Performance enhancement of eulerian video magnification

In this study, a linear and phase-based Eulerian video magnification (EVM) methods are developed to minimize magnified noises and processing time. The developed approaches utilize the Lanczos resampling algorithm to reduce the frames' size of the source video so that the size of the processed data is significantly reduced. Then spatial decomposition is applied to the resized frames. Subsequently, temporal filters with specific cut-off frequencies are also used to filter only the desired frequencies to be amplified and then add them to the decomposed frames. The magnified frames are processed by a wavelet denoising algorithm to locate distributed noise over the different frequency bands and then remove it. The resulted denoised-magnified frames are resized up and then reconstructed by the spatial synthesis process. The experiments show the superiority and effectiveness of the developed EVM approaches compared to the conventional ones and other related approaches in terms of the execution time and the quality of the magnified video. The developed EVM approach can be used in several applications such as the detection of human vital signs without contact so that it is very useful to avoid infection in several diseases such as Covid-19. Furthermore, it can be used in detection of human mood and lying detection, detection and localization of material and liquid variations. © 2023 University of Bahrain. All rights reserved.

An Effective COVID-19 CT Image Denoising Method Based on a Deep Convolutional Neural Network

Background: Faced with the global threat posed by SARS-CoV-2 (COVID-19), low-dose computed tomography (LDCT), as the primary diagnostic tool, is often accompanied by high levels of noise. This can easily interfere with the radiologist's assessment. Convolutional neural networks (CNN), as a method of deep learning, have been shown to have excellent effects in image denoising. Objective: The objective of the study was to use modified convolutional neural network algorithm to train the denoising model. The purpose was to make the model extract the highlighted features of the lesion region better and ensure its effectiveness in removing noise from COVID-19 lung CT images, preserving more important detail information of the images and reducing the adverse effects of denoising. Methods: We propose a CNN-based deformable convolutional denoising neural network (DCDNet). By combining deformable convolution methods with residual learning on the basis of CNN structure, more image detail features are retained in CT image denoising. Results: According to the noise reduction evaluation index of PSNR, SSIM and RMSE, DCDNet shows excellent denoising performance for COVID-19 CT images. From the visual effect of denoising, DCDNet can effectively remove image noise and preserve more detailed features of lung lesions. Conclusion: The experimental results indicate that the DCDNet-trained model is more suitable for image denoising of COVID-19 than traditional image denoising algorithms under the same training set. © 2023 Bentham Science Publishers.

JDSR-GAN: Constructing An Efficient Joint Learning Network for Masked Face Super-Resolution

With the growing importance of preventing the COVID-19 virus in cyber-manufacturing security, face images obtained in most video surveillance scenarios are usually low resolution together with mask occlusion. However, most of the previous face super-resolution solutions can not efficiently handle both tasks in one model. In this work, we consider both tasks simultaneously and construct an efficient joint learning network, called JDSR-GAN, for masked face super-resolution tasks. Given a low-quality face image with mask as input, the role of the generator composed of a denoising module and super-resolution module is to acquire a high-quality high-resolution face image. The discriminator utilizes some carefully designed loss functions to ensure the quality of the recovered face images. Moreover, we incorporate the identity information and attention mechanism into our network for feasible correlated feature expression and informative feature learning. By jointly performing denoising and face super-resolution, the two tasks can complement each other and attain promising performance. Extensive qualitative and quantitative results show the superiority of our proposed JDSR-GAN over some competitive methods. IEEE

How Connected is Crude Oil to Stock Sectors Before and After the COVID-19 Outbreak? Evidence from a Novel Network Method

