Article
Soil Science
Mitra Ebrahimi, Mohammad Reza Sarikhani, Jalal Shiri, Farzin Shahbazi
Summary: In this research, GEP and ANN techniques were used to estimate soil enzyme activity, with models using all available input parameters yielding the best performance, particularly in predicting urease activity.
APPLIED SOIL ECOLOGY
(2021)
Article
Chemistry, Physical
Muhammad Nasir Amin, Izaz Ahmad, Mudassir Iqbal, Asim Abbas, Kaffayatullah Khan, Muhammad Iftikhar Faraz, Anas Abdulalim Alabdullah, Shahid Ullah
Summary: Concrete is an economical and efficient material for attenuating radiation, with its density playing a crucial role in radiation shielding. The study identified thickness and density of concrete as the most influential parameters in radiation attenuation. The artificial neural network model outperformed the gene expression programming model in accuracy, showing a strong agreement between predicted and experimental results.
Article
Multidisciplinary Sciences
Mahmood Ahmad, Mohammad A. Al-Zubi, Ewa Kubinska-Jabcon, Ali Majdi, Ramez A. Al-Mansob, Mohanad Muayad Sabri Sabri, Enas Ali, Jamil Abdulrabb Naji, Ashraf Y. Elnaggar, Bakht Zamin
Summary: A new model based on Gaussian process regression (GPR) was developed to predict the CBR value of hydrated lime-activated rice husk ash (HARHA) treated soil. The GPR model showed higher accuracy compared to the artificial neural network (ANN) and gene expression programming (GEP) models in the literature.
SCIENTIFIC REPORTS
(2023)
Article
Chemistry, Multidisciplinary
Abolfazl Baghbani, Minh Duc Nguyen, Ali Alnedawi, Nick Milne, Thomas Baumgartl, Hossam Abuel-Naga
Summary: This study investigates the potential of artificial intelligence (AI) methods for predicting the California bearing ratio (CBR) of soils stabilized with alum sludge. Three AI methods, including two black box methods (artificial neural network and support vector machines) and one grey box method (genetic programming), were used to predict CBR, based on a database with nine input parameters. The results demonstrate the effectiveness of AI methods in predicting CBR with good accuracy.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Artificial Intelligence
Alireza Amirteimoori, Tofigh Allahviranloo, Majid Zadmirzaei, Fahimeh Hasanzadeh
Summary: Greenhouse gases, especially carbon dioxide emissions, have become a worldwide concern due to their harmful effects on climate change. This study proposes a novel model, combined with artificial intelligence algorithms, to measure environmental efficiency and predict optimal values for inefficient decision-making units in order to mitigate CO2 emissions.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Engineering, Multidisciplinary
Kareem Othman, Hassan Abdelwahab
Summary: The study aims to provide artificial neural network (ANN) prediction models for efficiently estimating the CBR value of subgrade soil in Egypt. Deep neural networks outperform shallow ANNs, and compared to traditional multiple linear regression (MLR) models, ANNs demonstrate better performance and produce highly accurate predictions.
AIN SHAMS ENGINEERING JOURNAL
(2023)
Article
Chemistry, Physical
Hammad Ahmed Shah, Qiang Yuan, Usman Akmal, Sajjad Ahmad Shah, Abdelatif Salmi, Youssef Ahmed Awad, Liaqat Ali Shah, Yusra Iftikhar, Muhammad Haris Javed, Muhammad Imtiaz Khan
Summary: This study models the mechanical properties of concrete with metakaolin using machine learning techniques, and finds that random forest has better predictive and generalization capability.
Article
Engineering, Civil
Wei-lie Zou, Zhong Han, Lu-qiang Ding, Xie-qun Wang
Summary: This study developed gene expression programming (GEP) and artificial neural network (ANN) models to predict the resilient modulus (M-R) of compacted pavement subgrade soils based on physical properties, external stress states, and environmental factors. The results showed that the type of soil and environmental factors have a greater impact on the MR of compacted subgrade soils compared to external stress states.
