Pu Lan

Dr. Pu Lan

School of Electronics and Information Engineering

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
15 September 2021 in Symmetry
Verified
Journal Article
Open access
PDF file
PLPu Lan
Pu Lan
Kewen XiaKewen Xia
Kewen Xia
YPyongke Pan
yongke Pan
FSFan Shurui
Fan Shurui
An improved equilibrium optimizer (EO) algorithm is proposed in this paper to address premature and slow convergence. Firstly, a highly stochastic chaotic mechanism is adopted to initialize the population for range expansion. Secondly, the capability to conduct global search to jump out of local optima is enhanced by assigning adaptive weights and setting adaptive convergence factors. In addition 25 classical benchmark functions are used to validate the algorithm. As revealed by the analysis of the accuracy, speed, and stability of convergence, the IEO algorithm proposed in this paper significantly outperforms other meta-heuristic algorithms. In practice, the distribution is asymmetric because most logging data are unlabeled. Traditional classification models have difficulty in accurately predicting the location of oil layer. In this paper, the oil layers related to oil exploration are predicted using long short-term memory (LSTM) networks. Due to the large amount of data used, however, it is difficult to adjust the parameters. For this reason, an improved equilibrium optimizer algorithm (IEO) is applied to optimize the parameters of LSTM for improved performance, while the effective IEO-LSTM is applied for oil layer prediction. As indicated by the results, the proposed model outperforms the current popular optimization algorithms including particle swarm algorithm PSO and genetic algorithm GA in terms of accuracy, absolute error, root mean square error and mean absolute error.

20 December 2021 in Electronics
Verified
Journal Article
Open access
PDF file
PLPu Lan
Pu Lan
Kewen XiaKewen Xia
Kewen Xia
YPyongke Pan
yongke Pan
FSFan Shurui
Fan Shurui
In this study, a model based on the improved grey wolf optimizer (GWO) for optimizing RVFL is proposed to enable the problem of poor accuracy of Oil layer prediction due to the randomness of the parameters present in the random vector function link (RVFL) model to be addressed. Firstly, GWO is improved based on the advantages of chaos theory and the marine predator algorithm (MPA) to overcome the problem of low convergence accuracy in the optimization process of the GWO optimization algorithm. The improved GWO algorithm was then used to optimize the input weights and implicit layer biases of the RVFL network model so that the problem of inaccurate and unstable classification of RVFL due to the randomness of the parameters was avoided. MPA-GWO was used for comparison with algorithms of the same type under a function of 15 standard tests. From the results, it was concluded that it outperformed the algorithms of its type in terms of search accuracy and search speed. At the same time, the MPA-GWO-RVFL model was applied to the field of Oil layer prediction. From the comparison tests, it is concluded that the prediction accuracy of the MPA-GWO-RVFL model is on average 2.9%, 3.04%, 2.27%, 8.74%, 1.47% and 10.41% better than that of the MPA-RVFL, GWO-RVFL, PSO-RVFL, WOA-RVFL, GWFOA-RVFL and RVFL algorithms, respectively, and its practical applications are significant.

17 October 2022 in Electronics
Verified
Journal Article
Open access
PDF file
GLGuo-dong Li
Guo-dong Li
YPyongke Pan
yongke Pan
PLPu Lan
Pu Lan
An accurate and stable reservoir prediction model is essential for oil location and production. We propose an predictive hybrid model ILSTM-BRVFL based on an improved long short-term memory network (IAOS-LSTM) and a bidirectional random vector functional link (Bidirectional-RVFL) for this problem. Firstly, the Atomic Orbit Search algorithm (AOS) is used to perform collective optimization of the parameters to improve the stability and accuracy of the LSTM model for high-dimensional feature extraction. At the same time, there is still room to improve the optimization capability of the AOS. Therefore, an improvement scheme to further enhance the optimization capability is proposed. Then, the LSTM-extracted high-dimensional features are fed into the random vector functional link (RVFL) to improve the prediction of high-dimensional features by the RVFL, which is modified as the bidirectional RVFL. The proposed ILSTM-BRVFL (IAOS) model achieves an average prediction accuracy of 95.28%, compared to the experimental results. The model’s accuracy, recall values, and F1 values also showed good performance, and the prediction ability achieved the expected results. The comparative analysis and the degree of improvement in the model results show that the high-dimensional extraction of the input data by LSTM is the most significant improvement in prediction accuracy. Secondly, it introduces a double-ended mechanism for IAOS to LSTM and RVFL for parameter search.