Decision Tree Classification Algorithm Research Articles

Potholes Detection in Doppler Radar Signal’s Power Spectral Density using Decision Tree

Potholes are defects on the surface of roads, streets, or pavements brought on by depressions or holes, which are hazardous for vehicles and pedestrians, whether small divots or huge craters. Various methods have been explored to improve the accuracy of potholes detection. Existing approaches have advantages and disadvantages. This paper presents the proposed method of pothole detection utilising Doppler Radar signal's Power Spectrum Density (PSD) together with the Decision Tree classification algorithm. While continuous waveform (CW) radar is able to identify moving targets, it cannot localise the exact depth of the reflector, which is the prominent characteristic of potholes. In addition, the target's reflected signal is likely to be masked by nearby harmonics. Since the radar is moving despite the target of interest, mounting it on a moving vehicle offers a different perspective. This paper explores the potential of Doppler radar's signal for pothole detection while comparing two Machine Learning (ML) techniques. A commercially over-the-shelf (COTS) K-LC2 Doppler radar was employed to acquire pothole and non-pothole raw datasets. Doppler signal was hardly distinguished between pothole and non-pothole, either in the time or frequency domain. Hence, Doppler signals were converted to power spectral density (PSD), and PSD's features were extracted. Extracted features were applied with the coarse Decision Tree (DT) and K-Nearest Neighbours (KNN) classification algorithms. The result exhibits a better accuracy of 91.2% for 80:20 distribution by using the Decision Tree.

Development of decision tree classification algorithms in predicting mortality of COVID-19 patients

IntroductionThe accurate prediction of COVID-19 mortality risk, considering influencing factors, is crucial in guiding effective public policies to alleviate the strain on the healthcare system. As such, this study aimed to assess the efficacy of decision tree algorithms (CART, C5.0, and CHAID) in predicting COVID-19 mortality risk and compare their performance with that of the logistic model.MethodsThis retrospective cohort study examined 5080 cases of COVID-19 in Babol, a city in northern Iran, who tested positive for the virus via PCR from March 2020 to March 2022. In order to check the validity of the findings, the data was randomly divided into an 80% training set and a 20% testing set. The prediction models, such as Logistic regression models and decision tree algorithms, were trained on the 80% training data and tested on the 20% testing data. The accuracy of these methods for the test samples was assessed using measures like ROC curve, sensitivity, specificity, and AUC.ResultsThe findings revealed that the mortality rate for COVID-19 patients who were admitted to hospitals was 7.7%. Through cross validation, it was determined that the CHAID algorithm outperformed other decision tree and logistic regression algorithms in specificity, and precision but not sensitivity in predicting the risk of COVID-19 mortality. The CHAID algorithm demonstrated a specificity, precision, accuracy, and F-score of 0.98, 0.70, 0.95, and 0.52 respectively. All models indicated that factors such as ICU hospitalization, intubation, age, kidney disease, BUN, CRP, WBC, NLR, O2 sat, and hemoglobin were among the factors that influenced the mortality rate of COVID-19 patients.ConclusionsThe CART and C5.0 models had outperformed in sensitivity but CHAID demonstrates a better performance compared to other decision tree algorithms in specificity, precision, accuracy and shows a slight improvement over the logistic regression method in predicting the risk of COVID-19 mortality in the population under study.

Research on Adaptive Control Systems for Building Shading Based on Decision Tree and Random Forest Classification Algorithms

Dynamic shading systems for buildings, due to their variable mechanisms and high adaptability, have the potential to reduce energy consumption in buildings significantly. However, the performance of dynamic shading is largely influenced by the control system employed. This study aims to explore an adaptive control method for building shading based on decision tree and random forest classification algorithms (machine learning), with the objective of minimizing energy demands related to lighting and cooling as much as possible. The adaptive control system model may independently modify the location of building shading in response to input environmental conditions, thereby achieving energy savings for both lighting and cooling. According to the findings, the automated control system model may reduce building energy consumption by 38% overall, which is close to the ideal level of energy conservation.

