Article
Multidisciplinary Sciences
Adamu Beyene, Narobika Tesema, Fekadu Fufa, Damtew Tsige
Summary: A landslide occurred in Lalisa village, Jimma Zone, Ethiopia, causing severe damage to 27 hectares of land. The study investigated the root cause of the incident and analyzed the safety of the sliding slope, proposing remedial actions. The rainfall infiltration and the existence of a weak saturated zone at a certain depth were identified as the driving factors for the occurrence and propagation of the landslide incident.
Article
Computer Science, Interdisciplinary Applications
N. Himanshu, V Kumar, A. Burman, D. Maity, B. Gordan
Summary: The study investigates the applicability and efficiency of grey wolf optimization (GWO) in solving slope stability problems by mimicking the social interaction of a pack of grey wolves. The results demonstrate the GWO technique can detect the critical failure surface accurately. Additionally, statistical analysis of the optimum solutions is presented in terms of safety factor F for different slope models.
ENGINEERING WITH COMPUTERS
(2021)
Article
Computer Science, Interdisciplinary Applications
Yi Yang, Weihang Ouyang, Si-Wei Liu
Summary: The proposed research aims to enhance the efficiency and stability of the Morgenstern-Price method by employing Gaussian quadrature and improving the computational scheme. By aligning a few Gauss points along the slip surface, the soil mass division can be improved, leading to a reduction in calculation efforts.
COMPUTERS AND GEOTECHNICS
(2022)
Article
Chemistry, Multidisciplinary
Gongfa Chen, Xiaoyu Kang, Mansheng Lin, Shuai Teng, Zongchao Liu
Summary: This paper presents a slope stability prediction model based on deep learning and digital twinning methods. By collecting 30 actual slopes and generating 100 digital twin models for each slope, a reliable slope database is established. The safety factors of all slope samples are calculated using the Limit Equilibrium Methods (LEMs). A convolutional neural network regression model is established and evaluated using the root mean square error (RMSE).
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Interdisciplinary Applications
Zhenyan Luo, Xuan-Nam Bui, Hoang Nguyen, Hossein Moayedi
Summary: This study proposed a new artificial intelligence model, the PSO-CA technique, for predicting FS in slope stability of open-pit mines, which was applied to quarry data in Vietnam. By comparing with other models, the results showed that the PSO-CA technique had higher accuracy in estimating slope stability.
ENGINEERING WITH COMPUTERS
(2021)
Article
Mathematics
Sumit Kumar, Shiva Shankar Choudhary, Avijit Burman, Raushan Kumar Singh, Abidhan Bardhan, Panagiotis G. Asteris, Zongwei Luo
Summary: This study presents an effective computational technique for probabilistic analyses of Mount St. Helens. By using a hybrid model of artificial neural network and firefly algorithm, the probability of failure of rock slope stability was estimated.
Article
Computer Science, Interdisciplinary Applications
Enrico Soranzo, Carlotta Guardiani, Ahsan Saif, Wei Wu
Summary: In this study, a numerical procedure for locating the critical slip surface of slopes using the method of slices is proposed. The Deep-Q Learning algorithm is employed to determine a non-circular slip surface. It is shown that this method is flexible and can accommodate other Limit Equilibrium Methods, and its accuracy and efficiency are demonstrated through comparison with other search methods.
COMPUTERS & GEOSCIENCES
(2022)
Article
Computer Science, Interdisciplinary Applications
Jiayi Ding, Jianfang Zhou, Wei Cai, Dingcong Zheng
Summary: The study introduces a modified optimization algorithm to accelerate the determination speed of critical slip surfaces in slope reliability analysis. By combining with subset simulation method, the algorithm demonstrates good convergence rate and effectiveness in four examples of soil slopes.
COMPUTERS AND GEOTECHNICS
(2021)
Article
Engineering, Geological
Hui Liu, Junjie Zheng, Rongjun Zhang, Wenyu Yang, Yifan Guo
Summary: This paper proposes a method for identifying representative slip surfaces (RSSs) from the perspective of system failure probability. By using the second-order reliability method (SORM) and multimodal optimization, the method is capable of identifying RSSs with significant contributions and providing a proper estimate of the system failure probability.
GEORISK-ASSESSMENT AND MANAGEMENT OF RISK FOR ENGINEERED SYSTEMS AND GEOHAZARDS
(2023)
Article
Engineering, Geological
Jiaping Sun, Tiantang Yu, Pingting Dong
Summary: This work proposes a novel approach combining the minimum potential energy principle with the pseudo-dynamic method to determine the safety factor of reinforced slopes. By solving the mobilized shear stress on the slip surface using the moment equilibrium equation and introducing the elastic foundation coefficient, the slope stability is evaluated by calculating the ratio of the anti-sliding moment to the sliding moment. The method is efficient and accurate, and the influence of various factors on the safety factor is examined.
