Article
Computer Science, Interdisciplinary Applications
Xu Zhang, Lin Liu, Minxuan Lan, Guangwen Song, Luzi Xiao, Jianguo Chen
Summary: The interpretability of advanced machine learning models is utilized in this study to overcome the limitation of estimating variable contributions in crime prediction. Based on routine activity theory and crime pattern theory, 17 variables are selected for crime prediction, and the Shapley additive explanation (SHAP) method is used to discern the contribution of individual variables. Findings reveal that the proportion of the non-local population and the ambient population aged 25-44 contribute the most to crime prediction. Local models provide insights for tackling important factors at each location, while the global model identifies essential factors for the entire region.
COMPUTERS ENVIRONMENT AND URBAN SYSTEMS
(2022)
Article
Chemistry, Multidisciplinary
Xiangdong Wang, Tian Lu, Wenyan Zhou, Xiaobo Ji, Wencong Lu, Jiong Yang
Summary: New ternary gold alloys with low resistivities were discovered using a interpretable machine learning strategy, with a strong generalization ability of the model. The outputs of the model were analyzed with critical SHAP values and an online web server was developed to share the model.
CHEMISTRY-AN ASIAN JOURNAL
(2022)
Article
Biology
Ke Wang, Jing Tian, Chu Zheng, Hong Yang, Jia Ren, Yanling Liu, Qinghua Han, Yanbo Zhang
Summary: This study established an ML model to accurately assess and stratify the risk of 3-year all-cause mortality in patients with heart failure caused by coronary heart disease. By combining ML with the SHAP method, individualized risk prediction was explained explicitly, providing physicians with an intuitive understanding of the influence of key features in the model.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Geosciences, Multidisciplinary
Xiangqi Wang, Zifa Wang, Jianming Wang, Pengyu Miao, Haotian Dang, Zhaoyan Li
Summary: This study used machine learning algorithms and SHAP analysis to predict and explain the impact of site conditions on seismic ground motion. The results showed that machine learning algorithms performed significantly better than traditional approaches, with XGBoost algorithm being the most effective. The explanation provided by the SHAP analysis enhanced the interpretability of the study. The combination of machine learning and SHAP analysis is expected to improve site amplification assessment in seismic hazard analysis.
FRONTIERS IN EARTH SCIENCE
(2023)
Article
Biology
Amiel Meiseles, Denis Paley, Mira Ziv, Yarin Hadid, Lior Rokach, Tamar Tadmor
Summary: Chronic lymphocytic leukemia (CLL) is a common type of leukemia that primarily affects the elderly population. Predicting the necessity of treatment for CLL is important due to the heterogeneous behavior of the disease. This study aimed to develop a machine learning model to predict whether a patient will require treatment for CLL within two years of diagnosis based on demographic data and routine laboratory tests. The results showed that machine learning models outperformed the traditional prognostic scoring system in predicting the need for treatment.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Construction & Building Technology
Benoit Hilloulin, Abdelhamid Hafidi, Sonia Boudache, Ahmed Loukili
Summary: This study introduces a machine learning framework for predicting the expansion of cementitious materials due to external sulfate attack (ESA). Four optimized machine learning models are compared and extreme Gradient Boosting (XGBoost) showed the best performance. SHapley Additive exPlanations (SHAP) enabled the identification of the most influential inputs and their relative influence. The model has been shown to accurately predict the time required to reach a given expansion.
JOURNAL OF BUILDING ENGINEERING
(2023)
Article
Medicine, General & Internal
Pan Ma, Ruixiang Liu, Wenrui Gu, Qing Dai, Yu Gan, Jing Cen, Shenglan Shang, Fang Liu, Yongchuan Chen
Summary: This study used machine learning to predict teicoplanin trough concentrations and explained the prediction model using the SHAP method. The results showed that teicoplanin administration and renal function were the most important factors in predicting teicoplanin trough concentrations.
