Avaliação de técnicas de inteligência computacional para identificação de atividades de vida diária
Resumo
Neste trabalho apresentamos a avaliação do desempenho de algoritmos de machine learning para identificar Atividades de Vida Diária (ADLs) e quedas.Nós avaliamos os seguintes algoritmos: K-Nearest Neighbors, Naive Bayes, Support Vector Machine, Decision Tree, Random Forest, Extra-Trees e Redes Neurais Recorrentes. Utilizamos um conjunto de dados coletados por uma Body Sensor Networks com cinco dispositivos sensores conectados através da interface Bluetooth Low Energy, chamado UMAFall. Obtivemos resultados satisfatórios, principalmente para as atividades saltar e queda frontal, com 100% de acurácia, utilizando o algoritmo Extra-Trees.
Referências
Alam, M. A. U. and Roy, N. (2017). Single bsn-based multi-label activity recognition. The Third IEEE International Workshop on Sensing Systems and Applications Using Wrist Worn Smart Devices, 2017.
Aloulou, H., Mokhtari, M., Tiberghien, T., Biswas, J., Phua, C., Lin, J. H. K., and Yap, P. (2013). Deployment of assistive living technology in a nursing home environment: methods and lessons learned. BMC Medical Informatics and Decision Making, pages 1–17.
Brain, G. (2017). Tensorflow api for python, version r1.6. Available at [link].
Breiman, L. (2001). Random forests. Machine Learning, pages 5–32.
Casilaria, E., Santoyo-Ramón, J. A., and Cano-García, J. M. (2017a). Umafall: A multisensor dataset for the research on automaticfall detection. The 14th International Conference on Mobile Systems and Pervasive Computing, pages 32–29.
Casilaria, E., Santoyo-Ramóna, J. A., and Cano-Garcíaa, J. M. (2017b). Umafall: A multisensor dataset for the research on automatic fall detection. The 14th International Conference on Mobile Systems and Pervasive Computing (MobiSPC 2017), pages 32–39.
Cover, T. and Hart, P. (1967). Nearest neighbor pattern classification. IEEE Transactions on Information Theory, pages 21–27.
Gasparrini, S., Cippitelli, E., Spinsante, S., and Gambi, E. (2014). A depth-based fall detection system using a kinect@ sensor. Sensors, page 2756–2775.
Geurts, P., Ernst, D., and Wehenkel, L. (2006). Extremely randomized trees. Machine Learning, pages 3–42.
Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press. [link].
Gope, P. and Hwang, T. (2016). Bsn-care: A secure iot-based modern healthcare system using body sensor network. IEEE Sensors Journal, pages 1368–1376.
JetBrains (2018). Pycharm v2018.1. Available at [link].
Karim, F., Majumdar, S., Darabi, H., and Chen, S. (2018). Lstm fully convolutional networks for time series classification. IEEE Access, 6:1662–1669.
Katz, S. (1984). Assessing self-maintenance: Activities of daily living, mobility, and instrumental activities of daily living. Journal of the American Geriatrics Society, 31:721–727.
Khan, A. M., Lee, Y. K., Lee, S. Y., and T.S. Kim, T. K. (2010). Human activity recognition via an accelerometer-enabled-smartphone using kernel discriminant analysis. 5th International Conference on Future Information Technology. IEEE, pages 1–6.
Lewis, D. D. (1998). Naive (bayes) at forty: The independence assumption in information retrieval. European Conference on Machine Learning, pages 4–15.
Mano, L. Y., Faiçal, B. S., Nakamura, L. H. V., Gomes, P. H., Libralon, G. L., Meneguete, R. I., Filho, G. P. R., Giancristofaro, G. T., Pessin, G., Krishnamachari, B., and Ueyama, J. (2016). Exploiting iot technologies for enhancing health smart homes through patient identification and emotion recognition. Elsevier Computer Communications, pages 178–190.
Micucci, D., Mobilio, M., and Napoletano, P. (1995). Support-vector networks. Springer Netherlands, pages 273–297.
Micucci, D., Mobilio, M., and Napoletano, P. (2016). Unimib shar: a new dataset for human activity recognition using acceleration data from smartphones. IEEE Sensors Lett, pages 15–18.
