An Improved Decision Tree Classification Approach for Expectation of Cardiotocogram

In India, the banks have a formidable edge in maintaining their customer retention ratio for past few decades. Downfall makes the private banks to reduce their operations and the nationalised banks merge with other banks. The researchers have used the traditional and ensemble algorithms with relevant feature engineering techniques to better classify the customers. The proposed algorithm uses a Meta classifier instead of an ensemble algorithm with an adaptive genetic algorithm for feature selection. Churn prediction is the number of customers who wants to terminate their services in the banking sector. The model considers twelve attributes like credit score, geography, gender, age, etc, to predict customer churn. The project consists of five modules as follows. First is the pre-processing module that identifies the missing data and fills the value with mean and mode. Second is the data transformation module where, the categorical data is converted into numerical data using label encoding to fasten the computations. The converted numerical data is normalized using the standard scalar technique. The feature selection module identifies the essential attributes using DragonFly and Firefly (Hybrid Fly) algorithms. The classification module designs an intelligent Meta learner, which combines the Ensemble Algorithm Extreme Gradient Boosting (XGBOOST) with base classifiers as "Extra Tree Classifier" and "Logistic Regression" to predict the churn customers.

show abstract

“…Dr A.P. Jagadeesan Logistic Regression + Decision Tree [5] The model does not care about pre-processing step.…”

Section: S Neelakandanmentioning

confidence: 99%

Adaptive XGBOOST Hyper Tuned Meta Classifier for Prediction of Churn Customers

Srikanth¹,

Papineni²,

Sridevi³

et al. 2022

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

show abstract

“…In order to analyze the classification performance of the model used in this study on the evaluation data, the selected comparison models are mainly SVM [ 19 ], k-nearest neighbor (KNN) [ 20 ], logistic regression (LR) [ 21 ], and decision tree (DT) [ 22 ]. The experimental results of each model on the Restaurant dataset are shown in Table 2 and Figure 2 .…”

Section: User Experience Sentiment Classification Based On Usvmmentioning

confidence: 99%

A Novel Sentiment Analysis Model of Museum User Experience Evaluation Data Based on Unbalanced Data Analysis Technology

Chen

Xiao

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the development of virtual reality and digital reconstruction technology, digital museums have been widely promoted in various cities. Digital museums offer new ways to display and disseminate cultural heritage. It allows remote users to autonomously browse displays in a physical museum environment in a digital space. It is also possible to reproduce the lost heritage through digital reconstruction and restoration, so as to digitally present tangible cultural heritage and intangible cultural heritage to the public. However, the user’s experience of using digital museums has not been fully and deeply studied at present. In this study, the user’s experience evaluation data of digital museum are classified and processed, so as to analyze the user’s emotional trend towards the museum. Considering that the user’s evaluation data are unbalanced data, this study uses an unbalanced support vector machine (USVM) in the classification of user evaluation data. The main idea of this method is that the boundary of the support vector is continuously shifted to the majority class by repeatedly oversampling some support vectors until the real support vector samples are found. The experimental results show that the classification obtained by the used USVM has a good practical reference value. Based on the classification results of the evaluation data, the construction of the digital museum can be further guided and maintained, thereby improving the user experience satisfaction of the museum. This research will make an important contribution to the construction of the museum and the inheritance of culture.

show abstract

“…Linear regression (LR), Naive Bayes (NB), Support vector machine (SVM)radial basis function, SVM Linear, and Classification trees [15] were among the classifiers being used to predict risk using FHR. The outcomes suggest that the method should made available in clinics to predict foetuses with intrauterine growth limitation [16].…”

Section: Introductionmentioning

confidence: 99%

Stack Ensemble Algorithm for Cardiotocography Based Foetal Health Risk Classification

Nagabotu,

Namburu

2024

RIA

View full text Add to dashboard Cite

Obstetricians utilize cardiotocography (CTG) to assess the fetal heart and lungs during pregnancy. It can help determine if the foetus is healthy, in doubt, or suffering from disease by providing data on the fetal heart rate and uterine breathing. The analysis of CTG data has typically made use of machine learning (ML) techniques such as support vector machines and decision trees to forecast fetal health and enhance the detection procedure. Fetal heart rate and uterine contraction timing were recorded by CTG. Monitoring fetal health and ensuring normal fetal growth and development throughout pregnancy rely heavily on CTG intelligent categorization. Pregnancies with a higher risk of problems are the most common cases in which CTG is used to evaluate the health of the fetus. ML algorithms are utilized to evaluate state of the foetal health based on CTG-obtained factors. Compared to ML techniques, ensemble models have been shown to increase detection speed and effectiveness. Ensemble modeling refers to the practice of combining the scores or distributions from multiple related but distinct analytical models. In order to predict foetal health, ensemble models such as Boosting, AdaBoost, Extreme Gradient Boosting, Light gradient boost method (LightGBM), and stack models were used in the paper. When the outcomes are compared, the proposed stack model using logistic regression, decision tree, random forest and LightGBM proved to obtain the best performance with 96.71% success rate. The proposed methodology, which can be used to classify foetal health based on Fetal Heart Rate (FHR) data, is more efficient and superior to existing machine learning models, which have already been taken into consideration.

show abstract

An Improved Decision Tree Classification Approach for Expectation of Cardiotocogram

Cited by 4 publications

References 6 publications

Adaptive XGBOOST Hyper Tuned Meta Classifier for Prediction of Churn Customers

Adaptive XGBOOST Hyper Tuned Meta Classifier for Prediction of Churn Customers

A Novel Sentiment Analysis Model of Museum User Experience Evaluation Data Based on Unbalanced Data Analysis Technology

Stack Ensemble Algorithm for Cardiotocography Based Foetal Health Risk Classification

Contact Info

Product

Resources

About