A novel network with Wavelet denoising-GARCHSK and Mixed CoVaR method is proposed to construct full-sample and dynamic networks for investigating the risk spillover effects across international crude oil and Chinese stock sectors before and after the COVID-19 outbreak. The empirical results denote that the total bidirectional oil-sector risk spillover effects increase rapidly after the COVID-19 outbreak. Interestingly, sectors shift from net risk receivers to net risk contributors in the oil-sector risk transfer effects during the pandemic period. Second, unlike the pre-COVID-19 period, Shanghai crude (SC) replaces Brent as the largest oil risk transmitter to stocks during the COVID-19 period. Third, there are notable sectoral features in the oil-sector risk spillovers, which differ across different periods. After the burst, Energy has an incredibly weak connection with crude oil, while the sectors, which oil products are input for, become close with crude oil. Far more surprising is that the petroleum-independent sectors have increasing closer risk transfer effects with crude, even becoming the largest risk contributors to oil, after that. Finally, the oil-sector relationships during the same period are time-varying but stable. This paper provides policymakers and investors with new method and insight into the oil-sector relationships. [ABSTRACT FROM AUTHOR] Copyright of Fluctuation & Noise Letters is the property of World Scientific Publishing Company and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The IMU Augment SLAM on Unmanned Vehicle for Detection of Protective Measures in COVID-19

Detecting protective measures (e.g., masks, goggles and protective clothing) is a momentous step in the fight against COVID-19. The detection mode of unmanned devices based on Simultaneous localization and mapping (SLAM) and fusion technology is more efficient, economical and safe than the traditional manual detection. In this paper, a tightly-coupled nonlinear optimization approach is used to augment the visual feature extraction of SLAM by the gyroscope of the IMU to obtain a high-precision visual inertial system for joint position and pose estimation. Based on the VINS-Mono frame, first, an LSD algorithm based on a conditional selection strategy is proposed to extract line features efficiently. Then, we propose recovering missing point features from line features. Moreover, we propose a strategy to recover vanishing point features from line features, and add residuals to the SLAM cost function based on optimization, which optimizes point-line features in real time to promote the tracking and matching accuracy. Second, the wavelet threshold denoising method based on the 3σ criterion is used to carry out real-time online denoising for gyroscope to improve the output precision. Our WD-PL-VINS was measured on publicly available EuRoC datasets, TUM VI datasets and evaluated and validated in lab testing with a unmanned vehicle (UV) based on the NVIDIA Jetson-TX2 development board. The results show that our method's APE and RPE on MH-03-easy sequences are improved by 69.28% and 97.66%, respectively, compared with VINS-Mono. © 2001-2012 IEEE.

Mask Detection for Covid-19 under Extreme Conditions

Mask detection has become a hot topic since the COVID-19 pandemic began in recent years. However, most scholars only focus on the speed and accuracy of detection, and fail to pay attention to the fact that mask detection is not suitable for people living under extreme conditions due to the degraded image quality. In this work, a denoising convolutional auto-encoder, a multitask cascaded convolutional networks (MTCNN) and a MobileNet were used to solve the problem of mask detection for COVID-19 under extreme environments. First of all, a network based on AlexNet is designed for the auto-encoder. This study found that the two-layer max pooling layers in AlexNet could not accurately extract image features but damage the quality of restored image. Therefore, they were deleted, and other parameters such as channel number were also modified to fit the new net, and finally trained using cosine distance. In addition, for MTCNN, this study changed the output condition of ONet from thresholding to maximum return, and lowered the thresholds of PNet and RNet to solve the problem that faces might not be found in low-quality images with mask and other covers. Furthermore, MobileNet was trained using categorical cross entropy loss function with adam optimizer. In the end, the accuracy of system for the photos captured under extreme conditions enhance from 50 % to 85% in test images. © 2022 IEEE.

