Weighted spatio-temporal taxi trajectory big data mining for regional traffic estimation

The estimation of traffic conditions in cities is becoming essential to establish a sustainable transportation system and to help traffic management authorities plan the traffic of cities. Recently, taxi trajectory big datasets are being collected during taxi drivers are routing around the cities. Taxi trajectory datasets provide behavioral information about the city residents, urban flows of the taxi passengers, and infrastructure for traffic condition estimation. This study aims to estimate regional traffic velocity of New York City using New York taxi trajectory dataset. A new method is proposed that uses weighted spatio-temporal trajectory big data mining approach and scores each region of the cities in terms of traffic velocity. A new algorithm is proposed, namely Regional Traffic Velocity Estimation (RTVE) algorithm, which uses proposed regional spatio-temporal velocity estimation method and experimentally evaluated using New York taxi trajectory dataset. Experimental results show that each region in New York have different velocity and usage characteristics in terms of hourly and daily analyses. Also, borough-level analyses are performed that reveal knowledge about the boroughs of New York. The estimated regional traffic velocity of cities based on taxi trajectory datasets would provide a decision support system for decision-makers in terms of regional hourly and daily evaluation of cities with cost-free and widespread city traffic dataset. •Taxi trajectory big dataset mining is performed for traffic estimation.•A new method is proposed that discovers regional spatio-temporal velocity.•Proposed method uses weighted spatio-temporal trajectory data mining.•A new algorithm is proposed that uses proposed method.•The proposed method is experimentally evaluated on real taxi trajectory dataset.