Tree-based Machine Learning Algorithms Research Articles

Predicting symptoms of downy mildew, powdery mildew, and gray mold diseases of grapevine through machine learning

Downy mildew, powdery mildew, and gray mold are major diseases of grapevine with a strong negative impact on fruit yield and fruit quality. These diseases are controlled by the application of chemicals, which may cause undesirable effects on the environment and on human health. Thus, monitoring and forecasting crop disease is essential to support integrated pest management (IPM) measures. In this study, two tree-based machine learning (ML) algorithms, random forest and C5.0, were compared to test their capability to predict the appearance of symptoms of grapevine diseases, considering meteorological conditions, spatial indices, the number of crop protection treatments and the frequency of monitoring days in which symptoms were recorded in the previous year. Data collected in Tuscany region (Italy), on the presence of symptoms on grapevine, from 2006 to 2017 were divided with an 80/20 proportion in training and test set, data collected in 2018 and 2019 were tested as independent years for downy mildew and powdery mildew. The frequency of symptoms in the previous year and the cumulative precipitation from April to seven days before the monitoring day were the most important variables among those considered in the analysis for predicting the occurrence of disease symptoms. The best performance in predicting the presence of symptoms of the three diseases was obtained with the algorithm C5.0 by applying (i) a technique to deal with imbalanced dataset (i.e., symptoms were detected in the minority of observations) and (ii) an optimized cut-off for predictions. The balanced accuracy achieved in the test set was 0.8 for downy mildew, 0.7 for powdery mildew and 0.9 for gray mold. The application of the models for downy mildew and powdery mildew in the two independent years (2018 and 2019) achieved a lower balanced accuracy, around 0.7 for both the diseases. Machine learning models were able to select the best predictors and to unravel the complex relationships among geographic indices, bioclimatic indices, protection treatments and the frequency of symptoms in the previous year.

Comparison of tree-based machine learning algorithms for predicting liquefaction potential using canonical correlation forest, rotation forest, and random forest based on CPT data

This research investigates and compares the performance of three tree-based Machine Learning (ML) methods, Canonical Correlation Forest (CCF), Rotation Forest (RotFor), and Random Forest (RF), for predicting the liquefaction potential of soils based on the cone penetration test (CPT) case history datasets collected from previously published research. The ML models are trained and validated using the Stratified Random Sampling technique for training and test datasets considering three sampling ratios as 50:50, 40:60, and 70:30. In addition, a comparative example was applied to show the difference between the Stratified Random Sampling and the Simple Random Sampling technique, which is the most common probability-based sampling method, considering only a dataset. The predictive capabilities of the developed models are evaluated using Overall Accuracy, Kappa, Precision, Recall, and F-Measure values. Lastly, the Wilcoxon Signed-Rank Test and the Pearson's Correlation Coefficient are adopted to determine the statistical significance of the accuracies between the tree-based ML methods. Generally, tree-based ML methods of CCF, RotFor and, RF are found robust with respect to the variations in training sample sizes, and the performance metrics revealed that the CCF and RotFor method exhibited slightly better performance than the conventional RF method. Finally, based on the results obtained from performance assessment output, CCF and RotFor methods which are the first application in the soil liquefaction issue to the best of our knowledge are worth considering in the prediction of soil liquefaction.

Understanding the link between audience engagement metrics and the perceived quality of online news using machine learning

This article aims to explain the perceived quality of online news articles. Discovering which elements of a news story influence readers’ perceptions could drive online popularity, which is the paramount factor of digital news readership. This work explores an approach to use tree-based machine learning algorithms to address this problem based on selected characteristics, which measure engagement, drawn from prior research mostly developed by communication scientists. A proposed extended model is used to examine the association between the engagement features and perceived quality concerning all the articles depending mainly on their genre. To demonstrate the capacity of using predictive analytics to facilitate journalistic news writing the proposed methodology is applied on a novel data set with 200K articles in total constructed from a blog site. The results of phase A, indicate interesting correlations between the features and the perceived quality of the articles. In stage B, the paper seeks to extract a set of rules that can be used as guidelines for authors in the writing of their next articles, indicating the probability of popularity that their articles may gain if these rules are taken into consideration.