KSMDB: A classification method in imbalanced COVID dataset based on KmeansSMOTE and DeBERT

2022 is already the third year of the COVID-19 outbreak, and public opinion information about the outbreak has always been at the forefront of hot searches. The imbalance problem prevalent in many reviews of COVID-19 causes classification models to favor most categories in training and prediction process, resulting in low accuracy of small sample classification data generated by imbalanced data sets. Therefore, it is suggested here that the text classification model is based on the combination of the KMeansSMOTE method combined with DeBERT. First of all, during data processing, the KmeansSMOTE algorithm is utilized to oversample the imbalance of the COVID dataset, which increases the classification accuracy of the model. Besides, we put a stacked denoising bidirectional transformer encoder (DeBERT) to use, a more and richer hidden feature vector is extracted by adding an embedded layer after the input tag, and the noise data is reconstructed to solve the noise problem in the process of raw data existence and oversampling. Furthermore, on the basis of model training, overfitting can be alleviated by adopting an early stopping strategy. A world of experiments using the COVID dataset demonstrates the effectiveness of the proposed method for solving simple imbalance and noise problems. With an overall accuracy of 87%, which improves the classification effect of minority samples and provides a new feasible method for the war of epidemic prevention. © 2022 IEEE.

A Novel Scheme Based on Variational Mode Decomposition and Multiple Denoising Technologies for Heartbeat Rate Estimation

In the face of the serious aging of the global population and the sudden outbreak of COVID-19, monitoring human vital signs such as heart rate is very important to save lives. For more accurate heartbeat detection, we propose a heartbeat detection scheme based on variational mode decomposition (VMD) and multiple technologies of noise and interference suppression. First, a filter is designed to suppress the impulse noise and reduce the loss of useful signal information. Then, VMD is performed to decompose the pre-processed vital signs into a series of intrinsic mode function (IMF) components. Thirdly, much attention is paid on denoising of IMF components corresponding to the heartbeat signals, an improved wavelet threshold denoising method is proposed to process these IMF components and reconstruct the heartbeat signal. Finally, an adaptive notch filter is used to process the residual respiratory harmonics in the reconstructed heartbeat signal. To verify the heartbeat detection accuracy of our method, the results are compared with a reliable reference sensor. Our results show that the mean average absolute error (AAE) of heart rate estimated by the proposed method is 1.06 bpm, which is 7.51 bpm better than the original method. © 2022 IEEE.

Detection of COVID-19 Using Denoising Autoencoders and Gabor Filters

As of 2019, COVID-19 is the most difficult issue that we are facing. Till now, it has reached over 30 million deaths. Since SARS-CoV-2 is the new virus, it took time to investigate and examine the influence of Coronavirus in human. After analyzing the spreading and infection of COVID-19, researchers applied Artificial Intelligence (AI) techniques to detect COVID-19 quickly to balance the rapid spreading of the virus. Image segmentation is a critical first step in clinical implementations, is a vital role in computer - aided diagnosis that relies heavily on image recognition. Image segmentation is used in medical MRI research to determine the proportions of different anatomical areas of the tissue, as well as how they change as the disease progresses. CT scans are often used to aid with diagnoses. Computer-assisted therapy (CAD) using AI is a particularly significant research area in intelligent healthcare. This paper presents the detection of COVID-19 at an early stage using autoencoders algorithm and Generative Adversarial Networks (GAN) using deep learning approach with more accurate results. The images of Chest Radiograph (CRG) and Chest Computed Tomography (CCT) are used as a trained dataset to detect since SARS-CoV-2 first affect the respiratory system in humans. We achieved a ratio of 1.0, 0.99, and 0.96, the combined dataset was randomly divided into the train, validation, and test sets. Although the early detection of Coronavirus is still a question since the accuracy of the deep learning approach is still under research. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Noise Suppression and Edge Preservation for Low-Dose COVID-19 CT Images Using NLM and Method Noise Thresholding in Shearlet Domain.