FRONTIERS IN MEDICINE
(2022)
Article
Environmental Sciences
Abolfazl Abdollahi, Biswajeet Pradhan
Summary: One of the worst environmental catastrophes in Australia is wildfire. Machine learning algorithms are used to identify fire occurrence patterns and susceptibility in wildfire-prone regions. The Shapley additive explanations model is used to interpret the results of a deep learning model for wildfire susceptibility prediction, revealing the significant contributions of factors such as humidity, wind speed, rainfall, elevation, slope, and NDMI.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Materials Science, Multidisciplinary
Lin Chi, Mian Wang, Kaihua Liu, Shuang Lu, Lili Kan, Xuemin Xia, Chendong Huang
Summary: Machine learning techniques can accurately predict the compressive strength of cement-based materials, and electrical resistivity as a nondestructive testing parameter can improve the accuracy of the prediction model.
MATERIALS TODAY COMMUNICATIONS
(2023)
Article
Engineering, Multidisciplinary
Yuequan Bao, Hui Li
Summary: The conventional vibration-based methods face challenges in accurately detecting structural damages, thus necessitating the development of novel diagnosis and prognosis methods based on various monitoring data.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2021)
Article
Engineering, Civil
Tadesse G. Wakjira, Mohamed Ibrahim, Usama Ebead, M. Shahira Alam
Summary: This paper presents a data-driven approach to determine the load and flexural capacities of RC beams strengthened with FRCM composites. Several machine learning models are evaluated to propose the best predictive model. The xgBoost model is found to be the most accurate and robust. A comparative study with existing analytical models shows the superiority of the proposed model. Additionally, an explanation approach and reliability analysis are used to interpret and validate the model.
ENGINEERING STRUCTURES
(2022)
Article
Multidisciplinary Sciences
Fawaz Alboghail, Abdulazeez Abdulraheem, Ahmed Farid Ibrahim, Salaheldin Elkatatny, Mohamed Mahmoud
Summary: The interest in AI predictive models in petrophysics and well logs is growing rapidly as it prevails as a powerful tool, given the relative data abundance. This study provides a framework for resistivity prediction and introduces AI models for predicting resistivity in horizontal low formation quality wells.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2023)
Article
Materials Science, Ceramics
XiaoWei Liu, ZhiLin Long, Li Peng
Summary: Amorphous alloys are formed by rapid cooling of liquid alloys, showing excellent mechanical properties due to the absence of grain boundaries, dislocations, and other defects, with Vickers hardness (HV) being one of its outstanding properties. In this study, four machine learning models were applied for HV modeling using atomic fraction, structural features, and load as input features. The Light Gradient Boosting Machine (LightGBM) model achieved higher determination coefficients R2 of 0.981 and 0.979 in the test set compared to the other three models, indicating superior generalization ability. Additionally, the introduction of shapley additive explanations (SHAP) theory improved the interpretability of the model, highlighting XP1 and Tm1 as the two most important features with critical values for improving HV if they fall within the correct range.
JOURNAL OF NON-CRYSTALLINE SOLIDS
(2023)
Article
Nanoscience & Nanotechnology
Weijie Liu, Chenglei Wang, Chaojie Liang, Junfeng Chen, Hong Tan, Jijie Yang, Mulin Liang, Xin Li, Chong Liu, Mei Huang, Xingjun Liu
Summary: In this study, a multi-layer structure prediction model was built to find HEAs with high ?' phase volume fraction and high strength. Four HEAs were selected from 800,000 candidate alloys by the model and experimentally verified to have high ?' phase volume fraction and high strength. Furthermore, a mathematical relationship model for the strengthening mechanism of HEAs was established using the machine learning model and the SHAP algorithm.
