Optimizing the configuration of an heterogeneous architecture of sensors for activity recognition, using the extended belief rule-based inference methodology

Macarena Espinilla, Javier Medina, Alberto Calzada, Jun Liu, Luis Martínez, Chris Nugent

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Smart environments are heterogeneous architectures with a broad range of heterogeneous electronic devices that are with high in processing capabilities for computing, considering low power consumption. They have the ability to record information about the behavior of the people by means of their interactions with the objects within an environment. This kind of environments are providing solutions to address some of the problems associated with the growing size and ageing of the population by means of the recognition of activities that can offer monitoring activities of daily living and adapting the environment. In order to deploy low-cost smart environments and reduce the computational complexity for activity recognition, it is a key issue to know the subset of sensors which are relevant for activity recognition. By using feature selection methods to optimize the subset of initial sensors in a smart environment, this paper proposes the adaption of the extended belief rule-based inference methodology (RIMER+) to handle data binary sensors and its use as the suitable classifier for activity recognition that keeps the accuracy of results even in situations where an essential sensor fails. A case study is presented in which a smart environment dataset for activity recognition with 14 sensors is set. Two optimizations with 7 and 10 sensors are obtained with two feature selection methods in which the adaptation of RIMER+ for smart environment provides an encouraged performance against the most popular classifiers in terms of robustness.
LanguageEnglish
JournalMicroprocessors and Microsystems
Volume1000
Early online date5 Nov 2016
DOIs
Publication statusE-pub ahead of print - 5 Nov 2016

Fingerprint

Sensors
Feature extraction
Classifiers
Computational complexity
Electric power utilization
Aging of materials
Monitoring
Processing
Costs

Keywords

  • Heterogeneous Architecture of Sensors · Optimization · Efficient Power-aware · Activity Recognition · Ambient Intelligence · Feature Selection · Data-Driven