In the COVID-19 era, it may be possible to detect COVID-19 by detecting lesions in scans, i.e., ground-glass opacity, consolidation, nodules, reticulation, or thickened interlobular septa, and lesion distribution, but it becomes difficult at the early stages due to embryonic lesion growth and the restricted use of high dose X-ray detection. Therefore, it may be possible for a patient who may or may not be infected with coronavirus to consider using high-dose X-rays, but it may cause more risks. Conclusively, using low-dose X-rays to produce CT scans and then adding a rigorous denoising algorithm to the scans is the best way to protect patients from side effects or a high dose X-ray when diagnosing coronavirus involvement early. Hence, this paper proposed a denoising scheme using an NLM filter and method noise thresholding concept in the shearlet domain for noisy COVID CT images. Low-dose COVID CT images can be further utilized. The results and comparative analysis showed that, in most cases, the proposed method gives better outcomes than existing ones.

New Real-Time Impulse Noise Removal Method Applied to Chest X-ray Images.

In this paper, we propose a new Modified Laplacian Vector Median Filter (MLVMF) for real-time denoising complex images corrupted by "salt and pepper" impulsive noise. The method consists of two rounds with three steps each: the first round starts with the identification of pixels that may be contaminated by noise using a Modified Laplacian Filter. Then, corrupted pixels pass a neighborhood-based validation test. Finally, the Vector Median Filter is used to replace noisy pixels. The MLVMF uses a 5 × 5 window to observe the intensity variations around each pixel of the image with a rotation step of π/8 while the classic Laplacian filters often use rotation steps of π/2 or π/4. We see better identification of noise-corrupted pixels thanks to this rotation step refinement. Despite this advantage, a high percentage of the impulsive noise may cause two or more corrupted pixels (with the same intensity) to collide, preventing the identification of noise-corrupted pixels. A second round is then necessary using a second set of filters, still based on the Laplacian operator, but allowing focusing only on the collision phenomenon. To validate our method, MLVMF is firstly tested on standard images, with a noise percentage varying from 3% to 30%. Obtained performances in terms of processing time, as well as image restoration quality through the PSNR (Peak Signal to Noise Ratio) and the NCD (Normalized Color Difference) metrics, are compared to the performances of VMF (Vector Median Filter), VMRHF (Vector Median-Rational Hybrid Filter), and MSMF (Modified Switching Median Filter). A second test is performed on several noisy chest x-ray images used in cardiovascular disease diagnosis as well as COVID-19 diagnosis. The proposed method shows a very good quality of restoration on this type of image, particularly when the percentage of noise is high. The MLVMF provides a high PSNR value of 5.5% and a low NCD value of 18.2%. Finally, an optimized Field-Programmable Gate Array (FPGA) design is proposed to implement the proposed method for real-time processing. The proposed hardware implementation allows an execution time equal to 9 ms per 256 × 256 color image.

How do crude oil futures hedge crude oil spot risk after the COVID-19 outbreak? A wavelet denoising-GARCHSK-SJC Copula hedge ratio estimation method.

In the current paper, we investigate the problem of how do crude oil futures hedge crude oil spot risk after the COVID-19 outbreak. Specifically, given that noise, conditional higher moments and asymmetric tail dependence may exist in crude oil markets, a Wavelet denoising-GARCHSK-SJC Copula hedge ratio estimation method is proposed to construct hedging portfolios in crude oil markets during the epidemic period. Based on the in-sample and out-of-sample results, the hedging roles of Brent futures and Shanghai crude oil (SC) futures for light and medium crude spots after the COVID-19 outbreak are further researched. The empirical results demonstrate that noise, conditional higher moments and asymmetric tail dependence do exist in crude futures and spots, which have impact on the precision of modeling results. Secondly, the Wavelet denoising-GARCHSK-SJC Copula hedge ratio estimation method outperforms all control groups, obtaining the best in-sample and out-of-sample hedging effectiveness. Finally, it is reported in the in-sample and out-of-sample hedging results that Brent is the optimal futures to hedge light oil, while SC is the optimal futures to hedge medium oil. The paper provides substantial recommendations for policymakers and investors.

