scholarly journals Load-Settlement Response of A Footing Over Buried Conduit in A Sloping Terrain: A Numerical Experiment-Based Artificial Intelligent Approach

2021 ◽  
Author(s):  
Muhammad Umer Arif Khan ◽  
Sanjay Kumar Shukla ◽  
Muhammad Nouman Amjad Raja
Keyword(s):  
Machine Learning ◽  
Applied Load ◽  
Slope Angle ◽  
Unit Weight ◽  
Burial Depth ◽  
Multi Layer Perceptron ◽  
Soil Slope ◽  
Percentage Difference ◽  
Constrained Modulus ◽  
Sloping Terrain

Abstract Settlement estimation of a footing located over a buried conduit in a sloping terrain is a challenging task for practicing civil/geotechnical engineers. In the recent past, the advent of machine learning technology has made many traditional approaches antiquated. This paper investigates the viability, development, implementation, and comprehensive comparison of five artificial intelligence-based machine learning models, namely, multi-layer perceptron (MLP), Gaussian processes regression (GPR), lazy K-Star (LKS), decision table (DT), and random forest (RF) to estimate the settlement of footing located over a buried conduit within a soil slope. The pertaining dataset of 3600 observations was obtained by conducting large-scale numerical simulations via the finite element modelling framework. After executing the feature selection technique that is correlation-based subset selection, the applied load, total unit weight of soil, constrained modulus of soil, slope angle ratio, hoop stiffness of conduit, bending stiffness of conduit, burial depth of conduit, and crest distance of footing were utilized as the influence parameters for estimating and forecasting the settlement. The predictive strength and accuracy of all models mentioned supra were evaluated using several well-established statistical indices such as Pearson’s correlation coefficient (r), root mean square error (RMSE), Nash-Sutcliffe efficiency (NSE), scatter index (SI), and relative percentage difference (RPD). The results showed that among all the models employed in this study, the multi-layer perceptron model has shown better results with r, RMSE, NSE, SI, and RPD values of (0.977, 0.298, 0.937, 0.31, and 4.31) and (0.974, 0.323, 0.928, 0.44 and 3.75) for training and testing dataset, respectively. The sensitivity analysis revealed that all the selected parameters play an important role in determining the output value. However, the applied load, constrained modulus, unit weight, slope angle ratio, hoop stiffness have the highest strength with the relative importance of 18.4%, 16.3% and 15.3%, 13.8%, 11.4%, respectively. Finally, the model was translated into a functional relationship for easy implementation and can prove useful for practitioners and researchers in predicting the settlement of a footing located over a buried conduit in a sloping terrain.

scholarly journals A comparative study of supervised machine learning approaches for slope failure production

2021 ◽  
Vol 325 ◽  
pp. 01001
Author(s):  
Ashanira Mat Deris ◽  
Badariah Solemon ◽  
Rohayu Che Omar
Keyword(s):  
Machine Learning ◽  
Slope Failure ◽  
Pressure Ratio ◽  
Slope Angle ◽  
Friction Angle ◽  
Supervised Machine Learning ◽  
Unit Weight ◽  
Learning Approaches ◽  
Ann Model ◽  
Grey Relational

Over the years, machine learning, which is a well-known method in artificial intelligent (AI) field has become a new trend and extensively applied in various applications to solve a realworld problem. This includes slope failure prediction. Slope failure is among the major geo-hazard phenomenon which gives the significant impact to the environment or human beings. The estimation of slope failure in slope stability analysis is a complex geotechnical engineering problem that involves many factors such as geology, topography, atmosphere, and land occupancy. Generally, slope failure can be estimated based on traditional methods such as limit equilibrium method (LEM) or finite equilibrium method (FEM). However, beside the methods are quite tedious and time consuming, LEM and FEM have their own limitations and do not guarantee the effectiveness when dealing against problem with various geometry or assumptions. Hence, the introduction of machine learning approaches provides the alternative tools for the prediction of slope failure. Current study applies two mostly used supervised machine learning approaches, support vector machine (SVM) and decision tree (DT) to predict the slope failure based on classification problem using historical cases. 148 of slope cases with six input parameters namely “unit weight, cohesion, internal friction angle, slope angle, slope height and pore pressure ratio and factor of safety (FOS) as an output parameter”, was collected from multinational dataset that has been extracted from the literature. For development of the prediction model, the slope data was divided into 80% training data and 20% testing data. The prediction result from testing data was validated based on statistical analysis. The result shows that SVM model has outperformed DT model by giving the prediction accuracy of 97%. ith the advent of technology and the introduction of computational intelligent methods, the prediction of slope failure using the machine learning (ML) approach is rapidly growing for the past few decades. This study employs an “artificial neural network” (ANN) to predict the slope failures based on historical circular slope cases. Using the feed-forward backpropagation algorithm with a multilayer perceptron network, ANN is a powerful ML method capable of predicting the complex model of slope cases. However, the prediction result of ANN can be improved by integrating the statistical analysis method, namely grey relational analysis (GRA), to the ANN model. GRA is capable of identifying the influencing factors of the input data based on the correlation level of the reference sequence and comparability sequence of the dataset. This statistical machine learning model can analyze the slope data and eliminate the unnecessary data samples to improve the prediction performance. Grey relational analysis-artificial neural network (GRANN) prediction model was developed based on six slope factors: unit weight, friction angle, cohesion, pore pressure ratio, slope height, and slope angle, with the factor of safety (FOS) as the output factor. The prediction results were analyzed based on accuracy percentage and receiver operating characteristic (ROC) values. It shows that the GRANN model has outperformed the ANN model by giving 99% accuracy and 0.999 ROC value, compared with 91% and 0.929.

