scholarly journals Convolutional Neural Networks with Transfer Learning for Recognition of COVID-19: A Comparative Study of Different Approaches

AI ◽  
2020 ◽  
Vol 1 (4) ◽  
pp. 586-606
Author(s):  
Tanmay Garg ◽  
Mamta Garg ◽  
Om Prakash Mahela ◽  
Akhil Ranjan Garg
Keyword(s):  
Neural Networks ◽  
Principal Component Analysis ◽  
Feature Selection ◽  
Convolutional Neural Networks ◽  
Image Representation ◽  
Principal Component ◽  
Classification Problem ◽  
The Other ◽  
X Ray ◽  
Image Representations

To judge the ability of convolutional neural networks (CNNs) to effectively and efficiently transfer image representations learned on the ImageNet dataset to the task of recognizing COVID-19 in this work, we propose and analyze four approaches. For this purpose, we use VGG16, ResNetV2, InceptionResNetV2, DenseNet121, and MobileNetV2 CNN models pre-trained on ImageNet dataset to extract features from X-ray images of COVID and Non-COVID patients. Simulations study performed by us reveal that these pre-trained models have a different level of ability to transfer image representation. We find that in the approaches that we have proposed, if we use either ResNetV2 or DenseNet121 to extract features, then the performance of these approaches to detect COVID-19 is better. One of the important findings of our study is that the use of principal component analysis for feature selection improves efficiency. The approach using the fusion of features outperforms all the other approaches, and with this approach, we could achieve an accuracy of 0.94 for a three-class classification problem. This work will not only be useful for COVID-19 detection but also for any domain with small datasets.

scholarly journals X-ray image based pneumonia classification using convolutional neural networks

2020 ◽  
Vol 6 (20) ◽  
pp. 54-67
Author(s):  
Sarah Badr AlSumairi ◽  
Mohamed Maher Ben Ismail
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Data Augmentation ◽  
Critical Factor ◽  
Classification Problem ◽  
X Rays ◽  
X Ray ◽  
Erroneous Decision ◽  
Short Period

Pneumonia is an infectious disease of the lungs. About one third to one half of pneumonia cases are caused by bacteria. Early diagnosis is a critical factor for a successful treatment process. Typically, the disease can be diagnosed by a radiologist using chest X-ray images. In fact, chest X-rays are currently the best available method for diagnosing pneumonia. However, the recognition of pneumonia symptoms is a challenging task that relies on the availability of expert radiologists. Such “human” diagnosis can be inaccurate and subjective due to lack of clarity and erroneous decision. Moreover, the error can increase more if the physician is requested to analyze tens of X-rays within a short period of time. Therefore, Computer-Aided Diagnosis (CAD) systems were introduced to support and assist physicians and make their efforts more productive. In this paper, we investigate, design, implement and assess customized Convolutional Neural Networks to overcome the image-based Pneumonia classification problem. Namely, ResNet-50 and DenseNet-161 models were inherited to design customized deep network architecture and improve the overall pneumonia classification accuracy. Moreover, data augmentation was deployed and associated with standard datasets to assess the proposed models. Besides, standard performance measures were used to validate and evaluate the proposed system.

scholarly journals Using Principal Component Analysis and Artificial Neural Networks for Fault Type Forecasting in an Automotive Company

2018 ◽  
Vol 1 (1) ◽  
pp. 1110-1119
Author(s):  
Tülay Korkusuz Polat
Keyword(s):  
Neural Networks ◽  
Principal Component Analysis ◽  
Quality Control ◽  
Principal Component ◽  
Production Quality ◽  
Quality Score ◽  
The Other ◽  
Paint Shop ◽  
Fault Type ◽  
Automotive Company

In this study, failures that occurred in the paint shop of an automotive company were discussed. The relationships between these failures and the probabilities of prospective occurrences were investigated. Any product produced in the company passes quality control at the end of production. Technical or operator-originated types of potential failures are examined during this control. Causes of failures in the paint shop and how they can be resolved pose a serious problem, just as in the other departments of the factory. This is because every failure encountered negatively influence the product quality and harm the company in terms of cost/productivity/image. The inability of the paint shop to predict the probability of failures in advance and its inability to establish a link between the types of failures also lead to its failure to pass quality control — which is the subsequent process — and cause its “production quality score” to fall, as well as other adversities. This study was carried out to determine which failures were usually caused by the activities in the paint shop and to develop a model that would predict the pass/fail state of the types of failures in question.

