International Journal of Complexity in Applied Science and Technology (8 papers in press)

Regular Issues

• Particle Swarm Optimisation with Modified Global Search and Local Search Exemplars for Large-scale Optimisation  
  by Minchong Chen, Hong Li, Qi Yu, Xuejing Hou 
  Abstract: Canonical particle swarm optimisation (cPSO) has been criticized for its premature convergence when tackling large-scale optimisation problems (LSOPs). During optimization, the swarm diversity of cPSO rapidly decays, leading to its poor global search performance. To improve the global search ability of cPSO, a particle swarm optimisation with modified global search and local search exemplars (PSO-MGLE) is proposed. In PSO-MGLE, two novel exemplar selection strategies are designed to diversify the selection of global search and local search exemplars for updated particles, thereby preserving high swarm diversity. Second, a dynamic adjustment strategy for the acceleration coefficient is designed to encourage the swarm to prioritise the global search at the early stage while emphasising the local search at the later stage. PSO-MGLE is tested on the 2022 benchmark suite, scaled to 500, 1000, and 2000 dimensions. Experimental results demonstrate the competitive performance and good scalability of PSO-MGLE in comparison with seven state-of-the-art approaches.
  Keywords: Particle Swarm Optimization; Large-scale Optimization; Global Search; Local Search; Swarm Diversity.
  DOI: 10.1504/IJCAST.2024.10068556
   
  
• A Constrained Multi-objective Evolutionary Algorithm Based on Dynamic Clustering Strategy  
  by Jiwei Tu, Hong Li, Yuanlong Hu, Shaojin Geng, Dongyang Li, Lei Wang 
  Abstract: The dual-population co-evolution strategy is a class of methods that can efficiently solve constrained multi-objective optimisation problems. However, the auxiliary population does not contribute effective individuals to the main population at all stages of population evolution. Considering the utilisation of auxiliary popualtion at later evolutionary stage, a constrained multi-objective evolutionary algorithm based on the dynamic clustering coevolutionary strategy is proposed. This paper proposes a dynamic clustering strategy that dynamically divides the population into active and inactive populations based on the auxiliary population status, where only the active population participates in generating the offspring, so as to reasonably allocate the computational resources and enhance the convergence of the population. In addition, the feasible solutions found by the auxiliary population are retained using an additional archived population to improve the diversity of the main population. Experimental results demonstrate the effectiveness of the algorithm.
  Keywords: constrained optimisation; evolutionary algorithm; dynamic clustering; multiple population.
  DOI: 10.1504/IJCAST.2024.10068604
   
  
• Integrating CNNs and ANNs: a Comprehensive AI Framework for Enhanced Breast Cancer Detection and Diagnosis  
  by Emir Oncu 
  Abstract: Among women globally, breast cancer is a major cause of cancer-related death. Accurate and timely diagnosis is essential, and results can be significantly improved. A new era in image analysis has been brought about by the emergence of Artificial Intelligence (AI), which has made significant progress in the diagnosis and customisation of treatment plans for breast cancer possible. This study aimed to develop a comprehensive AI framework for breast cancer detection by integrating Convolutional Neural Networks (CNNs) for image analysis with an Artificial Neural Networks (ANNs) for clinical data. Using a dataset of ultrasound and pathology images, along with clinical features from 569 patients, we trained CNN models to classify breast tissue as benign or malignant, and the ANN to process clinical data for the same task. The results demonstrate that the fusion of CNNs and ANNs enhances diagnostic accuracy and offers a promising tool for early breast cancer detection.
  Keywords: breast cancer; convolutional neural network; imaging; machine learning; prediction.
  DOI: 10.1504/IJCAST.2024.10068741
   
  
• Combining CNNs and Symptom Data for Monkeypox Virus Detection  
  by Emir Oncu 
  Abstract: Monkeypox, a zoonotic disease related to smallpox, poses diagnostic challenges due to symptom overlap with other illnesses. This study presents a novel approach to monkeypox detection using Convolutional Neural Networks (CNNs) combined with symptom analysis. A dataset of high-resolution lesion images and nine key symptoms was utilized to train the CNN model. The system classifies cases based on a probabilistic score from image analysis, with symptom-based evaluation as a secondary measure for inconclusive cases. Built with convolutional, pooling, and fully connected layers, the model effectively differentiates monkeypox from other conditions, demonstrating high predictive accuracy. Results underscore its potential to assess monkeypox risk with limited imaging data, supported by practical summaries of symptom-based predictions. This integration of CNNs and clinical data offers a reliable diagnostic tool, with future research focused on expanding datasets and refining methodologies to enhance applicability in outbreak scenarios.
  Keywords: monkeypox; convolutional neural network; virus; machine learning; prediction.
  DOI: 10.1504/IJCAST.2024.10068742
   