TRANSPORTATION GEOTECHNICS
(2021)
Article
Construction & Building Technology
Suleyman Ipek, Esra Mete Guneyisi
Summary: The present study proposes design models for predicting the peak strength of concrete-filled steel tubular (CFST) elliptical columns subjected to eccentric compressive loading. The study evaluates the applicability of current design codes and develops new numerical models based on gene expression programming (GEP) and artificial neural network (ANN) approaches. The results show that the developed GEP and ANN models perform better than the current design provisions in terms of prediction accuracy and robustness.
JOURNAL OF BUILDING ENGINEERING
(2022)
Article
Construction & Building Technology
Babatunde Abiodun Salami, Mudassir Iqbal, Abdulazeez Abdulraheem, Fazal E. Jalal, Wasiu Alimi, Arshad Jamal, T. Tafsirojjaman, Yue Liu, Abidhan Bardhan
Summary: This study proposed AI-based models to predict the compressive strength of foamed concrete and experimented with three different AI approaches. After training the models with experimental data, verification and analysis revealed that the GBT model had relatively better performance.
CEMENT & CONCRETE COMPOSITES
(2022)
Article
Mathematics
Zarghaam Haider Rizvi, Syed Jawad Akhtar, Syed Mohammad Baqir Husain, Mohiuddeen Khan, Hasan Haider, Sakina Naqvi, Vineet Tirth, Frank Wuttke
Summary: This study utilized neural networks to predict the effective thermal conductivity of soil, improving prediction accuracy through experiments and model construction. Different sands were validated using neural networks, with the GEP model performing best in the 99% quartz sand.
Article
Computer Science, Information Systems
Masood Nekoei, Seyed Amirhossein Moghaddas, Emadaldin Mohammadi Golafshani, Amir H. Gandomi
Summary: In the field of artificial intelligence automatic programming, artificial bee colony expression programming (ABCEP) presents new solutions by using expression sharing to improve performance. Experimental results indicate that predictions generated by ABCEP outperform other automatic programming algorithms based on successful runs, mean fitness values, and convergence rate.
INFORMATION SCIENCES
(2021)
Article
Construction & Building Technology
Ayaz Ahmad, Krisada Chaiyasarn, Furqan Farooq, Waqas Ahmad, Suniti Suparp, Fahid Aslam
Summary: The utilization of recycled coarse aggregate in concrete is an effective way to reduce environmental pollution, but the presence of adhered mortar on its surface affects its properties. A suitable mix design can enable the coarse aggregate to achieve the desired strength and be used in various construction projects. Employing supervised machine learning algorithms, gene expression programming, and artificial neural network can effectively predict the compressive strength of concrete.
Article
Mechanics
Husam Al Qablan, Tamara Al-Qablan
Summary: This study aims to develop semi-empirical formulas for predicting the buckling loads of clamped and simply supported rectangular isotropic panels with central circular perforation under different ratios of biaxial loads. The empirical formulas were developed and evaluated using Gene Expression Programming (GEP), Artificial Neural Network (ANN), and Finite Element Method (FEM). A total of 714 data set, generated using the FEM, were used to establish and validate the empirical formulas. The study investigates the effects of perforation sizes, plate aspect ratios, and biaxial load ratios on the buckling strength of perforated panels. The proposed formulas provide a quick and easy estimation of buckling loads for perforated rectangular panels with acceptable accuracy, without the need for sophisticated calculations. The results of the empirical formulas were reasonably well compared to the results of finite element analysis (FE) and existing literature findings.
MECHANICS BASED DESIGN OF STRUCTURES AND MACHINES
(2023)
Article
Computer Science, Artificial Intelligence
Song Deng, Xinya Yuan, Qianliang Li, Jie Zhang, Mengfei Sun, Xiong Fu, Lechan Yang
Summary: The open, interconnected, and shared operational characteristics of the energy Internet introduce more sophisticated cybersecurity attacks. Accurately detecting these cyber attacks is crucial for energy Internet security protection. This study utilizes gene expression programming (GEP) to optimize the parameters of convolutional neural networks (CNN) and proposes an intrusion detection algorithm based on GEP-CNN (GCNN-IDS). The experimental results demonstrate the high detection accuracy and performance of the optimized CNN-based intrusion detection algorithm.
APPLIED SOFT COMPUTING
(2023)
