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

Janicka, Małgorzata; Lango, Mateusz; Stefanowski, Jerzy

doi:10.2478/amcs-2019-0057

Cited by 37 publications

(14 citation statements)

References 27 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This indicates that the accuracy of at least one of the models is significantly different from others, hence the null hypothesis that all descriptors' performances are the same is rejected. Nemenyi's [51] post hoc test of the average rank of accuracies was performed with a critical difference (CD) of 5.1308. The top three performing descriptors were, 𝑃𝐶𝐴 + 𝐿𝐷𝐴 + 𝐺𝑎𝑏𝑜𝑟, 𝑃𝐶𝐴 + 𝐺𝑎𝑏𝑜𝑟 and Gabor in that order, while PCA was the worst-performing model with an average rank of 6.0.…”

Section: Resultsmentioning

confidence: 99%

Recognizing facial emotions for educational learning settings

Kingsley

Inyang

Msugh

et al. 2022

IJRA

View full text Add to dashboard Cite

Educational learning settings exploit cognitive factors as ultimate feedback to enhance personalization in teaching and learning. But besides cognition, the emotions of the learner which reflect the affective learning dimension also play an important role in the learning process. The emotions can be recognized by tracking explicit behaviors of the learner like facial or vocal expressions. Despite reasonable efforts to recognize emotions, the research community is currently constraints by two issues, namely : i) the lack of efficient feature descriptors to accurately represent and prospectively recogniz e (detecting) the emotions of the learner ; ii) lack of contextual datasets to benchmark performances of emotion recognizers in the learning - speci fic scenarios, resulting in poor generalizations. This paper presents a facial emotion recognition technique (FERT). The FERT is realized through results of preliminary analysis across various facial feature descriptors. Emotions are classified using the m ultiple kernel learning (MKL) method which reportedly possesses good merits. A contextually relevant simulated learning emotion ( SLE ) dataset is introduced to validate the FERT scheme. Recognition performance of the FERT scheme generalizes to 90.3% on the SLE dataset. On more popular but noncontextually datasets, the scheme achi e ved 90.0% and 82.8% respectively extended Cohn Kanade (CK+) and acted facial expressions in the wild ( AFEW ) datasets. A test for the null hypothesis that there is no significant difference in the performances accuracies of the descriptors rather proved otherwise ( x2 = 14 . 619 , df = 5 , p = 0 . 01212 ) for a model considered at a 95% confidence interval.

show abstract

Section: Resultsmentioning

confidence: 99%

Recognizing facial emotions for educational learning settings

Kingsley

Inyang

Msugh

et al. 2022

IJRA

View full text Add to dashboard Cite

show abstract

“…The main goal is to ascertain if there is any base classifiers whose performance is significantly different from others and also perform multiple comparison analysis. This was achieved by implementing non-parametric procedures [44,45] individually to each of the four categories of dataset-target setups for informed statistical inferences. Friedman testa non-parametric variant of the repeated-measures Analysis of Variance, was used to test the null hypothesis that there is no significant difference in the performances (accuracies and time costs) of the classifiers.…”

Section: Statistical Significance and Rank Validationmentioning

confidence: 99%

Optimality Assessments of Classifiers on Single and Multi-labelled Obstetrics Outcome Classification Problems

Udo¹,

Samuel²,

Funebi³

et al. 2021

IJACSA

View full text Add to dashboard Cite

It is indisputable that clinicians cannot exactly state the outcome of pregnancies through conventional knowledge and methods even as the surge in human knowledge continues. Hence, several computational techniques have been adapted for precise pregnancy outcome (PO) prediction. Obstetric datasets for PO determination exist as single label learning (SLL), multi-label learning (MLL) and multi-target (MTP) problems. There is however no single classifier recommended to optimally satisfy the needs of all the classification types. This work therefore identifies six widely used PO classifiers and investigates their performances in all three classification categories; to find the best performing classifier. Obstetric dataset exposed to input rank analysis via Principal component Analysis, produced thirteen (13) significant features for the experiment. Accuracy, F1-measure and build/test time were used as evaluation metrics. Decision tree (DT) had an average accuracy and F1 score of 89.23% and 88.23% respectively, with 1.0 average rank. Under MLL configuration, average accuracy (91.71%) and F1 score (94.28%) were highest in the random forest (RF) which had a 1.0 average test time rank. Using MTP, DT had an average accuracy of 88.80% and average F1 score of 71.13%, the multi-layered perceptron (MLP) had the best time cost with an average rank value of 2.0. From the results, RF is most optimal in terms of accuracy and average rank value, while DT is the most efficient in terms of time cost. The comparative analysis of global averages of the six base classifiers shows that RF is the most optimal algorithm with an average accuracy of 87.3% given all three data setups in the study. MLP on the other hand had an unexpectedly high time cost, making it unsuitable for similar data classifications if time is the main criterion. It is recommended that the choice of the classifier should either be RF or DT depending on the application domain and whether or not time cost is a major consideration.

show abstract

“…It can be seen that d c is the distance corresponding to the R * Mth value of d ij . (6) gives the expression of the distance δ i , representing the minimum distance from particle i to other particles that have a higher ρ i :…”

Section: Apso-rf Unbalanced Data Classification Modelmentioning

confidence: 99%

“…The most commonly used methods to solve the problem of class imbalance are 1) Resampling method [6], which through under-sampling and over-sampling methods to eliminate most class instances or increase a few class instances to change the original class distribution of unbalanced data; it would increase the misclassification of minority classes and loss information in general rules. 2)…”

Section: Introductionmentioning

confidence: 99%

Adaptive Optimization Swarm Algorithm Ensemble Model Applied to the Classification of Unbalanced Data

He¹,

Qin²

2021

IIM

View full text Add to dashboard Cite

In order to solve the problem that the hyper-parameters of the existing random forest-based classification prediction model depend on empirical settings, which leads to unsatisfactory model performance. We propose a based on adaptive particle swarm optimization algorithm random forest model to optimize data classification and an adaptive particle swarm algorithm for optimizing hyper-parameters in the random forest to ensure that the model can better predict unbalanced data. Aiming at the premature convergence problem in the particle swarm optimization algorithm, the population is adaptively divided according to the fitness of the population, and an adaptive update strategy is introduced to enhance the ability of particles to jump out of the local optimum. The main steps of the model are as follows: Normalize the data set, initialize the model on the training set, and then use the particle swarm optimization algorithm to optimize the modeling process to establish a classification model. Experimental results show that our proposed algorithm is better than traditional algorithms, especially in terms of F1-Measure and ACC evaluation standards. The results of the six-keel imbalanced data set demonstrate the advantages of our proposed algorithm.

show abstract

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

Cited by 37 publications

References 27 publications

Recognizing facial emotions for educational learning settings

Recognizing facial emotions for educational learning settings

Optimality Assessments of Classifiers on Single and Multi-labelled Obstetrics Outcome Classification Problems

Adaptive Optimization Swarm Algorithm Ensemble Model Applied to the Classification of Unbalanced Data

Contact Info

Product

Resources

About