Can a simple approach identify complex nurse care activity?

ABSTRACT

For the last two decades, more and more complex methods have been developed to identify human activities using various types of sensors, e.g., data from motion capture, accelerometer, and gyroscopes sensors. To date, most of the researches mainly focus on identifying simple human activities, e.g., walking, eating, and running. However, many of our daily life activities are usually more complex than those. To instigate research in complex activity recognition, the "Nurse Care Activity Recognition Challenge" [1] is initiated where six nurse activities are to be identified based on location, air pressure, motion capture, and accelerometer data. Our team, "IITDU", investigates the use of simple methods for this purpose. We first extract features from the sensor data and use one of the simplest classifiers, namely K-Nearest Neighbors (KNN). Experiment using an ensemble of KNN classifiers demonstrates that it is possible to achieve approximately 87% accuracy on 10-fold cross-validation and 66% accuracy on leave-one-subject-out cross-validation.

References

1. 2019. Nurse Care Activity Recognition Challenge. Last Accessed: Jun. 26, 2019.
2. Pritom Saha Akash, Md. Eusha Kadir, Amin Ahsan Ali, and Mohammad Shoyaib. 2019. Inter-node Hellinger Distance based Decision Tree. In IJCAI.
3. Leo Breiman. 2001. Random forests. Machine learning 45, 1 (2001), 5--32.
4. Evelyn Fix and J. L. Hodges. 1989. Discriminatory Analysis. Nonparametric Discrimination: Consistency Properties. International Statistical Review 57, 3 (1989), 238--247. http://www.jstor.org/stable/1403797
5. Sozo Inoe, Naonori Ueda, Yasunobu Nohara, and Naoki Nakashima. 2016. Understanding Nursing Activities with Long-term Mobile Activity Recognition with Big Dataset. Proceedings of the ISCIE International Symposium on Stochastic Systems Theory and its Applications 2016 (2016), 1--11.
6. Xiaoqiang Li, Yi Zhang, and Dong Liao. 2017. Mining key skeleton poses with latent svm for action recognition. Applied Computational Intelligence and Soft Computing 2017 (2017).
7. Diogo Carbonera Luvizon, Hedi Tabia, and David Picard. 2017. Learning features combination for human action recognition from skeleton sequences. Pattern Recognition Letters 99 (2017), 13--20.
8. J. Ross Quinlan. 1986. Induction of decision trees. Machine learning 1, 1 (1986), 81--106.
9. Alia Sayeda Shamma, Paula Lago, Shingo Takeda, Tittaya Mairittha, Nattaya Mairittha, Farina Faiz, Yusuke Nishimura, Kohei Adachi, Tsuyoshi Okita, Sozo Inoue, and Francois Charppillet. 2019. Nurse Care Activity Recognition Challenge: Summary and Results. In Proc. HASCA.
10. Sadia Sharmin, Mohammad Shoyaib, Amin Ahsan Ali, Muhammad Asif Hossain Khan, and Oksam Chae. 2019. Simultaneous feature selection and discretization based on mutual information. Pattern Recognition 91 (2019), 162--174.
11. Benyue Su, Huang Wu, Min Sheng, and Chuansheng Shen. 2019. Accurate Hierarchical Human Actions Recognition From Kinect Skeleton Data. IEEE Access 7 (2019), 52532--52541.
12. Jubil T Sunny, Sonia Mary George, Jubilant J Kizhakkethottam, Jubil T Sunny, Sonia Mary George, and Jubilant J Kizhakkethottam. 2015. Applications and challenges of human activity recognition using sensors in a smart environment. IJIRST Int. J. Innov. Res. Sci. Technol 2 (2015), 50--57.
13. Songyang Zhang, Yang Yang, Jun Xiao, Xiaoming Liu, Yi Yang, Di Xie, and Yueting Zhuang. 2018. Fusing geometric features for skeleton-based action recognition using multilayer LSTM networks. IEEE Transactions on Multimedia 20, 9 (2018), 2330--2343.