Abstract:
Recent smartphone sensors make identifying a locomotion mode easy. Locomomotion mode information improves trip planning, travel time estimation, and traffic management. Locomotion mode recognition work depends on labeled training instances and is not relevant.
The recognition model should be able to identify a new locomotion mode without a training instance because it is impractical to collect labeled instances for all locomotion modes. This paper proposes a sensors-based deep learning model to identify locomotion modes using labeled training instances.
Zero-Shot learning helps identify an unseen locomotion mode. Fusion of three semantic matrices yields an attribute matrix. Extracting deep learning and hand-crafted features from training instances creates a feature matrix.
The model then creates a classifier by mapping attribute and feature matrices. Finally, accuracy and F1 score are used to evaluate the approach on collected and existing datasets.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
