Article
Engineering, Marine
Suria Devi Vijaya Kumar, Michael Lo, Saravanan Karuppanan, Mark Ovinis
Summary: This study proposes an analytical equation based on finite element analysis to predict the failure pressure of corroded pipes with longitudinal interacting defects subjected to combined loadings. The equation is developed using an artificial neural network trained with failure pressure data obtained from finite element analysis. A parametric study is performed to demonstrate the correlation between defect geometries and failure pressure, and the equation shows good prediction accuracy.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2022)
Review
Chemistry, Physical
Suria Devi Vijaya Kumar, Michael Lo Yin Kai, Thibankumar Arumugam, Saravanan Karuppanan
Summary: This paper discusses the use of artificial neural networks integrated with the finite element method to predict the failure pressure of corroded pipelines. The integration of ANN and FEM has been proven to significantly reduce the time taken to obtain accurate results compared to traditional methods.
Article
Multidisciplinary Sciences
Mehmet Ozan Yilmaz, Serkan Bekiroglu
Summary: This study introduces the application of Generalized Regression Neural Networks to joint deformation problem and proposes a prediction model. The accuracy and reliability of the proposed model are demonstrated with statistical measures and comparison to various methods available in the literature.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Nagoor Basha Shaik, Srinivasa Rao Pedapati, A. R. Othman, Kishore Bingi, Faizul Azly Abd Dzubir
Summary: This study introduces an intelligent model using artificial neural networks to accurately predict pipeline conditions and classify metal loss faults. A sensitivity analysis reveals the interrelationship between factors impacting pipeline conditions and estimates the remaining useful life of pipeline sections. This research contributes to optimizing pipeline inspections and maintenance planning.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Biochemical Research Methods
Yuantong Li, Fei Wang, Mengying Yan, Edward Cantu, Fan Nils Yang, Hengyi Rao, Rui Feng
Summary: In this article, a novel neural network model called peel learning is proposed for gene expression studies, showing improved prediction accuracy compared to traditional regression models and other deep learning methods. The model effectively incorporates the prior relationship among genes and simplifies the overall structure while optimizing weight parameters through a revised backpropagation algorithm, demonstrating advantages in small sample size studies.
Article
Multidisciplinary Sciences
Linus Aronsson, Roland Andersson, Daniel Ansari
Summary: This study investigated the predictive ability of artificial neural networks and LASSO regression for 5-year disease-specific survival in patients with invasive IPMN of the pancreas. The results showed that both models had high and similar performance in predicting accuracy and precision for 5-year survival status.
Article
Multidisciplinary Sciences
Antonio Carlos da Silva Junior, Michele Jorge da Silva, Cosme Damiao Cruz, Isabela de Castro Sant'Anna, Gabi Nunes Silva, Moyses Nascimento, Camila Ferreira Azevedo
Summary: The study evaluated the importance of auxiliary traits of a principal trait in plant breeding using computational intelligence and machine learning. Results showed that computational intelligence and machine learning were able to extract nonlinear information and quantify the relative contributions of phenotypic traits. It was concluded that the relative contributions of auxiliary traits in plant breeding programs can be efficiently predicted using computational intelligence and machine learning.
Article
Energy & Fuels
Junxian Wang, Yinbo Xu, Pingchang Sun, Zhaojun Liu, Jiaqiang Zhang, Qingtao Meng, Penglin Zhang, Baiqiang Tang
Summary: The total organic carbon (TOC) content is an important parameter for evaluating oil shale resources. Prediction methods based on resistivity, density, acoustic, and gamma ray logging curves have been used to predict TOC content. The study found that the artificial neural networks (ANN) model had the strongest prediction ability, followed by the linear regression (LR) model, while the Delta logR model had the lowest prediction ability. The difference in porosity characteristics caused by organic matter content is the primary factor affecting the inversion of TOC content logging between oil shale and source rock.
GEOMECHANICS AND GEOPHYSICS FOR GEO-ENERGY AND GEO-RESOURCES
(2022)
Article
Mathematics
Adnan Bashir, Muhammad Ahmed Shehzad, Aamna Khan, Ayesha Niaz, Muhammad Nabeel Asghar, Ramy Aldallal, Mutua Kilai
Summary: This study investigates a new hybrid model, the wavelet bootstrap quadratic response surface, for accurate streamflow prediction. The results show that this model provides the most efficient results.
JOURNAL OF MATHEMATICS
(2023)
Article
Materials Science, Coatings & Films
Z. Y. Liu, L. Yang, Y. C. Zhou
Summary: A multiscale life prediction model integrating artificial neural networks was developed to predict the failure of turbine blade coatings. The model considers the complex microstructure and multiphysics failure mechanisms, and takes into account factors like oxidation, creep, thermal mismatch, gas and coolant conditions, film cooling, and TBCs. The model shows better prediction accuracy on interface oxidation, damage evolution, and failure region of TBCs on turbine vane. The study also highlights the coupled effect of thermal, oxide growth, and thermal mismatch on TBCs failure of turbine vane.
