EBOC: Ensemble-Based Ordinal Classification in Transportation

Yıldırım, Pelin; Birant, Ulaş K.; Birant, Derya

doi:10.1155/2019/7482138

Cited by 20 publications

(11 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ensemble methods attempt to overcome the bias or variance effects of individual classifiers by combining several of them together [ 32 ], thus achieving better performance [ 33 , 34 ]. Despite the fact that ensemble methods for nominal classification have received considerable attention in the literature and have been chosen in preference to single individual learning algorithms for many classification tasks, the use of ordinal classification in ensemble algorithms has rarely been discussed [ 35 ]. In the literature, the most widely used ensemble methods are categorized into four techniques: bagging, boosting, stacking, and voting [ 35 , 36 ].…”

Section: Methodsmentioning

confidence: 99%

“…Despite the fact that ensemble methods for nominal classification have received considerable attention in the literature and have been chosen in preference to single individual learning algorithms for many classification tasks, the use of ordinal classification in ensemble algorithms has rarely been discussed [ 35 ]. In the literature, the most widely used ensemble methods are categorized into four techniques: bagging, boosting, stacking, and voting [ 35 , 36 ]. In this research, we suggest integrating the objective-based information gain into ensemble methods to enable the use of ordinal classification in ensemble algorithms.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Ordinal Decision-Tree-Based Ensemble Approaches: The Case of Controlling the Daily Local Growth Rate of the COVID-19 Epidemic

Singer

Marudi

2020

Entropy

View full text Add to dashboard Cite

In this research, we develop ordinal decision-tree-based ensemble approaches in which an objective-based information gain measure is used to select the classifying attributes. We demonstrate the applicability of the approaches using AdaBoost and random forest algorithms for the task of classifying the regional daily growth factor of the spread of an epidemic based on a variety of explanatory factors. In such an application, some of the potential classification errors could have critical consequences. The classification tool will enable the spread of the epidemic to be tracked and controlled by yielding insights regarding the relationship between local containment measures and the daily growth factor. In order to benefit maximally from a variety of ordinal and non-ordinal algorithms, we also propose an ensemble majority voting approach to combine different algorithms into one model, thereby leveraging the strengths of each algorithm. We perform experiments in which the task is to classify the daily COVID-19 growth rate factor based on environmental factors and containment measures for 19 regions of Italy. We demonstrate that the ordinal algorithms outperform their non-ordinal counterparts with improvements in the range of 6–25% for a variety of common performance indices. The majority voting approach that combines ordinal and non-ordinal models yields a further improvement of between 3% and 10%.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Ordinal Decision-Tree-Based Ensemble Approaches: The Case of Controlling the Daily Local Growth Rate of the COVID-19 Epidemic

Singer

Marudi

2020

Entropy

View full text Add to dashboard Cite

show abstract

“…Meanwhile, ordinal classification, which assumes that the class attributes of experimental datasets have an inherent order, has been recently preferred in ML. This paradigm has been utilized in software engineering (Diamantopoulos et al, 2021; Fontana & Zanoni, 2017; Kıyak et al, 2019) as well as in many areas, such as healthcare (Durán‐Rosal et al, 2021; Liu et al, 2020; Pal et al, 2018), banking (Manthoulis et al, 2020), meteorology (Guijo‐Rubio et al, 2018), and transportation (Kıyak et al, 2019; Yıldırım et al, 2019) for a classification task. Researchers (Kıyak et al, 2019) proposed an ordinal classification approach using RF, SVM, NB, and k‐nearest neighbour (kNN) algorithms as base learners for software bug prediction in their study.…”

Section: Related Workmentioning

confidence: 99%

A novel multi‐view ordinal classification approach for software bug prediction

Taşer

2022

Expert Systems

View full text Add to dashboard Cite

Software bug prediction aims to enhance software quality and testing efficiency by constructing predictive classification models using code properties. This enables the prompt detection of fault‐prone modules. There are several machine learning‐based software bug prediction studies, which mainly focus on single view data by disregarding the natural ordering relation among the class labels in the literature. Thus, these studies cause losing each view's own intrinsic structure and the inherent order of the labels that positively affect the prediction performance. To overcome this drawback, this study focuses on integrating ordering information and a multi‐view learning strategy. This paper proposes a novel approach multi‐view ordinal classification (MVOC), which learns from different views (complexity, coupling, cohesion, inheritance and scale) of the software dataset separately and predicts software bugs taking the inherent order of class labels (non‐buggy, less buggy and more buggy) into consideration. To demonstrate its prediction performance, the MVOC approach was executed on the 40 different real‐world software datasets using six different classification algorithms as base learners. In the experiments, the MVOC approach was compared with traditional classifiers and their multi‐view implementations in terms of precision, recall, f‐measure and accuracy rate metrics. The results indicate that the MVOC approach presents better prediction performance on average than the multi‐view‐based and traditional classifiers. It is also observed from the results that the MVOC.RF model achieved the highest classification performance with an average accuracy rate of 85.65%.

show abstract

“…AdaBoost. AdaBoost trains multiple single split decision trees consecutively to convert weak learners to strong ones by reweighting variables in the training set [13].…”

Section: Extra Tree Regression (Etr)mentioning

confidence: 99%

An Intelligent Multi-output Regression Model for Soil Moisture Prediction

KÜÇÜK

Birant

Taşer

2021

Intelligent and Fuzzy Techniques for Emerging Conditions and Digital Transformation

Self Cite

View full text Add to dashboard Cite

Soil moisture prediction plays a vital role in developing plants, soil properties, and sustenance of agricultural systems. Considering this motivation, in this study, an intelligent Multi-output regression method was implemented on daily values of meteorological and soil data obtained from Kemalpaşa-Örnekköy station in Izmir, Turkey, at three soil depths (15, 30, and 45 cm) between the years 2017 and 2019. In this study, nine different machine learning algorithms (Linear Regression (LR), Ridge Regression (RR), Least Absolute Shrinkage and Selection Operator (Lasso), Random Forest (RF), Extra Tree Regression (ETR), Adaptive Boosting (AdaBoost), Gradient Boosting (GB), Extreme Gradient Boosting (XGBoost), and Histogram-Based Gradient Boosting (HGB)) were compared each other in terms of MAE, RMSE, and R 2 metrics. The experiments indicate that the implemented Multi-output regression models show good soil moisture prediction performance. Also, the ETR algorithm provided the best prediction performance with an 0.81 R 2 value among the other models.

show abstract

EBOC: Ensemble-Based Ordinal Classification in Transportation

Cited by 20 publications

References 20 publications

Ordinal Decision-Tree-Based Ensemble Approaches: The Case of Controlling the Daily Local Growth Rate of the COVID-19 Epidemic

Ordinal Decision-Tree-Based Ensemble Approaches: The Case of Controlling the Daily Local Growth Rate of the COVID-19 Epidemic

A novel multi‐view ordinal classification approach for software bug prediction

An Intelligent Multi-output Regression Model for Soil Moisture Prediction

Contact Info

Product

Resources

About