Search

Previous research on automatic control of high-speed trains in speed limit sections is insufficient. This article proposes a new offline reinforcement learning strategy for automatic tracking of autonomous trains. Firstly, the operating speed and deceleration starting point were determined for different speed limit scenarios. Then, a tracking controller based on the improved offline conservative Q-learning (CQL) algorithm was designed to avoid frequent interaction between the train and the environment. Selected an appropriate policy to implement the CQL algorithm. The data samples were reclassified to increase sample concentration. The value and strategy network structure was redesigned. The state space and action space of tracking trains were limited, and the dimension of state space was increased. A multi-objective reward function was designed to distinguish the tracking process of trains in different sections. The simulation results show that the proposed high-speed railway tracking interval automatic control algorithm is superior to traditional online reinforcement learning methods in terms of safety, comfort, and convergence efficiency.

The introduction of thermal relaxation makes non-Fourier heat transfer more effective than Pennes equation to reflect rapid bio-heat transferring during HIFU, however, the contribution of thermal relaxation in specific tissues needs to be further clarified. In this study, we first measured the thermal relaxation times of porcine muscle and porcine fat. Combining with experimental measurements, the effects of thermal relaxation on temperature elevation in the tissues were investigated by using Pennes equation, thermal wave model of bio-heat transfer (TWMBT) and dual phase-lag (DPL) bio-heat transfer. Results showed that: a) The thermal relaxation times of porcine muscle and porcine fat are experimentally determined as 5.71± 0.11 s and 5.02± 0.06 s, respectively. b) In the absence of cavitation, DPL bio-heat transfer is more accurate to predict the temperature elevation at the focus and 2 mm from the focus than Pennes equation and TWMBT. Particularly, comparing with the reported of bologna (16 s) used in most of the theoretical analysis, the utilization of the measured thermal relaxation time for a specific tissue in DPL bio-heat transfer is more effective in predicting the temperature elevation during HIFU. c) Acoustic cavitation and nonlinear propagation is easier to happen in fat, under which all bio-heat transfer models are failed to forecast the temperature elevation induced by HIFU. The results demonstrate that different tissues have different thermal relaxation, DPL bio-heat transfer with the measured thermal relaxation times of specific tissues can accurately predict the temperature elevation during HIFU without cavitation.

Due to the rapidly growing volume of publications, it is an urgent task to evaluate the potential impact of emerging works and identify valuable publications for the benefit of researchers with limited time. The impact of authors is significant in terms of personal promotion and fund raising. However, the criterion used to evaluate the impact of authors is largely based on credits they have received, not potential credits. We take the citation count, the most direct and widely used metric for publication popularity, as the potential impact and evaluate its predictability. To this end, we propose a neural network-based point process model for predicting the citation count of individual publications. Our approach integrates signals from paper-specific features and their citation traces, which reflect the trend of either losing or gaining popularity. The model is learned in an adversarial way, which mitigates the bias-exposure efficiently. We verify our model on the largest publicly available academic publication repository, and our model outperforms alternatives with a notable margin.