SURFACE & COATINGS TECHNOLOGY
(2023)
Article
Engineering, Chemical
Jai Krishna Sahith Sayani, Vinayagam Sivabalan, Khor Siak Foo, Srinivasa Rao Pedapati, Bhajan Lal
Summary: An artificial intelligence model is developed to accurately predict the gas hydrate formation rate and reaction kinetics in multiphase transmission pipelines. The multilayer perceptron (MLP) model demonstrates higher prediction accuracy.
CHEMICAL ENGINEERING & TECHNOLOGY
(2022)
Article
Engineering, Industrial
Yue Su, Jingfa Li, Bo Yu, Yanlin Zhao, Jun Yao
Summary: A fast and accurate method for predicting the failure pressure of defective pipelines using a deep learning model has been developed. The deep learning model showed high prediction accuracy and significantly accelerated calculation speed compared to finite element method simulations. The analysis of the influence of defect sizes on pipeline failure pressure was conducted using the deep neural network.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2021)
Article
Multidisciplinary Sciences
Zhengcai Li, Xinmin Hu, Chun Chen, Chenyang Liu, Yalu Han, Yuanfeng Yu, Lizhi Du
Summary: This paper investigates the optimization algorithms based on machine learning for settlement prediction. By comparing the performance of different algorithms, the study finds that Sparrow Search Algorithm (SSA) significantly improves the optimization effect of the gradient descent model and enhances its stability to a certain degree.
SCIENTIFIC REPORTS
(2022)
Article
Multidisciplinary Sciences
Gyanesh Patnaik, Anshul Kaushik, M. Johnson Singh, A. Rajput, G. Prakash, L. Borana
Summary: Underground pipelines play a crucial role in the present time. This study develops artificial intelligence (AI) models to predict damage in underground steel pipelines subjected to explosions. Through blast simulations and performance indicators evaluation, artificial neural network shows the best performance. This study proposes an effective learning model for damage prediction in buried pipelines.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2022)
Article
Energy & Fuels
Yisheng Wu, Yusen Liu, Xinling Li, Zhen Huang, Dong Han
Summary: In this study, a determination model for research octane numbers (RONs) of gasoline fuels was developed using near-infrared (NIR) spectroscopy and artificial neural networks (ANN). The model was validated with 200 gasoline fuels from different regions in China, showing a high prediction accuracy. The contributions of the NIR spectra to the model were analyzed using the partial least squares regression method.
Article
Environmental Sciences
Sanaz Tabatabaee, Saeed Reza Mohandes, Rana Rabnawaz Ahmed, Amir Mahdiyar, Mehrdad Arashpour, Tarek Zayed, Syuhaida Ismail
Summary: The research aims to identify and analyze the barriers impeding the use of IoT-based technologies in Construction Site Safety Management (CSSM). The most significant barriers include productivity reduction, the need for technical training, and the need for continuous monitoring. Addressing these barriers is crucial for promoting the application and development of technology in ensuring safety and efficiency in construction sites.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
(2022)
Article
Green & Sustainable Science & Technology
Beenish Bakhtawar, Muhammad Jamaluddin Thaheem, Husnain Arshad, Salman Tariq, Khwaja Mateen Mazher, Tarek Zayed, Naheed Akhtar
Summary: This study presents a model for conducting a sustainability-based risk assessment of P3 infrastructure projects using global data and Monte Carlo simulation. The findings are validated through case studies and relevant mitigation strategies and future recommendations are provided.
Article
Environmental Sciences
Mohammed Abdul Rahman, Tarek Zayed, Ashutosh Bagchi
Summary: Ground-Penetrating Radar (GPR) is a non-destructive technique for evaluating RC bridge elements, and a proposed model improves the traditional image-based analysis by automatically detecting hyperbolas and using mathematical modeling for classification. The model generates deterioration maps that correspond to the actual state of concrete, facilitating the identification of deteriorated zones for repair and rehabilitation.
Review
Environmental Sciences
Ridwan Taiwo, Mohamed El Amine Ben Seghier, Tarek Zayed
Summary: This study fills the research gap by conducting a bibliometric analysis and systematic review of predictive models for the failure probability of water pipes. It finds that machine-learning based models are understudied compared to physical and statistical models, and suggests the exploration of social and operation-related predictors in future research.
WATER RESOURCES RESEARCH
(2023)
Review
Environmental Sciences
Ali Fares, Tarek Zayed
Summary: This study systematically investigated the various trends in pavement roughness measurement techniques within the industry and research community in the past five decades. In the industry, laser inertial profilers prevailed over response-type methods. Among the research community, there has been a boom of research focusing on roughness measurement in recent years.
Article
Construction & Building Technology
Comfort Salihu, Saeed Reza Mohandes, Ahmed Farouk Kineber, M. Reza Hosseini, Faris Elghaish, Tarek Zayed
Summary: Sewer pipeline failures have significant implications for the environment and public health. Existing deterioration models based on CCTV inspection reports suffer from errors due to subjectivity and human involvement, and are hindered by inadequate data. To overcome these limitations, this paper proposes an AI-based deterioration model for sewer pipes. The model integrates unsupervised multilinear regression and Weibull analysis, revealing the useful service life of different pipe materials and the impact of various factors on pipe deterioration. These findings can assist decision-makers in identifying critical pipes and prioritizing maintenance actions, promoting the design of sustainable urban drainage systems.
