Jinxin Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jinxin Zhu has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Jun Shao
School of Information Technology, Yancheng Institute of Technology, Yancheng 224051, China
3 shared publications - Xuesheng Bian
Department of Information Engineering, Yancheng Institute of Technology, Yancheng 224007, China
2 shared publications Binbin Guo
School of Information Engineering, Yancheng Institute of Technology 1 , Yancheng
1 shared publicationChao Zhang
School of Information Engineering, Yancheng Institute of Technology 1 , Yancheng
1 shared publication- Chao Zhang
School of Information Engineering, Yancheng Institute of Technology, Yancheng, China
1 shared publication - Cheng Wang
Fujian Key Laboratory of Sensing and Computing for Smart Cities, Xiamen University, Xiamen, Fujian, China
1 shared publication
Latest Publications
- 1 September 2026
- Published by AIP Publishing in Journal of Renewable and Sustainable Energy
- Vol. 18 (5)
Closed-loop prediction and optimization of multi-energy flow coupling in virtual power plants
In order to cope with global warming and control carbon emissions, virtual power plants (VPPs) have become a key means to improve the capacity of renewable energy consumption and reduce the ecological impact of existing energy infrastructure. This paper proposes a multi-energy flow coupled VPP scheduling optimization model based on electrical synergy and carbon capture technology combined with the organic Rankine cycle. In the model, waste heat boilers and heat pumps are used to improve the energy conversion efficiency and flexibility of the combined heat and power system and to achieve the coordinated scheduling and complementarity of electricity-, heat-, and gas-based multi-energy flows. In view of the complexity of the VPP system and the need for the coordinated scheduling of multiple units, a closed-loop prediction and optimization (CPO) framework is introduced to reduce the system operating cost by coordinating renewable-energy forecasting with multi-energy scheduling decisions. The effectiveness of the proposed model is verified by examples. Experimental results show that compared with the open-loop prediction and optimization (OPO) framework, the CPO framework significantly improves the economy of the VPP system, reduces the actual cost of the system by 2.75%, and improves the daily economy by 13.41%. Although the cost-oriented prediction accuracy is lower than that of OPO in some time periods, it effectively reduces the additional cost caused by rescheduling (SUSD, i.e., start-stop cost, is reduced by 53%), takes into account both economy and prediction accuracy in multi-energy flow coupling scheduling, and improves the overall efficiency of the system.
- 1 September 2026
- Published by AIP Publishing in Journal of Renewable and Sustainable Energy
- Vol. 18 (5)
Closed-loop prediction and optimization of multi-energy flow coupling in virtual power plants
In order to cope with global warming and control carbon emissions, virtual power plants (VPPs) have become a key means to improve the capacity of renewable energy consumption and reduce the ecological impact of existing energy infrastructure. This paper proposes a multi-energy flow coupled VPP scheduling optimization model based on electrical synergy and carbon capture technology combined with the organic Rankine cycle. In the model, waste heat boilers and heat pumps are used to improve the energy conversion efficiency and flexibility of the combined heat and power system and to achieve the coordinated scheduling and complementarity of electricity-, heat-, and gas-based multi-energy flows. In view of the complexity of the VPP system and the need for the coordinated scheduling of multiple units, a closed-loop prediction and optimization (CPO) framework is introduced to reduce the system operating cost by coordinating renewable-energy forecasting with multi-energy scheduling decisions. The effectiveness of the proposed model is verified by examples. Experimental results show that compared with the open-loop prediction and optimization (OPO) framework, the CPO framework significantly improves the economy of the VPP system, reduces the actual cost of the system by 2.75%, and improves the daily economy by 13.41%. Although the cost-oriented prediction accuracy is lower than that of OPO in some time periods, it effectively reduces the additional cost caused by rescheduling (SUSD, i.e., start-stop cost, is reduced by 53%), takes into account both economy and prediction accuracy in multi-energy flow coupling scheduling, and improves the overall efficiency of the system.