Tree-based machine learning algorithms in the Internet of Things environment for multivariate flood status prediction

Abstract Floods are one of the most common natural disasters in the world that affect all aspects of life, including human beings, agriculture, industry, and education. Research for developing models of flood predictions has been ongoing for the past few years. These models are proposed and built-in proportion for risk reduction, policy proposition, loss of human lives, and property damages associated with floods. However, flood status prediction is a complex process and demands extensive analyses on the factors leading to the occurrence of flooding. Consequently, this research proposes an Internet of Things-based flood status prediction (IoT-FSP) model that is used to facilitate the prediction of the rivers flood situation. The IoT-FSP model applies the Internet of Things architecture to facilitate the flood data acquisition process and three machine learning (ML) algorithms, which are Decision Tree (DT), Decision Jungle, and Random Forest, for the flood prediction process. The IoT-FSP model is implemented in MATLAB and Simulink as development platforms. The results show that the IoT-FSP model successfully performs the data acquisition and prediction tasks and achieves an average accuracy of 85.72% for the three-fold cross-validation results. The research finding shows that the DT scores the highest accuracy of 93.22%, precision of 92.85, and recall of 92.81 among the three ML algorithms. The ability of the ML algorithm to handle multivariate outputs of 13 different flood textual statuses provides the means of manifesting explainable artificial intelligence and enables the IoT-FSP model to act as an early warning and flood monitoring system.

Predicting Flow Rate Escalation for Pediatric Patients on High Flow Nasal Cannula Using Machine Learning.

Background: High flow nasal cannula (HFNC) is commonly used as non-invasive respiratory support in critically ill children. There are limited data to inform consensus on optimal device parameters, determinants of successful patient response, and indications for escalation of support. Clinical scores, such as the respiratory rate-oxygenation (ROX) index, have been described as a means to predict HFNC non-response, but are limited to evaluating for escalations to invasive mechanical ventilation (MV). In the presence of apparent HFNC non-response, a clinician may choose to increase the HFNC flow rate to hypothetically prevent further respiratory deterioration, transition to an alternative non-invasive interface, or intubation for MV. To date, no models have been assessed to predict subsequent escalations of HFNC flow rates after HFNC initiation.Objective: To evaluate the abilities of tree-based machine learning algorithms to predict HFNC flow rate escalations.Methods: We performed a retrospective, cohort study assessing children admitted for acute respiratory failure under 24 months of age placed on HFNC in the Johns Hopkins Children's Center pediatric intensive care unit from January 2019 through January 2020. We excluded encounters with gaps in recorded clinical data, encounters in which MV treatment occurred prior to HFNC, and cases electively intubated in the operating room. The primary study outcome was discriminatory capacity of generated machine learning algorithms to predict HFNC flow rate escalations as compared to each other and ROX indices using area under the receiver operating characteristic (AUROC) analyses. In an exploratory fashion, model feature importance rankings were assessed by comparing Shapley values.Results: Our gradient boosting model with a time window of 8 h and lead time of 1 h before HFNC flow rate escalation achieved an AUROC with a 95% confidence interval of 0.810 ± 0.003. In comparison, the ROX index achieved an AUROC of 0.525 ± 0.000.Conclusion: In this single-center, retrospective cohort study assessing children under 24 months of age receiving HFNC for acute respiratory failure, tree-based machine learning models outperformed the ROX index in predicting subsequent flow rate escalations. Further validation studies are needed to ensure generalizability for bedside application.

A Tree Based Machine Learning Approach for PTB Diagnostic Dataset

The primary objective of this particular paper is to classify the health-related data without feature extraction in Machine Learning, which hinder the performance and reliability. The assumption of our work will be like, can we able to get better result for health-related data with the help of Tree based Machine Learning algorithms without extracting features like in Deep Learning. This study performs better classification with Tree based Machine Learning approach for the health-related medical data. After doing pre-processing, without feature extraction, i.e., from raw data signal with the help of Machine Learning algorithms we are able to get better results. The presented paper which has better result even when compared to some of the advanced Deep Learning architecture models. The results demonstrate that overall classification accuracy of Random Forest, XGBoost, LightGBM and CatBoost, Tree-based Machine Learning algorithms for normal and abnormal condition of the datasets was found to be 97.88%, 98.23%, 98.03% and 95.57% respectively.

