International Journal of Simulation and Process Modelling (9 papers in press)

Regular Issues

• Improving maritime distress target detection through modelling and simulation with YOLOv5s and Next-ViT  
  by Xinbo Chang, Kun Liu, Zhen Liu 
  Abstract: To additionally raise the accuracy of maritime distress target detection, an improved YOLOv5s model with Next-ViT is proposed through modeling and simulation. In this model, Next-ViT is applied to extract representations, followed by adopting a neck network with spatial context pyramid and Focal-GIoU loss to identify the targets. To validate its effectiveness, extensive experiments are conducted on the sub-dataset of the SeaDronesSee dataset. Contrasted to the primary YOLOv5s model, the proposed model has promoted Recall, mAP0.5 and mAP0.5?0.95 by 9.2, 6.3 and 3.3 percentage points, respectively, demonstrating superior performance over existing models.
  Keywords: YOLOv5s model; target detection; Next-ViT; spatial context pyramid.
  DOI: 10.1504/IJSPM.2025.10070958
   
  
• Design of ventilation preheating system for pig nursery based on ANFIS  
  by Zhidong Wu, Kaixiang Xu, Yanwei Chen, Meiqi Liu, Yonglan Liu 
  Abstract: Aiming at the problem that the low temperature of the air supply in the pig nursery in cold areas during winter, the ventilation preheating system and control strategy are designed. The proposed system combines in house heating, a heat exchanger with a ventilation heater. The adaptive neuro fuzzy inference system (ANFIS) is established by learning sample data, and the ventilated heater controller is designed. The results of simulations and field tests show that the proposed system based on the ANFIS algorithm can efficiently raise the temperature of the air supply to 20
  Keywords: ventilation preheating; computational fluid dynamics; adaptive neuro fuzzy inference system; cold region.
  DOI: 10.1504/IJSPM.2025.10071181
   
  
• Defect detection method of Chinese mitten crab based on improved EfficientVit  
  by Guangyu Mu, Heng Zhang, Zhongxiang Fei, Guodong Gao, Haiguang Zhang 
  Abstract: An improved EfficientVit-based defect detection method for Chinese mitten crabs (Eriocheir sinensis) is proposed to enhance detection efficiency and accuracy while reducing human interference. A dataset of intact and defective crab images was constructed to improve the model’s adaptability. The Squeeze-and-Excitation (SE) module and Mix of Experts Hidden (MoH) module were integrated into the EfficientVit model to strengthen its feature extraction ability and sensitivity to subtle differences. The ReLU activation function was replaced with the Parametric Rectified Linear Unit (PReLU) activation function to address the “dying neuron” issue and improve the model’s sensitivity to negative inputs. The improved model achieved an accuracy of 97.34%, precision of 97.35%, recall of 97.34%, and F1 score of 97.34%, showing significant improvements over the baseline model. Future work will focus on optimizing model performance and exploring its adaptability and generalization in different environments.
  Keywords: Chinese mitten crab; EfficientVit; defect detection; attention mechanism; activation function.
  DOI: 10.1504/IJSPM.2025.10071192
   
  
• Simulation-Driven Fault Diagnosis for Track Circuits Using Multi-Scale Convolution and Transformers Under Imbalanced Data Conditions  
  by Jundong Fu, Xiaojun Yuan 
  Abstract: With the increasing complexity of railway systems, diagnosing faults in ZPW-2000A track circuits poses significant challenges, especially under imbalanced data conditions. This paper introduces a novel simulation-driven fault diagnosis framework combining multi-scale convolution, Transformer encoders, and LDAM loss to enhance classification accuracy. The method extracts short- and long-term features from time-series data, effectively addressing data imbalance through gated convolution and optimized classification boundaries. Simulation experiments on 1,600 samples demonstrated a 98.75% accuracy, significantly outperforming existing approaches. Ablation studies validated the contribution of each module. The findings show potential for real-time fault detection and improved railway safety. Future work includes validating the model on real-world data and optimizing its computational efficiency. This research contributes to simulation and process modelling by offering a robust, scalable solution for fault diagnosis, aligning with industrial needs and advancing the state-of-the-art in imbalanced data analysis.
  Keywords: Fault Diagnosis; Imbalanced Data Handling; Simulation-Based Methods ; Railway Safety Systems; Deep Learning Models; Process Modelling.
  
