Feature selection and resampling in class imbalance learning: Which comes first? An empirical study in the biological domain

Zhang, Chongsheng; Bi, Jingjun; Soda, Paolo

doi:10.1109/bibm.2017.8217782

Cited by 16 publications

(12 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep metric learning methods may also be used to achieve better performance such as Siamese networks [9]. Future work, may also consider loss functions method that perform well on imbalanced datasets [57][58][59][60][61]. There are some limitations in terms of the number of pain datasets from facial expressions in pain detection research.…”

Section: Classification Models Auc Accuracymentioning

confidence: 99%

Ensemble neural network approach detecting pain intensity from facial expressions

Bargshady

Zhou

Deo

et al. 2020

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

This paper reports on research to design an ensemble deep learning framework that integrates fine-tuned, threestream hybrid deep neural network (i.e., Ensemble Deep Learning Model, EDLM), employing Convolutional Neural Network (CNN) to extract facial image features, detect and accurately classify the pain. To develop the approach, the VGGFace is fine-tuned and integrated with Principal Component Analysis and employed to extract features in images from the Multimodal Intensity Pain database at the early phase of the model fusion. Subsequently, a late fusion, three layers hybrid CNN and recurrent neural network algorithm is developed with their outputs merged to produce imageclassified features to classify pain levels. The EDLM model is then benchmarked by means of a single-stream deep learning model including several competing models based on deep learning methods. The results obtained indicate that the proposed framework is able to outperform the competing methods, applied in a multi-level pain detection database to produce a feature classification accuracy that exceeds 89%, with a receiver operating characteristic of 93%. To evaluate the generalization of the proposed EDLM model, the UNBC-McMaster Shoulder Pain dataset is used as a test dataset for all of the modelling experiments, which reveals the efficacy of the proposed method for pain classification from facial images. The study concludes that the proposed EDLM model can accurately classify pain and generate multi-class pain levels for potential applications in the medical informatics area, and should therefore, be explored further in expert systems for detecting and classifying the pain intensity of patients, and automatically evaluating the patients' pain level accurately.

show abstract

Section: Classification Models Auc Accuracymentioning

confidence: 99%

Ensemble neural network approach detecting pain intensity from facial expressions

Bargshady

Zhou

Deo

et al. 2020

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

show abstract

“…After dealing with missing data and class imbalance, keeping only relevant attributes is a building stone in design of predictive models. According to [33]- [34], feature selection methods can be divided into three categories: filter methods, wrapper methods and embedded methods.…”

Section: Features Selectionmentioning

confidence: 99%

“…The first category, which is filter methods, includes CiS, Fish, Ttest, Info and Gini methods [34]. Variable selection is made regardless of the learning algorithms.…”

Section: Features Selectionmentioning

confidence: 99%

“…Under the umbrella of wrapper methods [34], which are the second category, we found search strategies like best-first search, genetic algorithms, hill-climbing search, sequential search and branch-and-bound search. They are proposed to reach optimal local learning performance.…”

Section: Features Selectionmentioning

confidence: 99%

“…But, in practice, wrapper methods are rarely used despite allowing for the detection of possible interactions between variables thanks to variables subsets evaluation. Reasons of their rare use are computation time and overfitting [34]- [36]. In fact, with large variables number, computation time becomes important.…”

Section: Features Selectionmentioning

confidence: 99%

See 2 more Smart Citations

New Approach based on Machine Learning for Short-Term Mortality Prediction in Neonatal Intensive Care Unit

Kefi¹,

Aloui²,

Naceur³

2019

IJACSA

View full text Add to dashboard Cite

Mortality remains one of the most important outcomes to predict in Intensive Care Units (ICUs). In fact, the sooner mortality is predicted, the better critical decisions are made by doctors based on patient's illness severity. In this paper, a new approach based on Machine Learning (ML) techniques for short-term mortality prediction in Neonatal Intensive Care Unit (NICU) is proposed. This approach relies on many steps. At first, relevant features are selected from available data upon neonates' admission and from the time-series variables collected within the two first hours of stay in the NICU from the Medical Information Mart for Intensive Care III (MIMIC-III). After that, to predict mortality, many classifiers were tested which are Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Classification and Regression Trees (CART), Logistic Regression (LR), Support Vector Machine (SVM), Naïve Bayes (NB) and Random Forest (RF). The experimental results showed that LDA was the best performing classifier with an accuracy equal to 0.947 and AUROC equal to 0.97 with 31 features. The third step of this approach is mortality time prediction using the Galaxy-Random Forest method achieving an f-score equal to 0.871. The proposed approach compared favorably in terms of time, accuracy and AUROC with existing scoring systems and ML techniques. It is the first work predicting neonates mortality based on ML techniques and time-series data after only two hours of admission to the NICU.

show abstract

Prediction of pituitary adenoma surgical consistency: radiomic data mining and machine learning on T2-weighted MRI

et al. 2020

View full text Add to dashboard Cite

Purpose Pituitary macroadenoma consistency can influence the ease of lesion removal during surgery, especially when using a transsphenoidal approach. Unfortunately, it is not assessable on standard qualitative MRI. Radiomic texture analysis could help in extracting mineable quantitative tissue characteristics. We aimed to assess the accuracy of texture analysis combined with machine learning in the preoperative evaluation of pituitary macroadenoma consistency in patients undergoing endoscopic endonasal surgery. Methods Data of 89 patients (68 soft and 21 fibrous macroadenomas) who underwent MRI and transsphenoidal surgery at our institution were retrospectively reviewed. After manual segmentation, radiomic texture features were extracted from original and filtered MR images. Feature stability analysis and a multistep feature selection were performed. After oversampling to balance the classes, 80% of the data was used for hyperparameter tuning via stratified 5-fold cross-validation, while a 20% hold-out set was employed for its final testing, using an Extra Trees ensemble meta-algorithm. The reference standard was based on surgical findings. Results A total of 1118 texture features were extracted, of which 741 were stable. After removal of low variance (n = 4) and highly intercorrelated (n = 625) parameters, recursive feature elimination identified a subset of 14 features. After hyperparameter tuning, the Extra Trees classifier obtained an accuracy of 93%, sensitivity of 100%, and specificity of 87%. The area under the receiver operating characteristic and precision-recall curves was 0.99. Conclusion Preoperative T2-weighted MRI texture analysis and machine learning could predict pituitary macroadenoma consistency.

show abstract

Feature selection and resampling in class imbalance learning: Which comes first? An empirical study in the biological domain

Cited by 16 publications

References 18 publications

Ensemble neural network approach detecting pain intensity from facial expressions

Ensemble neural network approach detecting pain intensity from facial expressions

New Approach based on Machine Learning for Short-Term Mortality Prediction in Neonatal Intensive Care Unit

Prediction of pituitary adenoma surgical consistency: radiomic data mining and machine learning on T2-weighted MRI

Contact Info

Product

Resources

About