International Journal of Complexity in Applied Science and Technology (11 papers in press)

Regular Issues

• 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
   
  
• Brain tumour identification using improved YOLOv8  
  by Rupesh Dulal, Rabin Dulal 
  Abstract: Accurately identifying the extent of brain tumours remains a major challenge in brain cancer treatment, primarily due to the difficulty in detecting tumour boundaries from MRI scans. Manual detection is time-consuming and requires expert knowledge. In this study, we propose a modified YOLOv8 model for precise brain tumour detection in MRI images. We replaced the traditional non-maximum suppression (NMS) with a real-time detection transformer (RT-DETR) to eliminate hand-designed filtering. Additionally, we integrated ghost convolution to reduce computational costs while maintaining accuracy, and introduced a vision transformer block in the backbone to enhance context-aware feature extraction. The model was trained and tested on a publicly available brain tumour dataset. Experimental results show that our modified YOLOv8 outperforms the original YOLOv8 and other popular object detectors including faster R-CNN, mask R-CNN, YOLOv3-v5, SSD, RetinaNet, EfficientDet, and DETR, achieving a mAP@0.5 of 0.91.
  Keywords: brain tumour detection; deep learning; attention; transformer; YOLOv8.
  DOI: 10.1504/IJCAST.2025.10071167
   
  
• FourierNAT: a Fourier-mixing-based non-autoregressive transformer for parallel sequence generation  
  by Andrew Kiruluta 
  Abstract: We present FourierNAT, a novel non-autoregressive transformer (NAT) architecture that leverages Fourier-based mixing in the decoder to generate output sequences in parallel. While traditional NAT approaches often face challenges in capturing global dependencies, our method uses a discrete Fourier transform with learned frequency-domain gating to mix token embeddings across the entire sequence dimension. This design enables efficient propagation of context without explicit autoregressive steps. Empirically, FourierNAT achieves competitive results on WMT14 En-De and CNN/DailyMail benchmarks, highlighting that frequency-domain operations can mitigate coherence gaps often associated with NAT generation. Our approach underscores the potential of integrating spectral-domain operations to accelerate and improve parallel text generation.
  Keywords: non-autoregressive transformer: NAT; Fourier mixing; parallel sequence generation; global spectral operations; NAT architecture.
  DOI: 10.1504/IJCAST.2025.10071491
   
  
• A comprehensive review of machine learning techniques for detecting fraud in banking and payment services  
  by Sushmita Kumari, Kamlesh Kumar, Ashutosh Gaurav 
  Abstract: In today’s digital age, fraud detection in financial services has become essential due to the rapid growth and complexity of online transactions. Machine learning techniques are widely used to detect unusual activities in real time. This paper focuses on fraud in banking and payment services and proposes a three-stage review framework: formulating research questions, defining the research methodology, and analysing existing literature. The review reveals that supervised and unsupervised learning algorithms, such as Naïve Bayes, K-nearest neighbours, deep learning, support vector machine, decision tree, artificial neural network, XGBoost, and AdaBoost, are commonly applied for fraud detection. These models are evaluated using metrics like precision, recall, and F-score. Ensemble methods that combine multiple algorithms are also shown to improve detection accuracy. Finally, the review highlights future research directions, especially the need to strengthen wallet payment systems by developing more robust and efficient fraud detection algorithms to ensure secure digital transactions.
  Keywords: fraud detection; mobile payment; machine learning; unsupervised learning; supervised learning.
  DOI: 10.1504/IJCAST.2025.10072040
   
  
• A comparative analysis of optimisation methods for classification on various datasets  
  by Simanta Das, Soumitra Das 
  Abstract: Optimisation studies how a variety of mathematical structures can be analysed through the minimisation or maximisation of a function. In deep learning (DL), optimisation encompasses everything from hyperparameter tuning to weight and bias adjustment until the convergence of a loss or cost function (J), such that the model’s performance metrics and reliability in classification and regression are increased. Over the last few years, stochastic gradient methods and their variants - or adaptive gradient methods - have become very popular, with varying levels of success or otherwise. This study provides a neat comparison of adaptive gradient methods with respect to their accuracies and cross-entropy loss (CEL) in the mentioned tasks; it tested nine optimisation algorithms across three CNN architectures on MNIST, Fashion-MNIST, and CIFAR-10 datasets over 30 epochs. The overall top-performing optimisers were SGD, RMSProp, Adam, and Nadam, whereas Adagrad and Adadelta consistently performed lower.
  Keywords: adaptive gradient methods; optimisation methods; convolutional neural networks; CNNs; MNIST; FashionMNIST; CIFAR10.
  DOI: 10.1504/IJCAST.2025.10072041
   
