A macroscopic loading model for multi-directional, time-varying and congested pedestrian flows is proposed in this paper. Walkable space is represented by a network of streams that are each associated with an area in which they interact. To describe this interaction, a stream-based pedestrian fundamental diagram is used that relates density and walking speed in multi-directional flow. The proposed model is applied to two different case studies. The explicit modeling of anisotropy in walking speed is shown to significantly improve the ability of the model to reproduce empirically observed walking time distributions. Moreover, the obtained model parametrization is in excellent agreement with the literature.

No abstract

Abstract-This paper presents an overtaking decision algorithm for networked intelligent vehicles. The algorithm is based on a cooperative tracking and sensor fusion algorithm that we previously developed. The ego vehicle is equipped with lane keeping and lane changing capabilities, as well as a forward-looking lidar sensor. The lidar data are fed to the tracking module which detects other vehicles, such as the vehicle that is to be overtaken (leading) and the oncoming traffic. Based on the estimated distances to the leading and the oncoming vehicles and their speeds, a risk is calculated and a corresponding overtaking decision is made. We compare the performance of the overtaking algorithm between the case when the ego vehicle only relies on its lidar sensor, and the case in which it fuses object estimates received from the leading car which also has a forward-looking lidar. Systematic evaluations are performed in Webots, a calibrated high-fidelity simulator.

As online shopping becomes ever more prevalent, customers rely increasingly on product rating websites for making purchase decisions. The reliability of online ratings, however, is potentially compromised by the so-called herding effect: when rating a product, customers may be biased to follow other customers' previous ratings of the same product. This is problematic because it skews long-term customer perception through haphazard early ratings. The study of herding poses methodological challenges. In particular, observational studies are impeded by the lack of counterfactuals: simply correlating early with subsequent ratings is insufficient because we cannot know what the subsequent ratings would have looked like had the first ratings been different. The methodology introduced here exploits a setting that comes close to an experiment, although it is purely observational-a natural experiment. Our key methodological device consists in studying the same product on two separate rating sites, focusing on products that received a high first rating on one site, and a low first rating on the other. This largely controls for confounds such as a product's inherent quality, advertising, and producer identity, and lets us isolate the effect of the first rating on subsequent ratings. In a case study, we focus on beers as products and jointly study two beer rating sites, but our method applies to any pair of sites across which products can be matched. We find clear evidence of herding in beer ratings. For instance, if a beer receives a very high first rating, its second rating is on average half a standard deviation higher, compared to a situation where the identical beer receives a very low first rating. Moreover, herding effects tend to last a long time and are noticeable even after 20 or more ratings. Our results have important implications for the design of better rating systems.

Synthetic data can be used in various applications, such as correcting bias datasets or replacing scarce original data for simulation purposes. Generative Adversarial Networks (GANs) are considered stateof-the-art for developing generative models. However, these deep learning models are data-driven, and it is, thus, difficult to control the generation process. It can, therefore, lead to the following issues: lack of representativity in the generated data, the introduction of bias, and the possibility of overfitting the sample's noise. This article presents the Directed Acyclic Tabular GAN (DATGAN) to address these limitations by integrating expert knowledge in deep learning models for synthetic tabular data generation. This approach allows the interactions between variables to be specified explicitly using a Directed Acyclic Graph (DAG). The DAG is then converted to a network of modified Long Short-Term Memory (LSTM) cells to accept multiple inputs. Multiple DATGAN versions are systematically tested on multiple assessment metrics. We show that the best versions of the DATGAN outperform state-of-the-art generative models on multiple case studies. Finally, we show how the DAG can create hypothetical synthetic datasets.