scholarly journals Evaluating Seismic Soil Liquefaction Potential Using Bayesian Belief Network and C4.5 Decision Tree Approaches

2019 ◽  
Vol 9 (20) ◽  
pp. 4226 ◽  
Author(s):  
Mahmood Ahmad ◽  
Xiao-Wei Tang ◽  
Jiang-Nan Qiu ◽  
Feezan Ahmad
Keyword(s):  
Decision Tree ◽  
Domain Knowledge ◽  
Probabilistic Reasoning ◽  
Learning Algorithm ◽  
Bayesian Belief Network ◽  
Soil Liquefaction ◽  
Point Of View ◽  
Liquefaction Potential ◽  
Belief Network ◽  
C4.5 Decision Tree

Liquefaction is considered a damaging phenomenon of earthquakes and a major cause of concern in civil engineering. Therefore, its predictory assessment is an essential task for geotechnical experts. This paper investigates the performance of Bayesian belief network (BBN) and C4.5 decision tree (DT) models to evaluate seismic soil liquefaction potential based on the updated and relatively large cone penetration test (CPT) dataset (which includes 251 case histories), comparing them to a simplified procedure and an evolutionary-based approach. The BBN model was developed using the K2 machine learning algorithm and domain knowledge (DK) with data fusion methodology, while the DT model was created using a C4.5 algorithm. This study shows that the BBN model is preferred over the others for evaluation of seismic soil liquefaction potential. Owing to its overall performance, simplicity in practice, data-driven characteristics, and ability to map interactions between variables, the use of a BBN model in assessing seismic soil liquefaction is quite promising. The results of a sensitivity analysis show that ‘equivalent clean sand penetration resistance’ is the most significant factor affecting liquefaction potential. This study also interprets the probabilistic reasoning of the robust BBN model and most probable explanation (MPE) of seismic soil liquefied sites, based on an engineering point of view.

scholarly journals Probabilistic evaluation of CPT-based seismic soil liquefaction potential: towards the integration of interpretive structural modeling and bayesian belief network

2021 ◽  
Vol 18 (6) ◽  
pp. 9233-9252
Author(s):  
Mahmood Ahmad ◽  
◽  
Feezan Ahmad ◽  
Jiandong Huang ◽  
Muhammad Junaid Iqbal ◽  
...  
Keyword(s):  
Graphical Model ◽  
Influence Factors ◽  
Structural Modeling ◽  
Bayesian Belief Network ◽  
Soil Liquefaction ◽  
Support Vector ◽  
Probabilistic Graphical Model ◽  
Interpretive Structural Modeling ◽  
Liquefaction Potential ◽  
Belief Network

<abstract> <p>This paper proposes a probabilistic graphical model that integrates interpretive structural modeling (ISM) and Bayesian belief network (BBN) approaches to predict cone penetration test (CPT)-based soil liquefaction potential. In this study, an ISM approach was employed to identify relationships between influence factors, whereas BBN approach was used to describe the quantitative strength of their relationships using conditional and marginal probabilities. The proposed model combines major causes, such as soil, seismic and site conditions, of seismic soil liquefaction at once. To demonstrate the application of the propose framework, the paper elaborates on each phase of the BBN framework, which is then validated with historical empirical data. In context of the rate of successful prediction of liquefaction and non-liquefaction events, the proposed probabilistic graphical model is proven to be more effective, compared to logistic regression, support vector machine, random forest and naive Bayes methods. This research also interprets sensitivity analysis and the most probable explanation of seismic soil liquefaction appertaining to engineering perspective.</p> </abstract>

scholarly journals Probabilistic Evaluation of CPT-based Seismic Soil Liquefaction Potential: Towards the Integration of Interpretive Structural Modeling and Bayesian Belief Network

2021 ◽  
Author(s):  
Mahmood Ahmad ◽  
Xiao-Wei Tang ◽  
Feezan Ahmad ◽  
Nima Pirhadi ◽  
Xusheng Wan ◽  
...  
Keyword(s):  
Graphical Model ◽  
Influence Factors ◽  
Structural Modeling ◽  
Bayesian Belief Network ◽  
Soil Liquefaction ◽  
Support Vector ◽  
Probabilistic Graphical Model ◽  
Interpretive Structural Modeling ◽  
Liquefaction Potential ◽  
Belief Network

