scholarly journals Comparison of GANs for Covid-19 X-ray classification

2021 ◽  
Author(s):  
Luiz Felipe Cavalcanti ◽  
Lilian Berton
Keyword(s):  
Machine Learning ◽  
Data Augmentation ◽  
Original Data ◽  
Machine Learning Algorithms ◽  
Generative Adversarial Networks ◽  
Artificial Data ◽  
X Ray ◽  
Adversarial Networks ◽  
Radiological Images

Image classification has been applied to several real problems. However, getting labeled data is a costly task, since it demands time, resources and experts. Furthermore, some domains like disease detection suffer from unbalanced classes. These scenarios are challenging and degrade the performance of machine learning algorithms. In these cases, we can use Data Augmentation (DA) approaches to increase the number of labeled examples in a dataset. The objective of this work is to analyze the use of Generative Adversarial Networks (GANs) as DA, which are capable of synthesizing artificial data from the original data, under an adversarial process of two neural networks. The GANs are applied in the classification of unbalanced Covid-19 radiological images. Increasing the number of images led to better accuracy for all the GANs tested, especially in the multi-label dataset, mitigating the bias for unbalanced classes.

scholarly journals Data Augmentation of X-Ray Images in Baggage Inspection Based on Generative Adversarial Networks

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 86536-86544 ◽  
Author(s):  
Yue Zhu ◽  
Yutao Zhang ◽  
Haigang Zhang ◽  
Jinfeng Yang ◽  
Zihao Zhao
Keyword(s):  
Data Augmentation ◽  
Generative Adversarial Networks ◽  
X Ray ◽  
Adversarial Networks

scholarly journals Data Augmentation for X-Ray Prohibited Item Images Using Generative Adversarial Networks

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 28894-28902 ◽  
Author(s):  
Jinfeng Yang ◽  
Zihao Zhao ◽  
Haigang Zhang ◽  
Yihua Shi
Keyword(s):  
Data Augmentation ◽  
Generative Adversarial Networks ◽  
X Ray ◽  
Adversarial Networks

scholarly journals Classification of masked image data

PLoS ONE ◽  
2021 ◽  
Vol 16 (7) ◽  
pp. e0254181
Author(s):  
Kamila Lis ◽  
Mateusz Koryciński ◽  
Konrad A. Ciecierski
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Image Data ◽  
Original Data ◽  
Machine Learning Algorithms ◽  
General Data Protection Regulation ◽  
Additional Information ◽  
Classification Of Images ◽  
Applications Of Machine Learning

Data classification is one of the most commonly used applications of machine learning. The are many developed algorithms that can work in various environments and for different data distributions that perform this task with excellence. Classification algorithms, just like other machine learning algorithms have one thing in common: in order to operate on data, they must see the data. In the present world, where concerns about privacy, GDPR (General Data Protection Regulation), business confidentiality and security are growing bigger and bigger; this requirement to work directly on the original data might become, in some situations, a burden. In this paper, an approach to the classification of images that cannot be directly accessed during training has been made. It has been shown that one can train a deep neural network to create such a representation of the original data that i) without additional information, the original data cannot be restored, and ii) that this representation—called a masked form—can still be used for classification purposes. Moreover, it has been shown that classification of the masked data can be done using both classical and neural network-based classifiers.

scholarly journals Handling Imbalanced Data in Intrusion Detection Systems using Generative Adversarial Networks

2020 ◽  
Vol 2020 (1) ◽  
pp. 1-13
Author(s):  
Ly Vu ◽  
Quang Uy Nguyen
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Detection System ◽  
Imbalanced Data ◽  
Original Data ◽  
Machine Learning Techniques ◽  
Generative Adversarial Networks ◽  
Detection Systems ◽  
Adversarial Networks ◽  
Attack Data

Machine learning-based intrusion detection hasbecome more popular in the research community thanks to itscapability in discovering unknown attacks. To develop a gooddetection model for an intrusion detection system (IDS) usingmachine learning, a great number of attack and normal datasamples are required in the learning process. While normaldata can be relatively easy to collect, attack data is muchrarer and harder to gather. Subsequently, IDS datasets areoften dominated by normal data and machine learning modelstrained on those imbalanced datasets are ineffective in detect-ing attacks. In this paper, we propose a novel solution to thisproblem by using generative adversarial networks to generatesynthesized attack data for IDS. The synthesized attacks aremerged with the original data to form the augmented dataset.Three popular machine learning techniques are trained on theaugmented dataset. The experiments conducted on the threecommon IDS datasets and one our own dataset show thatmachine learning algorithms achieve better performance whentrained on the augmented dataset of the generative adversarialnetworks compared to those trained on the original datasetand other sampling techniques. The visualization techniquewas also used to analyze the properties of the synthesizeddata of the generative adversarial networks and the others.

scholarly journals Counterfactual Examples for Data Augmentation: A Case Study

2021 ◽  
Vol 34 (1) ◽  
Author(s):  
Md Golam Moula Mehedi Hasan ◽  
Douglas A. Talbert
Keyword(s):  
Machine Learning ◽  
Potential Application ◽  
Data Augmentation ◽  
Generative Adversarial Networks ◽  
Application Area ◽  
Learning Models ◽  
Adversarial Networks ◽  
Feature Values ◽  
Machine Learning Models

