Dynamic Campus Origin-Destination Mobility Prediction using Graph Convolutional Neural Network on WiFi Logs

TL;DR

This paper introduces a graph convolutional neural network model that predicts campus building occupancy and movement patterns using WiFi logs, achieving superior accuracy over traditional methods.

Contribution

The paper proposes a novel GCLSTM model that combines graph convolution and LSTM to learn traffic flow patterns from WiFi data without invasive occupant behavior assumptions.

Findings

GCLSTM outperforms MLP and Linear Regression in prediction accuracy.

The model effectively captures dynamic traffic flow patterns.

WiFi logs can be used for privacy-preserving occupancy prediction.

Abstract

We present an integrated graph-based neural networks architecture for predicting campus buildings occupancy and inter-buildings movement at dynamic temporal resolution that learns traffic flow patterns from Wi-Fi logs combined with the usage schedules within the buildings. The relative traffic flows are directly estimated from the WiFi data without assuming the occupant behaviour or preferences while maintaining individual privacy. We formulate the problem as a data-driven graph structure represented by a set of nodes (representing buildings), connected through a route of edges or links using a novel Graph Convolution plus LSTM Neural Network (GCLSTM) which has shown remarkable success in modelling complex patterns. We describe the formulation, model estimation, interpretability and examine the relative performance of our proposed model. We also present an illustrative architecture of the models and apply on real-world WiFi logs collected at the Toronto Metropolitan University campus. The results of the experiments show that the integrated GCLSTM models significantly outperform traditional pedestrian flow estimators like the Multi Layer Perceptron (MLP) and Linear Regression.