Jiajie Luo

Jiajie Luo

Auto-generated profile, based on publicly available information

Jiajie Luo

School of Computing, Newcastle University, Newcastle upon Tyne, U.K.

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
6 January 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
ZQZhaohui Qi
Zhaohui Qi
YNYingqiang Ning
Yingqiang Ning
LXLin Xiao
Lin Xiao
YHYongjun He
Yongjun He
JLJiajie Luo
Jiajie Luo
BLBiao Luo
Biao Luo
As an extension of the Lyapunov equation, the time-varying plural Lyapunov tensor equation (TV-PLTE) can carry multidimensional data, which can be solved by zeroing neural network (ZNN) models effectively. However, existing ZNN models only focus on time-varying equations in field of real number. Besides, the upper bound of the settling time depends on the value of ZNN model parameters, which is a conservative estimation for existing ZNN models. Therefore, this article proposes a novel design formula for converting the upper bound of the settling time into an independent and directly modifiable prior parameter. On this basis, we design two new ZNN models called strong predefined-time convergence ZNN (SPTC-ZNN) and fast predefined (FP)-time convergence ZNN (FPTC-ZNN) models. The SPTC-ZNN model has a nonconservative upper bound of the settling time, and the FPTC-ZNN model has excellent convergence performance. The upper bound of the settling time and robustness of the SPTC-ZNN and FPTC-ZNN models are verified by theoretical analyses. Then, the effect of noise on the upper bound of settling time is discussed. The simulation results show that the SPTC-ZNN and FPTC-ZNN models have better comprehensive performance than existing ZNN models.

10 July 2024 in IEEE Systems, Man, and Cybernetics Magazine
Verified
Journal Article
Closed access
LXLin Xiao
Lin Xiao
JLJiajie Luo
Jiajie Luo
JLJichun Li
Jichun Li
LJLei Jia
Lei Jia
JLJiguang Li
Jiguang Li
The zeroing neural network (ZNN) has been utilized in various control applications, such as tracking and motion control. While ZNN has been widely employed, its utilization in consensus control schemes is rarely reported. In this study, we propose a novel distributed fixed-time ZNN (DFTZNN) scheme designed to achieve fixed-time and robust consensus in multiagent systems operating under a switching topology. Theoretical analysis is provided to establish the fixed-time stability and robustness of the proposed scheme in the presence of bounded noises. To highlight the superiority of the proposed method, we introduce an example demonstrating the estimation of the upper bound of a settling-time function. Theoretical analysis and a novel upper-bound estimation method are subsequently validated through numerical experiments, including a practical application in formation control. The comprehensive theoretical and simulation results demonstrate the superior performance of the DFTZNN scheme under both fixed and switching topologies, establishing it as a novel and systematic framework for designing consensus control schemes.

11 November 2025 in IEEE Transactions on Emerging Topics in Computing
Verified
Journal Article
Closed access
JLJiajie Luo
Jiajie Luo
JLJiguang Li
Jiguang Li
LXLin Xiao
Lin Xiao
JLJichun Li
Jichun Li
WJWenxing Ji
Wenxing Ji
PQPeng Qi
Peng Qi
Zeroing neural network (ZNN) with variable convergence parameter has been a research hotspot recently, and it can be divided into two categories: the varying-parameter ZNN (VP-ZNN) model, and the fuzzy-parameter ZNN (FP-ZNN) model. Both of the two models have their own advantages and disadvantages. VP-ZNN models are usually efficient but not intelligent, while FP-ZNN models are usually intelligent but not efficient. Inspired by the classic proportional–integral–derivative (PID) control technology, we proposed a novel proportional-integral-parameter ZNN (PIP-ZNN) model, which is both efficient and intelligent, to solve the quaternion-valued time-varying linear matrix inequalities (QVTV-LMI) problem. Integrated with adaptive convergence parameters (ACP), the PIP-ZNN model dynamically adjusts its convergence in response to error changes and then achieves optimized performance. Compared with FP-ZNN models which are based on fuzzy logic systems, the PID-based PIP-ZNN models are simpler and more efficient. With the incorporation of a robust activation function (RAF), the PIP-ZNN model demonstrates fixed-time stability and robustness in the presence of both attenuated and constant disturbances. Theoretical analyses in this paper establish the fixed-time stability and robustness of the PIP-ZNN model, including an estimation of the upper bound of the settling-time function. Numerical experiments here validate these advanced features further, emphasizing the efficacy and excellent performance of the proposed PIP-ZNN model.

16 March 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
JLJiaqing Li
Jiaqing Li
YZYu Zhou
Yu Zhou
JLJiguang Li
Jiguang Li
SZShuo Zhao
Shuo Zhao
JLJiajie Luo
Jiajie Luo
JLJichun Li
Jichun Li
Instance selection is an important preprocessing step in data mining and machine learning, particularly for large-scale datasets where instance redundancy and noise can degrade computational efficiency and generalization performance. Motivated by physical interaction principles, this paper proposes a Local Coulomb Force-based Instance Selection method (LCFIS). In the proposed framework, each data point is modeled as a charged particle, with its local density—estimated by combining reverse nearest neighbors and Gaussian kernel density estimation—serving as the charge magnitude. Neighborhood interactions are explicitly captured through the resultant Coulomb force acting on each point. We show that, as the neighborhood size increases, the rate of change of the resultant force differs significantly among boundary and core points. Utilizing this character, LCFIS effectively identifies boundary instances. A compact and representative training set is constructed by combining selected boundary points with randomly sampled instances to preserve data diversity. Extensive experiments on multiple public benchmark datasets using two standard classifiers demonstrate that LCFIS achieves a favorable trade-off between compression and classification performance, outperforming nine representative instance selection methods across accuracy, reduction rate, effectiveness, and computational cost.

13 November 2023
Verified
Book Chapter
Closed access
PDF file
JLJiajie Luo
Jiajie Luo
LXLin Xiao
Lin Xiao
PTPing Tan
Ping Tan
JLJiguang Li
Jiguang Li
WYWei Yao
Wei Yao
JLJichun Li
Jichun Li

21 April 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
JLJiaqing Li
Jiaqing Li
YZYu Zhou
Yu Zhou
JLJiguang Li
Jiguang Li
SZShuo Zhao
Shuo Zhao
JLJiajie Luo
Jiajie Luo
JLJichun Li
Jichun Li
Instance selection is an important preprocessing step in data mining and machine learning, particularly for large-scale datasets where instance redundancy and noise can degrade computational efficiency and generalization performance. Motivated by physical interaction principles, this paper proposes a Local Coulomb Force-based Instance Selection method (LCFIS). In the proposed framework, each data point is modeled as a charged particle, with its local density—estimated by combining reverse nearest neighbors and Gaussian kernel density estimation—serving as the charge magnitude. Neighborhood interactions are explicitly captured through the resultant Coulomb force acting on each point. We show that, as the neighborhood size increases, the rate of change of the resultant force differs significantly among boundary and core points. Utilizing this character, LCFIS effectively identifies boundary instances. A compact and representative training set is constructed by combining selected boundary points with randomly sampled instances to preserve data diversity. Extensive experiments on multiple public benchmark datasets using two standard classifiers demonstrate that LCFIS achieves a favorable trade-off between compression and classification performance, outperforming nine representative instance selection methods across accuracy, reduction rate, effectiveness, and computational cost.