MATERIALS SCIENCE AND ENGINEERING A-STRUCTURAL MATERIALS PROPERTIES MICROSTRUCTURE AND PROCESSING
(2023)
Article
Construction & Building Technology
Syed Farasat Ali Shah, Bing Chen, Muhammad Zahid, Muhammad Riaz Ahmad
Summary: Alkali activated material (AAM) or geopolymer has become a sustainable alternative to cement due to its low power consumption and greenhouse gas emissions, as well as good mechanical and durability features. However, developing AAM mixtures with desired properties is challenging due to the nature and diversity of available source materials. This study evaluates the performance of various machine learning models for predicting the compressive strength of one-part AAM binder, with XGBoost outperforming other algorithms. The use of SHapley Additive exPlanations (SHAP) helps interpret the predicted compressive strength and evaluate the effects of various parameters. The interpretable ML strategy used in this study aids in the production and performance tuning of durable and sustainable one-part AAMs for widespread applications.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Computer Science, Interdisciplinary Applications
Bo Liu, Barry M. Lehane, Jianfeng Xue
Summary: This paper introduces a novel elasto-viscoplastic macro-element model for shallow foundations on sand, which explicitly accounts for creep in a realistic manner. The model is capable of reproducing load-settlement responses of footings tested in the field and in the geotechnical centrifuge at typical working loads, as well as effects seen in practice such as post-creep stiffening and settlements induced by unload-reload cycles.
COMPUTERS AND GEOTECHNICS
(2022)
Article
Construction & Building Technology
Wei Dong, Yimiao Huang, Barry Lehane, Guowei Ma
Summary: This study proposes a comprehensive data-driven method for the multi-objective design optimization of GN-reinforced cementitious composites (GNRCC) using machine learning techniques and a non-dominated sorting genetic algorithm. It establishes prediction models for the properties of GNRCC and quantifies the influence of critical features. The proposed method successfully achieves a set of Pareto solutions for the optimization of GNRCC properties.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Engineering, Geological
Barry M. Lehane, Varvara Zania, Shiao Huey Chow, Mathias Jensen
Summary: This study systematically investigates the effects of stress level, penetrometer diameter, penetration depth, and relative density on the end resistance measured in centrifuge-scale cone penetration tests. Empirical formulations are developed to provide a good description of the measurements and enable correlations that are applicable at full scale. These formulations address the discrepancies seen between centrifuge and field scale measurements and provide a means to interpret very shallow CPTs in the field.
Article
Engineering, Geological
H. Wang, B. M. Lehane, M. F. Bransby, L. Z. Wang, Y. Hong
Summary: This study investigates the response characteristics of large diameter rigid monopiles under lateral load through field tests and numerical analysis. The field tests demonstrate that the contribution of the pile base to the lateral response is negligible. Numerical analysis shows that the contribution of the base to the lateral capacity of monopiles with a diameter as large as 10 m can be disregarded.
Article
Engineering, Geological
Bin Huang, Barry M. Lehane, Phillip Watson
Summary: This paper investigates the potential of model-scale testing to replicate the ageing characteristic of shaft friction in clay. By comparing tests on model piles and full-scale driven piles, it is observed that there is good agreement between the laboratory and field experiments when considering consolidation periods.
INTERNATIONAL JOURNAL OF PHYSICAL MODELLING IN GEOTECHNICS
(2023)
Article
Construction & Building Technology
Guowei Ma, Aidi Cui, Yimiao Huang, Wei Dong
Summary: This study developed an ensemble machine learning modeling method to predict the strength of fly ash-based geopolymer, showing that the XGBoost model outperformed others and accurately predicted the strength. The impact of curing conditions, alkali-activator solution variables, and the mole of sodium hydroxide on the model output was analyzed using the SHapley Additive exPlanations theory.
JOURNAL OF MATERIALS IN CIVIL ENGINEERING
(2022)
Article
Engineering, Marine
H. Wang, B. M. Lehane, M. F. Bransby, A. Askarinejad, L. Z. Wang, Y. Hong
Summary: This paper presents the results of a numerical investigation on the lateral moment-rotation response of a monopile in sand, demonstrating that it can be represented using a single non-linear rotational spring. A simple approximate expression is developed to determine the response of a monopile to a lateral load in sand.
Article
Engineering, Geological
Eduardo Bittar, Barry M. Lehane, Anthony Blake, David Richards, David White, Sam Mahdavi, Benjamin Cerfontaine
Summary: This paper presents the results of field investigations on helical piles, examining the effects of various parameters on their axial tension and compression capacity. It proposes a new design method that shows good predictions of axial capacities and incorporates load-displacement response and installation torque estimation.
