AuthorsA. Nawaz, Z. Huang, S. Wang and A. Naseer
EditorsL. O’Conner
TitleDeep neural architecture for geospatial trajectory completion over occupancy gridmap
AfilliationMachine Learning
Project(s)Data-Driven Software Engineering Department
Publication TypeProceedings, refereed
Year of Publication2020
Conference Name2020 IEEE 13th International Conference on Cloud Computing (CLOUD)2020 IEEE 13th International Conference on Cloud Computing (CLOUD)
Date Published10/2020
Place PublishedBeijing, China
ISBN Number978-1-7281-8780-8
ISSN Number2159-6190
Keywordsdeep learning, GPS, trajectories

GPS data is widely used in many real-world applications. The quality of GPS data is critically important to produce high-quality results. In real-world applications, certain GPS trajectories are sparse and incomplete, which causes challenges to GPS trajectory-based applications. Few existing studies have tried to address this problem using complicated algorithms based on conventional heuristics; this requires extensive domain knowledge of underlying applications. Deep learning in the recent era has achieved great success in solving many sequences to sequence prediction problems. In this paper, deep learning-based bidirectional convolutional recurrent encoder-decoder architecture using an attention mechanism is proposed that predicts the missing data points, resulting in a complete GPS trajectory. The proposed method shows significant improvement over state-of-the-art benchmark methods.

Citation Keynaseer2020:deep

Contact person