Social Networks, Female Unemployment, and the Urban-Rural Divide in Turkey: Evidence from Tree-Based Machine Learning Algorithms

This study takes a novel, algorithmic approach for understanding the underlying mechanisms related to the employment status of individuals. Using the data from the most recent survey of the International Social Survey Programme (ISSP) on Turkey, the present study examines how social connectivity and location play a role in the prediction of employment status through the use of two tree-based modern machine learning techniques, namely random forest, and extreme gradient boosting. We obtain a wide array of observations, with gender being the most prominent finding when periphery and rural locations are considered.

Decision tree\u2013based identification of Staphylococcus aureus via infrared spectral analysis of ambient gas

In this study, eight types of bacteria were cultivated, including Staphylococcus aureus. The infrared absorption spectra of the gas surrounding cultured bacteria were recorded at a resolution of 0.5 cm−1 over the wavenumber range of 7500–500 cm−1. From these spectra, we searched for the infrared wavenumbers at which characteristic absorptions of the gas surrounding Staphylococcus aureus could be measured. This paper reports two wavenumber regions, 6516–6506 cm−1 and 2166–2158 cm−1. A decision tree–based machine learning algorithm was used to search for these wavenumber regions. The peak intensity or the absorbance difference was calculated for each region, and the ratio between them was obtained. When these ratios were used as training data, decision trees were created to classify the gas surrounding Staphylococcus aureus and the gas surrounding other bacteria into different groups. These decision trees show the potential effectiveness of using absorbance measurement at two wavenumber regions in finding Staphylococcus aureus.Graphical abstract

Cardiotocography Data Analysis to Predict Fetal Health Risks with Tree-Based Ensemble Learning

A sizeable number of women face difficulties during pregnancy, which eventually can lead the fetus towards serious health problems. However, early detection of these risks can save both the invaluable life of infants and mothers. Cardiotocography (CTG) data provides sophisticated information by monitoring the heart rate signal of the fetus, is used to predict the potential risks of fetal wellbeing and for making clinical conclusions. This paper proposed to analyze the antepartum CTG data (available on UCI Machine Learning Repository) and develop an efficient tree-based ensemble learning (EL) classifier model to predict fetal health status. In this study, EL considers the Stacking approach, and a concise overview of this approach is discussed and developed accordingly. The study also endeavors to apply distinct machine learning algorithmic techniques on the CTG dataset and determine their performances. The Stacking EL technique, in this paper, involves four tree-based machine learning algorithms, namely, Random Forest classifier, Decision Tree classifier, Extra Trees classifier, and Deep Forest classifier as base learners. The CTG dataset contains 21 features, but only 10 most important features are selected from the dataset with the Chi-square method for this experiment, and then the features are normalized with Min-Max scaling. Following that, Grid Search is applied for tuning the hyperparameters of the base algorithms. Subsequently, 10-folds cross validation is performed to select the meta learner of the EL classifier model. However, a comparative model assessment is made between the individual base learning algorithms and the EL classifier model; and the finding depicts EL classifiers’ superiority in fetal health risks prediction with securing the accuracy of about 96.05%. Eventually, this study concludes that the Stacking EL approach can be a substantial paradigm in machine learning studies to improve models’ accuracy and reduce the error rate.

Evaluation of Tree-Based Machine Learning Algorithms for Accident Risk Mapping Caused by Driver Lack of Alertness at a National Scale

