Tree-based and deep learning methods can automatically generate useful features. Not only can it enhance the original feature representation, but it can also learn to generate new features. This paper develops a strategy based on Light Gradient Boosting Machine (LightGBM or LGB) and Gated Recurrent Unit (GRU) to generate features to improve the expression ability of limited features. Moreover, a SARIMA-GRU prediction model considering the weekly periodicity is introduced. First, LightGBM is used to learn features and enhance the original features representation; secondly, GRU neural network is used to generate features; finally, the result ensemble is used as the input for prediction. Moreover, the SARIMA-GRU model is constructed for predicting. The GRU prediction consequences are revised by the SARIMA model that a better prediction can be obtained. The experiment was carried out with the data collected by Ride-hailing in Chengdu, and four predicted indicators and two performance indexes are utilized to evaluate the model. The results validate that the model proposed has significant improvements in the accuracy and performance of each component.
The existing coordinated control methods of green wave are complicated, difficult to operate and mainly applicable to intersection groups with symmetrical arriving upstream flows. Based on engineering practice, a new method of bidirectional progression green wave coordination control was presented by designing particular overlapping phases on the basis of NEMA dual-ring phasing configuration. Applying the characteristics of asymmetric release mode and the requirements of green wave coordinated control, the overall optimization designs of phase sequence combination and offset were carried out, and the influences of cruising speed and residual queues at red light on offset were considered, and then the classical bidirectional green wave graphic method was optimized. Based on the investigation data of the intersections group of Ziwu Road in Qujing City, bidirectional green wave designs were conducted under both symmetric and asymmetric release mode. The results show that the latter approach not only improved the bandwidth of bidirectional green wave band effectively, but also reduced the average delay and the average number of stops on the main road.
The existing coordinated control methods of green wave are more complicated and less operable, which are mainly applicable to intersection groups with symmetrical entrance release mode. Based on engineering practice, a new method of bidirectional progression green wave coordination control is presented by designing particular overlapping phases on the basis of NEMA dual-ring phasing configuration. According to the characteristics of asymmetric release mode and the requirements of green wave coordinated control, the overall optimization designs of phase sequence combination and offset were carried out, and the influences of cruising speed and residual queues at red light on offset were considered, and then the classical bidirectional green wave graphic method was optimized. Based on the investigation data of the intersections group of Ziwu Road in Qujing city, bidirectional green wave designs were conducted under both symmetric and asymmetric release mode. The results show that the latter approach not only improves the bandwidth of bidirectional green wave band effectively, but also reduces the average delay and the average number of stops on the main road.
This paper is concerned with the problem of delay-dependent robust fault-tolerant control for delta operator formulated uncertain systems with time-varying delays and regional pole assignment constraints. Based on Lyapunov stability theory and linear matrix inequality (LMI) approach, a sufficient condition of delay-dependent robust fault-tolerant D-stabilization for delta operator systems with time-delay and actuator failure is provided. When LMI is feasible, the state feedback control law of the delay- dependent systems is also obtained. A numerical simulation shows the advantages of delta operator approach and the effectiveness of the proposed method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.