scholarly journals The Classification of Medicinal Plant Leaves Based on Multispectral and Texture Feature Using Machine Learning Approach

Agronomy ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. 263
Author(s):  
Samreen Naeem ◽  
Aqib Ali ◽  
Christophe Chesneau ◽  
Muhammad H. Tahir ◽  
Farrukh Jamal ◽  
...  
Keyword(s):  
Machine Learning ◽  
Medicinal Plant ◽  
Texture Feature ◽  
Stevia Rebaudiana ◽  
Ocimum Sanctum ◽  
Multi Layer Perceptron ◽  
Plant Leaves ◽  
Chi Square ◽  
Lemon Balm

This study proposes the machine learning based classification of medical plant leaves. The total six varieties of medicinal plant leaves-based dataset are collected from the Department of Agriculture, The Islamia University of Bahawalpur, Pakistan. These plants are commonly named in English as (herbal) Tulsi, Peppermint, Bael, Lemon balm, Catnip, and Stevia and scientifically named in Latin as Ocimum sanctum, Mentha balsamea, Aegle marmelos, Melissa officinalis, Nepeta cataria, and Stevia rebaudiana, respectively. The multispectral and digital image dataset are collected via a computer vision laboratory setup. For the preprocessing step, we crop the region of the leaf and transform it into a gray level format. Secondly, we perform a seed intensity-based edge/line detection utilizing Sobel filter and draw five regions of observations. A total of 65 fused features dataset is extracted, being a combination of texture, run-length matrix, and multi-spectral features. For the feature optimization process, we employ a chi-square feature selection approach and select 14 optimized features. Finally, five machine learning classifiers named as a multi-layer perceptron, logit-boost, bagging, random forest, and simple logistic are deployed on an optimized medicinal plant leaves dataset, and it is observed that the multi-layer perceptron classifier shows a relatively promising accuracy of 99.01% as compared to the competition. The distinct classification accuracy by the multi-layer perceptron classifier on six medicinal plant leaves are 99.10% for Tulsi, 99.80% for Peppermint, 98.40% for Bael, 99.90% for Lemon balm, 98.40% for Catnip, and 99.20% for Stevia.

scholarly journals Classifying Lensed Gravitational Waves in the Geometrical Optics Limit with Machine Learning

2019 ◽  
Vol 16 (2) ◽  
pp. 5-16
Author(s):  
Amit Singh ◽  
Ivan Li ◽  
Otto Hannuksela ◽  
Tjonnie Li ◽  
Kyungmin Kim
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Gravitational Wave ◽  
Gravitational Waves ◽  
Geometrical Optics ◽  
Supervised Machine Learning ◽  
Support Vector ◽  
Multi Layer Perceptron ◽  
Machine Learning Classifiers ◽  
Learning Classifiers

Gravitational waves are theorized to be gravitationally lensed when they propagate near massive objects. Such lensing effects cause potentially detectable repeated gravitational wave patterns in ground- and space-based gravitational wave detectors. These effects are difficult to discriminate when the lens is small and the repeated patterns superpose. Traditionally, matched filtering techniques are used to identify gravitational-wave signals, but we instead aim to utilize machine learning techniques to achieve this. In this work, we implement supervised machine learning classifiers (support vector machine, random forest, multi-layer perceptron) to discriminate such lensing patterns in gravitational wave data. We train classifiers with spectrograms of both lensed and unlensed waves using both point-mass and singular isothermal sphere lens models. As the result, classifiers return F1 scores ranging from 0:852 to 0:996, with precisions from 0:917 to 0:992 and recalls ranging from 0:796 to 1:000 depending on the type of classifier and lensing model used. This supports the idea that machine learning classifiers are able to correctly determine lensed gravitational wave signals. This also suggests that in the future, machine learning classifiers may be used as a possible alternative to identify lensed gravitational wave events and to allow us to study gravitational wave sources and massive astronomical objects through further analysis. KEYWORDS: Gravitational Waves; Gravitational Lensing; Geometrical Optics; Machine Learning; Classification; Support Vector Machine; Random Tree Forest; Multi-layer Perceptron

scholarly journals Erosion Failure of a Soil Slope by Heavy Rain: Laboratory Investigation and Modified GA Model of Soil Slope Failure

