Determination of the most relevant features to improve the performance of RF classifier in human activity recognition
The impact that neurodegenerative diseases have in our society, have made human activity recognition (HAR) arise as a relevant field of study. The quality of life of people with such conditions, can be significantly improved with the outcomes of the projects within this area. The application of mach...
- Autores:
-
Jiménez-Gómez, Geovanna
Navarro-Escorcia, Daniela
Neira Rodado, Dionicio
Cleland, Ian
- Tipo de recurso:
- Article of journal
- Fecha de publicación:
- 2021
- Institución:
- Corporación Universidad de la Costa
- Repositorio:
- REDICUC - Repositorio CUC
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.cuc.edu.co:11323/8843
- Acceso en línea:
- https://hdl.handle.net/11323/8843
https://repositorio.cuc.edu.co/
- Palabra clave:
- HAR
Machine learning
Feature selection
RF classifier
- Rights
- embargoedAccess
- License
- CC0 1.0 Universal
| id |
RCUC2_1897b07e33699e8bd5ce4ace3b1e0c6c |
|---|---|
| oai_identifier_str |
oai:repositorio.cuc.edu.co:11323/8843 |
| network_acronym_str |
RCUC2 |
| network_name_str |
REDICUC - Repositorio CUC |
| repository_id_str |
|
| dc.title.spa.fl_str_mv |
Determination of the most relevant features to improve the performance of RF classifier in human activity recognition |
| title |
Determination of the most relevant features to improve the performance of RF classifier in human activity recognition |
| spellingShingle |
Determination of the most relevant features to improve the performance of RF classifier in human activity recognition HAR Machine learning Feature selection RF classifier |
| title_short |
Determination of the most relevant features to improve the performance of RF classifier in human activity recognition |
| title_full |
Determination of the most relevant features to improve the performance of RF classifier in human activity recognition |
| title_fullStr |
Determination of the most relevant features to improve the performance of RF classifier in human activity recognition |
| title_full_unstemmed |
Determination of the most relevant features to improve the performance of RF classifier in human activity recognition |
| title_sort |
Determination of the most relevant features to improve the performance of RF classifier in human activity recognition |
| dc.creator.fl_str_mv |
Jiménez-Gómez, Geovanna Navarro-Escorcia, Daniela Neira Rodado, Dionicio Cleland, Ian |
| dc.contributor.author.spa.fl_str_mv |
Jiménez-Gómez, Geovanna Navarro-Escorcia, Daniela Neira Rodado, Dionicio Cleland, Ian |
| dc.subject.spa.fl_str_mv |
HAR Machine learning Feature selection RF classifier |
| topic |
HAR Machine learning Feature selection RF classifier |
| description |
The impact that neurodegenerative diseases have in our society, have made human activity recognition (HAR) arise as a relevant field of study. The quality of life of people with such conditions, can be significantly improved with the outcomes of the projects within this area. The application of machine learning techniques on data from low level sensors such as accelerometers is the base of HAR. To improve the performance of these classifiers, it is necessary to carry out an adequate training process. To improve the training process, an analysis of the different features used in literature to tackle these problems was performed on datasets constructed with students performing 18 different activities of daily living. The outcome of the process shows that an adequate selection of features improves the performance of Random Forest from 94.6% to 97.2%. It was also found that 78 features explain 80% of the variability. |
