Representing Urban Functions through Zone Embedding with Human Mobility Patterns

Authors: Zijun Yao, Yanjie Fu, Bin Liu, Wangsu Hu, Hui Xiong

IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct extensive experiments with real-world urban datasets of New York City. Experimental results demonstrate the effectiveness of the proposed embedding model to represent urban functions of zones with human mobility data.
Researcher Affiliation Collaboration Zijun Yao1, Yanjie Fu2, Bin Liu3, Wangsu Hu1, Hui Xiong1 1Rutgers University 2Missouri University of Science and Technology 3IBM Thomas J. Watson Research Center
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement or link indicating that the source code for the described methodology is open-source or publicly available.
Open Datasets Yes We use the trip records of yellow taxi from NYC taxi & limousine commission2 to obtain citywide human mobility patterns. (...) The second dataset is the zone data. We use the city zones designed by US Census Bureau3 for zone embedding learning. (...) The last dataset is the Foursquare check-in data formulated by the work in [Yang et al., 2015]
Dataset Splits No Finally we obtain 33,842,934 trips as our training data. The paper mentions this as 'training data' but does not specify a separate validation split or explicit cross-validation setup for the model training itself. It uses a separate 'land use dataset' as ground truth for evaluating clustering performance, but this is not a validation split from the primary mobility data.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory, or cloud instance types) used for running the experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes For experimental setup, we empirically set embedding dimension D = 50. Gravity matrices Gwd and Gwe are calculated with βwd = 0.4674 and βwe = 0.3881.