  
• PreStroke_ML: a machine learning approach to heat stroke prediction  
  by Md. Zahurul Haque, Mimuza Tazvia, Afreen Sultana Kuna 
  Abstract: Heatstroke is an increasingly critical public health concern, intensified by rising global temperatures and the growing frequency of extreme heat events. This study addresses the urgent need for timely and accurate heatstroke risk prediction by leveraging machine learning techniques. The primary objective is to develop a predictive model capable of identifying individuals at risk based on environmental and physiological data. An extensive dataset of 81,215 instances and 69 features underwent thorough preprocessing and analysis. Four machine learning algorithms - decision tree, random forest, logistic regression, and light gradient boosting machine (LightGBM) - were implemented and evaluated. Among these, LightGBM achieved the highest accuracy of 99.93%, demonstrating superior predictive performance and generalisation capability, as validated through confusion matrices and trainingvalidation accuracy curves. Feature selection played a crucial role in optimising model effectiveness. The findings underscore the potential of machine learning as a valuable tool in predictive healthcare. Future work will focus on integrating real-time sensor data, enabling personalised risk assessments, and deploying a mobile-based alert system to enhance heatstroke prevention. This research contributes to proactive public health strategies through an AI-driven framework for early detection and intervention.
  Keywords: heatstroke prediction; AI in healthcare; public health; early warning system; health risk prevention.
  DOI: 10.1504/IJCAST.2025.10072080
   
  
• 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 criticised for its premature convergence when tackling large-scale optimisation problems (LSOPs). During optimisation, 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, 1,000, and 2,000 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 optimisation; PSO; large-scale optimisation; global search; local search; swarm diversity.
  DOI: 10.1504/IJCAST.2024.10068556
   
  
• Combining CNNs and symptom data for monkeypox virus detection  
  by Emir Oncu 
  Abstract: The zoonotic disease monkeypox, related to smallpox, presents diagnostic challenges due to its resemblance to other illnesses with similar symptoms. In this study, we propose a robust method for monkeypox detection utilising convolutional neural networks (CNNs). Our approach integrates lesion images and symptom analysis to enhance diagnostic reliability. A dataset comprising high-definition lesion images and nine significant symptoms was employed to train the CNN model. The model classifies cases based on a probabilistic score, while symptom-based analysis is used as a secondary measure when lesion analysis is inconclusive. Built with convolutional, pooling, and fully connected layers, the model demonstrates strong predictive capabilities, effectively distinguishing monkeypox from other conditions. The study highlights the CNN model's ability to assess monkeypox risk with high confidence, even with limited high-resolution imaging data, underscoring its potential in medical diagnostics. Tables summarise the model's predictions based on symptom combinations, showcasing its practical applicability. This research emphasises the integration of CNNs with clinical symptom data as a promising tool for accurate and early monkeypox diagnosis. Future work could further refine the model by incorporating larger datasets and advanced methodologies to improve its generalisability and effectiveness in outbreak scenarios.
  Keywords: monkeypox; convolutional neural networks; CNNs; 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 behaviours 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 modelling is presented. MLPNN and numerical modelling 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 modelling; multilayer perceptron neural network; MLPNN; vehicle dynamics.
  DOI: 10.1504/IJCAST.2024.10068818
   
  
• Super resolution in microscopic images of SARS-CoV-2 through deep learning  
  by Roberto Rodríguez, Laura Brito, Anthony León, 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 realising 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; SR; SARS-CoV-2 coronavirus; smart system; deep learning; DL; 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; LLMs; artificial intelligence; ChatGPT; Gemini; DeepSeek; Qwen.
  DOI: 10.1504/IJCAST.2025.10070222