Lijie Zhao

Prof. Lijie Zhao


Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
13 December 2012 in International Journal of Automation and Computing
Verified
Journal Article
Closed access
PDF file
LZLijie Zhao
Lijie Zhao
TCTian-You Chai
Tian-You Chai
DYDe-Cheng Yuan
De-Cheng Yuan

25 January 2012 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
LZLijie Zhao
Lijie Zhao
DWDianhui Wang
Dianhui Wang
TCTianyou Chai
Tianyou Chai

1 January 2006
Verified
Conference Paper
Closed access
LZLijie Zhao
Lijie Zhao
TCTianyou Chai
Tianyou Chai
QCQiumei Cong
Qiumei Cong
Poor-quality data has become a serous problem to the model, control and optimization. An improved robust EMPCA integrated with fuzzy c-means (FCM) clustering is used to classify the operational state in the activated sludge process. The method is demonstrated by IWA simulation benchmark. The experimental results show the proposed the method can accurately classify the operational state of the activated sludge process in the PC-space after outliers and missing data are effectively detect, rectified

1 January 2006
Verified
Conference Paper
Closed access
LZLijie Zhao
Lijie Zhao
TCTianyou Chai
Tianyou Chai
QCQiumei Cong
Qiumei Cong
Due to high complex of the biological wastewater treatment, it is difficult to develop an accurate mathematics model. A hybrid dynamic modeling in both parallel and serial configuration was used in an anoxic-aeration activated sludge process. In the hybrid model, case-based reasoning (CBR) system is placed in series with a mechanistic model, which was the Activated Sludge Model No. 1 (ASM1) by the International Water Association (IWA); whereas the CBR system was used to identify the key kinetic and stoichiometric parameter at the different conditions. A neural network in parallel configuration compensates for the known difference between the results of a purely mechanistic model and the process data. The proposed method was applied in the Shenyang wastewater treatment plant. Simulation results demonstrate the predictions of the hybrid model were significantly improved

25 June 2025 in Sensors
Verified
Journal Article
Open access
PDF file
GWGuogang Wang
Guogang Wang
YLYizhen Lv
Yizhen Lv
LZLijie Zhao
Lijie Zhao
YLyunpeng Liu
yunpeng Liu
Aiming at the problem of appearance drift and susceptibility to noise interference in visual place recognition (VPR), we propose DD–DPFE: a Dynamic Difference and Dual-Path Feature Enhancement method. Embedding differential attention mechanisms in the DINOv2 model to mitigate the effects of process interference and adding serial-parallel adapters allows efficient model parameter migration and task adaptation. Our method constructs a two-way feature enhancement module with global–local branching synergy. The global branch employs a dynamic fusion mechanism with a multi-layer Transformer encoder to strengthen the structured spatial representation to cope with appearance changes, while the local branch suppresses the over-response of redundant noise through an adaptive weighting mechanism and fuses the contextual information from the multi-scale feature aggregation module to enhance the robustness of the scene. The experimental results show that the model architecture proposed in this paper is an obvious improvement in different environmental tests. This is most obvious in the simulation test of a night scene, verifying that the proposed method can effectively enhance the discriminative power of the system and its anti-jamming ability in complex scenes.