Drivers’ lack of alertness is one of the main reasons for fatal road traffic accidents (RTA) in Iran. Accident-risk mapping with machine learning algorithms in the geographic information system (GIS) platform is a suitable approach for investigating the occurrence risk of these accidents by analyzing the role of effective factors. This approach helps to identify the high-risk areas even in unnoticed and remote places and prioritizes accident-prone locations. This paper aimed to evaluate tuned machine learning algorithms of bagged decision trees (BDTs), extra trees (ETs), and random forest (RF) in accident-risk mapping caused by drivers’ lack of alertness (due to drowsiness, fatigue, and reduced attention) at a national scale of Iran roads. Accident points and eight effective criteria, namely distance to the city, distance to the gas station, land use/cover, road structure, road type, time of day, traffic direction, and slope, were applied in modeling, using GIS. The time factor was utilized to represent drivers’ varied alertness levels. The accident dataset included 4399 RTA records from March 2017 to March 2019. The performance of all models was cross-validated with five-folds and tree metrics of mean absolute error, mean squared error, and area under the curve of the receiver operating characteristic (ROC-AUC). The results of cross-validation showed that BDT and RF performance with an AUC of 0.846 were slightly more accurate than ET with an AUC of 0.827. The importance of modeling features was assessed by using the Gini index, and the results revealed that the road type, distance to the city, distance to the gas station, slope, and time of day were the most important, while land use/cover, traffic direction, and road structure were the least important. The proposed approach can be improved by applying the traffic volume in modeling and helps decision-makers take necessary actions by identifying important factors on road safety.

Point-of-care detection and differentiation of anticoagulant therapy - development of thromboelastometry-guided decision-making support algorithms

BackgroundDOAC detection is challenging in emergency situations. Here, we demonstrated recently, that modified thromboelastometric tests can reliably detect and differentiate dabigatran and rivaroxaban. However, whether all DOACs can be detected and differentiated to other coagulopathies is unclear. Therefore, we now tested the hypothesis that a decision tree-based thromboelastometry algorithm enables detection and differentiation of all direct Xa-inhibitors (DXaIs), the direct thrombin inhibitor (DTI) dabigatran, as well as vitamin K antagonists (VKA) and dilutional coagulopathy (DIL) with high accuracy.MethodsFollowing ethics committee approval (No 17–525-4), and registration by the German clinical trials database we conducted a prospective observational trial including 50 anticoagulated patients (n = 10 of either DOAC/VKA) and 20 healthy volunteers. Blood was drawn independent of last intake of coagulation inhibitor. Healthy volunteers served as controls and their blood was diluted to simulate a 50% dilution in vitro. Standard (extrinsic coagulation assay, fibrinogen assay, etc.) and modified thromboelastometric tests (ecarin assay and extrinsic coagulation assay with low tissue factor) were performed. Statistical analyzes included a decision tree analyzes, with depiction of accuracy, sensitivity and specificity, as well as receiver-operating-characteristics (ROC) curve analysis including optimal cut-off values (Youden-Index).ResultsFirst, standard thromboelastometric tests allow a good differentiation between DOACs and VKA, DIL and controls, however they fail to differentiate DXaIs, DTIs and VKAs reliably resulting in an overall accuracy of 78%. Second, adding modified thromboelastometric tests, 9/10 DTI and 28/30 DXaI patients were detected, resulting in an overall accuracy of 94%. Complex decision trees even increased overall accuracy to 98%. ROC curve analyses confirm the decision-tree-based results showing high sensitivity and specificity for detection and differentiation of DTI, DXaIs, VKA, DIL, and controls.ConclusionsDecision tree-based machine-learning algorithms using standard and modified thromboelastometric tests allow reliable detection of DTI and DXaIs, and differentiation to VKA, DIL and controls.Trial registrationClinical trial number: German clinical trials database ID: DRKS00015704.

Quantification of Multi-Ion Mixtures Using a Machine Learning Assisted Integrated Electronic Tongue Leveraging Mobile and Cloud Platforms

Quantification of Multi-Ion Mixtures Using a Machine Learning Assisted Integrated Electronic Tongue Leveraging Mobile and Cloud Platforms

Exploring drivers of patient satisfaction using a random forest algorithm

BackgroundPatient satisfaction is a multi-dimensional concept that provides insights into various quality aspects in healthcare. Although earlier studies identified a range of patient and provider-related determinants, their relative importance to patient satisfaction remains unclear.MethodsWe used a tree-based machine-learning algorithm, random forests, to estimate relationships between patient and provider-related determinants and satisfaction level in two of the main patient journey stages, registration and consultation, through survey data from 411 patients at a hospital in Abu Dhabi, UAE. Radar charts were also generated to determine which type of questions—demographics, time, behaviour, and procedure—influence patient satisfaction.ResultsOur results showed that the ‘age’ attribute, a patient-related determinant, is the leading driver of patient satisfaction in both stages. ‘Total time taken for registration’ and ‘attentiveness and knowledge of the doctor/physician while listening to your queries’ are the leading provider-related determinants in each model developed for registration and consultation stages, respectively. The radar charts revealed that ‘demographics’ are the most influential type in the registration stage, whereas ‘behaviour’ is the most influential in the consultation stage.ConclusionsGenerating valuable results, the random forest model provides significant insights on the relative importance of different determinants to overall patient satisfaction. Healthcare practitioners, managers and researchers can benefit from applying the model for prediction and feature importance analysis in their particular healthcare settings and areas of their concern.

