arXiv subjects

Chaolun Ma

Publications and source records attributed to Chaolun Ma.

4 recordsLinked to original sources

arXiv2025

Recent Advances in Disaster Emergency Response Planning: Integrating Optimization, Machine Learning, and Simulation

The increasing frequency and severity of natural disasters underscore the critical importance of effective disaster emergency response planning to minimize human and economic losses. This survey provides a comprehensive review of recent advancements (2019--2024) in five essential areas of disaster emergency response planning: evacuation, facility location, casualty transport, search and rescue, and relief distribution. Research in these areas is systematically categorized based on methodologies, including optimization models, machine learning, and simulation, with a focus on their individual strengths and synergies. A notable contribution of this work is its examination of the interplay between machine learning, simulation, and optimization frameworks, highlighting how these approaches can address the dynamic, uncertain, and complex nature of disaster scenarios. By identifying key research trends and challenges, this study offers valuable insights to improve the effectiveness and resilience of emergency response strategies in future disaster planning efforts.

math.OC↗

arXiv2022

Lyapunov Function Consistent Adaptive Network Signal Control with Back Pressure and Reinforcement Learning

In traffic signal control, flow-based (optimizing the overall flow) and pressure-based methods (equalizing and alleviating congestion) are commonly used but often considered separately. This study introduces a unified framework using Lyapunov control theory, defining specific Lyapunov functions respectively for these methods. We have found interesting results. For example, the well-recognized back-pressure method is equal to differential queue lengths weighted by intersection lane saturation flows. We further improve it by adding basic traffic flow theory. Rather than ensuring that the control system be stable, the system should be also capable of adaptive to various performance metrics. Building on insights from Lyapunov theory, this study designs a reward function for the Reinforcement Learning (RL)-based network signal control, whose agent is trained with Double Deep Q-Network (DDQN) for effective control over complex traffic networks. The proposed algorithm is compared with several traditional and RL-based methods under pure passenger car flow and heterogenous traffic flow including freight, respectively. The numerical tests demonstrate that the proposed method outperforms the alternative control methods across different traffic scenarios, covering corridor and general network situations each with varying traffic demands, in terms of the average network vehicle waiting time per vehicle.

eess.SY↗

arXiv2022

Revealing Spatial-temporal Taxi Demand Patterns after Vaccination in COVID-19 Pandemic

The COVID-19 pandemic has had an unprecedented impact on our daily lives. With the increase in vaccination rate, normalcy gradually returns, so is the taxi demand. However, the changes in the spatial-temporal taxi demand pattern and factors impacting the recovery of this demand after COVID-19 vaccination started remain unclear. With the multisource time-series data from Chicago, including pandemic severity, vaccination progress and taxi trip volume, the recovery pattern of taxi demand is analyzed. The result reveals the taxi trip volume and average travel distance increased in most community areas in the city of Chicago after taking the COVID-19 vaccine. Taxi demand recovers relatively faster in the airport and area near the central downtown than in other areas in Chicago. Considering the asynchrony of data, the Pearson coefficient and Dynamic Time Warping (DTW) are both applied to investigate the correlations among different time series. It found that the recovery of taxi demand is not only related to the pandemic severity but strongly correlated with vaccination progress. Then, the leading and lagging relationship between vaccination progress and taxi demand is investigated by Time Lagging Cross-Correlation method. Taxi demand starts to recover after the first-dose vaccination period started and before the second-dose vaccination period. However, it was not until mid-April that the recovery rate of taxi demand exceeded the growth of the vaccination rate.

stat.AP↗

arXiv2020

Controlling the Hidden Growth of COVID-19

The COVID-19 pandemic has plagued the world for months. The U.S. has taken measures to counter it. On a daily basis, newly confirmed cases have been reported. In the early days, these numbers showed an increasing trend. Recently, the numbers have been generally flattened out. This report tries to estimate the hidden number of currently alive infections in the population by using the confirmed cases. A major result indicates an existing infections estimate at about 10-50 times the daily confirmed new cases, with the stringent social distancing policy tipping to the upper end of this range. It clarifies the relationship between the infection rate and the test rate to put the epidemic under control, which says that the test rate shall keep up at the same pace as infection rate to prevent an outbreak. This relationship is meaningful in the wake of business re-opening in the U.S. and the world. The report also reveals the connections of all the measures taken to the epidemic spread. A stratified sampling method is proposed to add to the current tool kits of epidemic control. Again, this report is a summary of some straight observations and thoughts, not through a thorough study backed with field data. The results appear obvious and suitable for general education to interested policymakers and the public.

physics.soc-ph↗