Article
Thermodynamics
Mohammad Ali Sahraei, Hakan Duman, Muhammed Yasin Codur, Ecevit Eyduran
Summary: This research aims to predict transport energy demand in Turkey using the MARS model, with the third MARS model selected as the best predictive model after evaluating multiple factors.
Article
Computer Science, Interdisciplinary Applications
Hayder Riyadh Mohammed Mohammed, Sumarni Ismail
Summary: This study investigates the capacity of new artificial intelligence methodologies for predicting the shear strength of reinforced concrete beams. The XGBoost and MARS models developed in this study show potential in modeling the V-s reinforced concrete beams with reliable accuracy.
ENGINEERING WITH COMPUTERS
(2022)
Article
Engineering, Geological
Wengang Zhang, Chongzhi Wu, Yongqin Li, Lin Wang, P. Samui
Summary: This study utilizes machine learning algorithms to construct predictive models for assessing pile drivability, comparing the performance of Random Forest Regression (RFR) and Multivariate Adaptive Regression Splines (MARS) models. The results indicate that the RFR model outperforms MARS in terms of fitting and operational efficiency.
GEORISK-ASSESSMENT AND MANAGEMENT OF RISK FOR ENGINEERED SYSTEMS AND GEOHAZARDS
(2021)
Article
Statistics & Probability
Jianhua Z. Huang, Ya Su
Summary: This paper develops a general theory on rates of convergence of penalized spline estimators for function estimation, allowing for various combinations of spline degree, penalty order, and smoothness of unknown functions. The theory's application spans across different contexts such as regression, density estimation, and estimation of spectral density function of a stationary time series.
ANNALS OF STATISTICS
(2021)
Article
Biochemical Research Methods
Ruiqing Zheng, Min Li, Xiang Chen, Siyu Zhao, Fang-Xiang Wu, Yi Pan, Jianxin Wang
Summary: Gene regulatory networks play a crucial role in biological processes and exhibit diversity under different biological conditions. Reconstructing these networks from gene expression data has been a significant challenge in the past decades. The proposed PBMarsNet method shows superior performance and generalization compared to other state-of-the-art methods in inferring directed GRNs from multifactorial gene expression data.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2021)
Article
Engineering, Environmental
Tengfei Wang, Hongfei Ma, Jiankun Liu, Qiang Luo, Qingzhi Wang, You Zhan
Summary: This study proposes a practical approach to assess the frost heave susceptibility of gravelly soils under unidirectional freezing conditions. Through frost heave tests and data analysis, an evaluation guideline for optimized railway roadbed is developed.
COLD REGIONS SCIENCE AND TECHNOLOGY
(2021)
Article
Computer Science, Interdisciplinary Applications
Minh-Tu Cao, Nhat-Duc Hoang, Viet Ha Nhu, Dieu Tien Bui
Summary: This study proposes an advanced meta-leaner, MOMEM, which integrates artificial electric field algorithm with neural networks and regression splines to accurately predict soil shear strength.
ENGINEERING WITH COMPUTERS
(2022)
Article
Engineering, Geological
Mohsin Usman Qureshi, Zafar Mahmood, Ali Murtaza Rasool
Summary: This paper analyzes the in situ permeability in limestone and sandstone formations for hydraulic structures in Oman and examines the relationship between permeability and rock quality designation. The study finds that in situ permeability decreases as rock quality designation increases at certain depths.
JOURNAL OF ROCK MECHANICS AND GEOTECHNICAL ENGINEERING
(2022)
Article
Construction & Building Technology
Sina Mansourdehghan, Kiarash M. Dolatshahi, Amir Hossein Asjodi
Summary: This paper proposes a damage assessment framework based on the visual features of a damaged reinforced concrete shear wall, and validates it using experimental data. Different machine learning techniques are used for classification, and predictive equations are proposed to estimate the performance level, residual strength, and drift ratio of the walls. The results show that the Random Forest model is the most efficient method, and the predictive equations can accurately estimate the peak drift ratio and residual strength.
JOURNAL OF BUILDING ENGINEERING
(2022)
Article
Engineering, Environmental
Mi Tian, Lihua Li, Zimin Xiong
Summary: This paper proposes a data-driven method to predict the runout of debris flows by integrating multivariate adaptive regression splines (MARS) and Akaike information criterion (AIC) without assuming input parameters and specific function relationships. Results show that the developed method can select the most appropriate MARS models for the debris-flow runout in the study area, with higher prediction accuracy compared to previous empirical correlations.
BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT
(2022)
Article
Construction & Building Technology
Roneh Glenn D. Libre Jr, Julius L. Leano Jr, Luis Felipe Lopez, Carlo Joseph D. Cacanando, Michael Angelo B. Promentilla, Ernesto J. Guades, Lessandro Estelito O. Garciano, Jason Maximino C. Ongpeng
Summary: In this research, small brick masonry wallettes were strengthened using bamboo fiber textile and short bamboo fiber-reinforced geopolymer mortar, resulting in an increase in shear performance. The wallettes strengthened on one side and both sides with textile showed an average increase in shear of about 24% and 35% respectively. These findings can be utilized in developing textile-reinforced geopolymer mortar systems for strengthening masonry walls.
Article
Computer Science, Information Systems
Xinglong Ju, Jay M. Rosenberger, Victoria C. P. Chen, Feng Liu
Summary: This paper presents an efficient and effective approach to find the global optimal value of MARS models that incorporate two-way interaction terms. Experimental results demonstrate that the proposed method can successfully and efficiently find the global optimal solution.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Gulsah Altinok, Pinar Karagoz, Inci Batmaz
Summary: Learning to rank is a supervised learning problem that aims to construct a ranking model for a given dataset, with MARS and CMARS being effective techniques for point-wise learning to rank. Experimental results show that MARS and ANN are effective methods for learning to rank problem and provide promising results.
COMPUTATIONAL INTELLIGENCE
(2021)
Article
Engineering, Environmental
Zhi-Ping Deng, Min Pan, Jing-Tai Niu, Shui-Hua Jiang, Wu-Wen Qian
Summary: This paper proposes a reliable analysis method for slopes based on the SIR-MARS method, which effectively solves the high dimensionality problem under spatially variable soils. By simulating the spatial variability of soil properties and establishing the relationship between soil shear strength parameters and safety factor, the method obtains accurate reliability results at a low cost.
BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT
(2021)
Article
Chemistry, Multidisciplinary
Musaab Sabah Abed, Firas Jawad Kadhim, Jwad K. Almusawi, Hamza Imran, Luis Filipe Almeida Bernardo, Sadiq N. Henedy
Summary: This study successfully predicted soil compaction parameters using the multivariate adaptive regression splines (MARS) model algorithm. The model showed high predictive ability and reliability, making it a potential alternative to traditional laboratory methods for estimating soil compaction parameters.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Civil
Soroush Zamanian, Abdollah Shafieezadeh
Summary: Sewer networks are at risk of infiltration or exfiltration, flow capacity restriction, and loss of structural integrity. This study uses global sensitivity analysis to analyze uncertainties in the service life performance of sewer pipes under corrosion deterioration and traffic loads. The results show that the tensile and compressive strength of concrete are the most influential parameters over the entire service life.
STRUCTURE AND INFRASTRUCTURE ENGINEERING
(2023)
Article
Engineering, Civil
Ji-Gang Xu, De-Cheng Feng, Sujith Mangalathu, Jong-Su Jeon
Summary: This paper proposes an approach for regional seismic performance assessment of reinforced concrete bridges using machine-learning techniques. The results show that the extreme gradient boosting (XGBoost) model has the best performance, accurately predicting the damage states of the bridges.
EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS
(2022)
Review
Construction & Building Technology
Xiaowei Wang, Ram K. Mazumder, Babak Salarieh, Abdullahi M. Salman, Abdollah Shafieezadeh, Yue Li
Summary: Population growth, economic development, and urbanization have increased the exposure and vulnerability of structural and infrastructure systems to hazards. Therefore, developing risk-based assessment and management tools is crucial. Machine learning techniques have shown promise in advancing risk and resilience assessment in structural engineering. However, there is a lack of a comprehensive review on machine learning progress in this field and a lack of in-depth analysis of risk assessment methods in the built environment.
JOURNAL OF STRUCTURAL ENGINEERING
(2022)
Article
Engineering, Civil
Ashkan B. Jeddi, Abdollah Shafieezadeh, Jieun Hur, Jeong-Gon Ha, Daegi Hahm, Min-Kyu Kim
Summary: This study presents the first set of multi-hazard fragility models for typhoons and earthquakes and reduces the computational complexity through the use of active learning. The research highlights the significance of multi-hazard effects on the fragility of transmission structures.
EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS
(2022)
Article
Engineering, Electrical & Electronic
Ashkan B. B. Jeddi, Abdollah Shafieezadeh, Roshanak Nateghi
Summary: Unmanned aerial vehicles equipped with cameras have improved disaster reconnaissance. Deep learning-based computer vision algorithms enable real-time analysis and damage detection. The proposed PDP-CNN model achieves high throughput and accuracy for onboard deployment in UAVs.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Industrial
Zeyu Wang, Abdollah Shafieezadeh
Summary: This paper presents a new approach to overcome the computational cost problem of Bayesian updating for complex computational models. It decomposes the updating problem into a set of sub-reliability problems with uncertain failure thresholds, enabling precise identification of intermediate failure thresholds and training of surrogate models. The proposed method reduces computational costs significantly while maintaining high accuracy.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Engineering, Civil
Bilal Ahmed, Sujith Mangalathu, Jong-Su Jeon
Summary: In order to organize accurate and effective emergency responses after an earthquake, an early and precise assessment of damage to structures is vital. The use of fragility/vulnerability curves is an advanced approach for structural damage assessments. However, the analysis based on these curves can vary significantly depending on soil conditions, ground motion, and structural characteristics. To address this issue, a stacked long short-term memory network is proposed in this research.
EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS
(2023)
Article
Automation & Control Systems
Chi Zhang, Abdollah Shafieezadeh
Summary: In this study, a physics-informed neural network (PINN) framework is proposed for the transient analysis of pipeline networks. It can solve the complex natural gas pipeline problem that the original PINNs cannot handle. The framework improves efficiency and accuracy by using a nested structure and an adaptive weights approach, and it can also be used as a surrogate model for the natural gas pipeline system. This framework greatly boosts the efficiency of complex many-query analyses.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Engineering, Civil
Nadia Saleem, Sujith Mangalathu, Bilal Ahmed, Jong-Su Jeon
Summary: This study presents a novel approach that integrates a geographic information system with a spatial data analysis-based machine learning PGA prediction model, achieving accurate results in predicting peak ground motion parameters and assessing seismic vulnerability of bridges.
EARTHQUAKE ENGINEERING & STRUCTURAL DYNAMICS
(2023)
Article
Engineering, Civil
Mengdie Chen, Sujith Mangalathu, Jong-Su Jeon
Summary: This paper proposes a methodology based on origin-destination pair betweenness centrality to rank bridges in a complex network according to their importance. The methodology considers user equilibrium and topology, and significantly reduces computational time. The study also suggests two strategies, retrofitting bridges and constructing new ones, to mitigate the seismic risk of bridge networks.
ENGINEERING STRUCTURES
(2023)
Article
Engineering, Civil
Chang Seok Lee, Jong-Su Jeon
Summary: This paper proposes a risk-based seismic design method using shape memory alloy wires to enhance the performance of older concrete bridge classes. It adopts an existing SMA-SCB system to examine further applications to nonductile bridges. A sophisticated finite element model, probabilistic bridge models, and the total probability theorem are employed to develop the risk-based seismic design of the SMA-SCB.
ENGINEERING STRUCTURES
(2023)
Article
Materials Science, Multidisciplinary
Bilal Ahmed, Taehyo Park, Jong-Su Jeon
Summary: This study utilizes machine learning techniques to predict the maximum vertical displacement of reinforced concrete slabs subjected to air-blast loading. Different convolutional neural networks were trained using images transformed from tabular data, and most models demonstrated promising results.
INTERNATIONAL JOURNAL OF DAMAGE MECHANICS
(2023)
Article
Instruments & Instrumentation
Eunsoo Choi, Jong-Su Jeon, Jong-Han Lee
Summary: This study investigates the self-centering capacity of RC columns with martensitic SMA bars in the plastic hinge region through experiments. The results show that the RC column with SMA bars exhibits a plastic hinge around the couplers, demonstrating excellent self-centering capacity, but lower energy-dissipation capacity compared to conventional RC columns.
SMART MATERIALS AND STRUCTURES
(2023)
Article
Engineering, Civil
Chang Seok Lee, Jong-Su Jeon
Summary: This study introduces the seismic risk-based design of SMA devices for steel moment-resisting frame buildings. The traditional design method was found to have inconsistencies in response compared to actual test results. To address this issue, a seismic risk-based design approach was employed, using nonlinear time history analysis and optimization algorithm to determine the quantity of SMA devices, resulting in cost reduction and a significant decrease in the probability of collapse and demolition.
ENGINEERING STRUCTURES
(2023)
Article
Construction & Building Technology
Sergei Shturmin, Chang Seok Lee, Jong-Su Jeon
Summary: A simplified modeling approach based on nonlinear spring model is proposed to simulate the seismic behavior of concrete-filled steel tube columns. The approach was calibrated and validated using experimental data, and it showed better accuracy and reduced computational time compared to the existing fiber-based beam-column model.
JOURNAL OF CONSTRUCTIONAL STEEL RESEARCH
(2023)