A Hybrid Convolutional Neural Network Model for Diagnosis of COVID-19 Using Chest X-ray Images

Article Subjects > Biomedicine Europe University of Atlantic > Research > Scientific Production
Ibero-american International University > Research > Scientific Production
Abierto Inglés COVID-19 declared as a pandemic that has a faster rate of infection and has impacted the lives and the country’s economy due to forced lockdowns. Its detection using RT-PCR is required long time and due to which its infection has grown exponentially. This creates havoc for the shortage of testing kits in many countries. This work has proposed a new image processing-based technique for the health care systems named “C19D-Net”, to detect “COVID-19” infection from “Chest X-Ray” (XR) images, which can help radiologists to improve their accuracy of detection COVID-19. The proposed system extracts deep learning (DL) features by applying the InceptionV4 architecture and Multiclass SVM classifier to classify and detect COVID-19 infection into four different classes. The dataset of 1900 Chest XR images has been collected from two publicly accessible databases. Images are pre-processed with proper scaling and regular feeding to the proposed model for accuracy attainments. Extensive tests are conducted with the proposed model (“C19D-Net”) and it has succeeded to achieve the highest COVID-19 detection accuracy as 96.24% for 4-classes, 95.51% for three-classes, and 98.1% for two-classes. The proposed method has outperformed well in expressions of “precision”, “accuracy”, “F1-score” and “recall” in comparison with most of the recent previously published methods. As a result, for the present situation of COVID-19, the proposed “C19D-Net” can be employed in places where test kits are in short supply, to help the radiologists to improve their accuracy of detection of COVID-19 patients through XR-Images. metadata Kaur, Prabhjot and Harnal, Shilpi and Tiwari, Rajeev and Alharithi, Fahd S. and Almulihi, Ahmed H. and Delgado Noya, Irene and Goyal, Nitin mail UNSPECIFIED, UNSPECIFIED, UNSPECIFIED, UNSPECIFIED, UNSPECIFIED, irene.delgado@uneatlantico.es, UNSPECIFIED (2021) A Hybrid Convolutional Neural Network Model for Diagnosis of COVID-19 Using Chest X-ray Images. International Journal of Environmental Research and Public Health, 18 (22). p. 12191. ISSN 1660-4601

Full text not available from this repository.

Abstract

COVID-19 declared as a pandemic that has a faster rate of infection and has impacted the lives and the country’s economy due to forced lockdowns. Its detection using RT-PCR is required long time and due to which its infection has grown exponentially. This creates havoc for the shortage of testing kits in many countries. This work has proposed a new image processing-based technique for the health care systems named “C19D-Net”, to detect “COVID-19” infection from “Chest X-Ray” (XR) images, which can help radiologists to improve their accuracy of detection COVID-19. The proposed system extracts deep learning (DL) features by applying the InceptionV4 architecture and Multiclass SVM classifier to classify and detect COVID-19 infection into four different classes. The dataset of 1900 Chest XR images has been collected from two publicly accessible databases. Images are pre-processed with proper scaling and regular feeding to the proposed model for accuracy attainments. Extensive tests are conducted with the proposed model (“C19D-Net”) and it has succeeded to achieve the highest COVID-19 detection accuracy as 96.24% for 4-classes, 95.51% for three-classes, and 98.1% for two-classes. The proposed method has outperformed well in expressions of “precision”, “accuracy”, “F1-score” and “recall” in comparison with most of the recent previously published methods. As a result, for the present situation of COVID-19, the proposed “C19D-Net” can be employed in places where test kits are in short supply, to help the radiologists to improve their accuracy of detection of COVID-19 patients through XR-Images.

Item Type: Article
Uncontrolled Keywords: convolutional neural network; COVID-19; disease detection; InceptionV4; SVM; chest XR images
Subjects: Subjects > Biomedicine
Divisions: Europe University of Atlantic > Research > Scientific Production
Ibero-american International University > Research > Scientific Production
Date Deposited: 23 Mar 2022 19:44
Last Modified: 04 Jul 2023 23:30
URI: https://repositorio.uneatlantico.es/id/eprint/530

Actions (login required)

View Item View Item

en

close

Do ICT firms manage R&D differently? Firm-level and macroeconomic effects on corporate R&D investment: Empirical evidence from a multi-countries context

