<abstract><p>The accurate estimation of time delays is crucial in traffic congestion analysis, as this information can be used to address fundamental questions regarding the origin and propagation of traffic congestion. However, the exact measurement of time delays during congestion remains a challenge owing to the complex propagation process between roads and high uncertainty regarding future behavior. To overcome this challenge, we propose a novel time delay estimation method for the propagation of traffic congestion due to accidents using lag-specific transfer entropy (TE). The proposed method adopts Markov bootstrap techniques to quantify uncertainty in the time delay estimator. To the best of our knowledge, our proposed method is the first to estimate time delays based on causal relationships between adjacent roads. We validated the method's efficacy using simulated data, as well as real user trajectory data obtained from a major GPS navigation system in South Korea.</p></abstract>

No abstract

No abstract

No abstract

Multivariate time series classification is an important and demanding task in sequence data mining. We focus on the multichannel representation of the time series and its corresponding convolutional neural network (CNN) classifier. The proposed method transforms multivariate time series into multichannel analogous image and it is fed into a pretrained multichannel CNN with transfer learning. To verify the efficacy of the proposed method, we compared it with recent deep learning-based time series classification models on five datasets with small amounts of training data. The results indicate that the proposed method provides improved performance on average compared with the other methods when incorporated with transfer learning.