D.C.J.L.S.T.: Online pose classification and walking speed estimation using handheld devices

We describe and evaluate two methods for pose classification and walking speed estimation that generalize well to new users, compared to previous work. These machine learning based methods are designed for the general case of a person holding a mobile device in an unknown location and require only a single low-cost, low-power sensor: a triaxial acceler-ometer. We evaluate our methods in straight-walking exper-iments as well as in natural indoor walking settings. Experi-ments with 14 human participants to test user generalization show that our pose classifier correctly selects among four device poses with 94 % accuracy compared to 82 % for pre-vious work, and our walking speed estimates are within 12-15 % (straight/indoor walk) of ground truth compared to 17-22 % for previous work. Implementation on a mobile phone demonstrates that both methods can run online