SeAct: Semantic Adaptive Segmentation of Sensor Data Streams for Human Activity Recognition

• Amanda D. P. Venceslau Universidade Federal do Ceará (UFC) http://orcid.org/0000-0003-4118-4224
• Vânia M. P. Vidal Universidade Federal do Ceará (UFC)
• Rossana M. C. Andrade Universidade Federal do Ceará (UFC)
• José Gilvan R. Maia Universidade Federal do Ceará (UFC)
• José Wellington F. da Silva Universidade Federal do Ceará (UFC)

DOI: https://doi.org/10.5753/sbbd.2022.225042

Resumo

Pervasive computing delivers services based on user needs through smart environments that incorporate and integrate everyday objects discreet and non-intrusive. Personal applications provide the data collected by sensors for Human Activity Recognition. The main limitation is that these activities need to be continuously segmented for HAR. Furthermore, a growing problem is related to the disambiguation of activities since some actions generated by the same sensors belong to different activities. This paper proposes a hybrid method, SeAct, which dynamically adjusts segment size, combining machine learning and semantic inference. Experiments with CAD-120 data sets and a state-of-the-art hybrid method improve recognition accuracy and precision.

Palavras-chave: Data Segmentation, Human Activity Recognition, Hybrid Method, Machine Learning and Semantic Inference

Referências

Akbar, A., Chaudhry, S. S., Khan, A., Ali, A., and Rafiq, W. (2019). On complex event processing for internet of things. In 2019 IEEE 6th International Conference on Engineering Technologies and Applied Sciences (ICETAS), pages 1-7. IEEE.

Asghari, P., Soleimani, E., and Nazerfard, E. (2020). Online human activity recognition employing hierarchical hidden markov models. Journal of Ambient Intelligence and Humanized Computing, 11(3):1141-1152.

Chen, C. Y., Fu, J. H., Sung, T., Wang, P.-F., Jou, E., and Feng, M.-W. (2014). Complex event processing for the internet of things and its applications. In 2014 IEEE International Conference on Automation Science and Engineering (CASE), pages 1144-1149. IEEE.

Civitarese, G., Bettini, C., Sztyler, T., Riboni, D., and Stuckenschmidt, H. (2018). Nectar: Knowledge-based collaborative active learning for activity recognition. In 2018 IEEE International Conference on Pervasive Computing and Communications (PerCom), pages 1-10. IEEE.

Civitarese, G., Sztyler, T., Riboni, D., Bettini, C., and Stuckenschmidt, H. (2019). Polaris: Probabilistic and ontological activity recognition in smart-homes. IEEE Transactions on Knowledge and Data Engineering, 33(1):209-223.

Diaz-Rodriguez, N., Cadahia, O. L., Cuellar, M. P., Lilius, J., and Calvo-Flores, M. D. (2014). Handling real-world context awareness, uncertainty and vagueness in real-time human activity tracking and recognition with a fuzzy ontology-based hybrid method. Sensors, 14(10):18131-18171.

Dong, Y., Liu, J., Gao, Y., Sarkar, S., Hu, Z., Fagert, J., Pan, S., Zhang, P., Noh, H. Y., and Mirshekari, M. (2020). A window-based sequence-to-one approach with dynamic voting for nurse care activity recognition using acceleration-based wearable sensor. In Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers, pages 390-395.

Elsaleh, T., Enshaeifar, S., Rezvani, R., Acton, S. T., Janeiko, V., and Bermudez-Edo, M. (2020). Iot-stream: A lightweight ontology for internet of things data streams and its use with data analytics and event detection services. Sensors, 20(4):953.

Fu, T. C. (2011). A review on time series data mining. Engineering Applications of Artificial Intelligence, 24(1):164-181.

Junior, E. C., Andrade, R. M. C., Venceslau, A. D. P., Oliveira, P. A. M., Santos, I. S., and Oliveira, B. S. (2022). Where is the internet of health things data? In Proceedings of the 24th International Conference on International Conference on Enterprise Information Systems (ICEIS), pages 1-10.