Mulak, P. and Talhar, N. (2015). Analysis of distance measures using k-nearest neighbor algorithm on kdd dataset. International Journal of Science and Research (IJSR), pages 2101–2104.
Ojetola, O., Gaura, E., and Brusey, J. (2015). Data set for fall events and daily activities from inertial sensors. Proceedings of the 6th ACM Multimedia Systems Conference (MMSys’15), pages 243–248.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, pages 2825–2830.
Python (2017). Python language reference, version 3.6.4. Available at [link].
Quinlan, J. R. (1986). Induction of decision trees. Machine Learning, pages 81–106.
Shahmohammadi, F., Hosseini, A., King, C. E., and Sarrafzadeh, M. (2017). Smartwatch based activity recognition using active learning. 2017 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), pages 321–329.
Shalev-Shwartz, S. and Ben-David, S. (2014). Understanding Machine Learning:From Theory to Algorithms. Cambridge University Press.
Smola, A. and Vishwanathan, S. (2008). Introduction to Machine Learning. Cambridge University Press.
Stone, M. (1974). Cross-validatory choice and assessment of statistical predictions. Journal of the Royal Statistical Society, pages 111–147.
Sucerquia, A., López, J., and Vargas-bonilla, J. (2017). Sisfall: A fall and movement dataset. Sensors (Basel), pages 1–14.
Vavoulas, G., Chatzaki, C., Malliotakis, T., and Pediaditis, M. (2016). The mobiact dataset: Recognition of activities of daily living using smartphones. Proceedings of the International Conference on Information and Communication Technologies for Ageing Well and e-Health (ICT4AWE), pages 143–151.
Vavoulas, G., Pediaditis, M., Spanakis, E., and Tsiknakis, M. (2013). The mobifall dataset: An initial evaluation of fall detection algorithms using smartphones. Proceedings of the IEEE 13th International Conference on Bioinformatics and Bioengineering (BIBE 2013), pages 1–4.
Weiss, G. M., Timko, J. L., Gallagher, C. M., Yoneda, K., and Schreiber, A. J. (2016). Smartwatch-based activity recognition : A machine learning approach. 2016 IEEE-EMBS International Conference on Biomedical and Health Informatics, pages 426–429.
Aloulou, H., Mokhtari, M., Tiberghien, T., Biswas, J., Phua, C., Lin, J. H. K., and Yap, P. (2013). Deployment of assistive living technology in a nursing home environment: methods and lessons learned. BMC Medical Informatics and Decision Making, pages 1–17.
Brain, G. (2017). Tensorflow api for python, version r1.6. Available at [link].
Breiman, L. (2001). Random forests. Machine Learning, pages 5–32.
Casilaria, E., Santoyo-Ramón, J. A., and Cano-García, J. M. (2017a). Umafall: A multisensor dataset for the research on automaticfall detection. The 14th International Conference on Mobile Systems and Pervasive Computing, pages 32–29.
Casilaria, E., Santoyo-Ramóna, J. A., and Cano-Garcíaa, J. M. (2017b). Umafall: A multisensor dataset for the research on automatic fall detection. The 14th International Conference on Mobile Systems and Pervasive Computing (MobiSPC 2017), pages 32–39.
Cover, T. and Hart, P. (1967). Nearest neighbor pattern classification. IEEE Transactions on Information Theory, pages 21–27.
Gasparrini, S., Cippitelli, E., Spinsante, S., and Gambi, E. (2014). A depth-based fall detection system using a kinect@ sensor. Sensors, page 2756–2775.
Geurts, P., Ernst, D., and Wehenkel, L. (2006). Extremely randomized trees. Machine Learning, pages 3–42.
Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press. [link].
Gope, P. and Hwang, T. (2016). Bsn-care: A secure iot-based modern healthcare system using body sensor network. IEEE Sensors Journal, pages 1368–1376.
JetBrains (2018). Pycharm v2018.1. Available at [link].
Karim, F., Majumdar, S., Darabi, H., and Chen, S. (2018). Lstm fully convolutional networks for time series classification. IEEE Access, 6:1662–1669.
