Shaojun Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Shaojun Li has a total of 63 co-authors. Here are the top co-authors by number of shared publications:
Yang Zhou
Automation Department, Shanghai University, Shanghai, China
8 shared publicationsXiang Ren
Key Laboratory of Advanced Control and Optimization for Chemical Processes, East China University of Science and Technology, Ministry of Education, Shanghai 200237, China
5 shared publications- Xiang Ren
Environmental and Occupational Health Sciences Institute (EOHSI), Rutgers University, Piscataway, NJ 08854, USA; Department of Chemical and Biochemical Engineering, Rutgers University, Piscataway, NJ 08854, USA
5 shared publications Hai Wang
4 shared publicationsQiong Jia
Key Laboratory of Advanced Control and Optimization for Chemical Processes, East China University of Science and Technology, Ministry of Education, Shanghai 200237, China
3 shared publicationsXuemei Li
Key Laboratory of Smart Manufacturing in Energy Chemical Processes, Ministry of Education, East China University of Science and Technology, Shanghai, China
3 shared publications
Latest Publications
- 9 September 2026
- Published by Elsevier in Computers & Chemical Engineering
- Vol. 216
An AIPC-based controller for chemical process operations: Development and validation on a rigorous dynamic model
- 9 September 2026
- Published by Elsevier in Computers & Chemical Engineering
- Vol. 216
An AIPC-based controller for chemical process operations: Development and validation on a rigorous dynamic model
- Open Access
- 31 August 2026
- Published by Elsevier in SSRN Electronic Journal
Multimodal Fusion of Clinicopathological Features, Transcriptomics and MRI Radiomics for Predicting Postoperative Recurrence in Cervical Cancer
Background Postoperative recurrence remains a major challenge in cervical cancer (CC). Current risk stratification based mainly on clinicopathological factors has limited predictive capability due to incomplete representation of molecular and imaging heterogeneity. This study aimed to develop a multimodal framework integrating clinicopathological features, transcriptomic profiles, and magnetic resonance imaging (MRI) radiomics for individualized recurrence prediction in CC. Methods This retrospective study included 219 CC patients who underwent radical surgery between 2018 and 2022. Clinicopathological data, preoperative MRI, and tumor transcriptomic profiles were collected. Unimodal models were developed using each data modality separately, while a multimodal fusion model was constructed using a stacking ensemble approach. Model performance was evaluated using nested cross-validation, discrimination metrics, calibration analysis, and decision curve analysis. Results Among unimodal models, transcriptomic and MRI radiomics models achieved higher discriminative performance than the clinicopathological model (AUC: 0.75, 0.73, and 0.65, respectively). The multimodal fusion model further improved recurrence prediction, achieving an AUC of 0.85, with accuracy, sensitivity, and specificity of 0.80, 0.75, and 0.81, respectively. The integrated model showed improved calibration and greater clinical net benefit compared with traditional Sedlis criteria. Ablation analysis demonstrated that each modality contributed complementary predictive information. Conclusions Integration of clinicopathological, transcriptomic, and MRI radiomic biomarkers improved postoperative recurrence prediction in CC, providing a potential approach for personalized risk stratification and postoperative management.
- 31 August 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessMultimodal Fusion of Clinicopathological Features, Transcriptomics and MRI Radiomics for Predicting Postoperative Recurrence in Cervical Cancer
Background Postoperative recurrence remains a major challenge in cervical cancer (CC). Current risk stratification based mainly on clinicopathological factors has limited predictive capability due to incomplete representation of molecular and imaging heterogeneity. This study aimed to develop a multimodal framework integrating clinicopathological features, transcriptomic profiles, and magnetic resonance imaging (MRI) radiomics for individualized recurrence prediction in CC. Methods This retrospective study included 219 CC patients who underwent radical surgery between 2018 and 2022. Clinicopathological data, preoperative MRI, and tumor transcriptomic profiles were collected. Unimodal models were developed using each data modality separately, while a multimodal fusion model was constructed using a stacking ensemble approach. Model performance was evaluated using nested cross-validation, discrimination metrics, calibration analysis, and decision curve analysis. Results Among unimodal models, transcriptomic and MRI radiomics models achieved higher discriminative performance than the clinicopathological model (AUC: 0.75, 0.73, and 0.65, respectively). The multimodal fusion model further improved recurrence prediction, achieving an AUC of 0.85, with accuracy, sensitivity, and specificity of 0.80, 0.75, and 0.81, respectively. The integrated model showed improved calibration and greater clinical net benefit compared with traditional Sedlis criteria. Ablation analysis demonstrated that each modality contributed complementary predictive information. Conclusions Integration of clinicopathological, transcriptomic, and MRI radiomic biomarkers improved postoperative recurrence prediction in CC, providing a potential approach for personalized risk stratification and postoperative management.