Developmental and Validation of Machine Learning Model for Prediction Complication after Cervical Spine Metastases Surgery.

This is a retrospective cohort study utilizing machine learning to predict postoperative complications in cervical spine metastases surgery. The main objective is to develop a machine learning model that accurately predicts complications following cervical spine metastases surgery. Cervical spine metastases surgery can enhance quality of life but carries a risk of complications influenced by various factors. Existing scoring systems may not include all predictive factors. Machine learning offers the potential for a more accurate predictive model by analyzing a broader range of variables. Data from January 2012 to December 2020 were retrospectively collected from medical databases. Predictive models were developed using Gradient Boosting, Logistic Regression, and Decision Tree Classifier algorithms. Variables included patient demographics, disease characteristics, and laboratory investigations. SMOTE was used to balance the dataset, and the models were assessed using AUC, F1-score, precision, recall, and SHAP values. The study included 72 patients, with a 29.17% postoperative complication rate. The Gradient Boosting model had the best performance with an AUC of 0.94, indicating excellent predictive capability. Albumin level, platelet count, and tumor histology were identified as top predictors of complications. The Gradient Boosting machine learning model showed superior performance in predicting postoperative complications in cervical spine metastases surgery. With continuous data updating and model training, machine learning can become a vital tool in clinical decision-making, potentially improving patient outcomes. Level III.

Research on the application of Bagging W-KNN algorithm in alloy steel identification with PXRF analyzer

In response to the inadequate alloy steel identification capability and intelligent recognition of domestic portable X-ray fluorescence analyzers, as well as the impact of existing classification algorithms due to factors such as imbalanced data distribution, this paper proposes the Bagging W-KNN intelligent identification algorithm for alloy steel grade. This method is based on the K-nearest neighbor classification algorithm, employs the Chi-Square statistical method, Bagging ensemble algorithm, introduces the Gini index from the decision tree classification algorithm, and utilizes the Gaussian function probability estimation method. Comparative experiments with four typical algorithms—Decision Tree, KNN, SVM, and Naive Bayes—demonstrate that the proposed algorithm achieves accuracy, precision, recall, and F1 values of 97.01%, 97.30%, 96.69%, and 96.18% respectively, significantly outperforming the other four algorithms and improving prediction accuracy.

P‐236: Late‐News Poster: Hard defect detection and classification for display panel products

Hard defect of display panel such as crack or chipping is one of the most critical defects that have fatal impacts on the product. Conventional deep‐learning‐based methods have difficulties in equipment control in practical point of view due to the vastness of training data and numerous parameters. Consequently, more simple and robust machine‐learning models jointly with traditional image processing algorithms with small number of parameters are increasingly required for the maintenance of inspection equipment. To resolve the issue, we proposed a novel image processing and decision tree classification algorithm that can be operated using smaller number of parameters than deep‐learning method. Firstly, panel image is fed into proposed image processing algorithm and converted into feature map to highlight the hard defect. After binary thresholding of the image, remaining pixels are specified as bounding box. Subsequently, features are extracted in the bounding box followed by classification into normal/defective panel. Additional RANSAC‐based outer edge inspection algorithm is processed. We conducted an experimental study using manufacturing data, and showed successful performance in hard defect detection and classification.

Automated Student Result Analysis and Career Guidance System Using Robotic Process Automation and Decision Tree Classification

For this project, we created a cutting-edge Robotic Process Automation (RPA) system that would improve and expedite the examination of student performance data. The student result PDFs are effectively converted by the system into an Excel format that is specified, with each row representing a student's results. The system conducts a thorough study of the outcomes using a machine learning technique called the Decision Tree Classification Algorithm. This analysis indicates appropriate career options, like software development or system analysis, for each student. By automating the data entry for eighty pupils, this extensive process takes place concurrently with the PDF-to-Excel conversion, greatly increasing efficiency and saving teachers a great deal of time. Furthermore, the system offers tailored career counseling, supporting educators in counseling students on the best career options and empowering students. By automating the data entry for eighty pupils, this extensive process takes place concurrently with the PDF-to-Excel conversion, greatly increasing efficiency and saving teachers a great deal of time. The system also offers pupils individualized career counseling, which helps teachers counsel students on the best job options and empowers students to make better decisions about their futures. The project provides a solid solution for automated result analysis and career path advice, showcasing the usefulness of RPA and machine learning in educational contexts. Key Words: Robotic Process Automation ,Analysis, Machine Learning, Excel File, PDF File, Software Bot

