G-mean based extreme learning machine for imbalance learning

Ri, JongHyok; Kim, Hun

doi:10.1016/j.dsp.2019.102637

Cited by 33 publications

(8 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since sensitivity and specificity take values in the [0, 1] interval, so does Gmean. Gmean is suited for class-unbalanced problems as this metric measures the balance between classification performances on both the majority and minority classes [36]. The closer Gmean is to 1, the better is the classification.…”

Section: Predictive Accuracy Calculationmentioning

confidence: 99%

Machine learning-based predictions of dietary restriction associations across ageing-related genes

et al. 2022

View full text Add to dashboard Cite

Background Dietary restriction (DR) is the most studied pro-longevity intervention; however, a complete understanding of its underlying mechanisms remains elusive, and new research directions may emerge from the identification of novel DR-related genes and DR-related genetic features. Results This work used a Machine Learning (ML) approach to classify ageing-related genes as DR-related or NotDR-related using 9 different types of predictive features: PathDIP pathways, two types of features based on KEGG pathways, two types of Protein–Protein Interactions (PPI) features, Gene Ontology (GO) terms, Genotype Tissue Expression (GTEx) expression features, GeneFriends co-expression features and protein sequence descriptors. Our findings suggested that features biased towards curated knowledge (i.e. GO terms and biological pathways), had the greatest predictive power, while unbiased features (mainly gene expression and co-expression data) have the least predictive power. Moreover, a combination of all the feature types diminished the predictive power compared to predictions based on curated knowledge. Feature importance analysis on the two most predictive classifiers mostly corroborated existing knowledge and supported recent findings linking DR to the Nuclear Factor Erythroid 2-Related Factor 2 (NRF2) signalling pathway and G protein-coupled receptors (GPCR). We then used the two strongest combinations of feature type and ML algorithm to predict DR-relatedness among ageing-related genes currently lacking DR-related annotations in the data, resulting in a set of promising candidate DR-related genes (GOT2, GOT1, TSC1, CTH, GCLM, IRS2 and SESN2) whose predicted DR-relatedness remain to be validated in future wet-lab experiments. Conclusions This work demonstrated the strong potential of ML-based techniques to identify DR-associated features as our findings are consistent with literature and recent discoveries. Although the inference of new DR-related mechanistic findings based solely on GO terms and biological pathways was limited due to their knowledge-driven nature, the predictive power of these two features types remained useful as it allowed inferring new promising candidate DR-related genes.

show abstract

Section: Predictive Accuracy Calculationmentioning

confidence: 99%

Machine learning-based predictions of dietary restriction associations across ageing-related genes

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The classical extreme learning machine (ELM) algorithm is unable to generate better performance in case of the imbalanced dataset. Ri et al [ 33 ] defined a novel cost function based on G -mean for ELM optimization problem in imbalanced data learning. They tested their methodology on 11 multi-class and 58 binary repositories having diverse gradation of imbalance ratio.…”

Section: Literature Reviewmentioning

confidence: 99%

An Improved Hybrid Approach for Handling Class Imbalance Problem

Desuky

Hussain

2021

Arab J Sci Eng

View full text Add to dashboard Cite

Class imbalance issue that presents in many real-world datasets exhibit favouritism toward the majority class and showcases poor performance for the minority class. Such misclassifications may incur dubious outcome in case of disease diagnosis and other critical applications. Hence, it is a hot topic for the researchers to tackle the class imbalance issue. We present a novel hybrid approach for handling such datasets. We utilize simulated annealing algorithm for undersampling and apply support vector machine, decision tree, k-nearest neighbor and discriminant analysis for the classification task. We validate our technique in 51 real-world datasets and compare it with other recent works. Our technique yields better efficacy than the existing techniques and hence it can be applied in imbalance datasets to mitigate the misclassification.

show abstract

“…Compared with other existing neural network learning methods, such as backpropagation networks (BP) [37], and typical machine learning algorithms, such as support vector machines (SVM) [10,38], the ELM performs the random initialization of input weights, and only by solving the equation can the advantage of the primary weight be determined. Therefore, the ELM algorithm has fast and powerful learning capabilities [39][40][41]. The internal state of the ELM has the function of mapping dynamic characteristics so that the system has the function of time-varying characteristics, and the generalization performance of the model is very good.…”

Section: Elm Classification Modelmentioning

confidence: 99%

Feature Fusion Combined With Raman Spectroscopy for Early Diagnosis of Cervical Cancer

Huiting

Chen

et al. 2021

IEEE Photonics J.

View full text Add to dashboard Cite

Cervical cancer is a serious threat to women's health due to malignant tumours, and early detection can greatly reduce mortality. In this paper, cervical tissue was used as the research object, and Raman spectroscopy analysis of cervical inflammation and precancerous tissues was used to detect cervical cancer. This provides a clinical basis for the use of Raman spectroscopy in analysis of cervical precancerous lesions. In this study, the actual Raman spectrum signal of precancerous cervical tissue was collected, and the PLS and Relief methods were used to extract the signal characteristics of the spectrum. Then, we established and compared KNN and ELM classification models and finally achieved the early diagnosis of cervical cancer. This experiment designed a novel feature fusion method in feature extraction, and we used the first and second derivative features that reflect more peak details of the original spectrum for fusion.The accuracy rate of KNN without feature fusion is 88.17%, and the accuracy rate after fusion is 93.55%. The accuracy rate of ELM without feature fusion is 90.81%, and the accuracy rate after fusion is 93.51%. The results show that the accuracy of feature fusion has been improved to a certain extent, and this method is expected to be used as a new method of spectral data fusion.

show abstract

G-mean based extreme learning machine for imbalance learning

Cited by 33 publications

References 24 publications

Machine learning-based predictions of dietary restriction associations across ageing-related genes

Machine learning-based predictions of dietary restriction associations across ageing-related genes

An Improved Hybrid Approach for Handling Class Imbalance Problem

Feature Fusion Combined With Raman Spectroscopy for Early Diagnosis of Cervical Cancer

Contact Info

Product

Resources

About