Performance Analysis of Wiener filter in Restoration of Covid-19 Chest X-Ray Images, Ultrasound Images and Mammograms

Medical images such as X-Ray images, Mammograms and Ultrasound images are very useful diagnostic techniques used for understanding the functions of different internal organs, bones, tissues, etc. Most of the times these medical images are degraded by some noises and different kinds of blur. Image blurring and degradation leads to loss of quality of images which in hand causes difficulty in proper diagnosis. This paper emphases on the efficacy of Wiener filter in image de blurring and denoising Chest X-Ray of Covid-19 patients, ultrasound images of fetal abdominal cyst, umbilical cord cyst and Common Carotid Artery, Mammogram of both pathological and non-pathological breasts. Performance of Wiener filter is analyzed using image restoration parameters like Structural Similarity (SSIM), Histogram, Peak Signal to Noise Ratio and Mean Square Error. © 2022 IEEE.

Comparative Analysis of Image Enhancement Techniques for Chest X-ray Images

X-ray radiography plays a crucial part in diagnosis of various diseases in human body like Covid-19, Cancer and Pneumonia. The images obtained through X-ray radiography is interpreted by Surgeons, Pathologists and Radiologists for detecting anomaly in scanned body part. Chest X-ray is one of the cheapest and easily accessible tests of functioning of chest and lungs. However, images obtained through X-ray are not very clear, low in contrast and with lesser variation in gray level. Image enhancement is done for better visualization of images and bringing forward the underlying details of image. The Kaggle repository of total 6334 chest X-ray images were used for experimentation and calculation works. In this paper, we have compared various combinations of contrast enhancement techniques such as CLAHE, Morphological operations (black and white hat transforms) and noise reduction techniques like Median filter, DCT and DWT. The Comparison was done on the basis of image quality assessment parameters such as MSE, PSNR, and AMBE. The results showed that fusion of CLAHE and DWT techniques gave best results with highest PSNR value and lowest AMBE among the various models discussed. The proposed methodology shall be very helpful in diagnosis of diseases from chest X-ray images. © 2022 IEEE.

Image enhancement techniques on deep learning approaches for automated diagnosis of COVID-19 features using CXR images.

The outbreak of novel coronavirus (COVID-19) disease has infected more than 135.6 million people globally. For its early diagnosis, researchers consider chest X-ray examinations as a standard screening technique in addition to RT-PCR test. Majority of research work till date focused only on application of deep learning approaches that is relevant but lacking in better pre-processing of CXR images. Towards this direction, this study aims to explore cumulative effects of image denoising and enhancement approaches on the performance of deep learning approaches. Regarding pre-processing, suitable methods for X-ray images, Histogram equalization, CLAHE and gamma correction have been tested individually and along with adaptive median filter, median filter, total variation filter and gaussian denoising filters. Proposed study compared eleven combinations in exploration of most coherent approach in greedy manner. For more robust analysis, we compared ten CNN architectures for performance evaluation with and without enhancement approaches. These models are InceptionV3, InceptionResNetV2, MobileNet, MobileNetV2, Vgg19, NASNetMobile, ResNet101, DenseNet121, DenseNet169, DenseNet201. These models are trained in 4-way (COVID-19 pneumonia vs Viral vs Bacterial pneumonia vs Normal) and 3-way classification scenario (COVID-19 vs Pneumonia vs Normal) on two benchmark datasets. The proposed methodology determines with TVF + Gamma, models achieve higher classification accuracy and sensitivity. In 4-way classification MobileNet with TVF + Gamma achieves top accuracy of 93.25% with 1.91% improvement in accuracy score, COVID-19 sensitivity of 98.72% and F1-score of 92.14%. In 3-way classification our DenseNet201 with TVF + Gamma gains accuracy of 91.10% with improvement of 1.47%, COVID-19 sensitivity of 100% and F1-score of 91.09%. Proposed study concludes that deep learning modes with gamma correction and TVF + Gamma has superior performance compared to state-of-the-art models. This not only minimizes overlapping between COVID-19 and virus pneumonia but advantageous in time required to converge best possible results.