Abstract This paper proposes a probabilistic graphical model that integrates interpretive structural modeling (ISM) and Bayesian belief network (BBN) approaches to predict CPT-based soil liquefaction potential. In this study, an ISM approach was employed to identify relationships between influence factors, whereas BBN approach was used to describe the quantitative strength of their relationships using conditional and marginal probabilities. The proposed model combines major causes, such as soil, seismic and site conditions, of seismic soil liquefaction at once. To demonstrate the application of the propose framework, the paper elaborates on each phase of the BBN framework, which is then validated with historical empirical data. In context of the rate of successful prediction of liquefaction and non-liquefaction events, the proposed probabilistic graphical model is proven to be more effective, compared to logistic regression, support vector machine, random forest and naïve Bayes methods. This research also interprets sensitivity analysis and the most probable explanation of seismic soil liquefaction appertaining to engineering perspective.

IDENTIFICATION OF NAMES AND ACTIONS OF PRINCIPAL OBJECTS IN TV PROGRAM SEGMENTS USING CLOSED CAPTIONS

2008 ◽  
Vol 02 (02) ◽  
pp. 191-206
Author(s):  
KIKUKA MIURA ◽  
ICHIRO YAMADA ◽  
HIDEKI SUMIYOSHI ◽  
NOBUYUKI YAGI
Keyword(s):  
Decision Tree ◽  
Learning Algorithm ◽  
Video Object ◽  
Video Clips ◽  
Video Objects ◽  
Tv Program ◽  
C4.5 Decision Tree ◽  
Video Shot ◽  
Closed Captions ◽  
Multimedia Encyclopedia

This paper proposes a method for automatically extracting principal video objects that appear in TV program segments and their actions using linguistic analysis of closed captions. We focus on features based on the text style of the closed captions by using Quinlan's C4.5 decision-tree learning algorithm. We extract a noun describing a video object and a verb describing an action for each video shot. To show the effectiveness of the method, we conducted experiments on the extraction of video segments in which animals appear and perform actions in twenty episodes of a Nature program. We obtained F-values of 0.609 on the extraction of video segments in which animals appear and 0.699 on extracting the action of "eating." We applied our method to a further 20 episodes, and generated a multimedia encyclopedia of animals. This provided a total of 387 video clips of 105 kinds of animals and 261 video clips of 56 kinds of actions.

scholarly journals Decision Tree Approach for Soil Liquefaction Assessment

2013 ◽  
Vol 2013 ◽  
pp. 1-8 ◽  
Author(s):  
Amir H. Gandomi ◽  
Mark M. Fridline ◽  
David A. Roke
Keyword(s):  
Logistic Regression ◽  
Decision Tree ◽  
Soil Properties ◽  
Decision Rules ◽  
Soil Liquefaction ◽  
Point Of View ◽  
Seismic Parameters ◽  
Points Of View ◽  
Liquefaction Assessment ◽  
Tree Approach

In the current study, the performances of some decision tree (DT) techniques are evaluated for postearthquake soil liquefaction assessment. A database containing 620 records of seismic parameters and soil properties is used in this study. Three decision tree techniques are used here in two different ways, considering statistical and engineering points of view, to develop decision rules. The DT results are compared to the logistic regression (LR) model. The results of this study indicate that the DTs not only successfully predict liquefaction but they can also outperform the LR model. The best DT models are interpreted and evaluated based on an engineering point of view.

