Auxiliary-LSTM based floor-level occupancy prediction using Wi-Fi access point logs

Abstract

Smart city concepts have gained increased traction over the years. The advances in technology such as the Internet of things (IoT) networks and their large-scale implementation has facilitated data collection, which is used to obtain valuable insights towards managing, improving, and planning for services. One key component in this process is the understanding of human mobility behaviour. Traditional data collection methods such as surveys and GPS data have been extensively used to study human mobility. However, a key concern with such data is the protection of user privacy. This study aims to overcome those concerns using Wi-Fi access point logs and demonstrate their utility by creating building occupancy prediction models using advanced machine learning techniques. The floor level occupancy counts and auxiliary variable for a campus building are extracted from the Wi-Fi logs. They are used to develop specifications of Long-Short Term Memory network (LSTM), Auxiliary LSTM (Aux-LSTM), Autoregressive Integrated Moving Average (ARIMA), and Multi-layer Perceptron (MLP) models. The LSTM performed better than the other models and can efficiently capture peak values. Aux-LSTM was shown to increase the reliability in prediction and applicability in the context of facilities management. Results show the effectiveness of the Wi-Fi dataset in capturing trends, providing supplementary information, and highlight the ability of LSTM to adequately model time-series data.