scholarly journals Dynamic Monitoring of Grinding Circuits by Use of Global Recurrence Plots and Convolutional Neural Networks

Minerals ◽  
2020 ◽  
Vol 10 (11) ◽  
pp. 958
Author(s):  
Jacques Olivier ◽  
Chris Aldrich
Keyword(s):  
Neural Networks ◽  
Principal Component Analysis ◽  
Convolutional Neural Networks ◽  
Process Monitoring ◽  
Principal Component ◽  
Component Analysis ◽  
Further Training ◽  
Efficient Operation ◽  
Dynamic Principal Component Analysis ◽  
Grinding Circuits

Reliable control of grinding circuits is critical to more efficient operation of concentrator plants. In many cases, operators still play a key role in the supervisory control of grinding circuits but are not always able to act timely to deal with disturbances, such as changes in the mill feed. Reliable process monitoring can play a major role in assisting operators to take more timely and reliable action. These monitoring systems need to be able to deal with what could be complex nonlinear dynamic behavior of comminution circuits. To this end, a dynamic process monitoring approach is proposed based on the use of convolutional neural networks. To take advantage of the availability of pretrained neural networks, the grinding circuit variables are treated as time series which can be converted into images. Features extracted from these networks are subsequently analyzed in a multivariate process monitoring framework with an underlying principal component model. Two variants of the approach based on convolutional neural networks are compared with dynamic principal component analysis on a simulated and real-world case studies. In the first variant, the pretrained neural network is used as a feature extractor without any further training. In the second variant, features are extracted following further training of the network in a synthetic binary classification problem designed to enhance the extracted features. The second approach yielded nominally better results than what could be obtained with dynamic principal component analysis and the approach using features extracted by transfer learning.

scholarly journals A Hybrid Intelligent Decision-Making System for Navigation with Optimized Performance

2019 ◽  
Vol 8 (10) ◽  
pp. 2510-2514
Keyword(s):  
Neural Networks ◽  
Principal Component Analysis ◽  
Feature Selection ◽  
Hybrid Model ◽  
Principal Component ◽  
Selection Model ◽  
Final Decision ◽  
Moving Vehicle ◽  
Automated Vehicle ◽  
Speed And Accuracy

A moving vehicle comes across some permanent components like roads and some variable components like other vehicles etc. Keeping these components at forefront, an automated vehicle needs to take astute and speedy decisions about its next move. In this research paper, we have proposed a hybrid model based on two soft computing techniques that is Neural Networks and Fuzzy Systems to optimize the performance of Navigation Systems in terms of speed and accuracy. The proposed model is an extension of authors previous work [ 1] in which the Best Feature Selection model was created to extract the most paramount features of navigation images. In that, it was observed that extracted feature set had direct impact on speed and accuracy of the working model as no resources were required to be spent on impertinent features. Our hybrid model performs three steps afore taking final decision that is either to move or stop the automated vehicle. The first step involves passing the outputs of Best Feature Selection Model and PCA as inputs through Convolutional Neural Network (CNN) deep learning model and obtaining the response in form of move or stop. Principal Component Analysis (PCA) technique was performed on the extracted feature set to improve our knowledge about input feature set by procreating new features. In our previous work [2], it was justified that Principal Component Analysis (PCA) when used in conjunction with Convolutional Neural Networks (CNN) yields better results as compared to standalone performance of PCA and CNN. It was withal analysed that PCA-CNN is going to give nearly same precision either we give ten percent training or we give high order training. The second step involves using one other variant of Neural Networks that is Re-current Neural Networks (RNN) for ascertaining out the bestest feature from all eleven features of Best Feature Selection Model. The factor with least Mean Square Error is used to calculate the decision in form of move or stop. The last step involves passing the outputs of CNN model and RNN model through Fuzzy Module. Here the Fuzzy rules are generated to take final decision for moving vehicle. The accuracy of this hybrid model came out be 89.28 percent which is far better than individual accuracies that is 72 percent and 60 percent of CNN model and RNN model respectively

scholarly journals A New Early Stage Diabetic Retinopathy Diagnosis Model Using Deep Convolutional Neural Networks and Principal Component Analysis