An Approach for Morse Code Translation from Eye Blinks Using Tree Based Machine Learning Algorithms and OpenCV

For ages, human beings have been communicating with one another through different modes of communication. Communication is a process through which a person can communicate his/her feelings and thoughts to the other person. To communicate we can do it through either speech or sign language. The spoken language is used by abled persons, While the differently abled persons (deaf and dumb) may find it difficult to understand the same. So, for effective communication between the differently abled and abled person sign language has been developed. For private communication between two people, morse code has been developed which is highly efficient to exchange secrets. It also helps in emergencies where a person cannot communicate through hand gestures. Different methods/modes are used in morse code, but our focus is on eye blinking. Our approach towards this area has been to implement morse code using eye blinks in real-time assistance using a webcam to provide predicting power based on machine learning’s tree algorithms.

Rare-class learning over Mg-doped ZnO nanoparticles

This interdisciplinary study is conducted to find answers to two important questions which researchers often face in Machine Learning (ML) and Material Science (MS) fields. In this work, we measure the performance of the most popular ML algorithms (more than a dozen) on rare-class learning problem and determine the best learning algorithm for atom type prediction over the Mg-doped ZnO nanoparticles data obtained from the density-functional tight-binding method. As a result, we observe that tree-based ML algorithms such as Extreme Gradient Boosting (XGB), Decision Trees (DT), Random Forest (RF), outperform other types of ML algorithms, e.g., cost-sensitive learning, prototype models, support vector machines, kernel methods, on both rare-class learning and atom type prediction.

Visual light perceptions caused by medical linear accelerator: Findings of machine-learning algorithms in a prospective questionnaire-based case-control study.

This study aimed to investigate the possible incidence of visual light perceptions (VLPs) during radiation therapy (RT). We analyzed whether VLPs could be affected by differences in the radiation energy, prescription doses, age, sex, or RT locations, and whether all VLPs were caused by radiation. From November 2016 to August 2018, a total of 101 patients who underwent head-and-neck or brain RT were screened. After receiving RT, questionnaires were completed, and the subjects were interviewed. Random forests (RF), a tree-based machine learning algorithm, and logistic regression (LR) analyses were compared by the area under the curve (AUC), and the algorithm that achieved the highest AUC was selected. The dataset sample was based on treatment with non-human units, and a total of 293 treatment fields from 78 patients were analyzed. VLPs were detected only in 122 of the 293 exposure portals (40.16%). The dataset was randomly divided into 80% and 20% as the training set and test set, respectively. In the test set, RF achieved an AUC of 0.888, whereas LR achieved an AUC of 0.773. In this study, the retina fraction dose was the most important continuous variable and had a positive effect on VLP. Age was the most important categorical variable. In conclusion, the visual light perception phenomenon by the human body during RT is induced by radiation rather than being a self-suggested hallucination or induced by phosphenes.

The Predictability of Tree-based Machine Learning Algorithms in the Big Data Context

This research work is concerned with the predictability of ensemble and singular tree-based machine learning algorithms during the recession and prosperity of the two companies listed in the Tehran Stock Exchange in the context of big data. In this regard, the main issue is that economic managers and the academic community require predicting models with more accuracy and reduced execution time; moreover, the prediction of the companies recession in the stock market is highly significant. Machine learning algorithms must be able to appropriately predict the stock return sign during the market downturn and boom days. Addressing the stated challenge will upgrade the quality of stock purchases and, subsequently, will increase profitability. In this article, the proposed solution relies on the utilization of tree-based machine learning algorithms in the context of big data. The proposed solution exploits the decision tree algorithm, which is a traditional and singular tree-based learning algorithm. Furthermore, two modern and ensemble tree-based learning algorithms, random forest and gradient boosted tree, has been utilized for predicting the stock return sign during recession and prosperity. The mentioned cases were implemented by applying the machine learning tools in python programming language and PYSPARK library that is used explicitly for the big data context. The utilized research data of the current study are the shares information of two companies of the Tehran Stock Exchange. The obtained results reveal that the applied ensemble learning algorithms have performed better than the singular learning algorithms. Additionally, adding 23 technical features to the initial data and subsequent applying of the PCA feature reduction method have demonstrated the best performance among other modes. In the meantime, it has been concluded that the initial data do not possess the proper resolution or generalizability, either during prosperity or recession.

