Master of Science (MS)
Civil and Environmental Engineering
Short-term traffic forecasting capabilities on freeways and major arterials have received special attention in the past decade due primarily to their vital role in supporting various travelers' trip decisions and traffic management functions. This research presents a hybrid model-based and memory-based methodology to improve freeway traffic prediction performance. The proposed methodology integrates both approaches to strengthen predictions under both recurrent and non-recurrent conditions. The model-based approach relies on a combination of static and dynamic neural network architectures to achieve optimal prediction performance under various input and traffic condition settings. Concurrently, the memory-based component is derived from the data archival system that encodes the commuters' travel experience in the past. The outcomes of the two approaches are two prediction values for each query case. The two values are subsequently processed by a prediction query manager, which ultimately produces one final prediction value using an error-based decision algorithm. It was found that the hybrid approach produces speed estimates with smaller errors than if the two approaches employed separately. The proposed prediction approach could be used in deriving travel times more reliable as the Traffic Management Centers move towards implementing Advanced Traveler Information Systems (ATIS) applications.
Document Availability at the Time of Submission
Release the entire work immediately for access worldwide.
Alecsandru, Ciprian Danut, "A hybrid model-based and memory-based short-term traffic prediction system" (2003). LSU Master's Theses. 1404.