Crowd Forecasting Based on WiFi Sensors and LSTM Neural Networks

Abstract

To ensure effective management and security in large scale public events, it is imperative for the event organizers to be aware of potentially critical crowd densities. This paper, therefore, presents a solution to the above problem in terms of WiFi based crowd counting and LSTM neural network based forecasting. Monitoring of an actual event organized in Brussels has been described, wherein crowd counts are obtained using WiFi sensors in a privacy-preserved manner. The time-stamped crowd counts are used to develop univariate time-series, which are in-turn utilized for forecasting. Five different LSTM models are utilized for crowd time-series forecasting and analyzed for their suitability. A random walk model is used as reference for performance assessment. Among different LSTM models, Convolutional LSTM delivered the best performance. Overall results and analysis show that the developed system is suitable for crowd monitoring.

A CNN-LSTM Hybrid Model for Wrist Kinematics Estimation Using Surface Electromyography

“…1) Topology of LSTM: LSTM is a network designed to encode contextual information of a temporal sequence with feedback loops. It contains cycles that feed the network activations from a previous time-step to influence predictions at the current time-step [33]. The unfolded chain structure of LSTM in an input sequence…”

Sensing and Forecasting Crowd Distribution in Smart Cities: Potentials and Approaches

“…However, in all these cases, the main task for a possible monitoring system is the automatic detection of the event and mobility data is one of the best sources to feed these kinds of systems [19][20][21]. Moreover, depending on the specific application, we might be interested in the automatic description of an event, i.e., by asking the question "Why are people gathering in there?".…”

“…Besides being very effective in many forecasting scenarios, these methods are also interpretable, which is an interesting features when aiming at producing explainable predictions. ARIMA has been used for crowd counts forecasting [20], to perform forecasts on international tourism time series data [60], and to correlate traffic congestions to socio-economic indicators [61].…”

Crowd Monitoring: State-of-the-Art and Future Directions

“…The authors used WiFi positioning data and statistical time series analysis to predict the queuing time. A recent and reliable approach for estimating and forecasting crowd counts using WiFi sensors in large-scale events is shown in [57]. Concerns like overestimation of crowd counts and privacy are duly addressed.…”

“…In this approach an artificial intelligence technique such as neural networks can be employed to learn crowd counts at specific time intervals; and then crowd counts for future time values can be predicted for a particular time horizon. A recent work on WiFi and deep learning based crowd forecasting is available in [57], which has been used for crowd count forecasting at a large scale public event. In fact, there is much more focus use of deep learning techniques in crowd monitoring as they provide better learning and prediction accuracy.…”