سامانه همایش های دانشگاه آزاد اسلامی واحد نجف آباد

صفحه اصلی / سومین کنفرانس بین المللی مهندسی و علوم کامپیوتر و اولین کنفرانس ملی سامانه های هوشمند، کلان داده و رایانش پیشرفته

A Comprehensive Review of Destination Prediction Methods Using Sequential Pattern Mining, Machine Learning, and T-Drive Dataset

نویسندگان :

Mahsa Salehi Sichani¹ Behrang Barekatain²

1- دانشگاه آزاد اسلامی واحد نجف آباد 2- دانشگاه آزاد اسلامی واحد نجف آباد

کلمات کلیدی :

Destination Prediction،Trajectory Data Mining،Sequential Pattern Mining; Compact Prediction Tree (CPT)،Dynamic Pattern-Sequence Prediction (DPSP)،T-Drive Dataset; Intelligent Transportation Systems

چکیده :

Destination prediction is a key problem in intelligent transportation systems and trajectory data mining, aiming to infer the final destination of a moving object based on partial trajectory information. The increasing availability of large-scale GPS trajectory datasets has motivated extensive research on data-driven prediction approaches. This paper presents a comprehensive review of destination prediction methods, with a particular focus on probabilistic models, sequential pattern mining techniques, and learning-based approaches. Special emphasis is placed on Compact Prediction Tree (CPT) and Dynamic Pattern-Sequence Prediction (DPSP) algorithms due to their effectiveness in handling sparse and irregular trajectory data. Furthermore, the paper reviews experimental insights reported on the widely used T-Drive dataset and analyzes the strengths and limitations of different modeling paradigms, including Markov-based models and deep learning approaches. Finally, open challenges and promising future research directions toward accurate, interpretable, and scalable destination prediction systems are discussed.