Cite this

@article{00bab342c8944677adeeea8837a6a34a,
title = "Optimizing the configuration of an heterogeneous architecture of sensors for activity recognition, using the extended belief rule-based inference methodology",
abstract = "Smart environments are heterogeneous architectures with a broad range of heterogeneous electronic devices that are with high in processing capabilities for computing, considering low power consumption. They have the ability to record information about the behavior of the people by means of their interactions with the objects within an environment. This kind of environments are providing solutions to address some of the problems associated with the growing size and ageing of the population by means of the recognition of activities that can offer monitoring activities of daily living and adapting the environment. In order to deploy low-cost smart environments and reduce the computational complexity for activity recognition, it is a key issue to know the subset of sensors which are relevant for activity recognition. By using feature selection methods to optimize the subset of initial sensors in a smart environment, this paper proposes the adaption of the extended belief rule-based inference methodology (RIMER+) to handle data binary sensors and its use as the suitable classifier for activity recognition that keeps the accuracy of results even in situations where an essential sensor fails. A case study is presented in which a smart environment dataset for activity recognition with 14 sensors is set. Two optimizations with 7 and 10 sensors are obtained with two feature selection methods in which the adaptation of RIMER+ for smart environment provides an encouraged performance against the most popular classifiers in terms of robustness.",
keywords = "Heterogeneous Architecture of Sensors · Optimization · Efficient Power-aware · Activity Recognition · Ambient Intelligence · Feature Selection · Data-Driven",
author = "Macarena Espinilla and Javier Medina and Alberto Calzada and Jun Liu and Luis Mart{\'i}nez and Chris Nugent",
note = "Reference text: 1. Alam, M., Hamida, E.: Surveying wearable human assistive technology for life and safety critical applications: Standards, challenges and opportunities. Sensors (Switzerland) 14(5), 9153–9209 (2014) 2. Calzada, A., Liu, J., Nugent, C., Wang, H., Martinez, L.: Sensor-based ac tivity recognition using extended belief rule-based inference methodology. In: Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual In ternational Conference of the IEEE, pp. 2694–2697. IEEE (2014) 3. Calzada, A., Liu, J., Wang, H., Kashyap, A.: Dynamic rule activation for extended belief rule bases. In: International Conference on Machine Learning and Cybernetics (ICMLC), vol. 4, pp. 1836–1841. IEEE (2013) 4. Calzada, A., Liu, J., Wang, H., Kashyap, A.: A new dynamic rule activation method for extended belief rule-based systems. Knowledge and Data Engineering, IEEE Transactions on PP(99), 1–1 (2014). DOI: 10.1109/TKDE.2014.2356460 5. Chen, L., Hoey, J., Nugent, C., Cook, D., Yu, Z.: Sensor-based activity recognition. Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on 42(6), 790–808 (2012) 6. Chen, L., Nugent, C.D., Wang, H.: A knowledge-driven approach to activity recognition in smart homes. IEEE Transactions on Knowledge and Data Engineering 24(6), 961–974 (2012) 7. Chen, Y., Garcia, E., Gupta, M., Rahimi, A., Cazzanti, L.: Similarity-based classification: Concepts and algorithms. Journal of Machine Learning Research 10, 747–776 (2009) 8. Cook, D., Augusto, J., Jakkula, V.: Ambient intelligence: Technologies, applications, and opportunities. Pervasive and Mobile Computing 5(4), 277–298 (2009). DOI 10.1016/j.pmcj.2009.04.001 9. Cook, D., Schmitter-Edgecombe, M.: Assessing the quality of activities in a smart