| publishDate |
2021 |
| dc.date.accessioned.none.fl_str_mv |
2021-11-08T13:11:42Z |
| dc.date.available.none.fl_str_mv |
2021-11-08T13:11:42Z |
| dc.date.issued.none.fl_str_mv |
2021-09-17 |
| dc.date.embargoEnd.none.fl_str_mv |
2022-09-17 |
| dc.type.spa.fl_str_mv |
Artículo de revista |
| dc.type.coar.fl_str_mv |
http://purl.org/coar/resource_type/c_2df8fbb1 |
| dc.type.coar.spa.fl_str_mv |
http://purl.org/coar/resource_type/c_6501 |
| dc.type.content.spa.fl_str_mv |
Text |
| dc.type.driver.spa.fl_str_mv |
info:eu-repo/semantics/article |
| dc.type.redcol.spa.fl_str_mv |
http://purl.org/redcol/resource_type/ART |
| dc.type.version.spa.fl_str_mv |
info:eu-repo/semantics/acceptedVersion |
| format |
http://purl.org/coar/resource_type/c_6501 |
| status_str |
acceptedVersion |
| dc.identifier.issn.spa.fl_str_mv |
978-303084339-7 |
| dc.identifier.uri.spa.fl_str_mv |
https://hdl.handle.net/11323/8843 |
| dc.identifier.doi.spa.fl_str_mv |
10.1007/978-3-030-84340-3_3 |
| dc.identifier.instname.spa.fl_str_mv |
Corporación Universidad de la Costa |
| dc.identifier.reponame.spa.fl_str_mv |
REDICUC - Repositorio CUC |
| dc.identifier.repourl.spa.fl_str_mv |
https://repositorio.cuc.edu.co/ |
| identifier_str_mv |
978-303084339-7 10.1007/978-3-030-84340-3_3 Corporación Universidad de la Costa REDICUC - Repositorio CUC |
| url |
https://hdl.handle.net/11323/8843 https://repositorio.cuc.edu.co/ |
| dc.language.iso.none.fl_str_mv |
eng |
| language |
eng |
| dc.relation.references.spa.fl_str_mv |
Dementia: https://www.who.int/news-room/fact-sheets/detail/dementia. Accessed 15 May 2021 Prince, M., Wimo, A., Guerchet, M., Ali, G.-C., Wu, Y.-T., Prina, M.: World Alzheimer Report 2015, The Global Impact of Dementia: An Analysis of Prevalence, Incidence, Cost and Trends, p. 87 Prince, M., Comas-Herrera, A., Knapp, M., Guerchet, M., Karagiannidou, M.: World Alzheimer Report 2016 Improving Healthcare for People Living with Dementia Coverage, QualIty and Costs Now and in the Future De-La-Hoz-Franco, E., Ariza-Colpas, P., Quero, J.M., Espinilla, M.: Sensor-based datasets for human activity recognition - a systematic review of literature. IEEE Access 6, 59192–59210 (2018). https://ezproxy.cuc.edu.co:2067/10.1109/ACCESS.2018.2873502 Aparisi, F., Carlos, J., Díaz, G.: Aumento de la potencia del gráfico de control multivariante T 2 de Hotelling utilizando señales adicionales de falta de control (2001) Noor, M.H.M., Salcic, Z., Wang, K.I.K.: Adaptive sliding window segmentation for physical activity recognition using a single tri-axial accelerometer. Perv. Mob. Comput. 38, 41–59 (2017). https://ezproxy.cuc.edu.co:2067/10.1016/j.pmcj.2016.09.009 Cerasuolo, J.O., et al.: Population-based stroke and dementia incidence trends: age and sex variations. Alzheimers Dement. 