Developing Crash Severity Model Handling Class Imbalance and Implementing Ordered Nature: Focusing on Elderly Drivers

Along with the rapid demographic change, there has been increased attention to the risk of vehicle crashes relative to older drivers. Due to senior involvement and their physical vulnerability, it is crucial to develop models that accurately predict the severity of senior-involved crashes. However, the challenge is how to cope with an imbalanced severity class distribution and the ordered nature of crash severities, as these can complicate the classification of the severity of crashes. In that regard, this study investigates the influence of implementing ordinal nature and handling imbalanced class distribution on the prediction performance. Using vehicle crash data in Ohio, U.S., as an example, the eight machine learning classifiers (logistic and ordered logistic regressions and random forest and ordered random forest with or without handling imbalanced classes) are suggested and then compared with their respective performances. The analysis outcomes show that balancing strategy enhances performance in predicting severe crashes. In contrast, the effects of implementing ordinal nature vary across models. Specifically, the ordered random forest classifier without balancing appears to be superior in terms of overall prediction accuracy, and the ordered random forest with balancing outperforms others in predicting severer crashes.

Download Full-text

CLASSIFICATION OF IMBALANCED DATA: A REVIEW

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s0218001409007326 ◽

2009 ◽

Vol 23 (04) ◽

pp. 687-719 ◽

Cited By ~ 534

Author(s):

YANMIN SUN ◽

ANDREW K. C. WONG ◽

MOHAMED S. KAMEL

Keyword(s):

Learning Algorithms ◽

Class Imbalance ◽

Imbalanced Data ◽

Class Imbalance Problem ◽

Class Distribution ◽

Imbalance Problem ◽

Misclassification Costs ◽

Imbalanced Class Distribution ◽

Classifier Learning

Classification of data with imbalanced class distribution has encountered a significant drawback of the performance attainable by most standard classifier learning algorithms which assume a relatively balanced class distribution and equal misclassification costs. This paper provides a review of the classification of imbalanced data regarding: the application domains; the nature of the problem; the learning difficulties with standard classifier learning algorithms; the learning objectives and evaluation measures; the reported research solutions; and the class imbalance problem in the presence of multiple classes.

Download Full-text

A Review on Data Level Approaches for Managing Imbalanced Classification Problem

International Journal of Scientific Research in Science Engineering and Technology ◽

10.32628/ijsrset196225 ◽

2019 ◽

pp. 91-97

Author(s):

Ayushi Chaplot ◽

Naveen Choudhary ◽

Kalpana Jain

Keyword(s):

Poor Performance ◽

Classification Problem ◽

Skewed Distribution ◽

Symmetric Form ◽

Imbalanced Classification ◽

Class Distribution ◽

Imbalanced Classes ◽

Imbalanced Class Distribution ◽

Data Level

In real world, the distribution of dataset is not in symmetric form. It can vary from application to application and distribution of data in that application. The un-symmetric form of this distribution is called imbalanced class distribution or skewed class distribution. So, the classification of data with skewed distribution of class can lead to the poor performance of the classifier. To solve the problem of imbalanced dataset in which the instances of one class is more than the instances of other class, there are different data level approaches for handling imbalanced classes. So, in this paper we will discuss about different data level approaches and have comparative study among them.

Download Full-text

Classification of Imbalanced Malaria Disease Using Naïve Bayesian Algorithm

International Journal of Engineering & Technology ◽

10.14419/ijet.v7i2.7.10978 ◽

2018 ◽

Vol 7 (2.7) ◽

pp. 786 ◽

Cited By ~ 1

Author(s):

T Sajana ◽

M R.Narasingarao

Keyword(s):

Comparative Study ◽

Class Imbalance ◽

Machine Learning Algorithms ◽

Bayesian Algorithm ◽

Naive Bayesian ◽

Class Distribution ◽

Naïve Bayesian ◽

R Programming ◽

The Impact

Malaria disease is one whose presence is rampant in semi urban and non-urban areas especially resource poor developing countries. It is quite evident from the datasets like malaria, dengue, etc., where there is always a possibility of having more negative patients (non-occurrence of the disease) compared to patients suffering from disease (positive cases). Developing a model based decision support system with such unbalanced datasets is a cause of concern and it is indeed necessary to have a model predicting the disease quite accurately. Classification of imbalanced malaria disease data become a crucial task in medical application domain because most of the conventional machine learning algorithms are showing very poor performance to classify whether a patient is affected by malaria disease or not. In imbalanced data, majority (unaffected) class samples are dominates the minority (affected) class samples leading to class imbalance. To overcome the nature of class imbalance problem, balancing the data samples is the best solution which produces the better accuracy in classification of minority samples. The aim of this research is to propose a comparative study on classifying the imbalanced malaria disease data using Naive Bayesian classifier in different environments like weka and using an R-language. We present here, clinical descriptive study on 165 patients of different age group people collected at medical wards of Narasaraopet from 2014-17. Synthetic Minority Oversampling Technique (SMOTE) technique has been used to balance the class distribution and then we performed a comparative study on the dataset using Naïve Bayesian algorithm in various platforms. Out of balanced class distribution data, 70% data was given to train the Naive Bayesian algorithm and the rest of the data was used for testing the model for both weka and R programming environments. Experimental results have indicated that, classification of malaria disease data in weka environment has highest accuracy of 88.5% than the Naive Bayesian algorithm accuracy of 87.5% using R programming language. The impact of vector borne disease is very high in medical applications. Prediction of disease like malaria is an hour of the need and this is possible only with a suitable model for a given dataset. Hence, we have developed a model with Naive Bayesian algorithm is used for current research.