CLASSIFICATION OF KAZAKH MUSIC GENRES USING MACHINE LEARNING TECHNIQUES

This article analysis a Kazakh Music dataset, which consists of 800 audio tracks equally distributed across 5 different genres. The purpose of this research is to classify music genres by using machine learning algorithms Decision Tree Classifier and Logistic regression. Before the classification, the given data was pre-processed, missing or irrelevant data was removed. The given dataset was analyzed using a correlation matrix and data visualization to identify patterns. To reduce the dimension of the original dataset, the PCA method was used while maintaining variance. Several key studies aimed at analyzing and developing machine learning models applied to the classification of musical genres are reviewed. Cumulative explained variance was also plotted, which showed the maximum proportion (90%) of discrete values ​​generated from multiple individual samples taken along the Gaussian curve. A comparison of the decision tree model to a logistic regression showed that for f1 Score Logistic regression produced the best result for classical music - 82%, Decision tree classification - 75%. For other genres, the harmonic mean between precision and recall for the logistic regression model is equal to zero, which means that this model completely fails to classify the genres Zazz, Kazakh Rock, Kazakh hip hop, Kazakh pop music. Using the Decision tree classifier algorithm, the Zazz and Kazakh pop music genres were not recognized, but Kazakh Rock with an accuracy and completeness of 33%. Overall, the proposed model achieves an accuracy of 60% for the Decision Tree Classifier and 70% for the Logistic regression model on the training and validation sets. For uniform classification, the data were balanced and assessed using the cross-validation method. The approach used in this study may be useful in classifying different music genres based on audio data without relying on human listening.

The Impact of Device Type Number on IoT Device Classification

Today, connected systems are widely used with the recent developments in technology. The internet-connected devices create data traffic when communicating with each other. These data may contain extremely confidential information. Observers can obtain confidential information from the traffic when the security of this traffic cannot be adequately ensured. This confidential information can be personal information as well as information about the type of device used by the person. Attackers could use machine learning to analyze encrypted data traffic patterns from IoT devices to infer sensitive information, even without decrypting the actual content. For example, if someone uses IoT devices for health monitoring or smoke detection, attackers could leverage machine learning to discern victims' habits or identify health conditions. An increase in the number of IoT devices may decrease the accuracy of classification when using machine learning. This paper presents the importance of the effect of device type number on the classification of IoT devices. Therefore, inference attacks on privacy with machine learning algorithms, attacks on machine learning models, and the padding method that is commonly used against such attacks are presented. Moreover, experiments are carried out by using the dataset of the traffic generated by the Internet of Things (IoT) devices. For this purpose, Random Forest, Decision Tree, and k-Nearest Neighbors (k-NN) classification algorithms are compared, and the accuracy rate changes according to the number of devices are presented. According to the results, the Random Forest and Decision Tree algorithms are found to be more effective than the k-NN algorithm. When considering a scenario with two device types, the Random Forest and Decision Tree algorithms achieved an accuracy rate of 98%, outperforming the k-NN algorithm, which had an accuracy rate of 95%.