2020 ◽  
Vol 37 (5) ◽  
pp. 711-722
Author(s):  
Mali Mohammedhasan ◽  
Harun Uğuz
Keyword(s):  
Neural Networks ◽  
Principal Component Analysis ◽  
Diabetic Retinopathy ◽  
Convolutional Neural Networks ◽  
Principal Component ◽  
Component Analysis ◽  
World Health ◽  
Diabetic Patients ◽  
Proposed Model ◽  
Diagnosis Accuracy

Diabetic retinopathy (DR) is a disease of the retina, which leads over time to vision problems such retinal detachment, vitreous hemorrhage, glaucoma, and in worse cases leads to blindness, which can initially be controlled by periodic DR-screening. Early diagnosis will lead to greater control of the disease, whereas performing retinal examinations on all diabetic patients is an unattainable need, as diabetes is a chronic disease and its global prevalence has been steadily increasing over the past few decades. According to recent World Health Organization statistics, about 422 million people worldwide have diabetes, the majority living in low-and middle-income countries. This paper proposes a new strategy that brings the strength of convolutional neural networks (CNNs) to the diagnosis of DR. Coupled with using principal component analysis (PCA) that performs dimension reduction to improve the diagnostic accuracy, the proposed model exploiting edge-preserving guided image filtering (E-GIF) that performs as a contrast enhancement mechanism, and in addition to smoothing low gradient areas, it also accentuates strong edges. Diabetic retinopathy causes progressive damage to the blood vessels in the retina to the extent that it leaves traces and lesions in the tissues of the retina. These lesions appear in the form of edges and when processing retinal images, we seek to accentuate these edges to enable better diagnosis of diabetic retinopathy symptoms. A new CNN architecture with residual connections is used, which performs very well in diagnosing DR. The proposed model is named with RUnet-PCA: Residual U-net Deep CNN with Principal Component Analysis. The well-known AlexNet, VggNet-s, VggNet-16, VggNet-19, GoogleNet, and ResNet models were adopted for comparison with the proposed model. Publicly available Kaggle dataset was employed for training exploring the DR diagnosis accuracy. Experimental results show that the proposed RUnet-PCA model achieved a diagnosis accuracy of 98.44% and it was extremely robust and promising in comparison to other diagnosis methods.

Scanning x-ray fluorescence microscopy and principal component analysis

1992 ◽  
Vol 50 (2) ◽  
pp. 1752-1753
Author(s):  
Brian Cross
Keyword(s):  
Principal Component Analysis ◽  
Fluorescence Microscopy ◽  
Spatial Resolution ◽  
High Speed ◽  
Image Acquisition ◽  
Principal Component ◽  
Fluorescence Microscope ◽  
Acquisition Rate ◽  
X Ray ◽  
Speed Up

A relatively new entry, in the field of microscopy, is the Scanning X-Ray Fluorescence Microscope (SXRFM). Using this type of instrument (e.g. Kevex Omicron X-ray Microprobe), one can obtain multiple elemental x-ray images, from the analysis of materials which show heterogeneity. The SXRFM obtains images by collimating an x-ray beam (e.g. 100 μm diameter), and then scanning the sample with a high-speed x-y stage. To speed up the image acquisition, data is acquired "on-the-fly" by slew-scanning the stage along the x-axis, like a TV or SEM scan. To reduce the overhead from "fly-back," the images can be acquired by bi-directional scanning of the x-axis. This results in very little overhead with the re-positioning of the sample stage. The image acquisition rate is dominated by the x-ray acquisition rate. Therefore, the total x-ray image acquisition rate, using the SXRFM, is very comparable to an SEM. Although the x-ray spatial resolution of the SXRFM is worse than an SEM (say 100 vs. 2 μm), there are several other advantages.

Sign in / Sign up

Export Citation Format

Share Document