CANADIAN GEOTECHNICAL JOURNAL
(2023)
Article
Engineering, Civil
Bo Liu, Jianfeng Xue, Barry M. Lehane
Summary: Experimental research on soil-structure interaction (SSI) showed that load redistribution in the superstructure depends on the relative structure-soil stiffness and the location of weak and/or rigid foundations. A simple numerical model with appropriate linear elastic springs can provide a reasonable prediction of SSI.
ENGINEERING STRUCTURES
(2023)
Article
Engineering, Geological
Stephen K. Suryasentana, Myles Lawler, Brian B. Sheil, Barry M. Lehane
Summary: Soil strata delineation is a crucial step in geotechnical engineering design, and the dynamic penetration test (DPT) is commonly used for this purpose. However, DPT data is often noisy and requires manual interpretation. This paper proposes a probabilistic method that uses Bayesian changepoint detection to delineate different soil strata based on their particle size distribution. The proposed method is evaluated using real-world DPT data, demonstrating its potential for faster and more cost-effective geotechnical designs.
JOURNAL OF GEOTECHNICAL AND GEOENVIRONMENTAL ENGINEERING
(2023)
Article
Engineering, Marine
H. Wang, B. M. Lehane, M. F. Bransby, L. Z. Wang, Y. Hong, A. Askarinejad
Summary: This paper presents a synthesis of recent and new research on laterally loaded monopiles in drained sand. The research involved field tests, model tests, simulations and comparisons with published data. The influence of the monopile base is shown to be negligible. The use of the API p-y formulation is found to lead to inaccurate predictions and a new rotational spring model is proposed based on new insights and observations.
Article
Engineering, Geological
Zewen Wang, Wenhan Du, B. M. Lehane
Summary: This paper presents a new, simple, and inexpensive method for accurately measuring the three-dimensional deformation of soil specimens during triaxial tests. The method utilizes a cost-effective image capture system and an automated post-image analysis approach. The system achieves high accuracy in measuring axial and radial displacements, and it can determine the full nonlinear stiffness-strain degradation of soil samples without the need for additional sensors.
Article
Engineering, Civil
Renbing An, Jiacong Yuan, Yi Pan, Duhang Yi
Summary: Traditional timber structures built on sloped land are more susceptible to seismic damage compared to structures built on flat land. The upper portion of the structure is found to be the weak point on sloped land, with potential issues such as tenon failure and column foot sliding.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Elyas Bayat, Federica Tubino
Summary: The current design guidelines for assessing floor vibration performance do not consider the influence of variability in the walking path on the dynamic response of floors. This study investigates the dynamic response of floors under a single pedestrian walking load, taking into account the randomness of the walking path and load. The effectiveness of the current guidelines in predicting floor response is critically assessed.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Gao Ma, Chunxu Hou, Hyeon-Jong Hwang, Linghui Chen, Zhenhao Zhang
Summary: Minimizing earthquake damage and improving repair efficiency are the main principles of resilient structures. This study proposed a repairable column with UHPC segments and replaceable energy dissipaters. The test results showed that the columns with UHPC segments and replaceable dissipaters exhibited high strength, deformation capacity, and energy dissipation.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Kartheek S. M. Sonti, Pavan Kumar Penumakala, Suresh Kumar Reddy Narala, S. Vincent
Summary: In this study, the compressive behavior of alumina hollow particles reinforced aluminum matrix syntactic foams (AMSF) was investigated using analytical, numerical, and experimental methods. The results showed that the FE solver ABAQUS could accurately predict the elastic and elastio-plastic behavior of AMSFs. The study also suggested that FE models have great potential in developing new materials and composites under compression loading.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Zheqi Peng, Xin Wang, Zhishen Wu
Summary: In this study, the statistical modeling of fiber-reinforced polymer (FRP) cables using the classic fiber bundle model is explored. The study considers important features of large-scale multi-tendon FRP cables, such as initial random slack and uneven tensile deformation among tendons. A parametric study and reliability analysis are conducted to predict the load-displacement relation and design thousand-meter-scale FRP cables. The study emphasizes the relation between the reliability index beta of the cable and the safety factor gamma of the FRP material.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Yanchao Shi, Shaozeng Liu, Ye Hu, Zhong-Xian Li, Yang Ding