13(10), 1081–1088 (2017). https://ezproxy.cuc.edu.co:2067/10.1016/j.jalz.2017.02.010 Neira-Rodado, D., Nugent, C., Cleland, I., Velasquez, J., Viloria, A.: Evaluating the impact of a two-stage multivariate data cleansing approach to improve to the performance of machine learning classifiers: a case study in human activity recognition. Sensors 20(7), 2020 (1858). https://ezproxy.cuc.edu.co:2067/10.3390/s20071858 Ni, Q., García Hernando, A., de la Cruz, I.: The elderly’s independent living in smart homes: a characterization of activities and sensing infrastructure survey to facilitate services development. Sensors 15(5), 11312–11362 (2015). https://ezproxy.cuc.edu.co:2067/10.3390/s150511312 Mukhopadhyay, S.C.: Wearable sensors for human activity monitoring: a review. IEEE Sens. J. 15(3), 1321–1330 (2015). https://ezproxy.cuc.edu.co:2067/10.1109/JSEN.2014.2370945 Chen, L., Hoey, J., Chris, N., Cook, D., Yu, Z.: Sensor-based activity recognition. IEEE Trans. 42(6), 790–808 (2012) Kleinberger, T., Becker, M., Ras, E., Holzinger, A., Müller, P.: Ambient intelligence in assisted living: enable elderly people to handle future interfaces. In: Stephanidis, Constantine (ed.) UAHCI 2007. LNCS, vol. 4555, pp. 103–112. Springer, Heidelberg (2007). https://ezproxy.cuc.edu.co:2067/10.1007/978-3-540-73281-5_11 Chen, Y., Xue, Y.: A deep learning approach to human activity recognition based on single accelerometer. In: Proceedings of the 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015, pp. 1488–1492 (2016). https://ezproxy.cuc.edu.co:2067/10.1109/SMC.2015.263 Qi, W., Su, H., Yang, C., Ferrigno, G., De Momi, E., Aliverti, A.: A fast and robust deep convolutional neural networks for complex human activity recognition using smartphone. Sensors (Switzerland) 19(17), 3731 (2019). https://ezproxy.cuc.edu.co:2067/10.3390/s19173731 Domingos, P.: A few useful things to know about machine learning. Commun. ACM 55(10), 78–87 (2012). https://ezproxy.cuc.edu.co:2067/10.1145/2347736.2347755 Pires, I., et al.: From data acquisition to data fusion: a comprehensive review and a roadmap for the identification of activities of daily living using mobile devices. Sensors 16(2), 184 (2016). https://ezproxy.cuc.edu.co:2067/10.3390/s16020184 Veeriah, V., Zhuang, N., Qi, G.-J.: Differential recurrent neural networks for action recognition (2015) Janidarmian, M., Roshan Fekr, A., Radecka, K., Zilic, Z.: A comprehensive analysis on wearable acceleration sensors in human activity recognition. Sensors 17(3), 529 (2017). https://ezproxy.cuc.edu.co:2067/10.3390/s17030529 Tian, Y., Zhang, J., Wang, J., Geng, Y., Wang, X.: Robust human activity recognition using single accelerometer via wavelet energy spectrum features and ensemble feature selection. Syst. Sci. Contr. Eng. 8(1), 83–96 (2020). https://ezproxy.cuc.edu.co:2067/10.1080/21642583.2020.1723142 Li, F., Shirahama, K., Nisar, M.A., Köping, L., Grzegorzek, M.: Comparison of feature learning methods for human activity recognition using wearable sensors. Sensors 18(3), 679 (2018). https://ezproxy.cuc.edu.co:2067/10.3390/s18020679 Irvine, N.: The Impact of Dataset Quality on the Performance of Data-Driven Approaches for Human Activity Recognition, pp. 1–8 Cornacchia, M., Ozcan, K., Zheng, Y., Velipasalar, S.: A survey on activity detection and classification using wearable sensors. IEEE Sens. J. 17(2), 386–403 (2017). https://ezproxy.cuc.edu.co:2067/10.1109/JSEN.2016.2628346 Koziarski, M., Krawczyk, B., Woźniak, M.: The deterministic subspace method for constructing classifier ensembles. Pattern Anal. Appl. 20(4), 981–990 (2017). https://ezproxy.cuc.edu.co:2067/10.1007/s10044-017-0655-2 |
| dc.rights.spa.fl_str_mv |
CC0 1.0 Universal |
| dc.rights.uri.spa.fl_str_mv |
http://creativecommons.org/publicdomain/zero/1.0/ |
| dc.rights.accessrights.spa.fl_str_mv |
info:eu-repo/semantics/embargoedAccess |
| dc.rights.coar.spa.fl_str_mv |