- 24 August 2026
- Published by Elsevier in Chemical Engineering Science
- Vol. 338
Multi-period interval optimization of a renewable steam-methanol system for uncertainty-aware industrial decarbonization
- 24 August 2026
- Published by Elsevier in Chemical Engineering Science
- Vol. 338
Multi-period interval optimization of a renewable steam-methanol system for uncertainty-aware industrial decarbonization
- Open Access
- 11 June 2026
- Published by Elsevier in SSRN Electronic Journal
An AIPC-based controller for chemical process operations: Development and validation on a rigorous dynamic model
This paper proposes an AIPC-based controller integrating a PINN surrogate with monotonicity constraints, a TD3 agent, and a steady-state detection module, along with an operator experience integration strategy (AIPC-OE) that activates rule-based corrective actions near constraint boundaries. Three reward functions are evaluated to guide reward design. Validated on a rigorous dynamic model of an industrial pre-distillation column, the controller reduces side-stream FBP overshoot by 89% vs. PID and achieves 44% faster settling than PID in the baseline scenario. Under crude property variation, AIPC-OE further reduces side-stream overshoot by 44% compared to standalone AIPC. Under simultaneous variation of crude properties and throughput, both AIPC and AIPC-OE substantially suppress side-stream FBP overshoot relative to MPC (2.0°C and 2.3°C vs. 7.3°C). To our knowledge, this is the first validation of a PINN-augmented DRL controller on a rigorous first-principles dynamic model of an industrial distillation column, demonstrating its potential for practical deployment in complex chemical processes.
- 11 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessAn AIPC-based controller for chemical process operations: Development and validation on a rigorous dynamic model
This paper proposes an AIPC-based controller integrating a PINN surrogate with monotonicity constraints, a TD3 agent, and a steady-state detection module, along with an operator experience integration strategy (AIPC-OE) that activates rule-based corrective actions near constraint boundaries. Three reward functions are evaluated to guide reward design. Validated on a rigorous dynamic model of an industrial pre-distillation column, the controller reduces side-stream FBP overshoot by 89% vs. PID and achieves 44% faster settling than PID in the baseline scenario. Under crude property variation, AIPC-OE further reduces side-stream overshoot by 44% compared to standalone AIPC. Under simultaneous variation of crude properties and throughput, both AIPC and AIPC-OE substantially suppress side-stream FBP overshoot relative to MPC (2.0°C and 2.3°C vs. 7.3°C). To our knowledge, this is the first validation of a PINN-augmented DRL controller on a rigorous first-principles dynamic model of an industrial distillation column, demonstrating its potential for practical deployment in complex chemical processes.
- 10 June 2025
- Published by Elsevier in Chemical Engineering Science
- Vol. 317
Multirate vine copula-based dependence description for multirate process monitoring
- 10 June 2025
- Published by Elsevier in Chemical Engineering Science
- Vol. 317
Multirate vine copula-based dependence description for multirate process monitoring
- 19 September 2024
- Published by Elsevier in Computers & Chemical Engineering
- Vol. 192
Process monitoring method based on vine copula and transfer learning strategy
- 19 September 2024
- Published by Elsevier in Computers & Chemical Engineering
- Vol. 192
Process monitoring method based on vine copula and transfer learning strategy
- 3 July 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (10) , 106201
A data-driven LSTMSCBLS model for soft sensor of industrial process
In the chemical industry, data-driven soft sensor modeling plays a crucial role in efficiently monitoring product quality and status. Industrial data in these applications typically exhibit significant temporal characteristics, meaning that current information is influenced by data from previous periods. Effectively extracting and utilizing these temporal features is essential for achieving accurate soft sensor modeling in complex chemical scenarios. To address this challenge, this study proposes a data-driven Broad Learning System (BLS) model, which combines Long Short-Term Memory (LSTM) networks with an adaptive algorithm known as the Stochastic Configuration Algorithm (SC), referred to as LSTMSCBLS. The model operates in two stages: temporal feature extraction and final prediction. In the temporal feature extraction stage, the integration of the LSTM network with a feature attention mechanism allows for efficient extraction of temporal features from high-dimensional time-series data. In the final prediction stage, the SC is integrated into the BLS, effectively mitigating issues related to node space redundancy and the determination of the number of nodes. The effectiveness and superiority of the proposed model are demonstrated through two industrial case studies involving a debutanizer column and a sulfur recovery unit.
- 3 July 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (10) , 106201
A data-driven LSTMSCBLS model for soft sensor of industrial process
In the chemical industry, data-driven soft sensor modeling plays a crucial role in efficiently monitoring product quality and status. Industrial data in these applications typically exhibit significant temporal characteristics, meaning that current information is influenced by data from previous periods. Effectively extracting and utilizing these temporal features is essential for achieving accurate soft sensor modeling in complex chemical scenarios. To address this challenge, this study proposes a data-driven Broad Learning System (BLS) model, which combines Long Short-Term Memory (LSTM) networks with an adaptive algorithm known as the Stochastic Configuration Algorithm (SC), referred to as LSTMSCBLS. The model operates in two stages: temporal feature extraction and final prediction. In the temporal feature extraction stage, the integration of the LSTM network with a feature attention mechanism allows for efficient extraction of temporal features from high-dimensional time-series data. In the final prediction stage, the SC is integrated into the BLS, effectively mitigating issues related to node space redundancy and the determination of the number of nodes. The effectiveness and superiority of the proposed model are demonstrated through two industrial case studies involving a debutanizer column and a sulfur recovery unit.