Learning Convolutional Neural Network Using Data from Other Domains in case of Insufficient Data

Objective: Pneumonia is a lung infection and causes the inflammation of the small air sacs (Alveoli) in one or both lungs. Proper and faster diagnosis of pneumonia at an early stage is imperative for optimal patient care. Currently, chest X-ray is considered as the best imaging modality for diagnosing pneumonia. However, the interpretation of chest X-ray images is challenging. To this end, we aimed to use an automated convolutional neural network-based transfer-learning approach to detect pneumonia in paediatric chest radiographs. Methods: Herein, an automated convolutional neural network-based transfer-learning approach using four different pre-trained models (i.e. VGG19, DenseNet121, Xception, and ResNet50) was applied to detect pneumonia in children (1–5 years) chest X-ray images. The performance of different proposed models for testing data set was evaluated using five performances metrics, including accuracy, sensitivity/recall, Precision, area under curve, and F1 score. Results: All proposed models provide accuracy greater than 83.0% for binary classification. The pre-trained DenseNet121 model provides the highest classification performance of automated pneumonia classification with 86.8% accuracy, followed by Xception model with an accuracy of 86.0%. The sensitivity of the proposed models was greater than 91.0%. The Xception and DenseNet121 models achieve the highest classification performance with F1-score greater than 89.0%. The plotted area under curve of receiver operating characteristics of VGG19, Xception, ResNet50, and DenseNet121 models are 0.78, 0.81, 0.81, and 0.86, respectively. Conclusion: Our data showed that the proposed models achieve a high accuracy for binary classification. Transfer learning was used to accelerate training of the proposed models and resolve the problem associated with insufficient data. We hope that these proposed models can help radiologists for a quick diagnosis of pneumonia at radiology departments. Moreover, our proposed models may be useful to detect other chest-related diseases such as novel Coronavirus 2019. Advances in knowledge: Herein, we used transfer learning as a machine learning approach to accelerate training of the proposed models and resolve the problem associated with insufficient data. Our proposed models achieved accuracy greater than 83.0% for binary classification.

Download Full-text

Damage Detection of Composite Materials Using Data Fusion With Deep Neural Networks

Volume 10B: Structures and Dynamics ◽

10.1115/gt2020-15097 ◽

2020 ◽

Author(s):

Shweta Dabetwar ◽

Stephen Ekwaro-Osire ◽

João Paulo Dias

Keyword(s):

Neural Network ◽

Neural Networks ◽

Composite Materials ◽

Data Fusion ◽

Damage Detection ◽

Convolutional Neural Network ◽

Deep Neural Networks ◽

Mixed Data ◽

Image Encoding ◽

Using Data

Abstract Composite materials have enormous applications in various fields. Thus, it is important to have an efficient damage detection method to avoid catastrophic failures. Due to the existence of multiple damage modes and the availability of data in different formats, it is important to employ efficient techniques to consider all the types of damage. Deep neural networks were seen to exhibit the ability to address similar complex problems. The research question in this work is ‘Can data fusion improve damage classification using the convolutional neural network?’ The specific aims developed were to 1) assess the performance of image encoding algorithms, 2) classify the damage using data from separate experimental coupons, and 3) classify the damage using mixed data from multiple experimental coupons. Two different experimental measurements were taken from NASA Ames Prognostic Repository for Carbon Fiber Reinforced polymer. To use data fusion, the piezoelectric signals were converted into images using Gramian Angular Field (GAF) and Markov Transition Field. Using data fusion techniques, the input dataset was created for a convolutional neural network with three hidden layers to determine the damage states. The accuracies of all the image encoding algorithms were compared. The analysis showed that data fusion provided better results as it contained more information on the damages modes that occur in composite materials. Additionally, GAF was shown to perform the best. Thus, the combination of data fusion and deep neural network techniques provides an efficient method for damage detection of composite materials.