The IMU augment SLAM on Unmanned Vehicle for detection of protective measures in COVID-19

Detecting protective measures (e.g., masks, goggles and protective clothing) is a momentous step in the fight against COVID-19. The detection mode of unmanned devices based on Simultaneous localization and mapping (SLAM) and fusion technology is more efficient, economical and safe than the traditional manual detection. In this paper, a tightly-coupled nonlinear optimization approach is used to augment the visual feature extraction of SLAM by the gyroscope of the IMU to obtain a high-precision visual inertial system for joint position and pose estimation. Based on the VINS-Mono frame, first, an LSD algorithm based on a conditional selection strategy is proposed to extract line features efficiently. Then, we propose recovering missing point features from line features. Moreover, we propose a strategy to recover vanishing point features from line features, and add residuals to the SLAM cost function based on optimization, which optimizes point-line features in real time to promote the tracking and matching accuracy. Second, the wavelet threshold denoising method based on the 3σcriterion is used to carry out real-time online denoising for gyroscope to improve the output precision. Our WD-PL-VINS was measured on publicly available EuRoC datasets, TUM VI datasets and evaluated and validated in lab testing with a unmanned vehicle (UV) based on the NVIDIA Jetson-TX2 development board. The results show that our method’s APE and RPE on MH 03 easy sequences are improved by 69.28% and 97.66%, respectively, compared with VINS-Mono. IEEE

Deep Denoising of Raw Biomedical Knowledge Graph From COVID-19 Literature, LitCovid, and Pubtator: Framework Development and Validation.

BACKGROUND: Multiple types of biomedical associations of knowledge graphs, including COVID-19-related ones, are constructed based on co-occurring biomedical entities retrieved from recent literature. However, the applications derived from these raw graphs (eg, association predictions among genes, drugs, and diseases) have a high probability of false-positive predictions as co-occurrences in the literature do not always mean there is a true biomedical association between two entities. OBJECTIVE: Data quality plays an important role in training deep neural network models; however, most of the current work in this area has been focused on improving a model's performance with the assumption that the preprocessed data are clean. Here, we studied how to remove noise from raw knowledge graphs with limited labeled information. METHODS: The proposed framework used generative-based deep neural networks to generate a graph that can distinguish the unknown associations in the raw training graph. Two generative adversarial network models, NetGAN and Cross-Entropy Low-rank Logits (CELL), were adopted for the edge classification (ie, link prediction), leveraging unlabeled link information based on a real knowledge graph built from LitCovid and Pubtator. RESULTS: The performance of link prediction, especially in the extreme case of training data versus test data at a ratio of 1:9, demonstrated that the proposed method still achieved favorable results (area under the receiver operating characteristic curve >0.8 for the synthetic data set and 0.7 for the real data set), despite the limited amount of testing data available. CONCLUSIONS: Our preliminary findings showed the proposed framework achieved promising results for removing noise during data preprocessing of the biomedical knowledge graph, potentially improving the performance of downstream applications by providing cleaner data.

Restoring Lesions in Low-Dose Computed Tomography Images of COVID-19 Using Deep Learning

The use of Low-dose Computed Tomography (LDCT) in clinical medicine for diagnosis and treatment planning is widespread due to the minimal exposure of patients to radiation. Also, recent studies have confirmed that LDCT is a feasible medical imaging modality for diagnosing COVID-19 cases. In general, X-ray tube current is being reduced to acquire the LDCT images. Reduction of the X-ray flux introduces the Quantum noise into the generated LDCT images and, as a result, it produces visually low-quality CT images. Therefore, it is challenging to differentiate the lesions in the diagnosis of COVID-19 patients using the LDCT images due to low contrast and failure to preserve the subtle structures. Therefore, in this study, we proposed a Deep Learning (DL) model based on the Generative Adversarial Network (GAN) for post-processing the LDCT images to enhance their visual quality. In this proposed model, the generator network is designed as a U-net to generate the restored CT images by filter out the noise. Also, the discriminator network follows a patch-GAN model to discriminate the real and generated images while preserving the texture details. The quantitative and qualitative results demonstrated the effectiveness of noise suppression and structure preservation of the proposed DL method. Hence, it provides an acceptable quality improvement for LDCT images to discriminate the lesions for diagnosing the COVID-19 positive cases. © 2022, Springer Nature Switzerland AG.