SOIL DYNAMICS AND EARTHQUAKE ENGINEERING
(2022)
Article
Computer Science, Interdisciplinary Applications
Xinxin Li, Jianshe Liu, Wenping Gong, Yi Xu, Victor Mwango Bowa
Summary: This paper develops an efficient modeling scheme based on discrete fracture networks (DFNs) for stability investigation. The effectiveness of the proposed approach is validated by comparison against analytical and numerical solutions. The study shows that fracture distribution and slope geometric features are important factors influencing the stability of fractured rock slopes.
COMPUTERS AND GEOTECHNICS
(2022)
Article
Construction & Building Technology
Genbao Zhang, Jianfeng Zhu, Changfu Chen, Renhua Tang, Shimin Zhu, Xiao Luo
Summary: An analytical three-dimensional slope reliability evaluation framework, independent of numerical simulations, was developed in this study. The slope stability analysis was conducted using an extended three-dimensional Morgenstern-Price method, which features analytical formulations and competitive computational efficiency. The framework was validated using a real landslide case and a hypothetical slope example, and the impact of correlation coefficients and probability distribution patterns on the evaluation results was investigated.
Article
Computer Science, Interdisciplinary Applications
Jinqing Jia, Shiyuan Ju
Summary: In slope stability analysis, the strength reduction method (SRM) combined with the finite element method (FEM) can directly obtain the factor of safety (FOS) of complex slopes, but it cannot directly locate the critical slip surface in the plastic zone. A cluster-based method for locating the critical slip surface was proposed in this study to solve this problem. The method uses the various parameters calculated by FEM and treats each node in the finite element model as a data point. It classifies all nodes into two classes using clustering algorithm, and the boundary between them is the critical slip surface. The effectiveness of the proposed method was demonstrated through examples and comparison with other methods.
COMPUTERS AND GEOTECHNICS
(2023)
Article
Geosciences, Multidisciplinary
Mingwei Guo, Jiahang Li, Xuechao Dong
Summary: Slope-stability assessment involves determining the critical slip surface and calculating the corresponding factor of safety. This research introduces the vector sum method based on force-vector characteristics and calculates the factor of safety directly using the force limit equilibrium equation. The analysis and calculations demonstrate the rationality and feasibility of this method in slope stability assessment.
FRONTIERS IN EARTH SCIENCE
(2022)
Article
Chemistry, Multidisciplinary
Yongfeng Cheng, Zhibao Nie, Chao Han, Shijun Ding, Kaiyuan Liu
Summary: The finite element-strength reduction method is used in two-dimensional slope stability analysis for elastic-perfectly plastic material, with the failure criterion of plastic zone penetration. The critical slip surface is determined using wavelet packet analysis, showing that this proposed method is reasonable and effective when compared with Spencer's method.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Artificial Intelligence
N. Sadrekarimi, S. Talatahari, B. Farahmand Azar, A. H. Gandomi
Summary: This paper proposes a surrogate merit function (SMF) as an alternative to traditional merit functions for evaluation. Unlike the traditional merit functions that require expensive trial-and-error tuning processes, SMF does not require tuning factors and demonstrates statistically stable performance across different models. It directly converges to outstanding feasible points and offers advantages such as reduced iterations for convergence. This user-friendly and robust function could be a revolutionary step in commercializing design optimization in the real-world construction market.
Article
Computer Science, Artificial Intelligence
Raghunathan Krishankumar, Arunodaya Raj Mishra, K. S. Ravichandran, Samarjit Kar, Amir H. Gandomi, Romualdas Bausys
Summary: Online reviews from the web are valuable data sources for tourism analytics. Restaurants play a crucial role in the growth of tourism in India. However, existing decision frameworks for restaurant selection lack effective handling of uncertainty and consideration of heterogeneous sources.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Shams Forruque Ahmed, Md. Sakib Bin Alam, Maruf Hassan, Mahtabin Rodela Rozbu, Taoseef Ishtiak, Nazifa Rafa, M. Mofijur, A. B. M. Shawkat Ali, Amir H. Gandomi
Summary: Deep learning is revolutionizing evidence-based decision-making techniques and has the ability to overcome limitations posed by large datasets. However, as a multidisciplinary field that is still in its nascent phase, there is a limited number of articles that comprehensively review DL architectures. This paper aims to provide insights into state-of-the-art DL modelling techniques and their challenges and advantages.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Computer Science, Interdisciplinary Applications
Farshid Keivanian, Raymond Chiong, Ali R. Kashani, Amir H. Gandomi
Summary: This study investigates the seismic performance of reinforced concrete cantilever (RCC) retaining walls in earthquake-prone zones using horizontal and vertical pseudo-static coefficients. A novel adaptive fuzzy-based metaheuristic algorithm is proposed to efficiently search and produce sustainable and economical RCC designs that are robust against earthquake hazards. The algorithm achieves low-cost, low-weight, and low-CO2 emission RCC designs under nine seismic conditions compared to classical and best-performing design optimizers.
