International Journal of Simulation and Process Modelling (7 papers in press)

Regular Issues

• Open Access

  Simulation modelling of fashion colour harmonisation with visual transformers ( Free Full-text Access )

  by Bei Li 
  Abstract: In the field of fashion design, the harmony of color coordination plays a crucial role in the aesthetic appeal of a piece. Addressing the current research limitation of neglecting local image details, which results in suboptimal color coordination quality, this paper first employs spatial normalization and feature matching to vectorize fashion images. This enhances the model's ability to understand and represent colors within fashion images. Subsequently, a color coordination model based on a visual Transformer is designed. This model primarily consists of multiple stacked Transformer blocks, with a convolutional neural network embedded within the Transformer blocks to handle color coordination in apparel images. Simulation experiments conducted on public datasets demonstrate that the proposed model achieves image quality distance and color richness scores of 5.09 and 40.14, respectively, outperforming comparison models. Significant improvements are observed in color harmony and image generation quality.
  Keywords: fashion design; image color matching; vector encoding; visual transformer; convolutional neural network.
  DOI: 10.1504/IJSPM.2026.10077921
   
  

• Open Access

  Generative adversarial networks for simulating emotional resonance in industrial product design ( Free Full-text Access )

  by Jie Hu 
  Abstract: This paper addresses the lack of emotion-oriented simulation in industrial product design by proposing a novel generative adversarial network framework integrated with a quantifiable emotional model. The core of this approach is an emotion-attention mechanism that dynamically guides the form evolution process. Emotional features are first extracted from e-commerce reviews and modeled via an improved support vector regression algorithm to establish a quantifiable mapping between design elements and user emotions. This emotional model is then integrated into a GAN through a multi-head component attention module, which simulates product form evolution by explicitly weighting the contribution of each component to the target emotional resonance. Experimental results demonstrate the effectiveness of this simulation, with the Fr
  Keywords: product form simulation; process modelling; emotional resonance; generative adversarial networks; support vector regression.
  DOI: 10.1504/IJSPM.2026.10077922
   
  
• Simulation-driven deep learning framework for early poultry disease detection using faecal image classification with optimised CNN architectures  
  by Nonita Sharma, Monika Mangla, Manik Rakhra, Baljinder Kaur, Raj Kumar Mohanta, Bijay Kumar Paikaray 
  Abstract: The present investigation aims to devise an optimized Convolutional Neural Network (CNN) framework to identify prominent poultry diseases based on faecal images. The proposed research model uses a tri-convolutional layer architecture to enhance the accuracy of poultry disease classification and improve feature extraction. Three major diseases, namely coccidiosis, salmonella, and Newcastle, have been considered. The prime objective of current research is to achieve early detection by employing advanced deep-learning techniques. The proposed model uses fecal images to identify pathological conditions using the TriConvLayer architecture accurately. In this work, custom CNN models, viz. SoloConvLayer, TriConvLayer, and FiveConvLayer models are used to achieve an accuracy of 97%, 98%, and 98%, respectively. The achieved result advocates the efficacy of the proposed approach. It thus has the potential to revolutionize early disease detection in poultry farming, a major step towards improving animal health and farm productivity.
  Keywords: deep learning; poultry disease detection; convolutional neural networks; CNN; faecal image analysis; poultry health monitoring; disease classification; simulation framework.
  DOI: 10.1504/IJSPM.2025.10073525
   