environment. Methods of Information in Medicine 48(5), 480–485 (2009). DOI 10.3414/ME0592 10. Cortes, C., Vapnik, V.: Support vector networks. Machine Learning 20, 273– 297 (1995) 11. Cover, T., Hart, P.: Nearest neighbor pattern classification. Infor mation Theory, IEEE Transactions on 13(1), 21–27 (1967). DOI: 10.1109/TIT.1967.1053964 12. Das, B., Cook, D., Schmitter-Edgecombe, M., Seelye, A.: Puck: An auto mated prompting system for smart environments: Toward achieving auto mated prompting-challenges involved. Personal and Ubiquitous Computing 16(7), 859–873 (2012). DOI 10.1007/s00779-011-0445-6 13. Dash, M., Liu, H.: Feature selection for classification. Intelligent data analysis 1(3), 131–156 (1997) 14. Dash, M., Liu, H.: Consistency-based search in feature selection. Artificial intelligence 151(1), 155–176 (2003) 15. Devijver, P.A., Kittler, J.: Pattern recognition: A statistical approach, vol. 761. Prentice-Hall London (1982) 16. Domingos, P., Pazzani, M.: On the optimality of the simple bayesian classifier under zero-one loss. Machine Learning 29, 103–137 (1997) 17. Fang, H., He, L., Si, H., Liu, P., Xie, X.: Human activity recognition based on feature selection in smart home using back-propagation algorithm. ISA Transactions 53(5), 1629–1638 (2014). DOI 10.1016/j.isatra.2014.06.008 18. Fang, H., Srinivasan, R., Cook, D.: Feature selections for human activity recognition in smart home environments. International Journal of Innovative Computing, Information and Control 8(5 B), 3525–3535 (2012) 19. Feuz, K.D., Cook, D.J., Rosasco, C., Robertson, K., Schmitter-Edgecombe, M.: Automated detection of activity transitions for prompting. IEEE Transactions on Human-Machine Systems (2014). DOI 10.1109/THMS.2014.2362529 20. Ghasemzadeh, H., Amini, N., Saeedi, R., Sarrafzadeh, M.: Power-aware computing in wearable sensor networks: An optimal feature selection. IEEE Transactions on Mobile Computing 14(4), 800–812 (2015). DOI 10.1109/TMC.2014.2331969 21. Gu, T., Wang, L., Wu, Z., Tao, X., Lu, J.: A pattern mining approach to sensor-based human activity recognition. IEEE Transactions on Knowledge and Data Engineering 23(9), 1359–1372 (2011) 22. Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The weka data mining software: an update. ACM SIGKDD explorations newsletter 11(1), 10–18 (2009) 23. Hall, M.A.: Correlation-based feature subset selection for machine learning. Ph.D. thesis, University of Waikato, Hamilton, New Zealand (1998) 24. Hamming, R.W.: Error detecting and error correcting codes. Bell System technical journal 29(2), 147–160 (1950) 25. Holder, L., Cook, D.: Automated activity-aware prompting for ac tivity initiation. Gerontechnology 11(4), 534–544 (2013). DOI 10.4017/gt.2013.11.4.005.00 26. John, G.H., Kohavi, R., Pfleger, K.: Irrelevant features and the subset selection problem. In: ICML, vol. 94, pp. 121–129 (1994) 27. Kira, K., Rendell, L.A.: The feature selection problem: Traditional methods and a new algorithm. In: AAAI, vol. 2, pp. 129–134 (1992) 28. Kohavi, R., Sommerfield, D.: Feature subset selection using the wrapper method: Overfitting and dynamic search space topology. In: KDD, pp. 192–197 (1995) 29. Koller, D., Sahami, M.: Toward optimal feature selection. Stanford InfoLab (1996) 30. Kononenko, I.: Estimating attributes: analysis and extensions of relief. In: Machine Learning: ECML-94, pp. 171–182. Springer (1994) 31. Lee, M., Dey, A.: Sensor-based observations of daily living for aging in place. Personal and Ubiquitous Computing 19(1), 27–43 (2015). DOI 10.1007/s00779-014-0810-3 32. Liu, H., Setiono, R.: Feature selection and classification-a probabilistic wrap per approach. In: Proceedings of 9th International Conference on Industrial and Engineering Applications of AI and ES, pp. 419–424 (1997) 33. Liu, H., Setiono, R., et al.: A probabilistic