Technological firms invest in R&D looking for innovative solutions but assuming high costs and great (technological) uncertainty regarding final results and returns. Additionally, they face other problems related to R&D management. This empirical study tries to determine which of the factors favour or constrain the decision of these firms to engage in R&D. The analysis uses financial data of 14,619 ICT listed companies of 22 countries from 2003 to 2018. Additionally, macroeconomic data specific for the countries and the sector were used. For the analysis of dynamic panel data, a System-GMM method is used. Among the findings, we highlight that cash flow, contrary to the known theoretical models and empirical evidences, negatively impacts on R&D investment. Debt is neither the right source for R&D funding, as the effect is also negative. This suggests that ICT companies are forced to manage their R&D activities differently, relying more on other funding sources, taking advantage of growth opportunities and benefiting from a favourable macroeconomic environment in terms of growth and increased business sector spending on R&D. These results are similar in both sub-sectors and in all countries, both bank- and market based. The exception is firms with few growth opportunities and little debt.

Producción Científica

Inna Alexeeva-Alexeev mail inna.alexeeva@uneatlantico.es, Cristina Mazas Pérez-Oleag mail cristina.mazas@uneatlantico.es,

Alexeeva-Alexeev

en

close

Effects of enzymatic treatment on the in vitro digestion and fermentation patterns of mulberry fruit juice: A focus on carbohydrates

The aim of this study was to investigate the effects of enzymatic treatments (pectinase, pectin lyase, and cellulase) on the in vitro digestion and fermentation characteristics of whole mulberry fruit juice. The analysis focused on changes in carbohydrate properties within the black mulberry fruit matrix during simulated digestion and fermentation. Human fecal microbiota were collected and introduced to the fruit matrix to monitor the fate of both soluble and insoluble polysaccharides during fermentation. The results revealed that enzymatic treatments enhanced the solubilization of carbohydrates from mulberry fruits, with pectinase showing the most significant effect. Throughout the process of in vitro digestion, there was a gradual increase in the percentage of solubilized carbohydrates from the mulberry juice substrate. The digested suspensions underwent dialysis to remove degradation fragments, and a lower quantity of carbohydrate in the enzyme-treated groups compared to the control. Polysaccharide populations with varying molecular weights (Mw) were obtained from the soluble fractions of mulberry residues for subsequent fermentation. An increase in Mw of soluble polysaccharides was detected by HPSEC during fermentation in certain cases. The gut microbiota demonstrated the ability to convert specific insoluble fractions into soluble components, which were subsequently subjected to microbial utilization. Enzymatic treatments during mulberry juice preparation can potentially positively impact health by influencing gut microbiota and short-chain fatty acid (SCFA) modulations. Enzymes could serve as valuable tools for producing functional fruit and vegetable juices, with the need to specify processing conditions for specific raw materials remaining a subject of further investigation.

Producción Científica

Peihuan Luo mail , Jian Ai mail , Yuxin Wang mail , Songen Wang mail , Henk A. Schols mail , Hauke Smidt mail , Maurizio Battino mail maurizio.battino@uneatlantico.es, Weibin Bai mail , Lingmin Tian mail ,

Luo

en

close

Can the phenolic compounds of Manuka honey chemosensitize colon cancer stem cells? A deep insight into the effect on chemoresistance and self-renewal

Manuka honey, which is rich in pinocembrin, quercetin, naringenin, salicylic, p-coumaric, ferulic, syringic and 3,4-dihydroxybenzoic acids, has been shown to have pleiotropic effects against colon cancer cells. In this study, potential chemosensitizing effects of Manuka honey against 5-Fluorouracil were investigated in colonspheres enriched with cancer stem cells (CSCs), which are responsible for chemoresistance. Results showed that 5-Fluorouracil increased when it was combined with Manuka honey by downregulating the gene expression of both ATP-binding cassette sub-family G member 2, an efflux pump and thymidylate synthase, the main target of 5-Fluorouracil which regulates the ex novo DNA synthesis. Manuka honey was associated with decreased self-renewal ability by CSCs, regulating expression of several genes in Wnt/β-catenin, Hedgehog and Notch pathways. This preliminary study opens new areas of research into the effects of natural compounds in combination with pharmaceuticals and, potentially, increase efficacy or reduce adverse effects.