Unveiling the Power: A Comparative Analysis of Data Mining Tools through Decision Tree Classification on the Bank Marketing Dataset

The importance of data mining is growing rapidly, so the comparison of data mining tools has become important. Data mining is the process of extracting valuable data from large data to meet the need to see relationships between data and to make predictions when necessary. This study delves into the dynamic realm of data mining, presenting a comprehensive comparison of prominent data mining tools through the lens of the decision tree algorithm. The research focuses on the application of these tools to the BankMarketing dataset, a rich repository of financial interactions. The objective is to unveil the efficacy and nuances of each tool in the context of predictive modelling, emphasizing key metrics such as accuracy, precision, recall, and F1-score. Through meticulous experimentation and evaluation, this analysis sheds light on the distinct strengths and limitations of each data-mining tool, providing valuable insights for practitioners and researchers in the field. The findings contribute to a deeper understanding of tool selection considerations and pave the way for enhanced decision-making in data mining applications. Classification is a data mining task that learns from a collection of data in order to accurately predict new cases. The dataset used in this study is the Bank Marketing dataset from the UCI machine-learning repository. The bank marketing dataset contains 45211 instances and 17 features. The bank marketing dataset is related to the direct marketing campaigns (phone calls) of a Portuguese banking institution and the classification objective is to predict whether customers will subscribe to a deposit (variable y) in a period of time. To make the classification, the machine learning technique can be used. In this study, the Decision Tree classification algorithm is used. Knime, Orange, Tanagra, Rapidminerve, Weka yield mining tools are used to analyse the classification algorithm.

Comparison of Iris dataset classification with Gaussian naïve Bayes and decision tree algorithms

In this study, we apply two classification algorithm methods, namely the Gaussian naïve Bayes (GNB) and the decision tree (DT) classifiers. The Gaussian naïve Bayes classifier is a probability-based classification model that predicts future probabilities based on past experiences. Whereas the decision tree classifier is based on a decision tree, a series of tests that are performed adaptively where the previous test affects the next test. Both of these methods are simulated on the Iris dataset where the dataset consists of three types of Iris: setosa, virginica, and versicolor. The data is divided into two parts, namely training and testing data, in which there are several features as information on flower characteristics. Furthermore, to evaluate the performance of the algorithms on both methods and determine the best algorithm for the dataset, we evaluate it using several metrics on the training and testing data for each method. Some of these metrics are recall, precision, F1-score, and accuracy where the higher the value, the better the algorithm's performance. The results show that the performance of the decision tree classifier algorithm is the most outperformed on the Iris dataset.

Comparison Of Naïve Bayes And Decision Trees In Determining The Best Manager Of Nurul Jadid Islamic Boarding School Based On Forward Selection

In an effort to find a solution for determining the best administrators, Islamic boarding school administrators try to determine the nominations for the best administrators using existing service data and knowledge. The process of determining nominations for the best administrators is less accurate, requiring computational methods to classify which administrators fall into the best category. In the context of data mining, classification is an important aspect. One of the classification models used is Naïve Bayes which focuses on class probability, and Decision Tree C4.5 which produces a decision tree to determine the priority of indicators that are most influential in predicting the best management. Both of these algorithms have their respective advantages. This research aims to analyze and compare the performance of the Naïve Bayes and Decision Tree classification algorithms. The comparative results of testing the Naïve Bayes and C4.5 algorithms in determining the nominations for the best administrators at the Nurul Jadid Paiton Probolinggo Islamic Boarding School on 455 administrator data tested in this study show that there is a fairly large comparison of accuracy. Naïve Bayes with Forward Selection has an accuracy rate of 91.21%, higher than Naïve Bayes itself whose accuracy results are only 87.64%. there is a difference of 3.57%. Likewise, the accuracy of C4.5 with Forward Selection has an accuracy rate of 90.99%, higher than C4.5 alone which has an accuracy rate of 90.11%. there is a difference of 0.88%. So in the comparison between 4 algorithm model trials, Naïve Bayes and Forward Selection had the most dominant accuracy with an accuracy result of 91.21%.