Distributed Tree-Based Machine Learning for Short-Term Load Forecasting With Apache Spark

Machine learning algorithms have been intensively applied to perform load forecasting to obtain better accuracies as compared to traditional statistical methods. However, with the huge increase in data size, sophisticated models have to be created which require big data platforms. Optimal and effective use of the available computational resources can be attained by maximizing the effective utilization of the cluster nodes. Parallel computing is demanded to allow for optimal resource utilization in dealing with smart grid big data. In this paper, a master-slave parallel computing paradigm is utilized and experimented with for load forecasting in a multi-AMI environment. The paper proposes a concurrent job scheduling algorithm in a multi-energy data source environment using Apache Spark. An efficient resource utilization strategy is proposed for submitting multiple Spark jobs to reduce job completion time. The optimal value of clustering is used in this paper to cluster the data into groups to be able to reduce the computational time additionally. Multiple tree-based machine learning algorithms are tested with parallel computation to evaluate the performance with tunable parameters on a real-world dataset. One thousand distribution transformers’ real data from Spain for three years are used to demonstrate the performance of the proposed methodology with a trade-off between accuracy and processing time.

Combining Machine Learning and Dynamic Time Wrapping for Vehicle Driving Event Detection Using Smartphones

The detection of driving events could be useful for reducing accidents, fleet management and insurance premiums etc. Currently, top of the range vehicles and large fleets employ expensive driver monitoring systems. However, most drivers do not have access to such systems. The required monitoring platform would have to deliver the required performance while also being affordable and accessible. A candidate with considerable promise is the smartphone with sensors built-in that could be exploited for the detection of driving events. However, to date it has not been possible to achieve the required correct, missed and false detection rates in addition to the computational efficiency for real-time operations. This paper proposes a novel bagging tree and dynamic time warping (DTW) integrated algorithm for the detection of driving events employing acceleration and orientation data from a smartphone's low cost three-axis accelerometers and gyroscopes. The bagging tree-based machine learning algorithm provides the initial maneuver detection results, as well as the location of the event start and end points. Event detection is then achieved by calculating the similarity of the results predicted through the bagging tree algorithm with the corresponding templates extracted from the experience datasets, while also applying a number of constraints to verify the calculated results. Field test results show that the proposed integrated algorithm is superior to the state-of-the-art, achieving a high correct detection accuracy of 97.5%, a low missed detection of 2.5% and a false detection rate of 2.9%. The corresponding results for the best alternative candidate method are 90.2%, 9.8% and 11.7%. Furthermore, the improvement in computational efficiency offered by our proposed approach is three to more than ten times greater than that of the other state-of-the-art algorithms.

A comparative study of patient and staff safety evaluation using tree-based machine learning algorithms

Medical errors constitute a significant challenge affecting patient and staff safety in complex and dynamic healthcare systems. While various organizational factors may contribute to such errors, limited studies have addressed patient and staff safety issues simultaneously in the same study setting. To evaluate this, we conduct an exploratory analysis using two types of tree-based machine learning algorithms, random forests and gradient boosting, and the hospital-level aggregate staff experience survey data from UK hospitals. Based on staff views and priorities, the results from both algorithms suggest that “health and wellbeing” is the leading theme associated with the number of reported errors and near misses harming patient and staff safety. Specifically, “work-related stress” is the most important survey item associated with safety outcomes. With respect to prediction accuracy, both algorithms provide similar results with comparable values in error metrics. Based on the analytical results, healthcare risk managers and decision-makers can develop and implement policies and practices that address staff experience and prioritize resources effectively to improve patient and staff safety.