Liqian Dou

Liqian Dou

Auto-generated profile, based on publicly available information

Liqian Dou

Tianjin University

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 October 2019 in Journal of Neural Engineering
Verified
Journal Article
Closed access
PDF file
RZRuilong Zhang
Ruilong Zhang
QZQun Zong
Qun Zong
LDLiqian Dou
Liqian Dou
XZXinyi Zhao
Xinyi Zhao
Objective . Learning the structures and unknown correlations of a motor imagery electroencephalogram (MI-EEG) signal is important for its classification. It is also a major challenge to obtain good classification accuracy from the increased number of classes and increased variability from different people. In this study, a four-class MI task is investigated. Approach . An end-to-end novel hybrid deep learning scheme is developed to decode the MI task from EEG data. The proposed algorithm consists of two parts: a . A one-versus-rest filter bank common spatial pattern is adopted to preprocess and pre-extract the features of the four-class MI signal. b . A hybrid deep network based on the convolutional neural network and long-term short-term memory network is proposed to extract and learn the spatial and temporal features of the MI signal simultaneously. Main results . The main contribution of this paper is to propose a hybrid deep network framework to improve the classification accuracy of the four-class MI-EEG signal. The hybrid deep network is a subject-independent shared neural network, which means it can be trained by using the training data from all subjects to form one model. Significance . The classification performance obtained by the proposed algorithm on brain–computer interface (BCI) competition IV dataset 2a in terms of accuracy is 83% and Cohen’s kappa value is 0.80. Finally, the shared hybrid deep network is evaluated by every subject respectively, and the experimental results illustrate that the shared neural network has satisfactory accuracy. Thus, the proposed algorithm could be of great interest for real-life BCIs.

1 April 2023 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
DLDa Liu
Da Liu
LDLiqian Dou
Liqian Dou
RZRuilong Zhang
Ruilong Zhang
XZXiuyun Zhang
Xiuyun Zhang
QZQun Zong
Qun Zong

24 June 2019 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
QMQi Mao
Qi Mao
LDLiqian Dou
Liqian Dou
ZYZhenshu Yang
Zhenshu Yang
Bailing TianBailing Tian
Bailing Tian
QZQun Zong
Qun Zong
This paper investigates the problem of attitude tracking control for reusable launch vehicles (RLV) with aeroservoelastic characteristic and disturbances in reentry phase. An aeroservoelastic model for reentry RLV is firstly established, where the synthetic disturbances are considered as well. Then a novel disturbance observer combined with fuzzy logic system is constructed by using both fuzzy approximation error and observation error to provide the disturbance estimation. The fuzzy disturbance observer (FDO) can be employed to the control scheme to counteract the perturbations and guarantee the estimation errors for converging to a small neighborhood around origin. Incorporated with the designed FDOs, the adaptive sliding mode technique is proposed for developing attitude angle and angular rate subsystem controllers respectively to ensure the reentry attitude tracking performance. Rigorous proof shows that the uniformly stability of the closed-loop system under the proposed control law can be guaranteed by using Lyapunov technique. Finally, numerical simulations are conducted to illustrate that the effectiveness of the developed technique for the RLV.

13 February 2024 in IEEE Transactions on Emerging Topics in Computational Intelligence
Verified
Journal Article
Closed access
DLDa Liu
Da Liu
QZQun Zong
Qun Zong
XZXiuyun Zhang
Xiuyun Zhang
RZRuilong Zhang
Ruilong Zhang
LDLiqian Dou
Liqian Dou
Bailing TianBailing Tian
Bailing Tian
Due to the characteristics of the small size and low cost of unmanned aerial vehicles (UAVs), Multi-UAV confrontation will play an important role in future wars. The Multi-UAV confrontation game in the air combat environment is investigated in this paper. To truly deduce the confrontation scene, a physics engine is established based on the Multi-UAV Confrontation Scenario (MCS) framework, enabling the real-time interaction between the agent and environment while making the learned strategies more realistic. To form an effective confrontation strategy, the Graph Attention Multi-agent Soft Actor Critic Reinforcement Learning with Target Predicting Network (GA-MASAC-TP Net) is firstly proposed for Multi-UAV confrontation game. The merits lie in that the Multi-UAV trajectory prediction, considering interactions among targets, is incorporated innovatively into the Multi-agent reinforcement learning (MARL), enabling Multi-UAVs to make decisions more accurately based on situation prediction. Specifically, the Soft Actor Critic (SAC) algorithm is extended to the Multi-agent domain and embed with the graph attention neural network into the Actor, Critic network, so the UAV could aggregate the information of the spatial neighbor teammates based on the attention mechanism for better collaboration. The comparative experiment and ablation study demonstrate the effectiveness of the proposed algorithm and the state-of-art performance in the MCS.

8 October 2018 in International Journal of Robust and Nonlinear Control
Verified
Journal Article
Closed access
PDF file
DWDandan Wang
Dandan Wang
QZQun Zong
Qun Zong
Bailing TianBailing Tian
Bailing Tian
FWFang Wang
Fang Wang
LDLiqian Dou
Liqian Dou

22 August 2019 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
NXNa Xing
Na Xing
QZQun Zong
Qun Zong
LDLiqian Dou
Liqian Dou
Bailing TianBailing Tian
Bailing Tian
QWQing Wang
Qing Wang
Unmanned aerial vehicle (UAV) swarms have attracted great interests in numerous civil and military scenarios due to their flexible deployment and mobility. The increased network size poses a challenge for the network scalability. Clustering as an effective scheme, is able to provide efficient communication and network performance. In order to adapt to the change of network topology, the link subsistence probability is used to evaluate the mobility of UAVs. However, the UAVs usually perform tasks collaboratively, which leads to their movements are typically group-based. To this end, a coalition game theoretic framework is proposed to cluster UAVs into coalitions in a distributed autonomous manner, based on the group and the mobility information. The proposed game allows the UAVs with the same group, as much as possible, into one coalition under some constraints, such as cluster size and cluster diameter. To solve the game, each UAV makes its decision whether to switch based on the coalition value. Finally, some comparisons are provided to illustrate the efficiency of the proposed algorithm.