Activity-based models in transport modeling and prediction are built from a large number of observed trips and their purposes. However, data acquired through traditional interview-based travel surveys is often inaccurate and insufficient. Recently, a human mobility sensing system, called Future Mobility Survey (FMS), was developed and used to collect travel data from more than 1,000 participants. FMS combines a smartphone and interactive web interface in order to better infer users activities and patterns. This paper presents a model that infers an activity at a certain location. We propose to generate a set of predictive features based on spatial, temporal, transitional, and environmental contexts with an appropriate quantization. In order to improve the generalization performance of the proposed model, we employ a robust approach with ensemble learning. Empirical results using FMS data demonstrate that the proposed method contributes significantly to providing accurate activity estimates for the user in our travel-sensing application.