Identifying Qualified Auditors' Opinions: A Data Mining Approach

2007 ◽  
Vol 4 (1) ◽  
pp. 183-197 ◽  
Author(s):  
Efstathios Kirkos ◽  
Charalambos Spathis ◽  
Alexandros Nanopoulos ◽  
Yannis Manolopoulos
Keyword(s):  
Neural Network ◽  
Data Mining ◽  
Decision Tree ◽  
Multilayer Perceptron ◽  
Bayesian Belief Network ◽  
Decision Makers ◽  
External Auditors ◽  
Data Mining Approach ◽  
C4.5 Decision Tree ◽  
Mining Methods

Data Mining methods can be used in order to facilitate auditors to issue their opinions. Numerous of these methods have not yet been tested on the purpose of discriminating cases of qualified opinions. In this study, we employ three Data Mining classification techniques to develop models capable of identifying qualified auditors' reports. The techniques used are C4.5 Decision Tree, Multilayer Perceptron Neural Network, and Bayesian Belief Network. The sample contains 450 publicly listed, nonfinancial U.K. and Irish firms. The input vector is composed of one qualitative and several quantitative variables. The three developed models are compared in terms of their performance. Additionally, variables that are associated with qualified reports and can be used as indicators are also revealed. The results of this study can be useful to internal and external auditors and company decision-makers.

scholarly journals Utilizing the Genetic Algorithm to Pruning the C4.5 Decision Tree Algorithm

2021 ◽  
Vol 9 (1) ◽  
Author(s):  
Maad M. Mijwil ◽  
Rana A. Abttan
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Decision Tree ◽  
Learning Algorithm ◽  
Machine Learning Algorithms ◽  
Continuous Data ◽  
Decision Tree Algorithm ◽  
Data Set ◽  
Confidence Factor ◽  
C4.5 Decision Tree

A decision tree (DTs) is one of the most popular machine learning algorithms that divide data repeatedly to form groups or classes. It is a supervised learning algorithm that can be used on discrete or continuous data for classification or regression. The most traditional classifier in this algorithm is the C4.5 decision tree, which is the point of this research. This classifier has the advantage of building a vast data set and does not stop until it reaches the desired goal. The problem with this classifier is that there are unnecessary nodes and branches leading to overfitting. This overfitting can negatively affect the classification process. In this context, the authors suggest utilizing a genetic algorithm to prune the effect of overfitting. This dataset study consists of four datasets: IRIS, Car Evaluation, GLASS, and WINE collected from UC Irvine (UCI) machine learning repository. The experimental results have confirmed the effectiveness of the genetic algorithm in pruning the effect of overfitting on the four datasets and optimizing confidence factor (CF) of the C4.5 decision tree. The proposed method has reached about 92% accuracy in this work.

scholarly journals Improvisasi Teknik Oversampling MWMOTE Untuk Penanganan Data Tidak Seimbang

2021 ◽  
Vol 5 (2) ◽  
pp. 398
Author(s):  
Pramana Yoga Saputra ◽  
Moch Zawaruddin Abdullah ◽  
Annisa Puspa Kirana
Keyword(s):  
Machine Learning ◽  
Decision Tree ◽  
Learning Algorithm ◽  
Synthetic Data ◽  
Classification Performance ◽  
Machine Learning Algorithm ◽  
Minority Class ◽  
Imbalance Data ◽  
Decision Tree Classification ◽  
C4.5 Decision Tree

Imbalance data is a condition which there is a distinction in the quantity of data that results withinside the majority class (classes with very many members) and minority class (classes with very few members). It can complicate the classification process since the machine learning algorithm method is designed to classify already balanced data. The oversampling process technique is used to resolve data imbalance by applying synthetic data to the minority class in such a manner that it has the same volume of data as the majority class. MWMOTE is an oversampling technique that generates synthetic data based on members of the minority class clusters that are close to the majority class. This approach is capable of generating synthetic data well. The resulting synthesis data remains in the nearby majority region and too dense on the border of the cluster. It is hence permitting the resulting synthetic data to go into the majority class classification. This study is objectives to improve the process of generating synthetic data on MWMOTE so that the resulting data is extensively dispensed withinside the minority class. The outcomes of the test show that the proposed method is capable of enhancing the classification performance for KNN and C4.5 Decision Tree classification sequentially by 0.46% and 0.96% compared to MWMOTE

Sign in / Sign up

Export Citation Format

Share Document