approach to feature selection-a filter solution. In: ICML, vol. 96, pp. 319–327. Citeseer (1996) 34. Liu, J., Martinez, L., Calzada, A., Wang, H.: A novel belief rule base representation, generation and its inference methodology. Knowledge-Based Systems 53, 129–141 (2013). DOI 10.1016/j.knosys.2013.08.019 35. McKeever, S., Ye, J., Coyle, L., Bleakley, C., Dobson, S.: Activity recognition using temporal evidence theory. Journal of Ambient Intelligence and Smart Environments 2(3), 253–269 (2010). DOI 10.3233/AIS-2010-0071 36. Miao, F., He, Y., Liu, J., Li, Y., Ayoola, I. Identifying typical physical activity on smartphone with varying positions and orientations (2015) BioMedical Engineering Online, 14 (1), art. no. 32. 37. Modrzejewski, M.: Feature selection using rough sets theory. In: Machine Learning: ECML-93, pp. 213–226. Springer (1993) 38. Mucciardi, A.N., Gose, E.E.: A comparison of seven techniques for choosing subsets of pattern recognition properties. IEEE Transactions on Computers 20(9), 1023–1031 (1971) 39. Narendra, P.M., Fukunaga, K.: A branch and bound algorithm for feature subset selection. Computers, IEEE Transactions on 100(9), 917–922 (1977) 40. Ordonez, F., Toledo, P., Sanchis, A.: Activity recognition using hybrid generative/discriminative models on home environments using binary sensors. Sensors 13(5), 5460–5477 (2013) 41. San Martin, L., Pelaez, V., Gonzalez, R., Campos, A., Lobato, V.: Environmental user-preference learning for smart homes: An autonomous approach. Journal of Ambient Intelligence and Smart Environments 2(3), 327–342 (2010) 42. Schlimmer, J.C., et al.: Efficiently inducing determinations: A complete and systematic search algorithm that uses optimal pruning. In: ICML, pp. 284–290. Citeseer (1993) 43. Shavlik, J.W., Dietterich, T.G.: Readings in machine learning. Morgan Kauf mann (1990) 44. Sheinvald, J., Dom, B., Niblack, W.: A modeling approach to feature selection. In: Pattern Recognition, 1990. Proceedings., 10th International Conference on, vol. 1, pp. 535–539. IEEE (1990) 45. Smith, G., Sala, S.D., Logie, R., Maylor, E.: Prospective and retrospective memory in normal aging and dementia: A questionnaire study. Memory 8, 311–321 (2000) 46. Stoppiglia, H., Dreyfus, G., Dubois, R., Oussar, Y.: Ranking a random feature for variable and feature selection. The Journal of Machine Learning Research 3, 1399–1414 (2003) 47. Szewcyzk, S., Dwan, K., Minor, B., Swedlove, B., Cook, D.: Annotating smart environment sensor data for activity learning. Technology and Health Care 17(3), 161–169 (2009). DOI 10.3233/THC-2009-0546 48. Van Hoof, J., Wouters, E., Marston, H., Vanrumste, B., Overdiep, R.: Ambient assisted living and care in the Netherlands: The voice of the user. International Journal of Ambient Computing and Intelligence 3(4), 25–40 (2011) 49. Van Kasteren, T., Noulas, A., Englebienne, G., Krose, B.: Accurate activity recognition in a home setting. In: Proceedings of the 10th international conference on Ubiquitous computing, pp. 1–9. ACM (2008) 50. Wang, L. , Gu, T., Tao, X., Lu, J. A hierarchical approach to real-time activity recognition in body sensor networks(2012) Pervasive and Mobile Computing, 8 (1), pp. 115-130 51. Yang, J., Liu, J., Wang, J., Sii, H., Wang, H.: Belief rule-base inference methodology using the evidential reasoning approach RIMER. IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans 36(2), 266–285 (2006). DOI 10.1109/TSMCA.2005.851270 52. Yang, J.B., Xu, D.L.: On the evidential reasoning algorithm for multiple at tribute decision analysis under uncertainty. IEEE Transactions on Systems, Man, and Cybernetics Part A: Systems and Humans. 32(3), 289–304 (2002). DOI 10.1109/TSMCA.2002.802746",
year = "2016",
month = "11",
day = "5",
doi = "10.1016/j.micpro.2016.10.007",
language = "English",
volume = "1000",