Producción Científica

Danila Cianciosi mail , Yasmany Armas Diaz mail , José M. Alvarez-Suarez mail , Xiumin Chen mail , Di Zhang mail , Nohora Milena Martínez López mail nohora.martinez@uneatlantico.es, Mercedes Briones Urbano mail mercedes.briones@uneatlantico.es, José L. Quiles mail jose.quiles@uneatlantico.es, Adolfo Amici mail , Maurizio Battino mail maurizio.battino@uneatlantico.es, Francesca Giampieri mail francesca.giampieri@uneatlantico.es,

Cianciosi

en

close

An Optimized Privacy Information Exchange Schema for Explainable AI Empowered WiMAX-based IoT networks

The Internet of Things (IoT) has recently surpassed wired communication. WiMAX is a wireless transmission technology that allows for faster internet access. Wireless network innovations, like some other communication networks, are not safe and secure. Security and authorization models are intended to prevent unauthorized use of network services. Numerous authorization and encrypted communication mechanisms have been introduced for WiMAX privacy, but the communication systems are still insecure and vulnerable to attacks such as zero-day attacks, rouge base station attacks, Man in the Middle (MITM) attacks, and Denial of Service (DoS) attacks. Wireless technologies have come a long way in the last few decades. Because most wireless transmission systems rely on radio signals, the system channel is essentially vulnerable to interception. As a result, data security is always critical in the presentation of a system. Because WiMAX is a wireless communication technology, it is particularly vulnerable to interception, so security is a top priority. Individuals must be protected from security breaches that occur across network interfaces, networking devices, and everything in between. Robust security management is required to protect WiMAX from attacks and vulnerabilities, despite the fact that emerging Artificial Intelligence (AI) technologies necessitate different security governance than existing technologies. We proposed an Optimized Privacy Information Exchange Schema for Explainable AI Empowered WiMAX-based IoT that addresses vulnerabilities and threats during the identification and authorization phases to improve the functionality and performance characteristics of the traditional system. The Scyther tool was used to validate the proposed privacy scheme, which is safer and more secure than existing systems.

Producción Científica

Premkumar Chithaluru mail , Aman Singh mail aman.singh@uneatlantico.es, Jagjit Singh Dhatterwal mail , Ali Hassan Sodhro mail , Marwan Ali Albahar mail , Anca Jurcut mail , Ahmed Alkhayyat mail ,

Chithaluru

en

close

Does the Menstrual Cycle Impact the Maximal Neuromuscular Capacities of Women? An Analysis Before and After a Graded Treadmill Test to Exhaustion

Morenas-Aguilar, MD, Ruiz-Alias, SA, Blanco, AM, Lago-Fuentes, C, García-Pinillos, F, and Pérez-Castilla, A. Does the menstrual cycle impact the maximal neuromuscular capacities of women? An analysis before and after a graded treadmill test to exhaustion. J Strength Cond Res 37(11): 2185–2191, 2023. This study explored the effect of the menstrual cycle (MC) on the maximal neuromuscular capacities of the lower-body muscles obtained before and after a graded exercise test conducted on a treadmill to exhaustion. Sixteen physically active women were tested at −11 ± 3, −5 ± 3, and 5 ± 3 days from the luteinizing peak for the early follicular, late follicular, and midluteal phases. In each session, the individualized load-velocity (L-V) relationship variables (load-axis intercept [L0], velocity-axis intercept [v0], and area under the L-V relationship line [Aline]) were obtained before and after a graded exercise test conducted on a treadmill to exhaustion using the 2-point method (3 countermovement jumps with a 0.5-kg barbell and 2 back squats against a load linked to a mean velocity of 0.55 m·second−1). At the beginning of each session, no significant differences were reported for L0 (p = 0.726; ES ≤ 0.18), v0 (p = 0.202; ES ≤ 0.37), and Aline (p = 0.429; ES ≤ 0.30) between the phases. The MC phase × time interaction did not reach statistical significance for any L-V relationship variable (p ≥ 0.073). A significant main effect of “time” was observed for L0 (p < 0.001; ES = −0.77) and Aline (p = 0.002; ES = −0.59) but not for v0 (p = 0.487; ES = 0.12). These data suggest that the lower-body maximal neuromuscular capacities obtained before and after a graded treadmill test are not significantly affected by MC, although there is a high variability in the individual response.

Producción Científica

María Dolores Morenas-Aguilar mail , Santiago A. Ruiz-Alias mail , Aitor Marcos Blanco mail , Carlos Lago-Fuentes mail carlos.lago@uneatlantico.es, Felipe García-Pinillos mail , Alejandro Pérez-Castilla mail ,

Morenas-Aguilar