Nguyen Dong Phuong¹, Nanthakumar Srivilliputtur Subbiah¹, Yabin Jin², Xiaoying Zhuang^1,3,*

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.1, pp. 263-303, 2025, DOI:10.32604/cmes.2025.067100 - 30 October 2025

Abstract Traditional inverse neural network (INN) approaches for inverse design typically require auxiliary feedforward networks, leading to increased computational complexity and architectural dependencies. This study introduces a standalone INN methodology that eliminates the need for feedforward networks while maintaining high reconstruction accuracy. The approach integrates Principal Component Analysis (PCA) and Partial Least Squares (PLS) for optimized feature space learning, enabling the standalone INN to effectively capture bidirectional mappings between geometric parameters and mechanical properties. Validation using established numerical datasets demonstrates that the standalone INN architecture achieves reconstruction accuracy equal or better than traditional tandem approaches while More >

Candan Tumer¹, Erdal Guvenoglu², Volkan Tunali^3,*

CMC-Computers, Materials & Continua, Vol.85, No.3, pp. 5135-5158, 2025, DOI:10.32604/cmc.2025.067840 - 23 October 2025

Abstract Automated cartoon character recognition is crucial for applications in content indexing, filtering, and copyright protection, yet it faces a significant challenge in animated media due to high intra-class visual variability, where characters frequently alter their appearance. To address this problem, we introduce the novel Kral Sakir dataset, a public benchmark of 16,725 images specifically curated for the task of multi-label cartoon character classification under these varied conditions. This paper conducts a comprehensive benchmark study, evaluating the performance of state-of-the-art pretrained Convolutional Neural Networks (CNNs), including DenseNet, ResNet, and VGG, against a custom baseline model trained More >

Muhammad Salman Qamar^1,2,*, Muhammad Fahad Munir², Athar Waseem²

CMES-Computer Modeling in Engineering & Sciences, Vol.144, No.3, pp. 3557-3584, 2025, DOI:10.32604/cmes.2025.067447 - 30 September 2025

Abstract Air pollution, specifically fine particulate matter (PM2.5), represents a critical environmental and public health concern due to its adverse effects on respiratory and cardiovascular systems. Accurate forecasting of PM2.5 concentrations is essential for mitigating health risks; however, the inherent nonlinearity and dynamic variability of air quality data present significant challenges. This study conducts a systematic evaluation of deep learning algorithms including Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and the hybrid CNN-LSTM as well as statistical models, AutoRegressive Integrated Moving Average (ARIMA) and Maximum Likelihood Estimation (MLE) for hourly PM2.5 forecasting. Model performance is… More >

You-Jyun Yeh¹, Edward T.-H. Chu^1,*, Chia-Rong Lee², Jiun Hsu³, Hui-Mei Wu³

CMC-Computers, Materials & Continua, Vol.85, No.2, pp. 3369-3391, 2025, DOI:10.32604/cmc.2025.065336 - 23 September 2025

Abstract Porters play a crucial role in hospitals because they ensure the efficient transportation of patients, medical equipment, and vital documents. Despite its importance, there is a lack of research addressing the prediction of completion times for porter tasks. To address this gap, we utilized real-world porter delivery data from National Taiwan University Hospital, Yunlin Branch, Taiwan. We first identified key features that can influence the duration of porter tasks. We then employed three widely-used machine learning algorithms: decision tree, random forest, and gradient boosting. To leverage the strengths of each algorithm, we finally adopted an… More >

Micheal Arockiaraj^1,*, Aravindan Maaran², C. I. Arokiya Doss²

CMC-Computers, Materials & Continua, Vol.85, No.1, pp. 637-655, 2025, DOI:10.32604/cmc.2025.065674 - 29 August 2025

Abstract Covalent organic frameworks (COFs) are crystalline materials composed of covalently bonded organic ligands with chemically permeable structures. Their crystallization is achieved by balancing thermal reversibility with the dynamic nature of the frameworks. Ionic covalent organic frameworks (ICOFs) are a subclass that incorporates ions in positive, negative, or zwitterionic forms into the frameworks. In particular, spiroborate-derived linkages enhance both the structural diversity and functionality of ICOFs. Unlike electroneutral COFs, ICOFs can be tailored by adjusting the types and arrangements of ions, influencing their formation mechanisms and physical properties. This study focuses on analyzing the graph-based structural… More >

