Data Augmentation of Minority Class with Transfer Learning for Classification of Imbalanced Breast Cancer Dataset Using Inception-V3

Saini, Manisha; Susan, Seba

doi:10.1007/978-3-030-31332-6_36

Cited by 28 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Saini and Susan [11] The DCGAN [11] and two networks model [12] considerably reduce the imbalance data problem and have limitations of overfitting problem. The IRRCNN model [13] has a limitation of overfitting problem and imbalance data problem in the classification.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

RETRACTED: Breast Cancer Classification using Improved Hybrid Model by Leveraging Slime Mould Algorithm and Whale Optimization Algorithm

Vaka

Soni

Abualigah

2023

Preprint

View full text Add to dashboard Cite

Breast Cancer Classification is important in the medical field for disease diagnosis and assists in decisions in treatment. Poor convergence and local optima are common limitations in the existing feature selection techniques. Overfitting and imbalance data problems are common limitations in existing classifiers. The hybrid method of Whale Optimization Algorithm (WOA) – Slime Mould Algorithm (SMA) is proposed for relevant feature selection and an Auto stacked encoder is applied for classification. The WOA technique performs exploration in the first half of the iteration and the SMA method performs exploitation in the second half of iterations for relevant feature selection. The WOA-SMA technique is applied in BreakHis and IDC datasets to evaluate breast cancer classification. The ResNet18 model uses the convolutional layer, pooling layer, and fully connected layer for feature extraction process. The stacked autoencoder technique helps to map relevant features to increase learning rate of the model. The feature selection method of WOA-SMA selects unique features to improve learning efficiency of the model.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

“…So, the ReLU activation function is not suffering from gradient vanishing or diffusion. The ReLU function is given in Equation (12).…”

Section: Auto-stacked Encodermentioning

confidence: 99%

RETRACTED: Breast Cancer Classification using Improved Hybrid Model by Leveraging Slime Mould Algorithm and Whale Optimization Algorithm

Vaka

Soni

Abualigah

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Imbalanced learning algorithms specific to the field of Computer Vision need to be devised since resampling strategies are not practical in situations when the computational complexity is high, the number of classes is too high and the class‐distribution profile is extremely uneven, as is the situation with most real‐world vision tasks. Data augmentation of the minority class was explored in Reference 94 as a simple but effective solution to correct class‐imbalance in Benign vs Malignant cancer classification for the BREAKHIS cancer dataset. Data augmentation is equivalent to oversampling, in computer vision.…”

Section: Future Directions Applications and Challengesmentioning

confidence: 99%

The balancing trick: Optimized sampling of imbalanced datasets—A brief survey of the recent State of the Art

Susan

Kumar

2020

Engineering Reports

Self Cite

View full text Add to dashboard Cite

This survey paper focuses on one of the current primary issues challenging data mining researchers experimenting on real-world datasets. The problem is that of imbalanced class distribution that generates a bias toward the majority class due to insufficient training samples from the minority class. The current machine learning and deep learning algorithms are trained on datasets that are insufficiently represented in certain categories. On the other hand, some other classes have surplus samples due to the ready availability of data from these categories.Conventional solutions suggest undersampling of the majority class and/or oversampling of the minority class for balancing the class distribution prior to the learning phase. Though this problem of uneven class distribution is, by and large, ignored by researchers focusing on the learning technology, a need has now arisen for incorporating balance correction and data pruning procedures within the learning process itself. This paper surveys a plethora of conventional and recent techniques that address this issue through intelligent representations of samples from the majority and minority classes, that are given as input to the learning module. The application of nature-inspired evolutionary algorithms to intelligent sampling is examined, and so are hybrid sampling strategies that select and retain the difficult-to-learn samples and discard the easy-to-learn samples. The findings by various researchers are summarized to a logical end, and various possibilities and challenges for future directions in research are outlined. K E Y W O R D Sclass-imbalance problem, hybrid sampling, imbalanced data, oversampling, sampling, undersampling INTRODUCTIONLearning from imbalanced datasets results in a bias toward the majority class whose labeled samples are available in plenty as compared to the insufficiently represented minority class. 1 In data mining, factors that bring down the classifier performance are the intrinsic characteristics of the data and an uneven class distribution. 2 Lack of adequate data in the minority class results in a fuzzy and ever-varying decision boundary, leading to erroneous results. The problem isThis is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.

show abstract

“…The InceptionV3 architecture (Szegedy et al, 2016) is used for the classification as it is one of the networks with the best accuracy in relation to the rate of operations required for their training (Canziani et al, 2016). This architecture has proven to work well in a multitude of object classification applications (Saini and Susan, 2019;Xia et al, 2017). The InceptionV3 network has an input size of 299x299x3 pixels.…”

Section: Classificationmentioning

confidence: 99%

Transfer Learning for Indoor Object Classification: From Images to Point Clouds

Balado

Díaz-Vilariño

Verbree

et al. 2020

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Indoor furniture is of great relevance to building occupants in everyday life. Furniture occupies space in the building, gives comfort, establishes order in rooms and locates services and activities. Furniture is not always static; the rooms can be reorganized according to the needs. Keeping the building models up to date with the current furniture is key to work with indoor environments. Laser scanning technology can acquire indoor environments in a fast and precise way, and recent artificial intelligence techniques can classify correctly the objects that contain. The objective of this work is to study how to minimize the use of point cloud samples in Neural Network training, tedious to label, and replace them with images obtained from online sources. For this, point clouds are converted to images by means of rotations and projections. The conversion of a 3D vector data to a 2D raster allows the use of Convolutional Neural Networks, the achievement of several images for each acquired point cloud object and the combination with images obtained from online sources, such as Google Images. The images have been distributed among the validation and testing training sets following different percentages. The results show that, although point cloud images cannot be completely dispensed within the training set, only 10% of these achieve high accuracy in the classification.

show abstract

Data Augmentation of Minority Class with Transfer Learning for Classification of Imbalanced Breast Cancer Dataset Using Inception-V3

Cited by 28 publications

References 13 publications

RETRACTED: Breast Cancer Classification using Improved Hybrid Model by Leveraging Slime Mould Algorithm and Whale Optimization Algorithm

RETRACTED: Breast Cancer Classification using Improved Hybrid Model by Leveraging Slime Mould Algorithm and Whale Optimization Algorithm

The balancing trick: Optimized sampling of imbalanced datasets—A brief survey of the recent State of the Art

Transfer Learning for Indoor Object Classification: From Images to Point Clouds

Contact Info

Product

Resources

About