F
Fan Zhang
Researcher at Chinese Academy of Sciences
Publications - 142
Citations - 3561
Fan Zhang is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Medicine & Cancer research. The author has an hindex of 30, co-authored 125 publications receiving 2622 citations. Previous affiliations of Fan Zhang include Hong Kong University of Science and Technology & Lanzhou University.
Papers
More filters
Journal ArticleDOI
Resource Allocation for Delay Differentiated Traffic in Multiuser OFDM Systems
TL;DR: Through the analysis, it is shown that the optimal power allocation over subcarriers follows a multi-level water-filling principle; moreover, the valid candidates competing for each subcarrier include only one NDC user but all DC users.
Journal ArticleDOI
Real-Time Charging Station Recommendation System for Electric-Vehicle Taxis
TL;DR: A real-time charging station recommendation system for EV taxis via large-scale GPS data mining is provided by combining each EV taxi's historical recharging events and real- time GPS trajectories, and the current operational state of each taxi is predicted.
Proceedings ArticleDOI
Exploring human mobility with multi-source data at extremely large metropolitan scales
TL;DR: A novel architecture mPat is proposed and implemented to explore human mobility using multi-source data and achieves a 75% inference accuracy, and that its real-world application reduces passenger travel time by 36%.
Journal ArticleDOI
Spatio-Temporal Analysis of Passenger Travel Patterns in Massive Smart Card Data
TL;DR: This paper proposes an effective data-mining procedure to better understand the travel patterns of individual metro passengers in Shenzhen, a modern and big city in China, and uses statistical-based and unsupervised clustering-based methods to understand the hidden regularities and anomalies of theTravel patterns.
Proceedings ArticleDOI
A Deep Value-network Based Approach for Multi-Driver Order Dispatching
TL;DR: This work proposes a deep reinforcement learning based solution for order dispatching and conducts large scale online A/B tests on DiDi's ride-dispatching platform to show that the proposed method achieves significant improvement on both total driver income and user experience related metrics.