Shi Yan

Shi Yan


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
19 October 2024 in Neural Networks
Verified
Journal Article
Closed access
XZXingwen Zhou
Xingwen Zhou
ZYZhenghao You
Zhenghao You
WSWeiguo Sun
Weiguo Sun
DZDongdong Zhao
Dongdong Zhao
SYShi Yan
Shi Yan

9 May 2024 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
DZDongdong Zhao
Dongdong Zhao
BLBoyu Li
Boyu Li
FLFuxiang Lu
Fuxiang Lu
Jinhua SheJinhua She
Jinhua She
SYShi Yan
Shi Yan
This article presents a deep bilinear Koopman model predictive control (DBKMPC) approach for modelling and control of unknown nonlinear systems. The bilinear model, which has the computational speed of a linear model and the predictive accuracy of a nonlinear model, can accurately characterize a large class of airborne and ground-based robotic systems. Specifically, a bilinear Koopman dynamic deep neural network (BKDDNN) is developed to learn the finite-dimensional bilinear Koopman operator in the lifting space without prior knowledge or system parameters. Moreover, the bilinear model is integrated into the standard model predictive control (MPC) optimization problem, facilitating the solution of the bilinear optimization problem. In such a way, the proposed DBKMPC avoids the problems of excessive inductive bias and selection difficulty of dictionary functions encountered by the existing methods, so that it enables a more effective solution to the problem of modeling and control of nonlinear robotic systems. The experimental results show that the proposed DBKMPC method surpasses the existing representative methods in terms of prediction and control performance.

19 April 2024 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
DZDongdong Zhao
Dongdong Zhao
XYXiaodi Yang
Xiaodi Yang
YLYichang Li
Yichang Li
LXLi Xu
Li Xu
Jinhua SheJinhua She
Jinhua She
SYShi Yan
Shi Yan
This article presents a Kalman–Koopman linear quadratic regulator (KKLQR) control approach to robotic systems. In the proposed approach, an optimal Koopman modeling method based on neural networks, in which continuous Koopman eigenfunctions are constructed without requiring any predefined dictionary, is proposed to obtain approximated linear models with high precision for robotic systems. Specifically, the linear model is constructed through a multistep prediction error minimization, which enables a long-term prediction capability. Furthermore, the Kalman filter is employed to alleviate the effects of disturbances in the KKLQR control approach. Experimental results show that the proposed KKLQR control approach achieves better prediction and control performance than other existing representative methods.

13 July 2023 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
DZDongdong Zhao
Dongdong Zhao
HLHongli Li
Hongli Li
SYShi Yan
Shi Yan
Capturing the long-range spatial-temporal correlation among joints of dynamic skeletal data efficiently is very challenging in hand gesture recognition (HGR). The flexibility of Transformer in modeling global dependencies among elements of any sequence makes it a perfect solution for skeleton-based HGR. However, the existing Transformer-based approaches only capture the correlation of intra-frame and inter-frame joints, respectively, without considering the relationship among different joints in several successive frames. In this paper, a novel spatial-temporal synchronous transformer (STST) method is proposed for skeleton-based HGR. The spatial-temporal chunks encoding module is proposed to encode the hand gesture skeleton sequence (HGSS) into several chunks, in which each chunk contains several consecutive frames to encode the relationship among spatial-temporal joints. Then, the encoding feature is fed into a spatial-temporal chunks transformer module and a temporal integration transformer module to model the spatial-temporal correlation of HGSSs, simultaneously, so that a more comprehensive understanding of the global and local spatial-temporal information can be achieved. In this way, the spatial-temporal information among joints can be efficiently extracted and utilized to better understand the semantics of gesture actions and then yield a higher recognition accuracy. Extensive experiments on SHREC’17 Track dataset and DHG-14/28 dataset show that the proposed method achieves the state-of-the-art performance compared with other representative methods.

29 June 2022 in IEEE Transactions on Computational Social Systems
Verified
Journal Article
Closed access
DZDongdong Zhao
Dongdong Zhao
QYQinglian Yang
Qinglian Yang
XZXingwen Zhou
Xingwen Zhou
HLHongli Li
Hongli Li
SYShi Yan
Shi Yan
Dynamic skeletal data contain advanced information represented by complex compound actions and have been extensively studied in human motion recognition. Previous works usually depend on designing the traversal rules made by hand or using two separate components to obtain spatial and temporal information based on skeleton graph, respectively, which still have generalization difficulties and significant challenges in learning effective spatial–temporal information. This article proposes a local spatial–temporal synchronous network (LSTSN) for skeleton-based dynamic gestures recognition, which can simultaneously deal with spatial and temporal information in gestures. Specifically, to fully obtain the spatial–temporal information of the skeleton data, a coupled position embedding and a three-neighbor local spatial–temporal graph (LSTG) are constructed. An adaptive threshold method is designed to describe the joint connections of LSTG, and then, an attention mechanism is used to efficiently capture complex local spatial–temporal correlations. Meanwhile, multiple spatial–temporal attention modules of different periods are designed to effectively capture the LSTG’s heterogeneity. Besides, from the data aspect, a hand motion vector (HMV) is also introduced into the model to express subtle finger motions. Extensive experiment results on DHG-14/28 and SHREC’17 Track datasets demonstrate that the proposed LSTSN is competitive with state-of-the-art methods.

24 July 2025 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
DZDongdong Zhao
Dongdong Zhao
MFMin Feng
Min Feng
WXWenjing Xian
Wenjing Xian
JQJiahu Qin
Jiahu Qin
Jinhua SheJinhua She
Jinhua She
SYShi Yan
Shi Yan
This article proposes linear quadratic controllers for unknown nonlinear systems with noise. Scenarios with unknown underlying nonlinear dynamics but measurable system states are considered. The unknown nonlinear systems are lifted to higher dimensional model-free linear predictors, with approximately linear system evolution by adopting the Koopman theory. The linear quadratic control (LQC) problem of the original nonlinear system is transformed into an LQC problem with a model-free linear predictor. To determine the gain of an optimal feedback control policy, quadratic cost, and associated value functions are designed for the lifted state, enhancing the theoretical performance of model-free reinforcement learning algorithms through control theory. An improved average Q-learning algorithm is presented to learn the gain of the optimal control policy based on the lifted noisy state observations. Helicopter experiments are presented to demonstrate the effectiveness of the model-free approach over representative methods.