Qian Li

Qian Li

Auto-generated profile, based on publicly available information

Qian Li

School of Advanced Manufacturing, Nanchang University, Nanchang, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
29 July 2021 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
ZWZhou Wu
Zhou Wu
QLQian Li
Qian Li
HZHaijun Zhang
Haijun Zhang
In this article, a chain-structure echo state network (CESN) with stacked subnetwork modules is newly proposed as a new kind of deep recurrent neural network for multivariate time series prediction. Motivated by the philosophy of “divide and conquer,” the related input vectors are first divided into clusters, and the final output results of CESN are then integrated by successively learning the predicted values of each clustered variable. Network structure, mathematical model, training mechanism, and stability analysis are, respectively, studied for the proposed CESN. In the training stage, least-squares regression is first used to pretrain the output weights in a module-by-module way, and stochastic local search (SLS) is developed to fine-tune network weights toward global optima. The loss function of CESN can be effectively reduced by SLS. To avoid overfitting, the optimization process is stopped when the validation error starts to increase. Finally, SLS-CESN is evaluated in chaos prediction benchmarks and real applications. Four different examples are given to verify the effectiveness and robustness of CESN and SLS-CESN.

10 December 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
TLTao Li
Tao Li
ZGZhijun Guo
Zhijun Guo
QLQian Li
Qian Li

4 January 2024 in IEEE Access
Verified
Journal Article
Open access
DYDayong Yang
Dayong Yang
TLTao Li
Tao Li
ZGZhijun Guo
Zhijun Guo
QLQian Li
Qian Li
In this article, a new kind of neural network model named multi-scale convolutional echo state network (MCESN) is proposed for solar irradiance prediction, which integrates the strong feature extraction capability of convolutional neural network (CNN) and the fast yet efficient prediction ability of echo state network (ESN). Firstly, the feature information at different time scales of solar irradiance (one dimensional series) data are extracted and selected by multi-scale CNN (MCNN) in the pre-training stage. Then, the trained features extracted above are concatenated and passed to ESN module as the input signal, which can be further encoded into high-dimensional state space; Meanwhile, the target solar irradiance value is fitted and predicted by ESN in the prediction phase. Finally, the effectiveness of MCESN is evaluated by hourly solar irradiance prediction. In experiment, RMSE, MAE, MAPE and R are chosen as four metrics to evaluate the performance of the proposed model. Simulation results demonstrate that the proposed MCESN perform better than classical ESN, MCNN, backpropagation (BP) random forest (RF), long short time memory (LSTM) and deep ESN (DESN) algorithms.

25 April 2024 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
TLTao Li
Tao Li
ZGZhijun Guo
Zhijun Guo
QLQian Li
Qian Li
ZWZhou Wu
Zhou Wu

22 November 2024 in Neurocomputing
Verified
Journal Article
Closed access
TLTao Li
Tao Li
ZGZhijun Guo
Zhijun Guo
QLQian Li
Qian Li

30 December 2024 in IEEE Transactions on Industrial Cyber-Physical Systems
Verified
Journal Article
Closed access
ZGZhijun Guo
Zhijun Guo
JXJunliang Xin
Junliang Xin
QLQian Li
Qian Li
The standard condition for achieving exponential convergence of distributed resource allocation is the strongly convex objective functions, which is hard to be guaranteed in many practical cyber-physical systems. To study the resource allocation problem in a more general setting, we provide a new condition which only requires that the gradient-based map satisfies the metric subregularity. This condition is weaker than the standard strongly convex condition and is imposed to the objective functions. Based on such a relaxed condition, two new kinds of distributed allocation algorithms are proposed under continuous-time and event-triggered communications, respectively. The exponential convergence of our proposed algorithms are verified by rigorous theoretical analyses and some economic dispatch examples in the industrial cyber-physical system.