© The Institution of Engineering and Technology
Proposed is a light-weight unsupervised decision tree based classification method to detect the user's postural actions, such as sitting, standing, walking and running as user states by analysing the data from a smartphone accelerometer sensor. The proposed method differs from other approaches by applying a sufficient number of signal processing features to exploit the sensory data without knowing any a priori information. Experiments show that the proposed method still makes a solid differentiation in user states (e.g. an above 90% overall accuracy) even when the sensor is operated under slower sampling frequencies.
References
-
-
1)
-
2. Kwapisz, J.R., Weiss, G.M., Moore, S.A.: ‘Activity recognition using cell phone accelerometers’, SIGKDD Explor. Newsl., 2011, 12, pp. 74–82 (doi: 10.1145/1964897.1964918).
-
2)
-
6. Lefëvre, F., Montacie, C., Caraty, M.: ‘On the influence of the delta coefficients in a HMM-based speech recognition system’. Int. Speech Science and Technology Conf., Sydney, Australia, 1998.
-
3)
-
3. Vinh, L., Lee, S., Le, H., Ngo, H., Kim, H., Han, M., Lee, Y.: ‘Semi-Markov conditional random fields for accelerometer-based activity recognition’, Appl. Intell., 2011, 35, pp. 226–241 (doi: 10.1007/s10489-010-0216-5).
-
4)
-
5. Bentley, J.L., Stanat, D.F., Williams, E.H.Jr.: ‘The complexity of finding fixed-radius near neighbors’, Inf. Process Lett.1977, 6, pp. 209–212 (doi: 10.1016/0020-0190(77)90070-9).
-
5)
-
1. Dernbach, S., Das, B., Krishnan, N.C., Thomas, B.L., Cook, D.J.: ‘Simple and complex activity recognition through smart phones’. Int. Conf. on Intelligent Environments, Guanajuato, Mexico, 2012, pp. 214–221.
-
6)
-
4. Miluzzo, E., Cornelius, C.T., Ramaswamy, A., Choudhury, T., Liu, Z., Campbell, A.T.: ‘Darwin phones: the evolution of sensing and inference on mobile phones’. Int. Conf. on Mobile Systems, Applications, and Services, San Fransisco, CA, USA, 2010, pp. 5–20.
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2013.0592
Related content
content/journals/10.1049/el.2013.0592
pub_keyword,iet_inspecKeyword,pub_concept
6
6