Download Full-text

COPING WITH CLASS IMBALANCE IN CLASSIFICATION OF TRAFFIC CRASH SEVERITY BASED ON SENSOR AND ROAD DATA: A FEATURE SELECTION AND DATA AUGMENTATION APPROACH

Computer Science & Information Technology (CS & IT ) ◽

10.5121/csit.2019.90611 ◽

2019 ◽

Author(s):

Deepti Lamba ◽

Majed Alsadhan ◽

William Hsu ◽

Eric Fitzsimmons

Keyword(s):

Feature Selection ◽

Data Augmentation ◽

Class Imbalance ◽

Crash Severity ◽

Traffic Crash ◽

Road Data

Download Full-text

Improving imbalanced scientific text classification using sampling strategies and dictionaries

Journal of Integrative Bioinformatics ◽

10.1515/jib-2011-176 ◽

2011 ◽

Vol 8 (3) ◽

pp. 90-104 ◽

Cited By ~ 10

Author(s):

L. Borrajo ◽

R. Romero ◽

E. L. Iglesias ◽

C. M. Redondo Marey

Keyword(s):

Ad Hoc ◽

Class Imbalance ◽

Svm Classifier ◽

Sampling Strategies ◽

Distribution Problem ◽

Scientific Database ◽

Biomedical Texts ◽

Scientific Documentation ◽

Imbalanced Class Distribution

Summary Many real applications have the imbalanced class distribution problem, where one of the classes is represented by a very small number of cases compared to the other classes. One of the systems affected are those related to the recovery and classification of scientific documentation.Sampling strategies such as Oversampling and Subsampling are popular in tackling the problem of class imbalance. In this work, we study their effects on three types of classifiers (Knn, SVM and Naive-Bayes) when they are applied to search on the PubMed scientific database.Another purpose of this paper is to study the use of dictionaries in the classification of biomedical texts. Experiments are conducted with three different dictionaries (BioCreative, NLPBA, and an ad-hoc subset of the UniProt database named Protein) using the mentioned classifiers and sampling strategies.Best results were obtained with NLPBA and Protein dictionaries and the SVM classifier using the Subsampling balancing technique. These results were compared with those ob- tained by other authors using the TREC Genomics 2005 public corpus.

Download Full-text

An in-depth performance analysis of the oversampling techniques for high-class imbalanced dataset

10.26594/register.v7i1.2206 ◽

2021 ◽

Vol 7 (1) ◽

pp. 63

Author(s):

Prasetyo Wibowo ◽

Chastine Fatichah

Keyword(s):

Random Forest ◽

Performance Analysis ◽

Nearest Neighbor ◽

Class Imbalance ◽

K Nearest Neighbor ◽

Class Imbalance Problem ◽

Minority Class ◽

High Class ◽

Imbalance Problem ◽

Imbalanced Classes

Class imbalance occurs when the distribution of classes between the majority and the minority classes is not the same. The data on imbalanced classes may vary from mild to severe. The effect of high-class imbalance may affect the overall classification accuracy since the model is most likely to predict most of the data that fall within the majority class. Such a model will give biased results, and the performance predictions for the minority class often have no impact on the model. The use of the oversampling technique is one way to deal with high-class imbalance, but only a few are used to solve data imbalance. This study aims for an in-depth performance analysis of the oversampling techniques to address the high-class imbalance problem. The addition of the oversampling technique will balance each class’s data to provide unbiased evaluation results in modeling. We compared the performance of Random Oversampling (ROS), ADASYN, SMOTE, and Borderline-SMOTE techniques. All oversampling techniques will be combined with machine learning methods such as Random Forest, Logistic Regression, and k-Nearest Neighbor (KNN). The test results show that Random Forest with Borderline-SMOTE gives the best value with an accuracy value of 0.9997, 0.9474 precision, 0.8571 recall, 0.9000 F1-score, 0.9388 ROC-AUC, and 0.8581 PRAUC of the overall oversampling technique.

Download Full-text

Using Information on Class Interrelations to Improve Classification of Multiclass Imbalanced Data: A New Resampling Algorithm

International Journal of Applied Mathematics and Computer Science ◽

10.2478/amcs-2019-0057 ◽

2019 ◽

Vol 29 (4) ◽

pp. 769-781 ◽

Cited By ~ 1

Author(s):

Małgorzata Janicka ◽

Mateusz Lango ◽

Jerzy Stefanowski

Keyword(s):

Experimental Evaluation ◽

Imbalanced Data ◽

Data Preprocessing ◽

Imbalanced Datasets ◽

Class Distribution ◽

Imbalanced Classes ◽

Preprocessing Technique ◽

Artificial Datasets ◽

Better Than

Abstract The relations between multiple imbalanced classes can be handled with a specialized approach which evaluates types of examples’ difficulty based on an analysis of the class distribution in the examples’ neighborhood, additionally exploiting information about the similarity of neighboring classes. In this paper, we demonstrate that such an approach can be implemented as a data preprocessing technique and that it can improve the performance of various classifiers on multiclass imbalanced datasets. It has led us to the introduction of a new resampling algorithm, called Similarity Oversampling and Undersampling Preprocessing (SOUP), which resamples examples according to their difficulty. Its experimental evaluation on real and artificial datasets has shown that it is competitive with the most popular decomposition ensembles and better than specialized preprocessing techniques for multi-imbalanced problems.

Download Full-text