  
• Optimising multi-modal fusion with a tri-encoder tensor network for process applications  
  by Jiayao Li, Li Li, Xiaochen Shi, Zeqiu Chen, Kaiyi Zhao, Ruizhi Sun 
  Abstract: Multi-modal fusion combines information from diverse modalities, enabling scalable predictions in complex data environments. To address the existing limitations in capturing modalities interactions and reducing time consumption, we propose an optimising multi-modal fusion with a tri-encoder tensor network for process applications (TS-OMMF). Specifically, the input modalities are encoded to abstract the intra-modal feature and obtain the representation, respectively. The representations are fused into a high dimension space with a low-rank factor to limit the dimension and linear extension pattern is employed to assist model extend for multi-modal. The fusion features are input into a novel tri-encoder to capture the inter-modal feature at a finer granularity and obtain the complementary features, thereby reducing the time consuming. Extensive experiments on benchmark multi-modal datasets demonstrate that TS-OMMF improves performance metrics by 0.8% to 6.1%. These results highlight TS-OMMF practical applicability, scalability, and potential for advancing process modelling and other complex multi-modal data-driven tasks.
  Keywords: multi-modal tensor fusion; encoder-decoder; tensor representation; multi-modal fusion; auto-encoder.
  DOI: 10.1504/IJSPM.2025.10071854
   
  
• Efficient master production scheduling for manufacturing systems using an enhanced SARSA algorithm  
  by Yuehan Liu, Haibo Shi, Chang Liu 
  Abstract: Efficient master production scheduling is crucial in production planning, yet automated solutions remain scarce. This current scholar primarily address introduces a novel scheduling method, master production scheduling with improved state-action-reward-state-action (MPS-ISARSA) algorithm, based on an enhanced state-action-reward-state-action (SARSA) framework. Using a Markov decision process model, the method optimises scheduling through innovative reward shaping and a linearly decaying epsilon-greedy (lin-greedy) policy to accelerate training. An overtime penalty ensures alignment between production capacity and demand. Extensive simulations validate the models effectiveness, demonstrating superior convergence and efficiency compared to traditional methods and other reinforcement learning algorithms. This approach offers a scalable, intelligent framework for capacity-constrained production scheduling, with practical applications for manufacturing industries aiming to enhance operational efficiency.
  Keywords: reinforcement learning; SARSA algorithm; production scheduling; master production scheduling; reward shaping; Markov decision process; capacity-constrained scheduling.
  DOI: 10.1504/IJSPM.2025.10072351
   
  
• The role of discrete-event simulation in emergency management during the COVID-19 pandemic  
  by Abdessalem Jerbi 
  Abstract: Since its emergence, the COVID-19 pandemic has rapidly evolved into a global health crisis. Despite efforts to contain it, deaths have continued to rise, resulting in profound impacts across all sectors of society. Discrete-event simulation (DES) is a critical tool that helps managing the crisis. This study examines the impact of DES in addressing issues related to the COVID-19 pandemic through bibliometric analysis. The findings show that DES has been widely used to simulate the effective implementation of public health measures, virus spread, and mass vaccination in addressing COVID-19 related issues. However, publications have shown variations over time. Highlighting the importance of DES in responding to the COVID-19 pandemic, this study also identifies key areas where this method can be effectively applied. These results provide valuable insights to guide future efforts in managing this global health crisis.
  Keywords: discrete event simulation; performance bibliometric evaluation; COVID-19; global health pandemic.
  DOI: 10.1504/IJSPM.2025.10072658
   
  
• Higher coordination system for a scheduling and control integrated layer management in process industry  
  by Eugênio Costa, Mauricio Figueiredo 
  Abstract: A higher coordination system is designed to manage the scheduling and control integrated layer architecture in process industries. Among its most important features are: (1) it may be used considering any combination of usual strategies adopted for scheduling and process control; (2) it is flexible and scalable; (3) it makes the scheduling and process control tasks synergistically integrated; and (4) it is able to deal with plant disturbances and also with changes in input scenarios. A non-linear chemical process is considered for analysis and comparison purposes according to several experiments. The system is able to identify, if any, a new schedule that minimizes the loss the perturbation may cause and able to replace the schedule generated initially. Simulation results show that the system manages the layer integration leading to a better performance than the case in which the layers operate in a segregated way.
  Keywords: process industry; process control; scheduling and control layer integration; enterprise integration.
  DOI: 10.1504/IJSPM.2025.10072780
   
  
• Optimising healthcare process efficiency with HyperBERT: embedding ICD code hierarchy for national healthcare systems simulation and improvement  
  by Dereje Weyessa, Berhanu Beyene, Teklu Urgessa, Gopi Krishna Tiruveedula, S. Mishra, Bijay Kumar Paikaray 
  Abstract: The focus of this research study is to design mechanisms on how to embed the code hierarchal tree structure of the ICD code on the task automatic ICD code assignment clinical text, namely: (1) how to introduce diagnosis code hierarchy as auxiliary information knowledge in the training process BERT approach (2) Transformer-based models like BERT applied as practice-oriented, interpretable AI considering Ethiopia's national classification of disease (NCOD) and Medical Information Mart in Intensive care unit (MIMIC) dataset. The research design is qualitative, using experimental and case study research strategies. The experiment results show that the new model architecture called HyperBERT increased macro average AUC 0.003 and 0.02 of F1 score and demonstrated the interpretability of the model using code-wise label attention mechanism using the BERT visualization tool. We used Riemannian optimization and Poincare loss to validate a new document representation model for Ethiopia's healthcare systems.
  Keywords: ICD coding; interpretable AI; code hierarchical; deep neural network; bidirectional encoder representation for transformer; BERT; hyperbolic embedding; healthcare systems.
  DOI: 10.1504/IJSPM.2025.10072798