Ensemble-based semi-supervised learning approaches for imbalanced splice site datasets

Stănescu, Ana Maria Alexandra; Caragea, Doina

doi:10.1109/bibm.2014.6999196

Cited by 17 publications

(24 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have applied the self-training algorithm defined in [3], which starts by creating a prediction model trained on the labeled data. Then, the model is used to classify the unlabeled observations.…”

Section: Semi-supervised Approachesmentioning

confidence: 99%

“…In spite of SL being a very efficient technique, the production of accurate classifiers depends on the quality and quantity of labeled data. SL approaches require large labeled datasets in order to produce more useful and accurate classification rules [2]. When the working dataset is of reduced size, and there is a lack of labeled data, the application of supervised machine learning algorithms can thus be jeopardized.…”

Section: Introductionmentioning

confidence: 99%

“…Classically, SSL uses large amounts of unlabeled data and small volumes of labeled data. Ideally, the training dataset should be sufficiently large and balanced in order to produce a classification model that outperforms a random decision rule [2]. To assure that the inclusion of unlabeled data will not worsen the performance of the classifier, it is crucial to consider rules that will define whether or not a given sample should be considered in the training process.…”

Section: Introductionmentioning

confidence: 99%

“…In fact, a nonuniform classes' distribution can lead to a partial learning, i.e., a model trained on an unbalanced dataset can tend to ignore the minority class, predicting samples as belonging to the majority one [4]. Therefore, in non-balanced class datasets, alternative solutions have been incorporated in both SL and SSL algorithms, either at data level, such as under and over sampling, or algorithm level, like costsensitive, active learning or even ensemble methods [2][3][4][5][6][7][8].…”

Section: Introductionmentioning

confidence: 99%

“…In many domains, obtaining labeled data is a particularly problematic task. One of the most appealing ways of circumventing the problem of the limited number of labeled samples is through automated semi-supervised learning (SSL) [2][3][4][5]. SSL uses both labeled and unlabeled data to construct a decision rule in order to improve a classifier trained only on the labeled pool.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Semi-supervised Self-training Approaches in Small and Unbalanced Datasets: Application to Xerostomia Radiation Side-Effect

Soares

Dias

Rocha

et al. 2016

XIV Mediterranean Conference on Medical and Biological Engineering and Computing 2016

View full text Add to dashboard Cite

Section: Semi-supervised Approachesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Semi-supervised Self-training Approaches in Small and Unbalanced Datasets: Application to Xerostomia Radiation Side-Effect

Soares

Dias

Rocha

et al. 2016

XIV Mediterranean Conference on Medical and Biological Engineering and Computing 2016

View full text Add to dashboard Cite

PlasmoSEP: Predicting surface-exposed proteins on the malaria parasite using semisupervised self-training and expert-annotated data

et al. 2016

View full text Add to dashboard Cite

Accurate and comprehensive identification of surface-exposed proteins (SEPs) in parasites is a key step in developing novel subunit vaccines. However, the reliability of MS-based high-throughput methods for proteome-wide mapping of SEPs continues to be limited due to high rates of false positives (i.e., proteins mistakenly identified as surface exposed) as well as false negatives (i.e., SEPs not detected due to low expression or other technical limitations). We propose a framework called PlasmoSEP for the reliable identification of SEPs using a novel semisupervised learning algorithm that combines SEPs identified by high-throughput experiments and expert annotation of high-throughput data to augment labeled data for training a predictive model. Our experiments using high-throughput data from the Plasmodium falciparum surface-exposed proteome provide several novel high-confidence predictions of SEPs in P. falciparum and also confirm expert annotations for several others. Furthermore, PlasmoSEP predicts that 25 of 37 experimentally identified SEPs in Plasmodium yoelii salivary gland sporozoites are likely to be SEPs. Finally, PlasmoSEP predicts several novel SEPs in P. yoelii and Plasmodium vivax malaria parasites that can be validated for further vaccine studies. Our computational framework can be easily adapted to improve the interpretation of data from high-throughput studies.

show abstract

Addressing Class Imbalance in Semi-supervised Image Segmentation: A Study on Cardiac MRI

Basak

Ghosal

Sarkar

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Due to the imbalanced and limited data, semi-supervised medical image segmentation methods often fail to produce superior performance for some specific tailed classes. Inadequate training for those particular classes could introduce more noise to the generated pseudo labels, affecting overall learning. To alleviate this shortcoming and identify the under-performing classes, we propose maintaining a confidence array that records class-wise performance during training. A fuzzy fusion of these confidence scores is proposed to adaptively prioritize individual confidence metrics in every sample rather than traditional ensemble approaches, where a set of predefined fixed weights are assigned for all the test cases. Further, we introduce a robust class-wise sampling method and dynamic stabilization for a better training strategy. Our proposed method considers all the under-performing classes with dynamic weighting and tries to remove most of the noises during training. Upon evaluation on two cardiac MRI datasets, ACDC and MMWHS, our proposed method shows effectiveness and generalizability and outperforms several state-of-the-art methods found in the literature.

show abstract

Ensemble-based semi-supervised learning approaches for imbalanced splice site datasets

Cited by 17 publications

References 23 publications

Semi-supervised Self-training Approaches in Small and Unbalanced Datasets: Application to Xerostomia Radiation Side-Effect

Semi-supervised Self-training Approaches in Small and Unbalanced Datasets: Application to Xerostomia Radiation Side-Effect

PlasmoSEP: Predicting surface-exposed proteins on the malaria parasite using semisupervised self-training and expert-annotated data

Addressing Class Imbalance in Semi-supervised Image Segmentation: A Study on Cardiac MRI

Contact Info

Product

Resources

About