Guo-Feng Fan^1,2, Jia-Jing Qian¹, Li-Ling Peng¹, Xin-Hang Jia¹, Ling-Han Zuo¹, Jia-Can Yan¹, Jiang-Yan Chen¹, Anantkumar J. Umbarkar³, Wei-Chiang Hong^4,*

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.3, pp. 3813-3837, 2025, DOI:10.32604/cmes.2025.073615 - 23 December 2025

Abstract Accurate prediction of perovskite photovoltaic materials’ optoelectronic properties is crucial for developing efficient and stable materials, advancing solar technology. To address poor interpretability, high computational complexity, and inaccurate predictions in relevant machine learning models, this paper proposes a novel methodology. The technical route of this paper mainly centers on the random forest-knowledge distillation-bidirectional gated recurrent unit with attention technology (namely RF-KD-BIGRUA), which is applied in perovskite photovoltaic materials. Primarily, it combines random forest to quantitatively assess feature importance, selecting variables with significant impacts on photoelectric conversion efficiency. Subsequently, statistical techniques analyze the weight distribution of More >

Yidong Xu¹, Weijie Zhuge^1,2, Jialei Wang¹, Xiaopeng Yu^3,*, Kan Wu⁴

Structural Durability & Health Monitoring, Vol.19, No.6, pp. 1507-1527, 2025, DOI:10.32604/sdhm.2025.069021 - 17 November 2025

Abstract The performance of concrete can be affected by many factors, including the material composition, environmental conditions, and construction methods, and it is challenging to predict the performance evolution accurately. The rise of artificial intelligence provides a way to meet the above challenges. This article elaborates on research overview of artificial neural network (ANN) and its prediction for concrete strength, deformation, and durability. The focus is on the comparative analysis of the prediction accuracy for different types of neural networks. Numerous studies have shown that the prediction accuracy of ANN can meet the standards of the More >

Junling Zhong¹, Furong Geng², Zhixiao Chen¹, Wenbin Hou^1,*

CMES-Computer Modeling in Engineering & Sciences, Vol.144, No.1, pp. 1-27, 2025, DOI:10.32604/cmes.2025.065664 - 31 July 2025

Abstract This study presents an interpretable surrogate framework for predicting pedestrian-leg injury severity that integrates high-fidelity finite-element (FE) simulations with a TabNet-based deep-learning model. We generated a parametric dataset of 3000 impact scenarios—covering ten vehicle types and various legform impactors—using automated FE runs configured via Latin hypercube sampling. After preprocessing and one-hot encoding of categorical features, we trained TabNet alongside Support-Vector Regression, Random Forest, and Decision-Tree ensembles. All models underwent hyperparameter tuning via Optuna’s Bayesian optimization coupled with repeated four-fold cross-validation (20 trials per model). TabNet achieved the best balance of explanatory power and predictive accuracy, More > Graphic Abstract

Xiao Sun¹, Huifan Huang¹, Yanjuan Zhao^2,*, Lianghuai Tong^3,*, Haibin Lin³, Yuliang Zhang⁴

FDMP-Fluid Dynamics & Materials Processing, Vol.21, No.6, pp. 1261-1298, 2025, DOI:10.32604/fdmp.2025.064329 - 30 June 2025

Abstract The reverse operation of existing centrifugal pumps, commonly referred to as “Pump as Turbine” (PAT), is a key approach for recovering liquid pressure energy. As a type of hydraulic machinery characterized by a simple structure and user-friendly operation, PAT holds significant promise for application in industrial waste energy recovery systems. This paper reviews recent advancements in this field, with a focus on pump type selection, performance prediction, and optimization design. First, the advantages of various prototype pumps, including centrifugal, axial-flow, mixed-flow, screw, and plunger pumps, are examined in specific application scenarios while analyzing their suitability… More >

Wonbyung Lee, Jang Hyun Kim^*

CMC-Computers, Materials & Continua, Vol.83, No.3, pp. 5393-5412, 2025, DOI:10.32604/cmc.2025.065413 - 19 May 2025

Abstract Predicting player performance in sports is a critical challenge with significant implications for team success, fan engagement, and financial outcomes. Although, in Major League Baseball (MLB), statistical methodologies such as sabermetrics have been widely used, the dynamic nature of sports makes accurate performance prediction a difficult task. Enhanced forecasts can provide immense value to team managers by aiding strategic player contract and acquisition decisions. This study addresses this challenge by employing the temporal fusion transformer (TFT), an advanced and cutting-edge deep learning model for complex data, to predict pitchers’ earned run average (ERA), a key More >