Keogh, E., Chakrabarti, K., Pazzani, M., and Mehrotra, S. (2001). Dimensionality reduction for fast similarity search in large time series databases. Knowledge and information Systems, 3(3):263-286.

Koppula, H. S., Gupta, R., and Saxena, A. (2013). Learning human activities and object affordances from rgb-d videos. The International Journal of Robotics Research, 32(8):951-970.

Krishnan, N. C. and Cook, D. J. (2014). Activity recognition on streaming sensor data. Pervasive and mobile computing, 10:138-154.

Krotzsch, M., Simancik, F., and Horrocks, I. (2012). A description logic primer. arXiv preprint arXiv:1201.4089.

Mallick, M., Kodeswaran, P., Sen, S., Kokku, R., and Ganguly, N. (2018). Tsfs: An integrated approach for event segmentation and adl detection in iot enabled smarthomes. IEEE Transactions on Mobile Computing, 18(11):2686-2700.

Memon, M., Wagner, S. R., Pedersen, C. F., Beevi, F. H. A., and Hansen, F. O. (2014). Ambient assisted living healthcare frameworks, platforms, standards, and quality attributes. Sensors, 14(3):4312-4341.

Okeyo, G., Chen, L., Wang, H., and Sterritt, R. (2014). Dynamic sensor data segmentation for real-time knowledge-driven activity recognition. Pervasive and Mobile Computing, 10:155-172.

Pan, S., Berges, M., Rodakowski, J., Zhang, P., and Noh, H. Y. (2019). Fine-grained recognition of activities of daily living through structural vibration and electrical sensing. In Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, pages 149-158.

Patel, A. and Shah, J. (2021). Smart ecosystem to facilitate the elderly in ambient assisted living. In Proceedings of International Conference on Recent Trends in Machine Learning, IoT, Smart Cities and Applications, pages 501-510. Springer.

Postolache, O., Madeira, R. N., Correia, N., and Girao, P. S. (2009). Ubismartwheel: a ubiquitous system with unobtrusive services embedded on a wheelchair. In Proceedings of the 2nd International Conference on PErvasive Technologies Related to Assistive Environments, pages 1-4.

Rawashdeh, M., Al Zamil, M. G., Samarah, S., Hossain, M. S., and Muhammad, G. (2020). A knowledge-driven approach for activity recognition in smart homes based on activity profiling. Future Generation Computer Systems, 107:924-941.

Salguero, A. G., Espinilla, M., Delatorre, P., and Medina, J. (2018). Using ontologies for the online recognition of activities of daily living. Sensors, 18(4):1202.

Serpush, F., Menhaj, M. B., Masoumi, B., and Karasfi, B. (2022). Wearable sensor-based human activity recognition in the smart healthcare system. Computational Intelligence and Neuroscience, 2022.

Sfar, H. and Bouzeghoub, A. (2019). Dataseg: dynamic streaming sensor data segmentation for activity recognition. In Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing, pages 557-563.

Triboan, D., Chen, L., Chen, F., and Wang, Z. (2017). Semantic segmentation of realtime sensor data stream for complex activity recognition. Personal and Ubiquitous Computing, 21(3):411-425.

Triboan, D., Chen, L., Chen, F., and Wang, Z. (2019). A semantics-based approach to sensor data segmentation in real-time activity recognition. Future Generation Computer Systems, 93:224-236.

Wan, J., O’grady, M. J., and O’Hare, G. M. (2015). Dynamic sensor event segmentation for real-time activity recognition in a smart home context. Personal and Ubiquitous Computing, 19(2):287-301.

Wohlin, C., Runeson, P., Host, M., Ohlsson, M. C., Regnell, B., and Wesslén, A. (2012). Experimentation in software engineering. Springer Science & Business Media.