http://purl.org/coar/access_right/c_f1cf |
| rights_invalid_str_mv |
CC0 1.0 Universal http://creativecommons.org/publicdomain/zero/1.0/ http://purl.org/coar/access_right/c_f1cf |
| eu_rights_str_mv |
embargoedAccess |
| dc.format.mimetype.spa.fl_str_mv |
application/pdf |
| dc.publisher.spa.fl_str_mv |
Springer International Publishing |
| dc.source.spa.fl_str_mv |
Lecture Notes in Computer Science |
| institution |
Corporación Universidad de la Costa |
| dc.source.url.spa.fl_str_mv |
https://www.springerprofessional.de/en/determination-of-the-most-relevant-features-to-improve-the-perfo/19669904 |
| bitstream.url.fl_str_mv |
https://repositorio.cuc.edu.co/bitstreams/e6128738-9b55-4699-9628-202ad383743b/download https://repositorio.cuc.edu.co/bitstreams/22867305-e2cf-4d71-b933-5e6d3de5483f/download https://repositorio.cuc.edu.co/bitstreams/474cb7ec-7c3a-4304-97f5-0c458389d65b/download https://repositorio.cuc.edu.co/bitstreams/5ee44446-c495-46c2-9322-6c805e019f69/download https://repositorio.cuc.edu.co/bitstreams/fc2f5ce6-0e84-4c07-9850-578b14991b4a/download |
| bitstream.checksum.fl_str_mv |
d69fd0e806211a6300b9ec57058b6f19 42fd4ad1e89814f5e4a476b409eb708c e30e9215131d99561d40d6b0abbe9bad b14e1c50f5cd3484b36e3d955c3edbfd 165dc7d09cecabc44f32d98ed7774b53 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio de la Universidad de la Costa CUC |
| repository.mail.fl_str_mv |
repdigital@cuc.edu.co |
| _version_ |
1828166880959922176 |
| spelling |
Jiménez-Gómez, GeovannaNavarro-Escorcia, DanielaNeira Rodado, DionicioCleland, Ian2021-11-08T13:11:42Z2021-11-08T13:11:42Z2021-09-172022-09-17978-303084339-7https://hdl.handle.net/11323/884310.1007/978-3-030-84340-3_3Corporación Universidad de la CostaREDICUC - Repositorio CUChttps://repositorio.cuc.edu.co/The impact that neurodegenerative diseases have in our society, have made human activity recognition (HAR) arise as a relevant field of study. The quality of life of people with such conditions, can be significantly improved with the outcomes of the projects within this area. The application of machine learning techniques on data from low level sensors such as accelerometers is the base of HAR. To improve the performance of these classifiers, it is necessary to carry out an adequate training process. To improve the training process, an analysis of the different features used in literature to tackle these problems was performed on datasets constructed with students performing 18 different activities of daily living. The outcome of the process shows that an adequate selection of features improves the performance of Random Forest from 94.6% to 97.2%. It was also found that 78 features explain 80% of the variability.Jiménez-Gómez, GeovannaNavarro-Escorcia, DanielaNeira Rodado, Dionicio-will be generated-orcid-0000-0003-0837-7083-600Cleland, Ian-will be generated-orcid-0000-0003-2368-7354-600application/pdfengSpringer International PublishingCC0 1.0 Universalhttp://creativecommons.org/publicdomain/zero/1.0/info:eu-repo/semantics/embargoedAccesshttp://purl.org/coar/access_right/c_f1cfLecture Notes in Computer Sciencehttps://www.springerprofessional.de/en/determination-of-the-most-relevant-features-to-improve-the-perfo/19669904HARMachine learningFeature selectionRF classifierDetermination of the most relevant features to improve the performance of RF classifier in human activity recognitionArtículo de revistahttp://purl.org/coar/resource_type/c_6501http://purl.org/coar/resource_type/c_2df8fbb1Textinfo:eu-repo/semantics/articlehttp://purl.org/redcol/resource_type/ARTinfo:eu-repo/semantics/acceptedVersionDementia: https://www.who.int/news-room/fact-sheets/detail/dementia. Accessed 15 May 2021Prince, M., Wimo, A., Guerchet, M., Ali, G.