Counterfactual explanations are gaining in popularity as a way of explaining machine learning models. Counterfactual examples are generally created to help interpret the decision of a model. In this case, if a model makes a certain decision for an instance, the counterfactual examples of that instance reverse the decision of the model. The counterfactual examples can be created by craftily changing particular feature values of the instance. Though counterfactual examples are generated to explain the decision of machine learning models, in this work, we explore another potential application area of counterfactual examples, whether counterfactual examples are useful for data augmentation. We demonstrate the efficacy of this approach on the widely used “Adult-Income” dataset. We consider several scenarios where we do not have enough data and use counterfactual examples to augment the dataset. We compare our approach with Generative Adversarial Networks approach for dataset augmentation. The experimental results show that our proposed approach can be an effective way to augment a dataset.

scholarly journals Multivariate mixed kernel density estimators and their application in machine learning for classification of biological objects based on spectral measurements

2019 ◽  
Vol 43 (4) ◽  
pp. 677-691
Author(s):  
A.A. Sirota ◽  
A.O. Donskikh ◽  
A.V. Akimov ◽  
D.A. Minakov
Keyword(s):  
Machine Learning ◽  
Density Estimation ◽  
Data Augmentation ◽  
Kernel Density ◽  
Machine Learning Algorithms ◽  
Spectral Measurements ◽  
Density Estimates ◽  
Biological Objects ◽  
Density Estimators

A problem of non-parametric multivariate density estimation for machine learning and data augmentation is considered. A new mixed density estimation method based on calculating the convolution of independently obtained kernel density estimates for unknown distributions of informative features and a known (or independently estimated) density for non-informative interference occurring during measurements is proposed. Properties of the mixed density estimates obtained using this method are analyzed. The method is compared with a conventional Parzen-Rosenblatt window method applied directly to the training data. The equivalence of the mixed kernel density estimator and the data augmentation procedure based on the known (or estimated) statistical model of interference is theoretically and experimentally proven. The applicability of the mixed density estimators for training of machine learning algorithms for the classification of biological objects (elements of grain mixtures) based on spectral measurements in the visible and near-infrared regions is evaluated.

scholarly journals Generating Rainfall Data using GANs

2019 ◽  
Vol 9 (2) ◽  
pp. 4124-4127
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Neural Nets ◽  
Rainfall Data ◽  
Generative Adversarial Networks ◽  
Rainfall Prediction ◽  
Adversarial Networks

Rainfall prediction is one of the major discussions in the meteorology because it is a major factor on which many things in the environment rely on. Neural Nets or any other machine learning algorithms need very large amount of data in order to achieve better accuracy but sometimes data can be scarce, this type of problems can be resolved by using Generative Adversarial Networks. Generative Adversarial Networks which are known for generating data by using the existing features from the old data, like generating images etc. There are many types of datasets which are scarce, rainfall data in one among them. So, the proposed system generates the rainfall data using GAN. The generated data is used for training the classifier, which predicts the rainfall.

scholarly journals A Comparative Study of the Impact of Data Augmentation in Machine Learning Based Classification Accuracy

2021 ◽  
Author(s):  
Arif Jahangir
Keyword(s):  
Machine Learning ◽  
Data Augmentation ◽  
Machine Learning Algorithms ◽  
Quadratic Discriminant Analysis ◽  
Crucial Importance ◽  
Markov Transition Matrix ◽  
Original Dataset ◽  
Markov Transition ◽  
The Impact

Traumatic Brain Injury is the primary cause of death and disability all over the world. Monitoring the intracranial pressure (ICP) and classifying it for hypertension signals is of crucial importance. This thesis explores the possibility of a better classification of the ICP signal and detection of hypertensive signal prior to the actual occurrence of the hypertensive episodes. This study differ from other approaches astime series is converted into images by Gramian angular field and Markov transition matrix and augmented with data. Due to unbalanced data, the effect of smote extended nearest neighbour algorithm for balancing the data is examined. We use various machine learning algorithms to classify the ICP signals. The results obtained shoe that Ada boost performance is the best among compared algorithms. F1 score of the Ada boost is 0.95 on original dataset, and 0.9967 on balanced and augmented dataset. Quadratic Discriminant Analysis F1 score is 1 when data is augmented and balanced.

scholarly journals A Multi-Stage GAN for Multi-Organ Chest X-ray Image Generation and Segmentation

Mathematics ◽  
2021 ◽  
Vol 9 (22) ◽  
pp. 2896
Author(s):  
Giorgio Ciano ◽  
Paolo Andreini ◽  
Tommaso Mazzierli ◽  
Monica Bianchini ◽  
Franco Scarselli
Keyword(s):  
Data Augmentation ◽  
Semantic Segmentation ◽  
Generative Adversarial Networks ◽  
Radiographic Images ◽  
X Ray ◽  
Adversarial Networks ◽  
Multi Stage ◽  
Segmentation Methods ◽  
Chest X Ray ◽  
Time Required

Multi-organ segmentation of X-ray images is of fundamental importance for computer aided diagnosis systems. However, the most advanced semantic segmentation methods rely on deep learning and require a huge amount of labeled images, which are rarely available due to both the high cost of human resources and the time required for labeling. In this paper, we present a novel multi-stage generation algorithm based on Generative Adversarial Networks (GANs) that can produce synthetic images along with their semantic labels and can be used for data augmentation. The main feature of the method is that, unlike other approaches, generation occurs in several stages, which simplifies the procedure and allows it to be used on very small datasets. The method was evaluated on the segmentation of chest radiographic images, showing promising results. The multi-stage approach achieves state-of-the-art and, when very few images are used to train the GANs, outperforms the corresponding single-stage approach.

Sign in / Sign up

Export Citation Format

Share Document