JOURNAL OF COMPUTATIONAL SCIENCE
(2023)
Article
Information Science & Library Science
Mahsa Keshavarz-Fathi, Niloufar Yazdanpanah, Sajad Kolahchi, Heliya Ziaei, Gary L. Darmstadt, Tommaso Dorigo, Filip Dochy, Lisa Levin, Visith Thongboonkerd, Shuji Ogino, Wei-Hsin Chen, Matjaz Perc, Mark S. Tremblay, Bolajoko O. Olusanya, Idupulapati M. Rao, Nikos Hatziargyriou, Maziar Moradi-Lakeh, Federico Bella, Laszlo Rosivall, Amir H. Gandomi, Armin Sorooshian, Manoj Gupta, Ciprian Gal, Andres M. Lozano, Connie Weaver, Michael Tanzer, Alessandro Poggi, Sadaf G. Sepanlou, Ralf Weiskirchen, Anet Rezek Jambrak, Pedro J. Torres, Esra Capanoglu, Francisco J. Barba, Chua Kian Jon Ernest, Mariano Sigman, Stefano Pluchino, Gevork B. Gharehpetian, Seyed-Mohammad Fereshtehnejad, Muh-Hwa Yang, Sabu Thomas, Wenju Cai, Elisabetta Comini, Neil J. Scolding, Paul S. Myles, Juan J. Nieto, George Perry, Constantine Sedikides, Nima Rezaeia
Summary: Scientometrics and bibliometrics are subfields of library and information science that study the quantity and quality of research outputs. The h-index is the most well-known scientometric index, but it relies on the count of highly cited publications. To address this limitation, we developed a new index called the Universal Research Index (UR-Index) that considers the impact of every single publication. We incorporated additional variables such as publication type, leading role, co-author count, and source metrics into the UR-Index. However, we recognize that unconscious biases in these variables may disadvantage research from specific groups, and encourage efforts to improve equitable scholarly impact in science and academia.
JOURNAL OF ACADEMIC LIBRARIANSHIP
(2023)
Article
Green & Sustainable Science & Technology
Mohammad G. Zamani, Mohammad Reza Nikoo, Fereshteh Niknazar, Ghazi Al-Rawas, Malik Al-Wardy, Amir H. Gandomi
Summary: Water quality is a major concern in reservoir management due to its negative impact on the environment and human life. The existing literature lacks exploration of the combination of different machine learning algorithms, which has the potential to greatly improve outcomes. This study evaluates the precision of various algorithms and finds that the BMEF model outperforms individual models, particularly in terms of oxidation-reduction potential.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Engineering, Mechanical
Pouria Hajikarimi, Mehrdad Ehsani, Fereidoon Moghadas Nejad, Amir H. Gandomi
Summary: The objective of this study is to create explicit prediction models for the complex shear modulus and phase angle of bitumen mastic using an evolutionary machine learning approach. The results showed that the hybrid machine learning approach can effectively develop precise, meaningful, and simple formulas for calculating these properties of the bitumen mastic.
JOURNAL OF ENGINEERING MECHANICS
(2023)
Article
Environmental Sciences
Masoumeh Zare, Mohammad Reza Nikoo, Banafsheh Nematollahi, Amir H. Gandomi, Raziyeh Farmani
Summary: Groundwater vulnerability mapping is crucial in environmental management due to increasing contamination caused by population growth. This study developed an innovative risk-based multi-objective optimization model using three different models. The results showed that the optimized SI and DRASTICA models improved the correlation for Nitrate and Sulfate contamination, with the highest correlation values of 0.6 and 0.7.