2019 ◽  
Vol 16 (6) ◽  
pp. 1075 ◽  
Author(s):  
Xiaofei Jing ◽  
Yulong Chen ◽  
Changshu Pan ◽  
Tianwei Yin ◽  
Wensong Wang ◽  
...  
Keyword(s):  
Laboratory Investigation ◽  
Slope Failure ◽  
Slope Angle ◽  
Heavy Rain ◽  
Annual Rainfall ◽  
Soil Slope ◽  
Saturated Zone ◽  
Wetting Front ◽  
Rainfall Condition ◽  
The Impact

Rainfall has been identified as one of the main causes for slope failures in areas where high annual rainfall is experienced. The slope angle is important for its stability during rainfall. This paper aimed to determine the impact of the angle of soil slope on the migration of wetting front in rainfall. The results proved that under the same rainfall condition, more runoff was generated with the increase of slope angle, which resulted in more serious erosion of the soil and the ascent of wetting front. A modified Green-Ampt (GA) model of wetting front was also proposed considering the seepage in the saturated zone and the slope angle. These findings will provide insights into the rainfall-induced failure of soil slopes in terms of angle.

scholarly journals Mapping the susceptibility of rain-triggered lahars at Vulcano island (Italy) combining field characterization, geotechnical analysis, and numerical modelling

2019 ◽  
Vol 19 (11) ◽  
pp. 2421-2449 ◽  
Author(s):  
Valérie Baumann ◽  
Costanza Bonadonna ◽  
Sabatino Cuomo ◽  
Mariagiovanna Moscariello ◽  
Sebastien Biass ◽  
...  
Keyword(s):  
Hydraulic Conductivity ◽  
Slope Angle ◽  
Field Measurements ◽  
Friction Angle ◽  
Unit Weight ◽  
Residual Water ◽  
Probabilistic Modelling ◽  
Cascading Effect ◽  
Geotechnical Tests ◽  
Tephra Fallout

Abstract. The characterization of triggering dynamics and remobilized volumes is crucial to the assessment of associated lahar hazards. We propose an innovative treatment of the cascading effect between tephra fallout and lahar hazards based on probabilistic modelling that also accounts for a detailed description of source sediments. As an example, we have estimated the volumes of tephra fallout deposit that could be remobilized by rainfall-triggered lahars in association with two eruptive scenarios that have characterized the activity of the La Fossa cone (Vulcano, Italy) in the last 1000 years: a long-lasting Vulcanian cycle and a subplinian eruption. The spatial distribution and volume of deposits that could potentially trigger lahars were analysed based on a combination of tephra fallout probabilistic modelling (with TEPHRA2), slope-stability modelling (with TRIGRS), field observations, and geotechnical tests. Model input data were obtained from both geotechnical tests and field measurements (e.g. hydraulic conductivity, friction angle, cohesion, total unit weight of the soil, and saturated and residual water content). TRIGRS simulations show how shallow landsliding is an effective process for eroding pyroclastic deposits on Vulcano. Nonetheless, the remobilized volumes and the deposit thickness threshold for lahar initiation strongly depend on slope angle, rainfall intensity, grain size, friction angle, hydraulic conductivity, and the cohesion of the source deposit.

scholarly journals MODELAGEM TEMPORAL DINÂMICA DO USO E OCUPAÇÃO DO SOLO BASEADO EM SIG PARA A BACIA DO RIO TAPACURÁ (PE)

2018 ◽  
Vol 37 (1) ◽  
pp. 193-210 ◽  
Author(s):  
Ana Paula Campos XAVIER ◽  
Richarde Marques da SILVA
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Machine Learning Algorithm ◽  
Multi Layer Perceptron ◽  
Land Change ◽  
Land Change Modeler

Este estudo teve por objetivo simular cenários de uso e ocupação do solo para t4 (2035), tendo como base as mudanças no uso do solo ocorridas em t1 (1989), t2 (2007) e t3 (2015) para a bacia do Rio Tapacurá, localizada no Estado de Pernambuco. Foi realizada a previsão do uso do solo para t3 (2015), usando três métodos: (a) Rede Neural Multi-Layer Perceptron (RNMLP), (b) Similarity-Weighted Instance-Based Machine Learning Algorithm (SimWeight) e (c) Regressão Logística (RL) e para a metodologia que mostrou melhor desempenho, foi realizada a predição dos cenários futuros para t4 (2035). Os cenários futuros simulados foram: (a) Cenário 1: de continuidade das transições e (b) Cenário 2: de continuidade das transições e intensificação da classe pecuária e expansão da área urbana, usando o módulo Land Change Modeler (LCM) do Idrisi TerrSet e imagens da cobertura do solo. Os resultados da previsão do uso do solo para 2015 mostraram que o melhor desempenho foi obtido usando o método RNMLP com treinamento de 84,22% e 10.000 iterações. A simulação dos cenários futuros para t4 mostrou intensificação das transições observadas nos três anos analisados, com previsão para expansão de cerca de 3% da classe pecuária para os dois cenários simulados.