- Open Access
- 15 August 2026
- Published by MDPI AG in Electronics
- Vol. 15 (16) , 3641
DAPR: Dynamic Distribution-Aware and Adaptive Pseudo-Label Refinement for Long-Tailed Semi-Supervised Oral Disease Classification
Oral disease image classification can support computer-assisted assessment of intraoral images. However, obtaining large-scale annotated medical data is expensive, while real-world oral disease datasets often exhibit severe long-tailed distributions, where minority disease categories contain only limited samples. Existing semi-supervised learning methods commonly rely on fixed-threshold pseudo labels and may produce prediction distributions dominated by majority classes, resulting in class bias and pseudo-label noise accumulation under long-tailed settings. To address these issues, we propose DAPR, a Distribution-Aware and Adaptive Pseudo-Label Refinement framework for long-tailed semi-supervised oral disease classification. DAPR employs Dynamic Category Distribution Modeling (DCDM) to track the evolving prediction distribution of unlabeled samples and generate distribution-aware soft pseudo labels. A class-adaptive dynamic thresholding (CADT) mechanism was further introduced to improve minority-class sample utilization. In addition, Relation-aware Representation Learning (RRL) aligns semantic and feature relationships to enhance feature discrimination. Experiments using stratified five-fold cross-validation on a long-tailed oral disease dataset show that DAPR achieves the highest average Accuracy and Macro-F1 among the compared methods under the evaluated setting. DAPR achieves the highest average Accuracy and Macro-F1 among the compared methods and obtains strong aggregate tail-class performance, particularly for Tooth Discoloration and Ulcers. These results indicate that DAPR improves aggregate class-balanced learning under the evaluated dataset, annotation ratio, and backbone configuration.
- 15 August 2026
- Published by MDPI AG in Electronics
- Vol. 15 (16) , 3641
Open AccessDAPR: Dynamic Distribution-Aware and Adaptive Pseudo-Label Refinement for Long-Tailed Semi-Supervised Oral Disease Classification
Oral disease image classification can support computer-assisted assessment of intraoral images. However, obtaining large-scale annotated medical data is expensive, while real-world oral disease datasets often exhibit severe long-tailed distributions, where minority disease categories contain only limited samples. Existing semi-supervised learning methods commonly rely on fixed-threshold pseudo labels and may produce prediction distributions dominated by majority classes, resulting in class bias and pseudo-label noise accumulation under long-tailed settings. To address these issues, we propose DAPR, a Distribution-Aware and Adaptive Pseudo-Label Refinement framework for long-tailed semi-supervised oral disease classification. DAPR employs Dynamic Category Distribution Modeling (DCDM) to track the evolving prediction distribution of unlabeled samples and generate distribution-aware soft pseudo labels. A class-adaptive dynamic thresholding (CADT) mechanism was further introduced to improve minority-class sample utilization. In addition, Relation-aware Representation Learning (RRL) aligns semantic and feature relationships to enhance feature discrimination. Experiments using stratified five-fold cross-validation on a long-tailed oral disease dataset show that DAPR achieves the highest average Accuracy and Macro-F1 among the compared methods under the evaluated setting. DAPR achieves the highest average Accuracy and Macro-F1 among the compared methods and obtains strong aggregate tail-class performance, particularly for Tooth Discoloration and Ulcers. These results indicate that DAPR improves aggregate class-balanced learning under the evaluated dataset, annotation ratio, and backbone configuration.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23, 17994-18010
Physics-Driven Characterization of the Dynamic Operating Security Space for Coastal Distribution Grids With Wind Power Integration Under Salt-Fog Conditions
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23, 17994-18010
Physics-Driven Characterization of the Dynamic Operating Security Space for Coastal Distribution Grids With Wind Power Integration Under Salt-Fog Conditions
- 28 January 2025
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19 (3) , 1-11
Improved lightweight deep learning architecture for household waste detection
- 28 January 2025
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19 (3) , 1-11
Improved lightweight deep learning architecture for household waste detection
- 11 September 2023
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 43 (2) , 916-940
Long-Time Speech Emotion Recognition Using Feature Compensation and Accentuation-Based Fusion
- 11 September 2023
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 43 (2) , 916-940
Long-Time Speech Emotion Recognition Using Feature Compensation and Accentuation-Based Fusion
- Open Access
Ins-ATP: Deep Estimation of ATP for Organoid Based on High Throughput Microscopic Images
Adenosine triphosphate (ATP) is a high-energy phosphate compound and the most direct energy source in organisms. ATP is an essential biomarker for evaluating cell viability in biology. Researchers often use ATP bioluminescence to measure the ATP of organoid after drug to evaluate the drug efficacy. However, ATP bioluminescence has some limitations, leading to unreliable drug screening results. Performing ATP bioluminescence causes cell lysis of organoids, so it is impossible to observe organoids' long-term viability changes after medication continually. To overcome the disadvantages of ATP bioluminescence, we propose Ins-ATP, a non-invasive strategy, the first organoid ATP estimation model based on the high-throughput microscopic image. Ins-ATP directly estimates the ATP of organoids from high-throughput microscopic images, so that it does not influence the drug reactions of organoids. Therefore, the ATP change of organoids can be observed for a long time to obtain more stable results. Experimental results show that the ATP estimation by Ins-ATP is in good agreement with those determined by ATP bioluminescence. Specifically, the predictions of Ins-ATP are consistent with the results measured by ATP bioluminescence in the efficacy evaluation experiments of different drugs.
