论文信息 - Activity Recognition with Time-Delay Emobeddings

Activity Recognition with Time-Delay Emobeddings

We outline an approach that uses time-delay embedding models and machine learning in order to recognize physical activities, based on data coming from cell phone accelerometers. The approach is very robust, cheap in terms of the amount of data and computation required, and easy to deploy.

[1] F. Takens. Detecting strange attractors in turbulence , 1981 .

[2] H. Kantz,et al. Nonlinear time series analysis , 1997 .

[3] Jeff A. Bilmes,et al. Recognizing Activities and Spatial Context Using Wearable Sensors , 2006, UAI.

[4] Gaetano Borriello,et al. A Practical Approach to Recognizing Physical Activities , 2006, Pervasive.

[5] Shie Mannor,et al. Activity and Gait Recognition with Time-Delay Embeddings , 2010, AAAI.

[6] Shie Mannor,et al. A novel similarity measure for time series data with applications to gait and activity recognition , 2010, UbiComp '10 Adjunct.