JOURNAL OF ENVIRONMENTAL MANAGEMENT
(2023)
Article
Multidisciplinary Sciences
K. Haritha, S. Shailesh, M. V. Judy, K. S. Ravichandran, Raghunathan Krishankumar, Amir H. Gandomi
Summary: The remarkable advancement in technology has led to an increase in data sizes, particularly in healthcare data, known for its large number of variables and samples. Artificial neural networks (ANN) have proven to be adaptable and effective in various tasks like classification, regression, and function approximation. However, the commonly used Back Propagation learning technique has limitations, especially in the case of Big Data. This paper proposes a Distributed Genetic Algorithm based ANN Learning Algorithm to address the challenges of ANN learning for Big Data. The proposed model shows significantly improved convergence time and accuracy compared to traditional methods, achieving an almost 80% improvement in computational time.
SCIENTIFIC REPORTS
(2023)
Article
Engineering, Geological
Terence Ma, Brigid Cami, Sina Javankhoshdel, Brent Corkum, Nicolas Chan, Amir H. Gandomi
Summary: A novel method is introduced to search for the critical slip surface in a 3D slope by transforming spline surfaces. The proposed method assumes the slip surface to be a nonuniform rational basis spline (NURBS) surface and involves varying the parameters and using a metaheuristic search algorithm. A major advantage of this method is the ability to locally optimize the final spline surface using surface altering optimization methods.
INTERNATIONAL JOURNAL OF GEOMECHANICS
(2023)
Article
Engineering, Civil
Jahir Iqbal Laskar, Mrinal Kanti Sen, Subhrajit Dutta, Amir H. Gandomi, Sujit Tewari
Summary: Resilience refers to the ability of infrastructure systems to absorb hazards and recover quickly. Quantifying resilience requires careful data collection and collaboration with local agencies. In this study, a D-S model was used to quantify the resilience of housing infrastructure in a specific region of India.
SUSTAINABLE AND RESILIENT INFRASTRUCTURE
(2023)
Article
Environmental Sciences
Ali Haddadi, Mohammad Reza Nikoo, Banafsheh Nematollahi, Ghazi Al-Rawas, Malik Al-Wardy, Mehdi Toloo, Amir H. Gandomi
Summary: An optimization model using NSGA-II is developed to design an effective air quality monitoring network (AQMN) considering mutual information and system uncertainties. The BME method generates potential stations, while the TE method maximizes coverage and minimizes station selection probability. Uncertainty analysis is performed using fuzzy degree of membership and NINP. The PROMETHEE approach is used to select the best AQMN properties. The methodology is applied to Los Angeles, Long Beach, and Anaheim in California, USA, resulting in recommendations for the number of stations to monitor CO, NO2, and ozone concentrations.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Construction & Building Technology
T. Q. Amirhossein Davarpanah, Amir R. Masoodi, Amir H. Gandomi
Summary: Recent developments in soft computing have enabled various human activities in civil engineering. Researchers have extensively used evolutionary numerical methods, such as Gene Expression Programming (GEP), to predict mechanical properties of construction materials. In this study, two GEP models were used to anticipate the compressive strength of engineered cementitious composite (ECC) containing fly ash (FA) and polyvinyl alcohol (PVA) fiber. The models were built using experimental results from the literature, with four different input variables and two distribution modes (sorted data distribution and random data distribution). Comparison between experimental results and modeling results showed that both distribution modes achieved similar accuracy (R-square more than 0.9), but the GEP-I (SDD) model was chosen as the best model based on its performance with the validation data set.
CASE STUDIES IN CONSTRUCTION MATERIALS
(2023)
Article
Computer Science, Cybernetics
Sanjiban Sekhar Roy, Akash Roy, Pijush Samui, Mostafa Gandomi, Amir H. Gandomi
Summary: Social media has improved our lives by enabling global interactions and expanding business networks, but it also brings negative impacts such as the rapid spread of hate speech targeting gender, religion, race, and disability, which can have psychological consequences. To address this issue, researchers have proposed hate speech detection models using machine learning and deep learning algorithms. This study introduces a hate speech detection model based on LSTM, using TF-IDF vectorization, and compares its performance with other models. The LSTM model achieved high precision, recall, and F1 score, with an accuracy rate of 97% for detecting hate speech.
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Ahmad Taheri, Keyvan RahimiZadeh, Amin Beheshti, Jan Baumbach, Ravipudi Venkata Rao, Seyedali Mirjalili, Amir H. Gandomi
Summary: In this paper, a novel evolutionary optimization algorithm called Partial Reinforcement Optimizer (PRO) is introduced. The PRO algorithm is based on the psychological theory of partial reinforcement effect (PRE) and is mathematically modeled to solve global optimization problems. Experimental results demonstrate that the PRO algorithm outperforms existing meta-heuristic algorithms in terms of accuracy and robustness.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)