  
• Analysis of Centrifugal Clutches in Two-Speed Automatic Transmissions with Multilayer Perceptron Neural Network-Based Engagement Prediction  
  by Bo-Yi Lin, Kai Chun Lin 
  Abstract: Numerical analysis of centrifugal clutch systems integrated with a two-speed automatic transmission is shown in this paper. Various clutch configurations and their effects on the dynamics of the considered transmission have been examined. Based on these configurations, torque transfer, upshifting, and downshifting behaviors under various conditions are discussed. This paper presents a Multilayer Perceptron Neural Network (MLPNN) model for clutch engagements, whose parameters are spring preload and shoe mass. In this paper, a computationally efficient alternative to the complex simulations for the modeling is presented. MLPNN and numerical modeling further help in the critical insights required for improvement in the design parameters, performance, and efficiency of the clutch-transmission system.
  Keywords: Centrifugal Clutch; Automatic Transmission; Numerical Modeling; Multilayer Perceptron Neural Network; Vehicle Dynamics.
  DOI: 10.1504/IJCAST.2024.10068818
   
  
• Machine Learning Models based on Financial Data for Stock Trend Predictions  
  by John Phan, Hung-Fu Chang 
  Abstract: This paper investigates the application of long short-term memory (LSTM), one-dimensional convolutional neural networks (1D CNN), and logistic regression (LR), for predicting stock trends based on fundamental analysis. This research emphasises a companys financial statements and its intrinsic value for stock price trend forecasting. Using a dataset of 269 data points from publicly traded companies across various sectors from 2019 to 2023, we employ key financial ratios and the Discounted Cash Flow (DCF) model for two tasks: Annual Stock Price Difference (ASPD) and Difference between Current Stock Price and Intrinsic Value (DCSPIV). Assessing the likelihood of profitability from relationship between financial data and price action, and the current discrepancy between true value and market price, respectively. Our results demonstrate that LR models outperform CNN and LSTM models, achieving an average test accuracy of 74.66% for ASPD and 72.85% for DCSPIV, highlighting the benefits for portfolio managers in their decision-making processes.
  Keywords: Stock Trend Prediction; Fundamental Analysis; Machine Learning; CNN; LSTM; Logistic Regression.
  DOI: 10.1504/IJCAST.2025.10069470
   
  
• Super Resolution in Microscopic Images of SARS-CoV-2 through Deep Learning  
  by Roberto Rodriguez Morales, Laura Brito, Anthony Leon, Esley Torres 
  Abstract: In this work, we carried out a study on the importance of super-resolution in SARS-CoV-2 microscopic images. We analysed the impossibility of realizing super-resolution in SARS-CoV-2 microscopic images, through deep learning, without a database of real images that allows training of convolutional neural networks. In this sense, we proposed an intelligent strategy that made it possible to select, by means of deep learning, the most appropriate algorithm from several previously developed ones. In other words, the strategy consisted in analysing, via deep learning, the characteristics of the microscopic images, classifying them and recommending the most appropriate algorithm to carry out the super-resolution task. In order to evaluate the effectiveness of the obtained results, we realised a quantitative comparison of the selected algorithm through our strategy with the one proposed by experts in computer vision. The efficiency of our smart strategy was over 97%.
  Keywords: Super-resolution; SARS-CoV-2 coronavirus; smart system; deep learning; hybrid algorithm.
  DOI: 10.1504/IJCAST.2025.10069743
   
  
• Evaluating the Effectiveness of Large Language Models in Medicine Education: a Comparison of Current Medicine Knowledge  
  by Md. Mahadi Hassan, Noushin Nohor 
  Abstract: Recent advancements in Artificial Intelligence have led to the development of powerful Large Language Models (LLMs) like ChatGPT-4-turbo, Gemini 2.0 Flash, DeepSeek-R1, and Qwen2.5-Max. This study evaluates their medical knowledge proficiency using multiple-choice questions (MCQs) sourced from a reputable medical textbook, with answers verified by experts. Each model was tested on its ability to select correct answers, and performance was analysed using ANOVA and Tukey's HSD tests. Results showed that while all models exhibited some proficiency, ChatGPT-4-turbo significantly outperformed Gemini 2.0 Flash and Qwen2.5-Max, with no notable difference between ChatGPT-4-turbo and DeepSeek-R1. Despite their capabilities, these models remain unreliable for medical education and assistance. Enhancing their accuracy and reliability is crucial for their effective application in healthcare, enabling medical students and professionals to utilise AI for learning and clinical decision-making. Further development is needed to improve their utility in medical practice.
  Keywords: Large Language Models; Artificial Intelligence; ChatGPT; Gemini; DeepSeek; Qwen.
  DOI: 10.1504/IJCAST.2025.10070222