 11(2):131–146
Cuntoor NP, Yegnanarayana B, Chellappa R (2008) Activity modeling using event probability sequences. IEEE Trans Image Process 17(4):594–607
Liao L, Choudhury T, Fox D, Kautz H (2007) Training conditional random fields using virtual evidence boosting. In: Proceedings of the International Joint Conference on Artificial Intelligence, Hyederabad, 2007
Chen L, Nugent CD, Wang H (2011) A knowledge-driven approach to activity recognition in smart homes. IEEE Trans Knowl Data Eng 99:1
Zhu C, Cheng Q, Sheng W (2010) Human activity recognition via motion and vision data fusion. In: IEEE asilomar conference on signals, systems, and computers, Pacific Grove, 2010
Mitchell T (1997) Machine learning. McGraw Hill, Columbus
Puig AO, Mansilla EB (2008) Evolutionary rule-based systems for imbalanced data sets. Soft Comput 13(3):213–225
van Kasteren TLM, Alemdar H, Ersoy C (2011) Effective performance metrics for evaluating. In: Second workshop on context-systems design, evaluation and optimisation, Italy, 2011
Jehad AMS, Lee YK, Lee S (2010) A smoothed naive Bayes-based classifier for activity recognition. IETE Tech Rev 27(2):107–119
Parisa R, Cook DJ (2010) Mining and monitoring patterns of daily routines for assisted living in real world. In: Proceedings of the 1st ACM international health informatics symposium, New York, 2010
Popescu M, Florea E (2008) Linking clinical events in elderly to in-home monitoring sensor data: a brief review and a pilot study on predicting pulse pressure. J Comput Inf Sci Eng 2(2):180–199
Xing H, Qu R (2011) A compact genetic algorithm for the network coding based resource minimization problem. Appl Intell 36(4):809–823
Shin KS, Jeong YS, Jeong MK (2011) A two-leveled symbiotic evolutionary algorithm for clustering problems. Appl Intell 36(4):788–799
Acknowledgement
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MEST) (No. 2011-0030823)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Fahim, M., Fatima, I., Lee, S. et al. EEM: evolutionary ensembles model for activity recognition in Smart Homes. Appl Intell 38, 88–98 (2013). https://doi.org/10.1007/s10489-012-0359-7
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-012-0359-7