In this paper, two new adaptive traffic signal control algorithms are proposed based on data from probe vehicles to realize the coordinated signal control of arterial roads. One is an iterative signal control algorithm, and the other is an optimized signal control algorithm. The proportion of vehicles in the nonstop group is selected as the indicator of the traffic state. The value for this indicator can be accurately estimated by data from probe vehicles. Our goal is to ease traffic congestion and enhance the capacities of traffic networks. Compared with the Webster fixed-time signal control algorithm, these two new adaptive signal control algorithms are evaluated on a microscopic simulation platform. Simulation results show that the average travel time is reduced by 32% under the iterative signal control algorithm and by 23% under the optimized signal control algorithm, and the average delay times are reduced by 36% and 35%, respectively. In the meantime, the average number of stops under the iterative signal control algorithm is reduced by 43%, and under the optimized signal control algorithm, by 67%. They indicate that the two new adaptive signal control algorithms are effective for easing traffic congestion and achieve the adaptive signal control objectives using real-time traffic information.

This study proposes an applicable driver identification method using machine learning algorithms with driving information. The driving data are collected by a 3‐axis accelerometer, which records the lateral, longitudinal and vertical accelerations. In this research, a data transformation way is developed to extract interpretable statistics features from raw 3‐axis sensor data and utilise machine learning algorithms to identify drivers. To eliminate the bias caused by the sensor installation and ensure the applicability of their approach, they present a data calibration method which proves to be necessary for a comparative test. Four basic supervised classification algorithms are used to perform on the data set for comparison. To improve classification performance, they propose a multiple classifier system, which combines the outputs of several classifiers. Experimental results based on real‐world data show that the proposed algorithm is effective on solving driver identification problem. Among the four basic algorithms, random forests (RFs) algorithm has the greatest performance on accuracy, recall and precision. With the proposed multiple classifier system, a greater performance can be achieved in small number of drivers’ groups. RFs algorithm takes the lead in running speed. In their experiment, ten drivers are involved and over 5,500,000 driving records per driver are collected.

This paper studies how autonomous vehicles (AVs) influence future traffic and energy consumption when adopting various route guidance strategies, which can be divided into global information strategies and local information strategies according to the scope of information collection. A mixed traffic flow model is established. Then, an autonomous vehicle model is improved to investigate the impact of six route guidance strategies. The selected strategies are specifically evaluated in a double-route scenario, considering both single-exit and dual-exit configurations. Three indicators are chosen to evaluate traffic efficiency, including traffic flow, average speed and quantity of vehicles. Consumption per unit flux is the indicator of energy consumption level. Simulation results show that autonomous vehicles can improve traffic efficiency and reduce energy consumption.

Self-similar growth and fractality are important properties found in many real-world networks, which could guide the modeling of network evolution and the anticipation of new links. However, in technology-convergence networks, such characteristics have not yet received much attention. This study provides empirical evidence for self-similar growth and fractality of the technology-convergence network in the field of intelligent transportation systems. This study further investigates the implications of such fractal properties for link prediction via partial information decomposition. It is discovered that two different scales of the network (i.e., the micro-scale structure measured by local similarity indices and the scaled-down structure measured by community-based indices) have significant synergistic effects on link prediction. Finally, we design a synergistic link prediction (SLP) approach which enhances local similarity indices by considering the probability of link existence conditional on the joint distribution of two scales. Experimental results show that SLP outperforms the benchmark local similarity indices in most cases, which could further validate the existence and usefulness of the synergistic effect between two scales on link prediction.

Zhiyuan Wang, Bokui Chen, Yinya Huang, Qingxing Cao, Ming He, Jianping Fan, Xiaodan Liang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track). 2025.

Innovation, which involves technological transformation and management reorganization, brings about significant changes in modern society. In this paper, to investigate how innovations can be promoted, we propose a game-based model to study the co-evolutionary dynamics of human innovative behaviors. A simulation on scale-free networks is conducted, in which the innovative behavior of each node is determined and updated based on the feedback regarding its innovation, namely the diffusion of the innovation status. Numerical simulations of the model generate a series of patterns, which is consistent with people’s daily experiences and perceptions as regards real-world innovative behaviors. Specifically, various scaling spatiotemporal properties and rich structural impacts on dynamics can be observed. This model provides a novel approach to understand the evolution of innovative behaviors and provides insight for strategy studies of innovation promotion.