Comparative Analysis of KNN and Decision Tree Classification Algorithms for Early Stroke Prediction: A Machine Learning Approach

Comparative Analysis of KNN and Decision Tree Classification Algorithms for Early Stroke Prediction: A Machine Learning Approach

Identifying the Learning Style of Students Using Machine Learning Techniques: An Approach of Felder Silverman Learning Style Model (FSLSM)

Identification of the learning style of the students in the teaching and learning environment plays a significant importance in improving both teaching and learning perspectives. The intension of the research was to investigate about applying the Machine Learning Techniques for identification of the Learning style of the students in online learning environment based on the Felder Silverman Learning Style (FSLSM) identification model. The significance of this experiment is that the proposed methodology considers the combination of access frequency (f) of course materials and total time (T) students spent on each course activity. For data collection process, it was designed reusable plugin for the Moodle for time tracking. Real-time dataset was prepared using three course modules designed according to the features of FSLSM model and the features for analyzing the students according to the FSLSM, it was selected seven criteria, and the features were validated using Pearson Correlation Coefficient method. These course modules were enrolled 150 students per each module. Once the data set was prepared, the data set was preprocessed and applied Five Supervised Classification Machine learning algorithms as Decision Tree, Logistic Regression, Random Forest, Support Vector Machine and K-Nearest Neighbors algorithm. The models were evaluated using Accuracy, Precision, Recall and F1 values. Over the five algorithms the Decision Tree classifier algorithm performed with best average accuracy with 93.5% for Input, 86% for Perception, 89.5 for Processing and 94% for Understanding dimension. The models were validated using the K-fold Cross validation and Standard Deviation values. Mean Squared Error, Bias and Variance values were considered the evaluation of underfitting or overfitting context of the model. To parameter optimization, the Grid Search Methodology was applied to find the best combination of criterion for the model. Finally, an application was developed for Identifying the Learning Style of the Students using the designed Machine learning model. The Consistency of the ML Model based on the Decision Tree classifier algorithm were evaluated using the results generated through developed application and the results suggested that consistency for taught machine learning algorithms is often between 85% to 95%, which is an acceptable range. The results generated by the application for identification of the learning style suggested the combination of learning style for particular students sample as Global-Mild, Visual- Strong, Sensing- Moderate and Reflective-Strong. Identification of these combination of learning style assist for teachers by giving an insight which components of the learning contents should be improved in course designing process.

Machine learning, Water Quality Index, and GIS-based analysis of groundwater quality

Abstract Water is essential for life, as it supports bodily functions, nourishes crops, and maintains ecosystems. Drinking water is crucial for maintaining good health and can also contribute to economic development by reducing healthcare costs and improving productivity. In this study, we employed five different machine learning algorithms – logistic regression (LR), decision tree classifier (DTC), extreme gradient boosting (XGB), random forest (RF), and K-nearest neighbors (KNN) – to analyze the dataset, and their prediction performance were evaluated using four metrics: accuracy, precision, recall, and F1 score. Physiochemical parameters of 30 groundwater samples were analyzed to determine the Water Quality Index (WQI) of Pano Aqil city, Pakistan. The samples were categorized into the following four classes based on their WQI values: excellent water, good water, poor water, and unfit for drinking. The WQI scores showed that only 43.33% of the samples were deemed acceptable for drinking, indicating that the majority (56.67%) were unsuitable. The findings suggest that the DTC and XGB algorithms outperform all other algorithms, achieving overall accuracies of 100% each. In contrast, RF, KNN, and LR exhibit overall accuracies of 88, 75, and 50%, respectively. Researchers seeking to enhance water quality using machine learning can benefit from the models described in this study for water quality prediction.

An evaluation of English distance information teaching quality based on decision tree classification algorithm

An evaluation of English distance information teaching quality based on decision tree classification algorithm

Research on the effect and guarantee of college sports on college students’ health under the background of ecological pollution

Abstract The rapid development of the social economy has led to the aggravation of ecological pollution and endangered human health, so the idea of promoting health through sports has been put forward. Based on physical health problems such as physical weakness, obesity, insomnia, and eye diseases, as well as psychological problems such as low self-esteem, easy generation of negative emotions, and unstable willpower among contemporary college students, according to college sports can activate brain chemicals and improve basic body functions. It studies the promotion effect of college sports on college students’ health. It puts forward the use of the C4.2 decision tree classification algorithm to ensure that college students play sports to promote health and the information gain rate in the C4.2 decision tree classification algorithm. Improve and optimize its original defects to better use it in the college sports system. Finally, questionnaires and volunteer stratified sampling experiments prove that college sports can better promote the physical and mental health development of college students, which has certain practical significance.