Summary: This paper introduces a damage assessment method for reinforced concrete (RC) columns under blast loading, using modal parameter measurement as the evaluation index. The validity of the proposed method is validated through numerical and experimental analysis. The results show that this modal-based damage assessment method is applicable for non-destructive evaluation of blast-induced damage of RC columns.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Xiaolin Zou, Maosheng Gong, Zhanxuan Zuo, Qifang Liu
Summary: This paper proposes an efficient framework for assessing the collapse capacity of structures in earthquake engineering. The framework is based on an accurate equivalent single-degree-of-freedom (ESDOF) system, calibrated by a meta-heuristic optimization method. The proposed framework has been validated through case studies, confirming its accuracy and efficiency.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Jie Hu, Weiping Wen, Chenyu Zhang, Changhai Zhai, Shunshun Pei, Zhenghui Wang
Summary: A deep learning-based rapid peak seismic response prediction model is proposed for the most common two-story and three-span subway stations. The model predicts the peak seismic responses of subway stations using a data-driven approach and limited information, achieving good predictive performance and generalization ability, and demonstrating significantly higher computational efficiency compared to numerical simulation methods.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Jin Ho Lee, Jeong-Rae Cho
Summary: A simplified model is proposed to estimate the earthquake responses of a rectangular liquid storage tank considering the fluid-structure interactions. The complex three-dimensional structural behavior of the tank is represented by a combination of fundamental modes of a rectangular-ring-shaped frame structure and a cantilever beam. The system's governing equation is derived, and earthquake responses such as deflection, hydrodynamic pressure, base shear, and overturning moment are obtained from the solution.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
W. J. Lewis, J. M. Russell, T. Q. Li
Summary: The work discusses the key features and advantages of optimal 2-pin arches shaped by statistically prevalent load and constant axial stress. It extends the design space of symmetric arches to cover asymmetric forms and provides minimum values of constant stress for form-finding of such arches made of different materials. The analysis shows that constant stress arches exhibit minimal stress response and have potential implications for sustainability and durability of future infrastructure.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Wen-ming Zhang, Han-xu Zou, Jia-qi Chang, Tian-cheng Liu
Summary: Saddle position is crucial in the construction and control of suspension bridges. This study proposes an analytical approach to estimate the saddle positions in the completed bridge state and discusses the calculation under different definitions. The relationship between the saddle position and the tower's centerline is analyzed, along with the eccentric compression of the tower. The feasibility of the proposed method is verified through a real-life suspension bridge.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Shaise K. John, Alessio Cascardi, Yashida Nadir
Summary: This study experimentally investigated the use of TRM material for reinforcing concrete columns. The results showed that increasing the number of textile layers effectively increased the axial strength. Additionally, the choice of fiber type and hybrid textile configuration also had a significant impact on strength improvement. A new design model that considers the effects of both the confining matrix and textile was proposed.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Chandrashekhar Lakavath, S. Suriya Prakash
Summary: This study experimentally investigated the shear behavior of post-tensioned UHPFRC girders, considering factors such as prestress level, fiber volume fraction, and types of steel fibers. The results showed that increasing prestress and fiber dosage could enhance the ultimate load-carrying capacity of the girders, reduce crack angle, and increase shear cracking load.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Vahid Goodarzimehr, Siamak Talatahari, Saeed Shojaee, Amir H. Gandomi
Summary: In this paper, an Improved Marine Predators Algorithm (IMPA) is proposed for size and shape optimization of truss structures subject to natural frequency constraints. The results indicate that IMPA performs better in solving these nonlinear structural optimization problems compared to other state-of-the-art algorithms.
ENGINEERING STRUCTURES
(2024)
Article
Engineering, Civil
Chun-Xu Qu, Jin-Zhao Jiang, Ting-Hua Yi, Hong-Nan Li
Summary: In this paper, a computer vision-based method is proposed to monitor the deformation and displacement of building structures by obtaining 3D coordinates of surface feature points. The method can acquire a large number of 3D coordinates in a noncontact form, improve the flexibility and density of measurement point layout, and is simple and cost-effective to operate.
ENGINEERING STRUCTURES
(2024)