Sarah M. Alhammad¹, Diaa Salama AbdElminaam^2,3,*, Asmaa Rizk Ibrahim⁴, Ahmed Taha²

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.069263 - 12 January 2026

Abstract Accurate parameter extraction of photovoltaic (PV) models plays a critical role in enabling precise performance prediction, optimal system sizing, and effective operational control under diverse environmental conditions. While a wide range of metaheuristic optimisation techniques have been applied to this problem, many existing methods are hindered by slow convergence rates, susceptibility to premature stagnation, and reduced accuracy when applied to complex multi-diode PV configurations. These limitations can lead to suboptimal modelling, reducing the efficiency of PV system design and operation. In this work, we propose an enhanced hybrid optimisation approach, the modified Spider Wasp Optimization… More >

Yaxin Zhao¹, Qi Han², Hui Shu², Yan Guang^2,*

CMC-Computers, Materials & Continua, Vol.86, No.2, pp. 1-24, 2026, DOI:10.32604/cmc.2025.070511 - 09 December 2025

Abstract Large Language Models (LLMs) are increasingly applied in the field of code translation. However, existing evaluation methodologies suffer from two major limitations: (1) the high overlap between test data and pretraining corpora, which introduces significant bias in performance evaluation; and (2) mainstream metrics focus primarily on surface-level accuracy, failing to uncover the underlying factors that constrain model capabilities. To address these issues, this paper presents TCode (Translation-Oriented Code Evaluation benchmark)—a complexity-controllable, contamination-free benchmark dataset for code translation—alongside a dedicated static feature sensitivity evaluation framework. The dataset is carefully designed to control complexity along multiple dimensions—including syntactic… More >

Bin Zhang^*, Zhancheng Xu

CMC-Computers, Materials & Continua, Vol.86, No.2, pp. 1-12, 2026, DOI:10.32604/cmc.2025.069979 - 09 December 2025

Abstract This study aimed to enhance the performance of semantic segmentation for autonomous driving by improving the 2DPASS model. Two novel improvements were proposed and implemented in this paper: dynamically adjusting the loss function ratio and integrating an attention mechanism (CBAM). First, the loss function weights were adjusted dynamically. The grid search method is used for deciding the best ratio of 7:3. It gives greater emphasis to the cross-entropy loss, which resulted in better segmentation performance. Second, CBAM was applied at different layers of the 2D encoder. Heatmap analysis revealed that introducing it after the second… More >

Roman Shults^1,2,*, Natalia Kulichenko³, Andriy Annenkov³, Oleksandr Adamenko³

Structural Durability & Health Monitoring, Vol.19, No.6, pp. 1433-1456, 2025, DOI:10.32604/sdhm.2025.068099 - 17 November 2025

Abstract Oil tanks are essential components of the oil industry, facilitating the safe storage and transportation of crude oil. Safely managing oil tanks is a crucial aspect of environmental protection. Oil tanks are often used under extreme operational conditions, including dynamic loads, temperature variations, etc., which may result in unpredictable deformations that can cause severe damage or tank collapses. Therefore, it is essential to establish a monitoring system to prevent and predict potential deformations. Terrestrial laser scanning (TLS) has played a significant role in oil tank monitoring over the past decades. However, the full extent of… More >

Omar Sabri¹, Bassam Al-Shargabi^2,*, Abdelrahman Abuarqoub²

CMC-Computers, Materials & Continua, Vol.85, No.2, pp. 2443-2486, 2025, DOI:10.32604/cmc.2025.066987 - 23 September 2025

Abstract This review comprehensively analyzes advancements in artificial intelligence, particularly machine learning and deep learning, in medical imaging, focusing on their transformative role in enhancing diagnostic accuracy. Our in-depth analysis of 138 selected studies reveals that artificial intelligence (AI) algorithms frequently achieve diagnostic performance comparable to, and often surpassing, that of human experts, excelling in complex pattern recognition. Key findings include earlier detection of conditions like skin cancer and diabetic retinopathy, alongside radiologist-level performance for pneumonia detection on chest X-rays. These technologies profoundly transform imaging by significantly improving processes in classification, segmentation, and sequential analysis across… More >

Muhamad Ammar Hanif Arif¹, Amir Sharifuddin Ab Latip^1,*, Siti Balqis Mohd Tun¹, Nur Azlina Hariffin¹, Adel Gohari², Mohd Hakimi Abdul Rahman¹