-C., Wu, Y.-T., Prina, M.: World Alzheimer Report 2015, The Global Impact of Dementia: An Analysis of Prevalence, Incidence, Cost and Trends, p. 87Prince, M., Comas-Herrera, A., Knapp, M., Guerchet, M., Karagiannidou, M.: World Alzheimer Report 2016 Improving Healthcare for People Living with Dementia Coverage, QualIty and Costs Now and in the FutureDe-La-Hoz-Franco, E., Ariza-Colpas, P., Quero, J.M., Espinilla, M.: Sensor-based datasets for human activity recognition - a systematic review of literature. IEEE Access 6, 59192–59210 (2018). https://ezproxy.cuc.edu.co:2067/10.1109/ACCESS.2018.2873502Aparisi, F., Carlos, J., Díaz, G.: Aumento de la potencia del gráfico de control multivariante T 2 de Hotelling utilizando señales adicionales de falta de control (2001)Noor, M.H.M., Salcic, Z., Wang, K.I.K.: Adaptive sliding window segmentation for physical activity recognition using a single tri-axial accelerometer. Perv. Mob. Comput. 38, 41–59 (2017). https://ezproxy.cuc.edu.co:2067/10.1016/j.pmcj.2016.09.009Cerasuolo, J.O., et al.: Population-based stroke and dementia incidence trends: age and sex variations. Alzheimers Dement. 13(10), 1081–1088 (2017). https://ezproxy.cuc.edu.co:2067/10.1016/j.jalz.2017.02.010Neira-Rodado, D., Nugent, C., Cleland, I., Velasquez, J., Viloria, A.: Evaluating the impact of a two-stage multivariate data cleansing approach to improve to the performance of machine learning classifiers: a case study in human activity recognition. Sensors 20(7), 2020 (1858). https://ezproxy.cuc.edu.co:2067/10.3390/s20071858Ni, Q., García Hernando, A., de la Cruz, I.: The elderly’s independent living in smart homes: a characterization of activities and sensing infrastructure survey to facilitate services development. Sensors 15(5), 11312–11362 (2015). https://ezproxy.cuc.edu.co:2067/10.3390/s150511312Mukhopadhyay, S.C.: Wearable sensors for human activity monitoring: a review. IEEE Sens. J. 15(3), 1321–1330 (2015). https://ezproxy.cuc.edu.co:2067/10.1109/JSEN.2014.2370945Chen, L., Hoey, J., Chris, N., Cook, D., Yu, Z.: Sensor-based activity recognition. IEEE Trans. 42(6), 790–808 (2012)Kleinberger, T., Becker, M., Ras, E., Holzinger, A., Müller, P.: Ambient intelligence in assisted living: enable elderly people to handle future interfaces. In: Stephanidis, Constantine (ed.) UAHCI 2007. LNCS, vol. 4555, pp. 103–112. Springer, Heidelberg (2007). https://ezproxy.cuc.edu.co:2067/10.1007/978-3-540-73281-5_11Chen, Y., Xue, Y.: A deep learning approach to human activity recognition based on single accelerometer. In: Proceedings of the 2015 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2015, pp. 1488–1492 (2016). https://ezproxy.cuc.edu.co:2067/10.1109/SMC.2015.263Qi, W., Su, H., Yang, C., Ferrigno, G., De Momi, E., Aliverti, A.: A fast and robust deep convolutional neural networks for complex human activity recognition using smartphone. Sensors (Switzerland) 19(17), 3731 (2019). https://ezproxy.cuc.edu.co:2067/10.3390/s19173731Domingos, P.: A few useful things to know about machine learning. Commun. ACM 55(10), 78–87 (2012). https://ezproxy.cuc.edu.co:2067/10.1145/2347736.2347755Pires, I., et al.: From data acquisition to data fusion: a comprehensive review and a roadmap for the identification of activities of daily living using mobile devices. Sensors 16(2), 184 (2016). https://ezproxy.cuc.edu.co:2067/10.3390/s16020184Veeriah, V., Zhuang, N., Qi, G.