Download Full-text

Image Scale Estimation Using Surface Textures for Quantitative Visual Inspection

Journal of Computational Vision and Imaging Systems ◽

10.15353/jcvis.v6i1.3541 ◽

2021 ◽

Vol 6 (1) ◽

pp. 1-3

Author(s):

Juan Park ◽

Chul Min Yeum ◽

Trevor Hrynyk

Keyword(s):

Neural Network ◽

Regression Model ◽

Convolutional Neural Network ◽

Surface Texture ◽

Visual Inspection ◽

Estimation Error ◽

Estimation Technique ◽

Surface Textures ◽

Scale Estimation ◽

Using Data

In this study, a learning-based scale estimation technique is proposed to enable quantitative evaluation of inspection regions. The underlying idea is that surface texture of structures (i.e. bridges or buildings) captured on images contains the scale information of the corresponding images, which is represented by pixel per physical dimension (e.g., mm, inch). This allows training a regression model that provides a relationship between surface textures on images and their corresponding scales. Deep convolutional neural network is used to extract scale-related features from the texture patches and estimate their scales. The trained model can be exploited to estimate scales for all images captured from structure surfaces that have similar textures. The capability of the proposed technique is fully demonstrated using data collected from surface textures of three different structures and achieves an overall average scale estimation error of less than 15%.

Download Full-text

Fault diagnosis of rolling bearing based on multi-scale one-dimensional convolutional neural network

IOP Conference Series Materials Science and Engineering ◽

10.1088/1757-899x/1207/1/012003 ◽

2021 ◽

Vol 1207 (1) ◽

pp. 012003

Author(s):

Xukun Hou ◽

Pengjie Hu ◽

Wenliao Du ◽

Xiaoyun Gong ◽

Hongchao Wang ◽

...

Keyword(s):

Neural Network ◽

Wavelet Transform ◽

Fault Diagnosis ◽

Convolutional Neural Network ◽

Rolling Bearing ◽

One Dimensional ◽

Bearing Fault ◽

Multi Scale ◽

Reconstructed Signal ◽

Using Data

Abstract Aiming at the typical non-stationary and nonlinear characteristics of rolling bearing vibration signals, a multi-scale convolutional neural network method for bearing fault diagnosis based on wavelet transform and one-dimensional convolutional neural network is proposed. First, the signal is decomposed into multi scale components with wavelet transform, and then each scale component is reconstructed. The reconstructed signal is subjected to the Fourier transform to obtain the frequency spectrum representation, which is used as the input of the one-dimensional convolutional neural network. Finally, one-dimensional convolution neural network is used to learn the features of the input data and recognize the bearing fault. The performance of the model is verified by using data sets of rolling bearing. The results show that this method can intelligent feature extraction and obtain 99.94% diagnostic accuracy.

Download Full-text

A Modified Convolutional Neural Network for ECG Beat Classification

Journal of Medical Imaging and Health Informatics ◽

10.1166/jmihi.2020.2913 ◽

2020 ◽

Vol 10 (3) ◽

pp. 654-660

Author(s):

Lulu Yang ◽

Junjiang Zhu ◽

Tianhong Yan ◽

Zhaoyang Wang ◽

Shangshi Wu

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Premature Ventricular Contraction ◽

Average Score ◽

Bundle Branch Block ◽

Rr Intervals ◽

Normal Sinus ◽

Beat Classification ◽

The Difference ◽

Using Data

Most convolutional neural networks (CNNs) used to classify electrocardiogram (ECG) beats tend to focus only on the beat, ignoring its relationships with its surrounding beats. This study aimed to propose a hybrid convolutional neural network (HCNN) structure, which classified ECG beats based on the beat's morphology and relationship such as RR intervals. The difference between the HCNN and the traditional CNN lies in the fact that the relationship can be added to any layer in the former. The HCNN was fed with RR intervals at 3 different positions, trained using data from 2170 patients. It was then evaluated with labeled clinical data from 2102 patients to classify ECG beats into premature ventricular contraction beat, atrial premature contraction beat (APC), left bundle branch block beat, right bundle branch block beat, and normal sinus beat. The results showed that the performance of the proposed HCNN method (with an average score of 86.61% on 12 leads) was 3.31% higher than that of the traditional CNN (83.30%) on the test set. In particular, the APC improved most significantly from 57.67% to 76.92% in terms of sensitivity and from 58.80% to 78.46% in terms of the positive predictive value in lead V1.

Download Full-text