}

Optimizing the configuration of an heterogeneous architecture of sensors for activity recognition, using the extended belief rule-based inference methodology. / Espinilla, Macarena; Medina, Javier; Calzada, Alberto; Liu, Jun; Martínez, Luis; Nugent, Chris.

Vol. 1000, 05.11.2016.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Optimizing the configuration of an heterogeneous architecture of sensors for activity recognition, using the extended belief rule-based inference methodology

AU - Espinilla, Macarena

AU - Medina, Javier

AU - Calzada, Alberto

AU - Liu, Jun

AU - Martínez, Luis

AU - Nugent, Chris

N1 - Reference text: 1. Alam, M., Hamida, E.: Surveying wearable human assistive technology for life and safety critical applications: Standards, challenges and opportunities. Sensors (Switzerland) 14(5), 9153–9209 (2014) 2. Calzada, A., Liu, J., Nugent, C., Wang, H., Martinez, L.: Sensor-based ac tivity recognition using extended belief rule-based inference methodology. In: Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual In ternational Conference of the IEEE, pp. 2694–2697. IEEE (2014) 3. Calzada, A., Liu, J., Wang, H., Kashyap, A.: Dynamic rule activation for extended belief rule bases. In: International Conference on Machine Learning and Cybernetics (ICMLC), vol. 4, pp. 1836–1841. IEEE (2013) 4. Calzada, A., Liu, J., Wang, H., Kashyap, A.: A new dynamic rule activation method for extended belief rule-based systems. Knowledge and Data Engineering, IEEE Transactions on PP(99), 1–1 (2014). DOI: 10.1109/TKDE.2014.2356460 5. Chen, L., Hoey, J., Nugent, C., Cook, D., Yu, Z.: Sensor-based activity recognition. Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on 42(6), 790–808 (2012) 6. Chen, L., Nugent, C.D., Wang, H.: A knowledge-driven approach to activity recognition in smart homes. IEEE Transactions on Knowledge and Data Engineering 24(6), 961–974 (2012) 7. Chen, Y., Garcia, E., Gupta, M., Rahimi, A., Cazzanti, L.: Similarity-based classification: Concepts and algorithms. Journal of Machine Learning Research 10, 747–776 (2009) 8. Cook, D., Augusto, J., Jakkula, V.: Ambient intelligence: Technologies, applications, and opportunities. Pervasive and Mobile Computing 5(4), 277–298 (2009). DOI 10.1016/j.pmcj.2009.04.001 9. Cook, D., Schmitter-Edgecombe, M.: Assessing the quality of activities in a smart environment. Methods of Information in Medicine 48(5), 480–485 (2009). DOI 10.3414/ME0592 10. Cortes, C., Vapnik, V.: Support vector networks. Machine Learning 20, 273– 297 (1995) 11. Cover, T., Hart, P.: Nearest neighbor pattern classification. Infor mation Theory, IEEE Transactions on 13(1), 21–27 (1967). DOI: 10.1109/TIT.1967.1053964 12. Das, B., Cook, D., Schmitter-Edgecombe, M., Seelye, A.: Puck: An auto mated prompting system for smart environments: Toward achieving auto mated prompting-challenges involved. Personal and Ubiquitous Computing 16(7), 859–873 (2012). DOI 10.1007/s00779-011-0445-6 13. Dash, M., Liu, H.: Feature selection for classification. Intelligent data analysis 1(3), 131–156 (1997) 14. Dash, M., Liu, H.: Consistency-based search in feature selection. Artificial intelligence 151(1), 155–176 (2003) 15. Devijver, P.A., Kittler, J.: Pattern recognition: A statistical approach, vol. 761. Prentice-Hall London (1982) 16. Domingos, P., Pazzani, M.: On the optimality of the simple bayesian classifier under zero-one loss. Machine Learning 29, 103–137 (1997) 17. Fang, H., He, L., Si, H., Liu, P., Xie, X.: Human activity recognition based on feature selection in smart home using back-propagation algorithm. ISA Transactions 53(5), 1629–1638 (2014). DOI 10.1016/j.isatra.2014.06.008 18. Fang, H., Srinivasan, R., Cook, D.: Feature selections for human activity recognition in smart home environments. International Journal of Innovative Computing, Information and Control 8(5 B), 3525–3535 (2012) 19. Feuz, K.D., Cook, D.J., Rosasco, C., Robertson, K., Schmitter-Edgecombe, M.: Automated detection of activity transitions for prompting. IEEE Transactions on Human-Machine Systems (2014). DOI 10.1109/THMS.2014.2362529 20. Ghasemzadeh, H., Amini, N., Saeedi, R., Sarrafzadeh, M.: Power-aware computing in wearable sensor networks: An optimal feature selection. IEEE Transactions on Mobile Computing 14(4), 800–812 (2015). DOI 10.1109/TMC.2014.2331969 21. Gu, T., Wang, L., Wu, Z., Tao, X., Lu, J.: A pattern mining approach to sensor-based human activity recognition. IEEE Transactions on Knowledge and Data Engineering 23(9), 1359–1372 (2011) 22. Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The weka data mining software: an update. ACM SIGKDD explorations newsletter 11(1), 10–18 (2009) 23. Hall, M.A.: Correlation-based feature subset selection for machine learning. Ph.D. thesis, University of Waikato, Hamilton, New Zealand (1998) 24. Hamming, R.W.: Error detecting and error correcting codes. Bell System technical journal 29(2), 147–160 (1950) 25. Holder, L., Cook, D.: Automated activity-aware prompting for ac tivity initiation. Gerontechnology 11(4), 534–544 (2013). DOI 10.4017/gt.2013.11.4.005.00 26. John, G.H., Kohavi, R., Pfleger, K.: Irrelevant features and the subset selection problem. In: ICML, vol. 94, pp. 121–129 (1994) 27. Kira, K., Rendell, L.A.: The feature selection problem: Traditional methods and a new algorithm. In: AAAI, vol. 2, pp. 129–134 (1992) 28. Kohavi, R., Sommerfield, D.: Feature subset selection using the wrapper method: Overfitting and dynamic search space topology. In: KDD, pp. 192–197 (1995) 29. Koller, D., Sahami, M.: Toward optimal feature selection. Stanford InfoLab (1996) 30. Kononenko, I.: Estimating attributes: analysis and extensions of relief. In: Machine Learning: ECML-94, pp. 171–182. Springer (1994) 31. Lee, M., Dey, A.: Sensor-based observations of daily living for aging in place. Personal and Ubiquitous Computing 19(1), 27–43 (2015). DOI 10.1007/s00779-014-0810-3 32. Liu, H., Setiono, R.: Feature selection and classification-a probabilistic wrap per approach. In: Proceedings of 9th International Conference on Industrial and Engineering Applications of AI and ES, pp. 419–424 (1997) 33. Liu, H., Setiono, R., et al.: A probabilistic approach to feature selection-a filter solution. In: ICML, vol. 96, pp. 319–327. Citeseer (1996) 34. Liu, J., Martinez, L., Calzada, A., Wang, H.: A novel belief rule base representation, generation and its inference methodology. Knowledge-Based Systems 53, 129–141 (2013). DOI 10.1016/j.knosys.2013.08.019 35. McKeever, S., Ye, J., Coyle, L., Bleakley, C., Dobson, S.: Activity recognition using temporal evidence theory. Journal of Ambient Intelligence and Smart Environments 2(3), 253–269 (2010). DOI 10.3233/AIS-2010-0071 36. Miao, F., He, Y., Liu, J., Li, Y., Ayoola, I. Identifying typical physical activity on smartphone with varying positions and orientations (2015) BioMedical Engineering Online, 14 (1), art. no. 32. 37. Modrzejewski, M.: Feature selection using rough sets theory. In: Machine Learning: ECML-93, pp. 213–226. Springer (1993) 38. Mucciardi, A.N., Gose, E.E.: A comparison of seven techniques for choosing subsets of pattern recognition properties. IEEE Transactions on Computers 20(9), 1023–1031 (1971) 39. Narendra, P.M., Fukunaga, K.: A branch and bound algorithm for feature subset selection. Computers, IEEE Transactions on 100(9), 917–922 (1977) 40. Ordonez, F., Toledo, P., Sanchis, A.: Activity recognition using hybrid generative/discriminative models on home environments using binary sensors. Sensors 13(5), 5460–5477 (2013) 41. San Martin, L., Pelaez, V., Gonzalez, R., Campos, A., Lobato, V.: Environmental user-preference learning for smart homes: An autonomous approach. Journal of Ambient Intelligence and Smart Environments 2(3), 327–342 (2010) 42. Schlimmer, J.C., et al.: Efficiently inducing determinations: A complete and systematic search algorithm that uses optimal pruning. In: ICML, pp. 284–290. Citeseer (1993) 43. Shavlik, J.W., Dietterich, T.G.: Readings in machine learning. Morgan Kauf mann (1990) 44. Sheinvald, J., Dom, B., Niblack, W.: A modeling approach to feature selection. In: Pattern Recognition, 1990. Proceedings., 10th International Conference on, vol. 1, pp. 535–539. IEEE (1990) 45. Smith, G., Sala, S.D., Logie, R., Maylor, E.: Prospective and retrospective memory in normal aging and dementia: A questionnaire study. Memory 8, 311–321 (2000) 46. Stoppiglia, H., Dreyfus, G., Dubois, R., Oussar, Y.: Ranking a random feature for variable and feature selection. The Journal of Machine Learning Research 3, 1399–1414 (2003) 47. Szewcyzk, S., Dwan, K., Minor, B., Swedlove, B., Cook, D.: Annotating smart environment sensor data for activity learning. Technology and Health Care 17(3), 161–169 (2009). DOI 10.3233/THC-2009-0546 48. Van Hoof, J., Wouters, E., Marston, H., Vanrumste, B., Overdiep, R.: Ambient assisted living and care in the Netherlands: The voice of the user. International Journal of Ambient Computing and Intelligence 3(4), 25–40 (2011) 49. Van Kasteren, T., Noulas, A., Englebienne, G., Krose, B.: Accurate activity recognition in a home setting. In: Proceedings of the 10th international conference on Ubiquitous computing, pp. 1–9. ACM (2008) 50. Wang, L. , Gu, T., Tao, X., Lu, J. A hierarchical approach to real-time activity recognition in body sensor networks(2012) Pervasive and Mobile Computing, 8 (1), pp. 115-130 51. Yang, J., Liu, J., Wang, J., Sii, H., Wang, H.: Belief rule-base inference methodology using the evidential reasoning approach RIMER. IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans 36(2), 266–285 (2006). DOI 10.1109/TSMCA.2005.851270 52. Yang, J.B., Xu, D.L.: On the evidential reasoning algorithm for multiple at tribute decision analysis under uncertainty. IEEE Transactions on Systems, Man, and Cybernetics Part A: Systems and Humans. 32(3), 289–304 (2002). DOI 10.1109/TSMCA.2002.802746