Article
Construction & Building Technology
Abdul-Mugis Yussif, Haleh Sadeghi, Tarek Zayed
Summary: This study proposes a low-cost approach to locating leakages in underground water distribution networks (WDNs) in urban areas using acoustic signal behavior and machine learning. The study achieves high accuracy in predicting leak locations and directions using regression machine learning algorithms, support vector machines (SVM) and ensemble k-nearest neighbors (k-NN). The models have been proven effective in an urban setting.
Article
Construction & Building Technology
Mohamed Assaf, Mohamed Hussein, Sherif Abdelkhalek, Tarek Zayed
Summary: Off-site construction (OSC) is an innovative construction method that transfers most site-based work to a controlled environment. Minimal research attention has been given to the procurement management in OSC, overlooking criteria related to OSC that impact the selection of appropriate procurement methods. This study contributes by identifying these criteria and developing a multi-criteria decision-making model for selecting the appropriate OSC procurement methods.
Review
Construction & Building Technology
Eslam Mohammed Abdelkader, Tarek Zayed, Nour Faris
Summary: This research paper presents a mixed review method that encompasses both bibliometric and systematic analyses of the state-of-the-art work pertinent to the assessment of reinforced concrete bridge defects using non-destructive techniques. It compiles and evaluates 505 core peer-reviewed journal articles and book chapters, and utilizes network visualization and scientometric mapping for data analysis. The study also conducts a multifaceted systematic review analysis of the identified literature, covering various aspects related to bridge defects, non-destructive techniques, data processing methods, public datasets, key findings, and future research directions.
Article
Mathematics
Eslam Mohammed Abdelkader, Tarek Zayed, Hassan El Fathali, Ghasan Alfalah, Abobakr Al-Sakkaf, Osama Moselhi
Summary: Public-private partnership (PPP) infrastructure projects have been the focus of attention in recent years. This research paper proposes an integrated multi-criteria decision-making (MCDM) model for selecting the best private partners in PPP projects. The model uses a two-tier approach, using the fuzzy analytical network process (FANP) to determine the relative importance of selection criteria, and seven MCDM algorithms to identify the best private partners. The results from real-world case studies show that the importance of criteria varies based on the nature of infrastructure projects, with financial and technical criteria being the most important.
Review
Social Sciences, Interdisciplinary
Ahmad Alshami, Moustafa Elsayed, Eslam Ali, Abdelrahman E. E. Eltoukhy, Tarek Zayed
Summary: Systematic reviews (SR) are important for synthesizing scientific literature to support evidence-based decision-making, but traditional methods have limitations. This research utilizes ChatGPT, a powerful language model, to automate and streamline the steps involved in SR. The findings demonstrate the potential of ChatGPT in enhancing efficiency and reliability, particularly in article filtering and categorization, while highlighting limitations in article extraction.
Review
Construction & Building Technology
Mohamed Assaf, Mohamed Hussein, Badr T. Alsulami, Tarek Zayed
Summary: Cash flow management is crucial in construction projects, but there is a lack of comprehensive review in this field. This study provides a holistic and up-to-date review of 172 journal articles on cash flow management in construction, highlighting future research areas and proposing an automated payment framework using Blockchain-based smart contracts.
Article
Construction & Building Technology
Ridwan Taiwo, Mohamed Hussein, Tarek Zayed
Summary: Many nations face housing deficits, and modular integrated construction (MiC) has been adopted as a reliable method to address this issue. However, previous studies have mostly focused on the productivity of the prefabrication stage of MiC, while neglecting the productivity of the installation process, especially for high-rise buildings. This study develops a model to assess the productivity of MiC installation, considering pragmatic and management factors. A case study in Hong Kong is conducted, and the model is shown to accurately predict productivity. Construction practitioners can use this model to make informed decisions during the planning and implementation of MiC projects.
Article
Construction & Building Technology
Abobakr Al-Sakkaf, Ashutosh Bagchi, Tarek Zayed
Summary: This study evaluates the life-cycle cost of energy for heritage buildings (HBs) and develops a comprehensive model for expenditure planning. The findings highlight the significant impact of the operation phase on energy consumption and building cost.
Article
Green & Sustainable Science & Technology
Abobakr Al-Sakkaf, Tarek Zayed, Ashutosh Bagchi, Sherif Mahmoud, David Pickup
Summary: This study aims to develop a specific assessment tool for heritage buildings, as there is a lack of rating systems designed specifically for this type of buildings. By researching the sustainability of heritage buildings, it was found that existing rating systems have deficiencies in assessing the specific characteristics of heritage buildings. Therefore, a new assessment tool needs to be developed to enable facility managers to evaluate and improve the sustainability of their heritage buildings.
SMART AND SUSTAINABLE BUILT ENVIRONMENT
(2022)