Grids Versus Graphs: Partitioning Space for Improved Taxi Demand-Supply Forecasts
| Autor: | Gaurav Raina, Krishna Jagannathan, Neema Davis |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning 050210 logistics & transportation Tessellation (computer graphics) Computational complexity theory Computer science Mechanical Engineering 05 social sciences Geohash Machine Learning (stat.ML) Context (language use) Computer Science::Computational Geometry computer.software_genre Ensemble learning Machine Learning (cs.LG) Computer Science Applications Data modeling Statistics - Machine Learning 0502 economics and business Automotive Engineering Data mining Voronoi diagram Space partitioning computer |
| Zdroj: | IEEE Transactions on Intelligent Transportation Systems. 22:6526-6535 |
| ISSN: | 1558-0016 1524-9050 |
| DOI: | 10.1109/tits.2020.2993798 |
| Popis: | Accurate taxi demand-supply forecasting is a challenging application of ITS (Intelligent Transportation Systems), due to the complex spatial and temporal patterns. We investigate the impact of different spatial partitioning techniques on the prediction performance of an LSTM (Long Short-Term Memory) network, in the context of taxi demand-supply forecasting. We consider two tessellation schemes: (i) the variable-sized Voronoi tessellation, and (ii) the fixed-sized Geohash tessellation. While the widely employed ConvLSTM (Convolutional LSTM) can model fixed-sized Geohash partitions, the standard convolutional filters cannot be applied on the variable-sized Voronoi partitions. To explore the Voronoi tessellation scheme, we propose the use of GraphLSTM (Graph-based LSTM), by representing the Voronoi spatial partitions as nodes on an arbitrarily structured graph. The GraphLSTM offers competitive performance against ConvLSTM, at lower computational complexity, across three real-world large-scale taxi demand-supply data sets, with different performance metrics. To ensure superior performance across diverse settings, a HEDGE based ensemble learning algorithm is applied over the ConvLSTM and the GraphLSTM networks. Submitted to IEEE Transactions on Intelligent Transportation Systems |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|