Imbalanced data learning by minority class augmentation using capsule adversarial networks

Shamsolmoali, Pourya; Zareapoor, Masoumeh; Shen, Linlin; Sadka, A.H.; Yang, Jie

doi:10.1016/j.neucom.2020.01.119

Cited by 58 publications

(53 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the proposed generator could be adopted in other application fields for the modeling of visual information, such as video captioning and action recognition. Finally, there were several recent research works dealing with the problem of complex and imbalanced data in GAN networks [ 60 , 61 , 62 , 63 , 64 ]. Although the study of this problem is out of the scope of this paper, we consider that future work in this direction can further improve the accuracy of the proposed network architecture.…”

Section: Discussionmentioning

confidence: 99%

Continuous Sign Language Recognition through a Context-Aware Generative Adversarial Network

Papastratis

Dimitropoulos

Daras

2021

Sensors

View full text Add to dashboard Cite

Continuous sign language recognition is a weakly supervised task dealing with the identification of continuous sign gestures from video sequences, without any prior knowledge about the temporal boundaries between consecutive signs. Most of the existing methods focus mainly on the extraction of spatio-temporal visual features without exploiting text or contextual information to further improve the recognition accuracy. Moreover, the ability of deep generative models to effectively model data distribution has not been investigated yet in the field of sign language recognition. To this end, a novel approach for context-aware continuous sign language recognition using a generative adversarial network architecture, named as Sign Language Recognition Generative Adversarial Network (SLRGAN), is introduced. The proposed network architecture consists of a generator that recognizes sign language glosses by extracting spatial and temporal features from video sequences, as well as a discriminator that evaluates the quality of the generator’s predictions by modeling text information at the sentence and gloss levels. The paper also investigates the importance of contextual information on sign language conversations for both Deaf-to-Deaf and Deaf-to-hearing communication. Contextual information, in the form of hidden states extracted from the previous sentence, is fed into the bidirectional long short-term memory module of the generator to improve the recognition accuracy of the network. At the final stage, sign language translation is performed by a transformer network, which converts sign language glosses to natural language text. Our proposed method achieved word error rates of 23.4%, 2.1%, and 2.26% on the RWTH-Phoenix-Weather-2014 and the Chinese Sign Language (CSL) and Greek Sign Language (GSL) Signer Independent (SI) datasets, respectively.

show abstract

Section: Discussionmentioning

confidence: 99%

Continuous Sign Language Recognition through a Context-Aware Generative Adversarial Network

Papastratis

Dimitropoulos

Daras

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Here, the ratio of the majority sample number to the minority sample is 6.5. By the SMOTE technique, this ratio was reduced to 1 [9] , [10] . The SMOTE method is based on the algorithm which is given below [32] .…”

Section: Methodsmentioning

confidence: 99%

“…The most widely used class imbalance measure in the literature is calculated as the ratio of the sample numbers of the largest majority class and the smallest minority class and is called the imbalance ratio. The higher this ratio is the greater the imbalance scope of the dataset and causes over fitting problem in the classification process and decreases performance [9] , [10] . A widely used method to eliminate the imbalance between data classes encountered by Deep Learning classifier models is SMOTE (Synthetic Minority Over-sampling Technique) method.…”

Section: Introductionmentioning

confidence: 99%

A novel classifier architecture based on deep neural network for COVID-19 detection using laboratory findings

Göreke

Sarı

Koçkanat

2021

Applied Soft Computing

View full text Add to dashboard Cite

Unfortunately, Coronavirus disease 2019 (COVID-19) is spreading rapidly all over the world. Along with causing many deaths, it has substantially affected the social life, economics, and infrastructure worldwide in a negative manner. Therefore, it is very important to be able to diagnose the COVID-19 quickly and correctly. In this study, a new feature group based on laboratory findings was obtained considering ethnical and genetic differences for interpretation of blood data. Then, using this feature group, a new hybrid classifier architecture based on deep learning was designed and COVID-19 detection was made. Classification performance indicators were obtained as accuracy of 94.95%, F1-score of 94.98%, precision of 94.98%, recall of 94.98% and AUC of 100%. Achieved results were compared with those of the deep learning classifiers suggested in literature. According to these results, proposed method shows superior performance and can provide more convenience and precision to experts for diagnosis of COVID-19 disease.

show abstract

“…Thus, people are directed to make augmentation of any data entering any system. Therefore, we will provide a method that benefits researchers to make augmentation of data so that they can deal with it later when it enters into deep learning and solves too many problems such as the problem of overfitting and memo, especially if these databases are imbalanced [15,16].…”

Section: Small Data and Augmentationmentioning

confidence: 99%

Why Are Generative Adversarial Networks Vital for Deep Neural Networks? A Case Study on COVID-19 Chest X-Ray Images

Shams

Elzeki

Elfattah³

et al. 2020

Studies in Big Data

View full text Add to dashboard Cite

The need to generate large scale datasets from a limited number of determined data is highly required. Deep neural networks (DNN) is one of the most important and effective tools in machine learning (ML) that required large scale datasets. Recently, generative adversarial networks (GAN) is considered as the most potent and effective method for data augmentation. In this chapter, we investigated the importance of using GAN as a preprocessing stage to applied DNN for image data augmentation. Moreover, we present a case study of using GAN networks for a limited COVID-19 X-Ray Chest images. The results indicate that the proposed system based on using GAN-DNN is powerful with minimum loss function for detecting COVID-19 X-Ray Chest images. Stochastic gradient descent (SGD) and Improved Adam (IAdam) optimizers are used during the training process of the COVID-19 X-Ray images, and the evaluation results depend on loss function are determined to ensure the reliability of the proposed GAN architecture.

show abstract

Imbalanced data learning by minority class augmentation using capsule adversarial networks

Cited by 58 publications

References 43 publications

Continuous Sign Language Recognition through a Context-Aware Generative Adversarial Network

Continuous Sign Language Recognition through a Context-Aware Generative Adversarial Network

A novel classifier architecture based on deep neural network for COVID-19 detection using laboratory findings

Why Are Generative Adversarial Networks Vital for Deep Neural Networks? A Case Study on COVID-19 Chest X-Ray Images

Contact Info

Product

Resources

About