Revue Internationale de Géomatique, Vol.34, pp. 691-705, 2025, DOI:10.32604/rig.2025.065949 - 29 August 2025

Abstract Digital Elevation Model (DEM) refers to a digital map of the surface of the Earth that only shows the bare ground, without any buildings, plants, or other characteristics. However, obtaining unlimited access to DEM data at high and medium resolutions is very hard. Consequently, users often question the accuracy of freely available DEMs and their suitability for various applications. By comparing them to Global Positioning System (GPS) elevation data, this study aimed to identify the most reliable and widely available DEM for various terrains. The objectives of this study were to generate DEMs from different… More >

Umer Farooq¹, Nabil Kerdid^2,*, Yasir Nawaz³, Muhammad Shoaib Arif ⁴

CMES-Computer Modeling in Engineering & Sciences, Vol.144, No.1, pp. 873-898, 2025, DOI:10.32604/cmes.2025.066800 - 31 July 2025

Abstract In this study, we proposed a numerical technique for solving time-dependent partial differential equations that arise in the electro-osmotic flow of Carreau fluid across a stationary plate based on a modified exponential integrator. The scheme is comprised of two explicit stages. One is the exponential integrator type stage, and the second is the Runge-Kutta type stage. The spatial-dependent terms are discretized using the compact technique. The compact scheme can achieve fourth or sixth-order spatial accuracy, while the proposed scheme attains second-order temporal accuracy. Also, a mathematical model for the electro-osmotic flow of Carreau fluid over… More >

S. M. Rezaul Karim^1,2, Md. Shouquat Hossain^1,3, Khadiza Akter¹, Debasish Sarker⁴, Md. Moniul Kabir ², Mamdouh Assad^5,*

Energy Engineering, Vol.122, No.8, pp. 3041-3054, 2025, DOI:10.32604/ee.2025.066867 - 24 July 2025

Abstract Knowing the influence of the size of datasets for regression models can help in improving the accuracy of a solar power forecast and make the most out of renewable energy systems. This research explores the influence of dataset size on the accuracy and reliability of regression models for solar power prediction, contributing to better forecasting methods. The study analyzes data from two solar panels, aSiMicro03036 and aSiTandem72-46, over 7, 14, 17, 21, 28, and 38 days, with each dataset comprising five independent and one dependent parameter, and split 80–20 for training and testing. Results indicate… More > Graphic Abstract

Prasanna Kottapalle^1,*, Tan Kuan Tak², Pravin Ramdas Kshirsagar³, Gopichand Ginnela⁴, Vijaya Krishna Akula⁵

CMC-Computers, Materials & Continua, Vol.84, No.2, pp. 3857-3892, 2025, DOI:10.32604/cmc.2025.065287 - 03 July 2025

Abstract Heart failure prediction is crucial as cardiovascular diseases become the leading cause of death worldwide, exacerbated by the COVID-19 pandemic. Age, cholesterol, and blood pressure datasets are becoming inadequate because they cannot capture the complexity of emerging health indicators. These high-dimensional and heterogeneous datasets make traditional machine learning methods difficult, and Skewness and other new biomarkers and psychosocial factors bias the model’s heart health prediction across diverse patient profiles. Modern medical datasets’ complexity and high dimensionality challenge traditional prediction models like Support Vector Machines and Decision Trees. Quantum approaches include QSVM, QkNN, QDT, and others.… More >

Tianwen Zhao¹, Guoqing Chen^2,3, Cong Pang⁴, Piyapatr Busababodhin^3,5,*

CMES-Computer Modeling in Engineering & Sciences, Vol.143, No.3, pp. 2883-2917, 2025, DOI:10.32604/cmes.2025.066442 - 30 June 2025

Abstract Existing power forecasting models struggle to simultaneously handle high-dimensional, noisy load data while capturing long-term dependencies. This critical limitation necessitates an integrated approach combining dimensionality reduction, temporal modeling, and robust prediction, especially for multi-day forecasting. A novel hybrid model, SLHS-TCN-XGBoost, is proposed for power demand forecasting, leveraging SLHS (dimensionality reduction), TCN (temporal feature learning), and XGBoost (ensemble prediction). Applied to the three-year electricity load dataset of Seoul, South Korea, the model’s MAE, RMSE, and MAPE reached 112.08, 148.39, and 2%, respectively, which are significantly reduced in MAE, RMSE, and MAPE by 87.37%, 87.35%, and 87.43%… More >