ML assisted enhanced recommendation system for reliable volunteering environment

The coronavirus pandemic has negatively impacted everyone around the globe. The need to follow social distancing has increased the demand for technology that makes remote volunteering accessible. Alerting, aiding, and educating individuals at risk in a privacy-preserving manner are the need of the hour. Several NGOs have taken up this responsibility but are lacking the resources to reach willing volunteers and donations. This project attempts to make a novel on-demand service application using ID3, CART, and C4.5 decision tree classification algorithms and compare their accuracies. Algorithm C4.5 here we use as a Decision Tree classifier that can be make decisions based on univariate or multivariate predictor. C4.5 Algorithm builds decision trees based on the conception of information gain, with the decision of each classification associated with the target classification. The best way to determine uncertainty is to use entropy that reflects the basis of decision. We aim to classify volunteer data based on predicted volunteer reliability. C4.5 algorithm shows 11.63 higher accuracy when compared to other algorithm and the value of 0.36 Gini index for the C4.5 indicates that there is an adequate equality. It is conferred that the C4.5 algorithm will best solve this problem based on the required dataset that we have created.

Machine learning algorithms to study the relative roles of jet convection and natural convection in the presence of surface roughness elements on enhancement of jet impingement heat transfer

Based on data-driven approaches, eight machine-learning algorithms have been proposed to characterize the heat transfer performance of turbulent jet impingement cooling. These algorithms are designed to cool high-heat-flux surfaces modified with single protrusions, multi-protrusions, or V-grooves. To train these algorithms, an experimental dataset was used, which included 184 experiments with Reynolds numbers ranging from 10,000 to 33,000, nozzle exit-to-plate distances ranging from 2 to 10 jet diameters, and two different heat inputs of 60 W and 90 W. Multiple linear regression algorithms in Python programming were used to model jet impingement cooling, showing that the proposed machine learning models provided more accurate predictions with a 20.4 % to 66.5 % relative residual improvement over the existing conventional regression model based on performance metrics like R2 and relative residual. This improvement was leveraged to quantify natural convection's impact on the effectiveness of heat transfer enhancement due to different types and sizes of roughness elements in high-temperature applications. The research found that as the protrusion surface area increased from 0.02 % to 0.188 % compared to the flat plate, the effectiveness of heat transfer enhancement decreased from 2.69 % to 8.37 % at similar operating conditions. These results revealed that natural convection, which opposes forced jet impingement, was strengthened with increased heat input values, roughness element surface area, and the local turbulence generated. The higher natural convection weakened the enhancement afforded by jet impingement on the modified plates relative to the flat plate. Additionally, the capabilities of machine learning algorithms were explored to unlock the full potential of the jet impingement technique and to overcome the associated complexity in jet impingement applications for next-generation electronics cooling. Finally, the Decision Tree Classifier algorithm was applied to classify the performance of the surface roughness element as either effective or ineffective.

Performance Analysis of the Decision Tree Classification Algorithm on the Water Quality and Potability Dataset

Ensuring water potability is paramount for public health and safety. This research aimed to assess the efficacy of the Decision Tree classification algorithm in predicting water potability using the Water Quality and Potability dataset. Employing a 5-fold cross-validation technique, the model showcased a moderate performance with an average accuracy of approximately 54.33%. While the Decision Tree provides a baseline and interpretable mechanism for classification, the results emphasize the need for further exploration using more intricate models or ensemble methods. This study contributes to the broader effort of leveraging machine learning techniques for water quality assessment and provides insights into the potential and limitations of such models in predicting water safety