Detection of Lung Ultrasound Covid-19 Disease Patients based Convolution Multifacet Analytics using Deep Learning

Deep Learning techniques for ultrasound images, from the front end to the most advanced applications, are the potential effect of deep learning methods on many aspects of the analysis of the ultrasound images. The Covid-19 epidemic has exposed global health care vulnerabilities, especially in developing countries. Lung Ultra-Sound (LUS) imaging as a real-time analytic tool for lung injuries is superior to X-rays and similar to CT, enabling real-time diagnosis. Relying on operator training and experience is the main limitation of the range. COVID-19 lung ultrasonography mainly reflects the pattern of pneumonia, and pleural effusion is not common. The previous system does not provide image accuracy, clarity, it is cost-effective screening large-scale traditional tests are not possible. To overcome the issues, this work proposed the method Convolutional Multi -Facet Analytics (CMFA) algorithm for using the Lung Ultra-Sound (LUS) imaging. Initially start the Preprocessing step based on the Geometric Image Noise Filtering (GINT) for removed the image noises, and unwanted values from the images, second steps of the image processing for Feature selection using the K-Nearest Neighbor (KNN) and Adaptive Gradient Boosting Algorithm (AGBA) for optimizing the image feature od efficient to reduce the same information form he original dataset. And then bagging with K-Nearest Neighbor (KNN) and Adaptive Gradient Boosting Regression (AGBR) Algorithm estimate the images feature weights like (shape, size, etc.) to test, and verify the best combined classifier model splitting training and testing for feature selection and evaluating the results in Softmax activation function. Classified the train and test features using the Convolutional Multi-Facet Analytics (CMFA) algorithm for analyzing the variety of different important features from the dataset. The simulation results show that Sensitivity, specificity, accuracy, and Error rate score shows better results. © 2022 IEEE.

COVID-19 CT images denoising method based on multi-scale parallel deep split CNN

The coronavirus disease 2019 (COVID-19) has spread worldwide. To early diagnose COVID-19 and reduce the pressure of medical staff, using deep learning methods to analyze chest computed tomography (CT) images of patients becomes more and more important. The images of pneumonia have rich texture details and fuzzy edge structure, which are easy to interfere with the diagnosis of machine and doctor. COVID-19 CT images denoising method based on multi-scale parallel deep split convolution neural network (MSP-ReCNN) is proposed in this paper to enhance the quality of pneumonia images. Multi scale feature extraction module can extract the details of texture features in pneumonia images from different scales. The parallel method of deep and shallow channels are utilized to extract the high-dimensional and low-dimensional features of pneumonia images. To further optimize the network model, the split convolution method is proposed. The feature graph can be divided into two categories, one is the primary concern feature, the other is the secondary concern feature. High complexity computing method is used to extract the core information from the primary concern features, and the low complexity calculation method is used to extract the compensation information for others. Compared with non-local mean (NLM) denoising algorithm, shrinkage convdutional neural network (SCNN) model, denosing convolutional neural network (DnCNN) model, and through network ablation experiments, it can be drawn that the proposed model can effectively remove the noise in COVID-19 CT images, and can retain the texture structure details of the original image, as well as provide more reliable auxiliary diagnosis for machines and doctors. © 2021, Editorial Department of the Journal of Chinese High Technology Letters. All right reserved.