PY - 2016/11/5

Y1 - 2016/11/5

N2 - Smart environments are heterogeneous architectures with a broad range of heterogeneous electronic devices that are with high in processing capabilities for computing, considering low power consumption. They have the ability to record information about the behavior of the people by means of their interactions with the objects within an environment. This kind of environments are providing solutions to address some of the problems associated with the growing size and ageing of the population by means of the recognition of activities that can offer monitoring activities of daily living and adapting the environment. In order to deploy low-cost smart environments and reduce the computational complexity for activity recognition, it is a key issue to know the subset of sensors which are relevant for activity recognition. By using feature selection methods to optimize the subset of initial sensors in a smart environment, this paper proposes the adaption of the extended belief rule-based inference methodology (RIMER+) to handle data binary sensors and its use as the suitable classifier for activity recognition that keeps the accuracy of results even in situations where an essential sensor fails. A case study is presented in which a smart environment dataset for activity recognition with 14 sensors is set. Two optimizations with 7 and 10 sensors are obtained with two feature selection methods in which the adaptation of RIMER+ for smart environment provides an encouraged performance against the most popular classifiers in terms of robustness.

AB - Smart environments are heterogeneous architectures with a broad range of heterogeneous electronic devices that are with high in processing capabilities for computing, considering low power consumption. They have the ability to record information about the behavior of the people by means of their interactions with the objects within an environment. This kind of environments are providing solutions to address some of the problems associated with the growing size and ageing of the population by means of the recognition of activities that can offer monitoring activities of daily living and adapting the environment. In order to deploy low-cost smart environments and reduce the computational complexity for activity recognition, it is a key issue to know the subset of sensors which are relevant for activity recognition. By using feature selection methods to optimize the subset of initial sensors in a smart environment, this paper proposes the adaption of the extended belief rule-based inference methodology (RIMER+) to handle data binary sensors and its use as the suitable classifier for activity recognition that keeps the accuracy of results even in situations where an essential sensor fails. A case study is presented in which a smart environment dataset for activity recognition with 14 sensors is set. Two optimizations with 7 and 10 sensors are obtained with two feature selection methods in which the adaptation of RIMER+ for smart environment provides an encouraged performance against the most popular classifiers in terms of robustness.

KW - Heterogeneous Architecture of Sensors · Optimization · Efficient Power-aware · Activity Recognition · Ambient Intelligence · Feature Selection · Data-Driven

U2 - 10.1016/j.micpro.2016.10.007

DO - 10.1016/j.micpro.2016.10.007

M3 - Article

VL - 1000

ER -