scholarly journals Prediction of Collapsibility of Loess of Construction Sites in Xining Based on Machine Learning Methods

2021 ◽  
Author(s):  
Qifei Zhao ◽  
Xiaojun Li ◽  
Yunning Cao ◽  
Zhikun Li ◽  
Jixin Fan
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Training Data ◽  
Support Vector ◽  
Engineering Practice ◽  
Burial Depth ◽  
Learning Methods ◽  
Data Set ◽  
Machine Learning Methods ◽  
North East

Abstract Collapsibility of loess is a significant factor affecting engineering construction in loess area, and testing the collapsibility of loess is costly. In this study, A total of 4,256 loess samples are collected from the north, east, west and middle regions of Xining. 70% of the samples are used to generate training data set, and the rest are used to generate verification data set, so as to construct and validate the machine learning models. The most important six factors are selected from thirteen factors by using Grey Relational analysis and multicollinearity analysis: burial depth、water content、specific gravity of soil particles、void rate、geostatic stress and plasticity limit. In order to predict the collapsibility of loess, four machine learning methods: Support Vector Machine (SVM), Random Subspace Based Support Vector Machine (RSSVM), Random Forest (RF) and Naïve Bayes Tree (NBTree), are studied and compared. The receiver operating characteristic (ROC) curve indicators, standard error (SD) and 95% confidence interval (CI) are used to verify and compare the models in different research areas. The results show that: RF model is the most efficient in predicting the collapsibility of loess in Xining, and its AUC average is above 80%, which can be used in engineering practice.

scholarly journals Sentiment Perception in Articulation

2021 ◽  
Vol 9 (VII) ◽  
pp. 2803-2812
Author(s):  
Ganesh NagaVenkataSai Mohan Kancherla
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Neural Networks ◽  
Daily Life ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Multi Layer Perceptron ◽  
Working Model ◽  
Initial Stage ◽  
Perception System

Emotion is quite prevalent aspect in daily life. Every individual has a inequity levels of anxiety in the finding the concealed emotion present in a speech or talk. So we had decided to procreate a new methodology in which every emotion which is present in a speech can be detected. The system we developed can detect any emotion with a great extent of efficiency. Any type of emotion will be detected using Machine learning algorithms in a effective way. We will utilize Multi-Layer Perceptron in the initial stage and then we will compare this with working model of Convolution Neural Networks. We want to develop an Artificial Intelligence perception system which leads to detection of emotion in any articulation

scholarly journals Deterministic and Probabilistic Analysis of Dasdhunga Soil Slope along Narayangarh-Mugling Road Section

2021 ◽  
Vol 6 ◽  
pp. 187-198
Author(s):  
Saurav Shrestha ◽  
Indra Prasad Acharya ◽  
Ranjan Kumar Dahal
Keyword(s):  
Limit Equilibrium ◽  
Water Pressure ◽  
Slope Angle ◽  
Friction Angle ◽  
Probability Of Failure ◽  
Soil Slope ◽  
Extrinsic Factors ◽  
Stability Of Slopes ◽  
Road Section ◽  
Truncated Normal

Instability of slopes is usually governed by a combination of intrinsic and extrinsic factors. The inherent variability of parameters make the problem probabilistic rather than a deterministic one. This research deals with evaluation of stability of slopes with the calculation of the factor of safety of Dasdhunga soil slope along Narayangarh- Mugling road section under different rainfall conditions through the use of coupled finite element and limit equilibrium method in GeoStudio and the determination of probability of failure by sliding, modeled as infinite slopes by using Monte Carlo simulation in R-Studio. Mean, standard deviation, minimum and maximum values of the parameters like- friction angle, cohesion and unit weight were computed from eight samples of the slope. The pore water pressure developed and its corresponding statistical data for different rainfall conditions were computed from FEM based SEEP/W simulation. The above parameters are assumed to follow truncated normal probability distribution function and the geometric parameters like height and slope angle are regarded as constant parameters. It was observed that the safety factors for theslopeis low in high intensity-low duration rainfalls and the probability of failure is high. The tendency to fail increases as the return period of rainfall increases and viceversa. Sensitivity analysis performed in both deterministic and probabilistic methods showed that friction angle is the most sensitive.

Sign in / Sign up

Export Citation Format

Share Document