Katz, S. (1984). Assessing self-maintenance: Activities of daily living, mobility, and instrumental activities of daily living. Journal of the American Geriatrics Society, 31:721–727.
Khan, A. M., Lee, Y. K., Lee, S. Y., and T.S. Kim, T. K. (2010). Human activity recognition via an accelerometer-enabled-smartphone using kernel discriminant analysis. 5th International Conference on Future Information Technology. IEEE, pages 1–6.
Lewis, D. D. (1998). Naive (bayes) at forty: The independence assumption in information retrieval. European Conference on Machine Learning, pages 4–15.
Mano, L. Y., Faiçal, B. S., Nakamura, L. H. V., Gomes, P. H., Libralon, G. L., Meneguete, R. I., Filho, G. P. R., Giancristofaro, G. T., Pessin, G., Krishnamachari, B., and Ueyama, J. (2016). Exploiting iot technologies for enhancing health smart homes through patient identification and emotion recognition. Elsevier Computer Communications, pages 178–190.
Micucci, D., Mobilio, M., and Napoletano, P. (1995). Support-vector networks. Springer Netherlands, pages 273–297.
Micucci, D., Mobilio, M., and Napoletano, P. (2016). Unimib shar: a new dataset for human activity recognition using acceleration data from smartphones. IEEE Sensors Lett, pages 15–18.
Mulak, P. and Talhar, N. (2015). Analysis of distance measures using k-nearest neighbor algorithm on kdd dataset. International Journal of Science and Research (IJSR), pages 2101–2104.
Ojetola, O., Gaura, E., and Brusey, J. (2015). Data set for fall events and daily activities from inertial sensors. Proceedings of the 6th ACM Multimedia Systems Conference (MMSys’15), pages 243–248.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, pages 2825–2830.
Python (2017). Python language reference, version 3.6.4. Available at [link].
Quinlan, J. R. (1986). Induction of decision trees. Machine Learning, pages 81–106.
Shahmohammadi, F., Hosseini, A., King, C. E., and Sarrafzadeh, M. (2017). Smartwatch based activity recognition using active learning. 2017 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), pages 321–329.
Shalev-Shwartz, S. and Ben-David, S. (2014). Understanding Machine Learning:From Theory to Algorithms. Cambridge University Press.
Smola, A. and Vishwanathan, S. (2008). Introduction to Machine Learning. Cambridge University Press.
Stone, M. (1974). Cross-validatory choice and assessment of statistical predictions. Journal of the Royal Statistical Society, pages 111–147.
Sucerquia, A., López, J., and Vargas-bonilla, J. (2017). Sisfall: A fall and movement dataset. Sensors (Basel), pages 1–14.
Vavoulas, G., Chatzaki, C., Malliotakis, T., and Pediaditis, M. (2016). The mobiact dataset: Recognition of activities of daily living using smartphones. Proceedings of the International Conference on Information and Communication Technologies for Ageing Well and e-Health (ICT4AWE), pages 143–151.
Vavoulas, G., Pediaditis, M., Spanakis, E., and Tsiknakis, M. (2013). The mobifall dataset: An initial evaluation of fall detection algorithms using smartphones. Proceedings of the IEEE 13th International Conference on Bioinformatics and Bioengineering (BIBE 2013), pages 1–4.
Weiss, G. M., Timko, J. L., Gallagher, C. M., Yoneda, K., and Schreiber, A. J. (2016). Smartwatch-based activity recognition : A machine learning approach. 2016 IEEE-EMBS International Conference on Biomedical and Health Informatics, pages 426–429.
Publicado
22/07/2018
Como Citar
MACHADO, Wylken S.; BARROS, Pedro H.; ALMEIDA, Eliana S.; AQUINO, Andre L. L..
Avaliação de técnicas de inteligência computacional para identificação de atividades de vida diária. In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO UBÍQUA E PERVASIVA (SBCUP), 10. , 2018, Natal.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2018
.
p. 141-150.
ISSN 2595-6183.
DOI: https://doi.org/10.5753/sbcup.2018.3296.