-J.: Differential recurrent neural networks for action recognition (2015)Janidarmian, M., Roshan Fekr, A., Radecka, K., Zilic, Z.: A comprehensive analysis on wearable acceleration sensors in human activity recognition. Sensors 17(3), 529 (2017). https://ezproxy.cuc.edu.co:2067/10.3390/s17030529Tian, Y., Zhang, J., Wang, J., Geng, Y., Wang, X.: Robust human activity recognition using single accelerometer via wavelet energy spectrum features and ensemble feature selection. Syst. Sci. Contr. Eng. 8(1), 83–96 (2020). https://ezproxy.cuc.edu.co:2067/10.1080/21642583.2020.1723142Li, F., Shirahama, K., Nisar, M.A., Köping, L., Grzegorzek, M.: Comparison of feature learning methods for human activity recognition using wearable sensors. Sensors 18(3), 679 (2018). https://ezproxy.cuc.edu.co:2067/10.3390/s18020679Irvine, N.: The Impact of Dataset Quality on the Performance of Data-Driven Approaches for Human Activity Recognition, pp. 1–8Cornacchia, M., Ozcan, K., Zheng, Y., Velipasalar, S.: A survey on activity detection and classification using wearable sensors. IEEE Sens. J. 17(2), 386–403 (2017). https://ezproxy.cuc.edu.co:2067/10.1109/JSEN.2016.2628346Koziarski, M., Krawczyk, B., Woźniak, M.: The deterministic subspace method for constructing classifier ensembles. Pattern Anal. Appl. 20(4), 981–990 (2017). https://ezproxy.cuc.edu.co:2067/10.1007/s10044-017-0655-2PublicationORIGINALDETERMINATION OF THE MOST RELEVANT FEATURES TO IMPROVE THE PERFORMANCE OF RF CLASSIFIER IN HUMAN ACTIVITY RECOGNITION.pdfDETERMINATION OF THE MOST RELEVANT FEATURES TO IMPROVE THE PERFORMANCE OF RF CLASSIFIER IN HUMAN ACTIVITY RECOGNITION.pdfapplication/pdf28853https://repositorio.cuc.edu.co/bitstreams/e6128738-9b55-4699-9628-202ad383743b/downloadd69fd0e806211a6300b9ec57058b6f19MD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8701https://repositorio.cuc.edu.co/bitstreams/22867305-e2cf-4d71-b933-5e6d3de5483f/download42fd4ad1e89814f5e4a476b409eb708cMD52LICENSElicense.txtlicense.txttext/plain; charset=utf-83196https://repositorio.cuc.edu.co/bitstreams/474cb7ec-7c3a-4304-97f5-0c458389d65b/downloade30e9215131d99561d40d6b0abbe9badMD53THUMBNAILDETERMINATION OF THE MOST RELEVANT FEATURES TO IMPROVE THE PERFORMANCE OF RF CLASSIFIER IN HUMAN ACTIVITY RECOGNITION.pdf.jpgDETERMINATION OF THE MOST RELEVANT FEATURES TO IMPROVE THE PERFORMANCE OF RF CLASSIFIER IN HUMAN ACTIVITY RECOGNITION.pdf.jpgimage/jpeg46803https://repositorio.cuc.edu.co/bitstreams/5ee44446-c495-46c2-9322-6c805e019f69/downloadb14e1c50f5cd3484b36e3d955c3edbfdMD54TEXTDETERMINATION OF THE MOST RELEVANT FEATURES TO IMPROVE THE PERFORMANCE OF RF CLASSIFIER IN HUMAN ACTIVITY RECOGNITION.pdf.txtDETERMINATION OF THE MOST RELEVANT FEATURES TO IMPROVE THE PERFORMANCE OF RF CLASSIFIER IN HUMAN ACTIVITY RECOGNITION.pdf.txttext/plain1235https://repositorio.cuc.edu.co/bitstreams/fc2f5ce6-0e84-4c07-9850-578b14991b4a/download165dc7d09cecabc44f32d98ed7774b53MD5511323/8843oai:repositorio.cuc.edu.co:11323/88432024-09-17 14:21:27.17http://creativecommons.org/publicdomain/zero/1.0/CC0 1.0 Universalopen.accesshttps://repositorio.cuc.edu.coRepositorio de la Universidad de la Costa CUCrepdigital@cuc.edu.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 |