Search

With the development of Global Navigation Satellite System (GNSS) and the opening of Application Programming Interface (API) of Android terminals, the positioning research of Android terminals has attracted the attention of GNSS community. In this paper, three static experiments were conducted to analyze the raw GNSS observations quality and positioning performances of the smartphones. For the two experimental smartphones, the numbers of visible satellites with dual-frequency signals are unstable and not enough for dual-frequency Precise Point Positioning (PPP) processing all through the day. Therefore, the ionosphere-constrained single-frequency PPP model was employed to improve the positioning with the smartphones, and its performance was evaluated and compared with those of the Single Point Positioning (SPP) and the traditional PPP models. The results show that horizontal positioning accuracies of the smartphones with the improved PPP model are better than 1 m, while those with the SPP and the traditional PPP models are about 2 m. [ABSTRACT FROM AUTHOR]

Currently, effective crowd management based on the information provided by crowd monitoring systems is difficult as this information comes in at the moment adverse crowd movements are already occurring. Up to this moment, very little forecasting techniques have been developed that predict crowd flows a longer time period ahead. Moreover, most contemporary state estimation methods apply demanding pre-processing steps, such as map-matching. The objective of this paper is to design, train and benchmark a data-driven procedure to forecast crowd movements, which can in real-time predict crowd movement. This procedure entails two steps. The first step comprises of a cell sequence derivation method that allows the representation of spatially continuous GPS traces in terms of discrete cell sequences. The second step entails the training of a Recursive Neural Network (RNN) with a Gated Recurrent Unit (GRU) and six benchmark models to forecast the next location of pedestrians. The RNN-GRU is found to outperform the other tested models. Some additional tests of the ability of the RNN-GRU to forecast illustrate that the RNN-GRU preserves its predictive power when a limited amount of data is used from the first few hours of a multi-day event and temporal information is incorporated in the cell sequences. [ABSTRACT FROM AUTHOR]