Konstantin Klemmer

is this you? claim profile

0 followers

  • Community structures, interactions and dynamics in London's bicycle sharing network

    Bikesharing schemes are transportation systems that not only provide an efficient mode of transportation in congested urban areas, but also improve last-mile connectivity with public transportation and local accessibility. Bikesharing schemes around the globe generate detailed trip data sets with spatial and temporal dimensions, which, with proper mining and analysis, reveal valuable information on urban mobility patterns. In this paper, we study the London bicycle sharing dataset to explore community structures. Using a novel clustering technique, we derive distinctive behavioural patterns and assess community interactions and spatio-temporal dynamics. The analyses reveal self-contained, interconnected and hybrid clusters that mimic London's physical structure. Exploring changes over time, we find geographically isolated and specialized communities to be relatively consistent, while the remaining system exhibits volatility, especially during and around peak commuting times. By increasing our understanding of the collective behaviour of the bikesharing users, this analysis supports policy appraisal, operational decision-making and motivates improvements in infrastructure design and management.

    04/16/2018 ∙ by Fernando Munoz-Mendez, et al. ∙ 0 share

    read it

  • Modeling Rape Reporting Delays Using Spatial, Temporal and Social Features

    We present a novel approach to estimate the delay observed between the occurrence and reporting of rape crimes. We explore spatial, temporal and social effects in sparse aggregated (area-level) and high-dimensional disaggregated (event-level) data for New York and Los Angeles. Focusing on inference, we apply Gradient Boosting and Random Forests to assess predictor importance, as well as Gaussian Processes to model spatial disparities in reporting times. Our results highlight differences and similarities between the two cities. We identify at-risk populations and communities which may be targeted with focused policies and interventions to support rape victims, apprehend perpetrators, and prevent future crimes.

    11/09/2018 ∙ by Konstantin Klemmer, et al. ∙ 0 share

    read it

  • Dynamic Demand Prediction for Expanding Electric Vehicle Sharing Systems: A Graph Sequence Learning Approach

    Electric Vehicle (EV) sharing systems have recently experienced unprecedented growth across the globe. During their fast expansion, one fundamental determinant for success is the capability of dynamically predicting the demand of stations as the entire system is evolving continuously. There are several challenges in this dynamic demand prediction problem. Firstly, unlike most of the existing work which predicts demand only for static systems or at few stages of expansion, in the real world we often need to predict the demand as or even before stations are being deployed or closed, to provide information and support for decision making. Secondly, for the stations to be deployed, there is no historical record or additional mobility data available to help the prediction of their demand. Finally, the impact of deploying/closing stations to the remaining stations in the system can be very complex. To address these challenges, in this paper we propose a novel dynamic demand prediction approach based on graph sequence learning, which is able to model the dynamics during the system expansion and predict demand accordingly. We use a local temporal encoding process to handle the available historical data at individual stations, and a dynamic spatial encoding process to take correlations between stations into account with graph convolutional neural networks. The encoded features are fed to a multi-scale prediction network, which forecasts both the long-term expected demand of the stations and their instant demand in the near future. We evaluate the proposed approach on real-world data collected from a major EV sharing platform in Shanghai for one year. Experimental results demonstrate that our approach significantly outperforms the state of the art, showing up to three-fold performance gain in predicting demand for the rapidly expanding EV sharing system.

    03/10/2019 ∙ by Man Luo, et al. ∙ 0 share

    read it

  • Augmenting correlation structures in spatial data using deep generative models

    State-of-the-art deep learning methods have shown a remarkable capacity to model complex data domains, but struggle with geospatial data. In this paper, we introduce SpaceGAN, a novel generative model for geospatial domains that learns neighbourhood structures through spatial conditioning. We propose to enhance spatial representation beyond mere spatial coordinates, by conditioning each data point on feature vectors of its spatial neighbours, thus allowing for a more flexible representation of the spatial structure. To overcome issues of training convergence, we employ a metric capturing the loss in local spatial autocorrelation between real and generated data as stopping criterion for SpaceGAN parametrization. This way, we ensure that the generator produces synthetic samples faithful to the spatial patterns observed in the input. SpaceGAN is successfully applied for data augmentation and outperforms compared to other methods of synthetic spatial data generation. Finally, we propose an ensemble learning framework for the geospatial domain, taking augmented SpaceGAN samples as training data for a set of ensemble learners. We empirically show the superiority of this approach over conventional ensemble learning approaches and rivaling spatial data augmentation methods, using synthetic and real-world prediction tasks. Our findings suggest that SpaceGAN can be used as a tool for (1) artificially inflating sparse geospatial data and (2) improving generalization of geospatial models.

    05/23/2019 ∙ by Konstantin Klemmer, et al. ∙ 0 share

    read it