  
• Process-oriented simulation and optimisation of 2D trabecular bone via fractal modelling  
  by Liu Yuhong, J.I.A. Liyan, Wang Zheng, Jincai Chang 
  Abstract: A process-oriented method for simulating and reconstructing 2D trabecular bone microstructures is proposed, based on Fractional Brownian Motion (FBM) and multi-parameter morphological con-straints. By adjusting the Hurst exponent, the Fractal Dimensions(FD) of trabecular structures can be controlled, enabling the reconstruction of biomimetic porous geometries with tunable porosity and thickness. A complete modelling framework is developed, including image preprocessing, pa-rameter extraction, simulation generation, and post-optimisation, and is validated using real femoral cross-sectional images. Comparative results show that this method outperforms existing Graph Convolutional Networks GCN-based approaches in preserving topological fidelity and geometric fidelity. This study provides a novel, simulation-driven pathway for customizable bone scaffold design and process modelling in bioengineering.
  Keywords: fractal modelling; trabecular bone structure; 2D geometric reconstruction; parameter-driven simulation; morphological optimisation.
  DOI: 10.1504/IJSPM.2025.10076820
   
  
• Optimising U-turn efficiency at median openings: a simulation study of traffic-responsive signal control  
  by Weidong Liu, Shanshan LI, Runtong Qiao 
  Abstract: This study proposes a methodologically novel approach to optimise the simulation and control of U-turn movements at central median openings. By integrating traffic dynamics in opposing lanes, we develop a parameterised signal control logic that determines optimal headway detector placement and calculates minimum green duration for U-turn phases, enabling adaptive phase adjustments. The model enhances simulation fidelity by directly linking field-observed traffic parameters to signal control logic in VISSIM. A calibrated micro simulation framework is established using real-world data, allowing for dynamic calibration and validation of control strategies. Comparative simulations demonstrate that the proposed method significantly improves traffic efficiency reducing vehicle delays and increasing travel speed particularly during peak periods. This work advances the simulation-driven optimisation of urban median openings, offering a replicable framework for adaptive signal control in complex traffic environments.
  Keywords: adaptive signal control; median openings; U-turn; microscopic simulation; traffic management.
  DOI: 10.1504/IJSPM.2026.10077669
   
  
• Modelling herd behaviour in traffic jams using Markov chains-based reinforcement learning learning  
  by Yamina Heddar, Youcef Oussama Fourar, Mébarek Djebabra 
  Abstract: Traffic congestion remains a persistent problem that compromises road safety. This phenomenon is often amplified by driver behaviors, particularly those characterized by the herd effect. This study aims to model the emergence and dynamics of the herd effect in traffic jams and to simulate a strategy for mitigating this behavior among drivers. To achieve these objectives, reinforcement learning (RL) was employed within the frameworks of memoryless Markov chains and multi-phase Markov chains. The results demonstrate the effectiveness of Markov chains in accurately modeling the collective behavior of specific drivers. Likewise, the simulations illustrate RL’s capacity to regulate the herd effect and optimize individual decision-making during congestion. The findings suggest that traffic authorities may consider implementing RL-based strategies to mitigate herd behavior, improve traffic flow, and enhance road safety.
  Keywords: herding behavior; traffic jams; Markov chains; reinforcement learning; agent.
  DOI: 10.1504/IJSPM.2026.10077670
   
  
• Enhanced redundancy allocation in biomedical manufacturing using opposition-based grey wolf optimiser  
  by Alina Banerjee, Deepika Garg, Mir Mohsin John 
  Abstract: In the current environment of epidemics like COVID-19, biomedical gadgets are crucial. The production of biomedical devices greatly contributes to the communitys ability to combat these diseases. The study aims to optimise redundancy in biomedical device production facilities due to globalisation and sophisticated machinery. Reliability optimisation is crucial for complex systems, and the redundancy allocation problem is a significant optimisation problem in reliability engineering. Scholars are increasingly interested in RAP due to its significance in reliability and system engineering. This study compares grey wolf optimiser and opposition-based learning in high-tech sectors. Grey wolf optimiser enhances exploratory behaviour while maintaining a rapid convergence rate. The modified version of grey wolf optimiser solves the redundancy allocation oroblem, comparing outcomes with modified particle swarm optimisation. The study highlights the importance of utilising metaheuristic algorithms for optimisation.
  Keywords: redundancy allocation; opposition-based learning; OBL; particle swarm optimisation; PSO; grey wolf optimisation.
  DOI: 10.1504/IJSPM.2026.10077844