Yongli Liu^1,2, Weihao Li^1,2,*, Haitao Wang^1,2,3, Taoren Du⁴

CMES-Computer Modeling in Engineering & Sciences, Vol.143, No.2, pp. 2261-2286, 2025, DOI:10.32604/cmes.2025.064179 - 30 May 2025

Abstract Coal dust explosions are severe safety accidents in coal mine production, posing significant threats to life and property. Predicting the maximum explosion pressure () of coal dust using deep learning models can effectively assess potential risks and provide a scientific basis for preventing coal dust explosions. In this study, a 20-L explosion sphere apparatus was used to test the maximum explosion pressure of coal dust under seven different particle sizes and ten mass concentrations (), resulting in a dataset of 70 experimental groups. Through Spearman correlation analysis and random forest feature selection methods, particle size… More >

Cong Zhang^1,2, Chutong Zhang², Lei Shen¹, Renwei Guo², Wan Chen¹, Hui Huang², Jie Ji^2,*

Energy Engineering, Vol.122, No.5, pp. 2077-2097, 2025, DOI:10.32604/ee.2025.064175 - 25 April 2025

Abstract This paper presents a solution for energy storage system capacity configuration and renewable energy integration in smart grids using a multi-disciplinary optimization method. The solution involves a hybrid prediction framework based on an improved grey regression neural network (IGRNN), which combines grey prediction, an improved BP neural network, and multiple linear regression with a dynamic weight allocation mechanism to enhance prediction accuracy. Additionally, an improved cuckoo search (ICS) algorithm is designed to empower the neural network model, incorporating a gamma distribution disturbance factor and adaptive inertia weight to balance global exploration and local exploitation, achieving… More >

Sheik Mohideen Shah¹, Meganathan Selvamani¹, Mahesh Thyluru Ramakrishna^2,*, Surbhi Bhatia Khan^3,4,5, Shakila Basheer⁶, Wajdan Al Malwi⁷, Mohammad Tabrez Quasim⁸

CMC-Computers, Materials & Continua, Vol.83, No.2, pp. 2907-2926, 2025, DOI:10.32604/cmc.2025.063809 - 16 April 2025

Abstract Efficient energy management is a cornerstone of advancing cognitive cities, where AI, IoT, and cloud computing seamlessly integrate to meet escalating global energy demands. Within this context, the ability to forecast electricity consumption with precision is vital, particularly in residential settings where usage patterns are highly variable and complex. This study presents an innovative approach to energy consumption forecasting using a bidirectional Long Short-Term Memory (LSTM) network. Leveraging a dataset containing over two million multivariate, time-series observations collected from a single household over nearly four years, our model addresses the limitations of traditional time-series forecasting… More >

Anandhavalli Muniasamy^1,*, Ashwag Alasmari²

CMES-Computer Modeling in Engineering & Sciences, Vol.143, No.1, pp. 569-592, 2025, DOI:10.32604/cmes.2025.060484 - 11 April 2025

Abstract The effective and timely diagnosis and treatment of ocular diseases are key to the rapid recovery of patients. Today, the mass disease that needs attention in this context is cataracts. Although deep learning has significantly advanced the analysis of ocular disease images, there is a need for a probabilistic model to generate the distributions of potential outcomes and thus make decisions related to uncertainty quantification. Therefore, this study implements a Bayesian Convolutional Neural Networks (BCNN) model for predicting cataracts by assigning probability values to the predictions. It prepares convolutional neural network (CNN) and BCNN models. More > Graphic Abstract

Saleh Albahli^*

CMES-Computer Modeling in Engineering & Sciences, Vol.143, No.1, pp. 1095-1128, 2025, DOI:10.32604/cmes.2025.058821 - 11 April 2025

Abstract Predicting hospital readmission and length of stay (LOS) for diabetic patients is critical for improving healthcare quality, optimizing resource utilization, and reducing costs. This study leverages machine learning algorithms to predict 30-day readmission rates and LOS using a robust dataset comprising over 100,000 patient encounters from 130 hospitals collected over a decade. A comprehensive preprocessing pipeline, including feature selection, data transformation, and class balancing, was implemented to ensure data quality and enhance model performance. Exploratory analysis revealed key patterns, such as the influence of age and the number of diagnoses on readmission rates, guiding the More >