Open AccessIns-ATP: Deep Estimation of ATP for Organoid Based on High Throughput Microscopic Images
Adenosine triphosphate (ATP) is a high-energy phosphate compound and the most direct energy source in organisms. ATP is an essential biomarker for evaluating cell viability in biology. Researchers often use ATP bioluminescence to measure the ATP of organoid after drug to evaluate the drug efficacy. However, ATP bioluminescence has some limitations, leading to unreliable drug screening results. Performing ATP bioluminescence causes cell lysis of organoids, so it is impossible to observe organoids' long-term viability changes after medication continually. To overcome the disadvantages of ATP bioluminescence, we propose Ins-ATP, a non-invasive strategy, the first organoid ATP estimation model based on the high-throughput microscopic image. Ins-ATP directly estimates the ATP of organoids from high-throughput microscopic images, so that it does not influence the drug reactions of organoids. Therefore, the ATP change of organoids can be observed for a long time to obtain more stable results. Experimental results show that the ATP estimation by Ins-ATP is in good agreement with those determined by ATP bioluminescence. Specifically, the predictions of Ins-ATP are consistent with the results measured by ATP bioluminescence in the efficacy evaluation experiments of different drugs.
- Open Access
- 25 December 2021
- Published by Hindawi Limited in Mathematical Problems in Engineering
- Vol. 2021, 1-5
Joint Transceiver Optimization of MIMO SWIPT Systems Assisted by Reconfigurable Intelligent Surface
In this work, a reconfigurable intelligent surface (RIS)-assisted multiple-input multiple-output (MIMO) system is studied with wireless energy harvesting (EH). Specifically, we focus on maximizing the harvested power at the receiver by joint optimization of the signal covariance, the phase shifter, and the power splitting factor, subject to the information rate and transmit power constraints. The formulated problem is hard to address due to the nonconcave objective and the nonconvex constraints. To tackle these challenges, an alternating optimization (AO) framework is proposed, where the phase shifter is solved by the penalty-based method. Simulation results validate the performance of the proposed approach.
- 25 December 2021
- Published by Hindawi Limited in Mathematical Problems in Engineering
- Vol. 2021, 1-5
Open AccessJoint Transceiver Optimization of MIMO SWIPT Systems Assisted by Reconfigurable Intelligent Surface
In this work, a reconfigurable intelligent surface (RIS)-assisted multiple-input multiple-output (MIMO) system is studied with wireless energy harvesting (EH). Specifically, we focus on maximizing the harvested power at the receiver by joint optimization of the signal covariance, the phase shifter, and the power splitting factor, subject to the information rate and transmit power constraints. The formulated problem is hard to address due to the nonconcave objective and the nonconvex constraints. To tackle these challenges, an alternating optimization (AO) framework is proposed, where the phase shifter is solved by the penalty-based method. Simulation results validate the performance of the proposed approach.
- Open Access
- 5 November 2021
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2021, 1-7
Outage Constraint Robust Cooperative Beamforming and Jamming Design for Secure AF Relay Networks
This paper investigates a joint robust scheme in a secrecy relay network where distributed relays perform cooperative beamforming and a friendly jammer transmits jamming signal to enhance the information security. Specifically, we consider the outage constraint secrecy rate maximization design with imperfect channel state information. Through semidefinite relaxation and one-dimensional search, we propose a two-layer optimization method to solve the nonconvex problem. In addition, the Bernstein-type inequality and large deviation inequality are utilized to convert the probabilistic constraint. Simulation results demonstrate the performance of the proposed design.
- 5 November 2021
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2021, 1-7
Open AccessOutage Constraint Robust Cooperative Beamforming and Jamming Design for Secure AF Relay Networks
This paper investigates a joint robust scheme in a secrecy relay network where distributed relays perform cooperative beamforming and a friendly jammer transmits jamming signal to enhance the information security. Specifically, we consider the outage constraint secrecy rate maximization design with imperfect channel state information. Through semidefinite relaxation and one-dimensional search, we propose a two-layer optimization method to solve the nonconvex problem. In addition, the Bernstein-type inequality and large deviation inequality are utilized to convert the probabilistic constraint. Simulation results demonstrate the performance of the proposed design.