Ruichao Zhang^1,*, Liqiang Wang¹, Dechun Chen²

Energy Engineering, Vol.118, No.4, pp. 1069-1082, 2021, DOI:10.32604/EE.2021.014961

Abstract In recent years, deep learning models represented by convolutional neural networks have shown incomparable advantages in image recognition and have been widely used in various fields. In the diagnosis of sucker-rod pump working conditions, due to the lack of a large-scale dynamometer card data set, the advantages of a deep convolutional neural network are not well reflected, and its application is limited. Therefore, this paper proposes an intelligent diagnosis method of the working conditions in sucker-rod pump wells based on transfer learning, which is used to solve the problem of too few samples in a dynamometer card data set. Based… More >

Yudong Zhang^1,3,*, Xin Zhang^2,*, Weiguo Zhu¹

CMES-Computer Modeling in Engineering & Sciences, Vol.127, No.3, pp. 1037-1058, 2021, DOI:10.32604/cmes.2021.015807

Abstract Aim: To diagnose COVID-19 more efficiently and more correctly, this study proposed a novel attention network for COVID-19 (ANC). Methods: Two datasets were used in this study. An 18-way data augmentation was proposed to avoid overfitting. Then, convolutional block attention module (CBAM) was integrated to our model, the structure of which is fine-tuned. Finally, Grad-CAM was used to provide an explainable diagnosis. Results: The accuracy of our ANC methods on two datasets are 96.32% ± 1.06%, and 96.00% ± 1.03%, respectively. Conclusions: This proposed ANC method is superior to 9 state-of-the-art approaches. More >

WENBIAO CHEN, KEFAN BI, JINGJING JIANG, XUJUN ZHANG, HONGYAN DIAO^*

BIOCELL, Vol.45, No.4, pp. 885-899, 2021, DOI:10.32604/biocell.2021.012938

Abstract The genome characteristics and structural functions of coding proteins correlate with the genetic diversity of the H1N1 virus, which aids in the understanding of its underlying pathogenic mechanism. In this study, analyses of the characteristic of the H1N1 virus infection-related genes, their biological functions, and infection-related reversal drugs were performed. Additionally, we used multi-dimensional bioinformatics analysis to identify the key genes and then used these to construct a diagnostic model for the H1N1 virus infection. There was a total of 169 differently expressed genes in the samples between 21 h before infection and 77 h after infection. They were used… More >

Ibrahim B.M. Taha¹, Diaa-Eldin A. Mansour^2,*

Intelligent Automation & Soft Computing, Vol.28, No.3, pp. 739-752, 2021, DOI:10.32604/iasc.2021.017703

Abstract Power transformer is one of the more important components of electrical power systems. The early detection of transformer faults increases the power system reliability. Dissolved gas analysis (DGA) is one of the most favorite approaches used for power transformer fault prediction due to its easiness and applicability for online diagnosis. However, the imbalanced, insufficient and overlap of DGA dataset impose a challenge towards powerful and accurate diagnosis. In this work, a novel fault diagnosis for power transformers is introduced based on DGA by using data transformation and six optimized machine learning (OML) methods. Four data transformation techniques are used with… More >

Yudong Zhang^1,*, Qilong Wang², Sean H. Y. Yuan³

CMES-Computer Modeling in Engineering & Sciences, Vol.127, No.2, pp. 385-387, 2021, DOI:10.32604/cmes.2021.016386

Abstract This article has no abstract. More >

Tapan Kumar Das¹, Pradeep Kumar Roy², Mohy Uddin³, Kathiravan Srinivasan¹, Chuan-Yu Chang^4,*, Shabbir Syed-Abdul⁵

CMC-Computers, Materials & Continua, Vol.68, No.2, pp. 2413-2429, 2021, DOI:10.32604/cmc.2021.016698

Abstract Machine learning based image analysis for predicting and diagnosing certain diseases has been entirely trustworthy and even as efficient as a domain expert’s inspection. However, the style of non-transparency functioning by a trained machine learning system poses a more significant impediment for seamless knowledge trajectory, clinical mapping, and delusion tracing. In this proposed study, a deep learning based framework that employs deep convolution neural network (Deep-CNN), by utilizing both clinical presentations and conventional magnetic resonance imaging (MRI) investigations, for diagnosing tumors is explored. This research aims to develop a model that can be used for abnormality detection over MRI data… More >

Javaria Amin¹, Muhammad Sharif², Muhammad Almas Anjum³, Yunyoung Nam^4,*, Seifedine Kadry⁵, David Taniar⁶

CMC-Computers, Materials & Continua, Vol.68, No.2, pp. 2451-2467, 2021, DOI:10.32604/cmc.2021.014199

Abstract Coronavirus 19 (COVID-19) can cause severe pneumonia that may be fatal. Correct diagnosis is essential. Computed tomography (CT) usefully detects symptoms of COVID-19 infection. In this retrospective study, we present an improved framework for detection of COVID-19 infection on CT images; the steps include pre-processing, segmentation, feature extraction/fusion/selection, and classification. In the pre-processing phase, a Gabor wavelet filter is applied to enhance image intensities. A marker-based, watershed controlled approach with thresholding is used to isolate the lung region. In the segmentation phase, COVID-19 lesions are segmented using an encoder-/decoder-based deep learning model in which deepLabv3 serves as the bottleneck and… More >

F. Castinetti, A. Barlier, F. Sebag, D. Taieb

Oncologie, Vol.21, No.2, pp. 105-111, 2019, DOI:10.3166/onco-2019-0050

Abstract Pheochromocytoma and paraganglioma are tumors leading to increased morbidity and mortality. Over the last 20 years, several major advances allowed a better characterization of these tumors, either from an imaging or from a genetic viewpoint. This is especially the case for the hereditary characteristics of these tumors, as roughly 20 new genes have been identified. This is why the initial steps of the management of a pheochromocytoma and/or a paraganglioma now require a dedicated tertiary referral center. The aim of this review is to depict the diagnostic steps of these tumors, so as to allow the clinician to determine the… More >

J. Boudier, G. Oldrini, C. Barlier, A. Lesur

Oncologie, Vol.21, No.1, pp. 11-16, 2019, DOI:10.3166/onco-2019-0034

Abstract When a breast cancer is diagnosed, the quality of the evaluation before treatment is essential to guide the therapeutic decision. The staging axillary is necessary because it estimates the regional extension of the disease, which makes it a paramount prognosis factor. Some different preoperative medical imaging can reveal metastasis axillary nodes. However, the axillary ultrasound remains the reference imaging and it also leads the biopsies too. Since theACOSOG-Z0011 trial, we are facing a therapeutic deescalation in the axillary surgery. According to recent results, we can note that the position of the axillary imaging is more and more important. The purpose… More >

Elio Caruso^*, Silvia Farruggio, Salvatore Agati, Corrado Di Mambro

Congenital Heart Disease, Vol.16, No.4, pp. 309-331, 2021, DOI:10.32604/CHD.2021.015470

Abstract Fetal arrhythmias reach up around 10% of the total third-level perinatal cardiology references. Sustained bradycardia is defined as a baseline fetal heart rate (FHR) of less than 110 bpm sustained for at least 10 min. The overall incidence of malignant fetal bradyarrhythmias, such as complete atrioventricular block (AVB) and channellopathies, is relatively rare, 1:5000 pregnancies, but represents a serious emergency for the gynecologist, neonatologists, and pediatric cardiologists. Fetal complete AVB is strongly associated with maternal connective tissue disease, but it can be also associated with congenital heart disease and usually with a poorer prognosis with high risk of fetal hydrops… More >