Traffic simulation is an essential tool for analyzing and predicting real-world traffic scenarios. It leverages real-world data to provide insights into various situations, even when data collection is impractical or inefficient. A critical aspect of simulation realism lies in developing sophisticated agent behavior models. In this paper, we propose an event-based rerouting framework for the UNIQ-SALT traffic simulation platform, designed to improve the realism of agent behaviors. Unlike static plans where vehicles follow predefined routes, this framework enables agents to dynamically respond to changing traffic conditions, facilitating the reproduction of diverse scenarios. Also, the framework was calibrated using real-world data from Daejeon in South Korea, and tested under a flood control event scenario. The evaluation, conducted through R-Square analysis of traffic flow, demonstrated high similarity between simulated and real-world data, achieving an R-Square (R2) value near 0.9. These results indicate the framework's effectiveness in accurately replicating real-world traffic dynamics during specific events. This research underscores the value of event-based models in enhancing simulation realism and supporting data-driven decision-making.

Data generation is becoming an increasingly important issue in the field of machine learning due to the high cost of data collection and the privacy concerns associated with raw data. Generating new data with high fidelity is extremely challenging because even a minor perturbation in high-dimensional data may alter its semantic meaning. The challenge becomes particularly acute in multivariate time-series data as it often exhibits human-imperceptible temporal patterns and lacks standard representation. To address this issue, we propose a straightforward yet effective technique that helps preserve the fidelity of the original data. Experimental results demonstrate that our technique enhances the performance of time-series forecasting model.

Graph Convolutional Networks (GCNs) have been successfully utilized in modeling complex graph-structured data and have been applied in various applications such as epidemic tracing and so on. However, the training phase in GCNs faces challenges due to the computational overhead of repeated and inefficient aggregations based on graph convolution operations. We present a novel method called GCNIR that leverages reachability with incremental properties to efficiently compute diffusions in diffusion-based GCNs for node classification and traffic prediction tasks. The proposed method achieves significant speed-up gains for training semi-supervised models for node classification tasks on benchmark datasets. In addition, the proposed approach reduces the training time for diffusion-based GCN models in traffic prediction applications.

The city traffic simulation is one of solutions to analyze and forecast the traffic state for urban road network. In order to simulate the real traffic situation well, the fine-tuning simulation inputs, including road network and traffic demands, closer to real measured data is important. In this paper, we propose the UNIQ-SALT, which is a cell-based traffic simulator, with the RTDG (Recurrent Traffic Demand Generation) model as an adjustment model for the simulation inputs. This RTDG model recurrently calibrates the simulation results with real traffic data in Daejeon and Sejong, South Korea until obtaining predefined target error rate between simulated and real values. Finally, we show the simulated result is under 10% error coverage, MAPE, on main spots of the simulation area and the correlation between the simulated data and the real data is reasonable as near 0.9 of the R2value.

KIWI is a SQL-on-Hadoop system enabling batch and interactive analytics for big data. In database systems, materialized views, stored pre-computed results for queries, are one of the most commonly used techniques to improve the query processing speed. However, the key challenge in using materialized views is maintaining their freshness as base data changes. This paper introduces a new approach for accelerating OLAP query processing using query workload statistics and query column sets instead of materialized views. We present an architecture of SQL-on-Hadoop system using query column sets of original tables in database. The experimental results demonstrate that our system can provide improved performance by 1.77x on average in terms of TPC-H query processing.