Yuliang Zhang^1,2,*, Zezhou Yang¹, Lianghuai Tong^3,*, Yanjuan Zhao⁴, Xiaoqi Jia⁵, Anda Han⁶

FDMP-Fluid Dynamics & Materials Processing, Vol.21, No.4, pp. 891-938, 2025, DOI:10.32604/fdmp.2024.059903 - 06 May 2025

Abstract This paper investigates the start-up and shutdown phases of a five-bladed closed-impeller centrifugal pump through experimental analysis, capturing the temporal evolution of its hydraulic performances. The study also predicts the transient characteristics of the pump under non-rated operating conditions to assess the accuracy of various machine learning methods in forecasting its instantaneous performance. Results indicate that the pump’s transient behavior in power-frequency mode markedly differs from that in frequency-conversion mode. Specifically, the power-frequency mode achieves steady-state values faster and exhibits smaller fluctuations before stabilization compared to the other mode. During the start-up phase, as… More >

Long Huang^1,2,3,*, Junjia Zou³, Baoqing Liu¹, Zhijiang Jin^1,2, Jinyuan Qian¹

Frontiers in Heat and Mass Transfer, Vol.22, No.6, pp. 1613-1643, 2024, DOI:10.32604/fhmt.2024.058231 - 19 December 2024

Abstract This study explores the effectiveness of machine learning models in predicting the air-side performance of microchannel heat exchangers. The data were generated by experimentally validated Computational Fluid Dynamics (CFD) simulations of air-to-water microchannel heat exchangers. A distinctive aspect of this research is the comparative analysis of four diverse machine learning algorithms: Artificial Neural Networks (ANN), Support Vector Machines (SVM), Random Forest (RF), and Gaussian Process Regression (GPR). These models are adeptly applied to predict air-side heat transfer performance with high precision, with ANN and GPR exhibiting notably superior accuracy. Additionally, this research further delves into… More >

Mohammad Javad Shayegan^*, Rosa Akhtari

Computer Systems Science and Engineering, Vol.48, No.5, pp. 1251-1272, 2024, DOI:10.32604/csse.2024.052587 - 13 September 2024

Abstract After the spread of COVID-19, e-learning systems have become crucial tools in educational systems worldwide, spanning all levels of education. This widespread use of e-learning platforms has resulted in the accumulation of vast amounts of valuable data, making it an attractive resource for predicting student performance. In this study, we aimed to predict student performance based on the analysis of data collected from the OULAD and Deeds datasets. The stacking method was employed for modeling in this research. The proposed model utilized weak learners, including nearest neighbor, decision tree, random forest, enhanced gradient, simple Bayes, More >

Dongyang Ou, Yongjian Ren, Congfeng Jiang^*

CMES-Computer Modeling in Engineering & Sciences, Vol.139, No.2, pp. 2043-2067, 2024, DOI:10.32604/cmes.2023.029987 - 29 January 2024

Abstract Cloud service providers generally co-locate online services and batch jobs onto the same computer cluster, where the resources can be pooled in order to maximize data center resource utilization. Due to resource competition between batch jobs and online services, co-location frequently impairs the performance of online services. This study presents a quality of service (QoS) prediction-based scheduling model (QPSM) for co-located workloads. The performance prediction of QPSM consists of two parts: the prediction of an online service’s QoS anomaly based on XGBoost and the prediction of the completion time of an offline batch job based… More >

Xinzheng Wang^1,2,*, Bing Guo¹, Yan Shen³

CMES-Computer Modeling in Engineering & Sciences, Vol.138, No.2, pp. 1183-1206, 2024, DOI:10.32604/cmes.2023.029552 - 17 November 2023

Abstract Predicting students’ academic achievements is an essential issue in education, which can benefit many stakeholders, for instance, students, teachers, managers, etc. Compared with online courses such as MOOCs, students’ academic-related data in the face-to-face physical teaching environment is usually sparsity, and the sample size is relatively small. It makes building models to predict students’ performance accurately in such an environment even more challenging. This paper proposes a Two-Way Neural Network (TWNN) model based on the bidirectional recurrent neural network and graph neural network to predict students’ next semester’s course performance using only their previous course More > Graphic Abstract