Publications by authors named "Seifedine Kadry"

41 Publications

Analysis of Brain MRI Images Using Improved CornerNet Approach.

Diagnostics (Basel) 2021 Oct 8;11(10). Epub 2021 Oct 8.

Research Group of Embedded Systems and Mobile Application in Health Science, College of Arts, Media and Technology, Chiang Mai University, Chiang Mai 50200, Thailand.

The brain tumor is a deadly disease that is caused by the abnormal growth of brain cells, which affects the human blood cells and nerves. Timely and precise detection of brain tumors is an important task to avoid complex and painful treatment procedures, as it can assist doctors in surgical planning. Manual brain tumor detection is a time-consuming activity and highly dependent on the availability of area experts. Therefore, it is a need of the hour to design accurate automated systems for the detection and classification of various types of brain tumors. However, the exact localization and categorization of brain tumors is a challenging job due to extensive variations in their size, position, and structure. To deal with the challenges, we have presented a novel approach, namely, DenseNet-41-based CornerNet framework. The proposed solution comprises three steps. Initially, we develop annotations to locate the exact region of interest. In the second step, a custom CornerNet with DenseNet-41 as a base network is introduced to extract the deep features from the suspected samples. In the last step, the one-stage detector CornerNet is employed to locate and classify several brain tumors. To evaluate the proposed method, we have utilized two databases, namely, the Figshare and Brain MRI datasets, and attained an average accuracy of 98.8% and 98.5%, respectively. Both qualitative and quantitative analysis show that our approach is more proficient and consistent with detecting and classifying various types of brain tumors than other latest techniques.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3390/diagnostics11101856DOI Listing
October 2021

A Deep Learning Based Approach for Patient Pulmonary CT Image Screening to Predict Coronavirus (SARS-CoV-2) Infection.

Diagnostics (Basel) 2021 Sep 21;11(9). Epub 2021 Sep 21.

Faculty of Engineering & Informatics, University of Bradford, Bradford BD7 1DP, UK.

The novel coronavirus (nCoV-2019) is responsible for the acute respiratory disease in humans known as COVID-19. This infection was found in the Wuhan and Hubei provinces of China in the month of December 2019, after which it spread all over the world. By March, 2020, this epidemic had spread to about 117 countries and its different variants continue to disturb human life all over the world, causing great damage to the economy. Through this paper, we have attempted to identify and predict the novel coronavirus from influenza-A viral cases and healthy patients without infection through applying deep learning technology over patient pulmonary computed tomography (CT) images, as well as by the model that has been evaluated. The CT image data used under this method has been collected from various radiopedia data from online sources with a total of 548 CT images, of which 232 are from 12 patients infected with COVID-19, 186 from 17 patients with influenza A virus, and 130 are from 15 healthy candidates without infection. From the results of examination of the reference data determined from the point of view of CT imaging cases in general, the accuracy of the proposed model is 79.39%. Thus, this deep learning model will help in establishing early screening of COVID-19 patients and thus prove to be an analytically robust method for clinical experts.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3390/diagnostics11091735DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8466782PMC
September 2021

Quantum Machine Learning Architecture for COVID-19 Classification Based on Synthetic Data Generation Using Conditional Adversarial Neural Network.

Cognit Comput 2021 Aug 10:1-12. Epub 2021 Aug 10.

Birla Institute of Technology, Mesra, Jharkhand India.

Background: COVID-19 is a novel virus that affects the upper respiratory tract, as well as the lungs. The scale of the global COVID-19 pandemic, its spreading rate, and deaths are increasing regularly. Computed tomography (CT) scans can be used carefully to detect and analyze COVID-19 cases. In CT images/scans, ground-glass opacity (GGO) is found in the early stages of infection. While in later stages, there is a superimposed pulmonary consolidation.

Methods: This research investigates the quantum machine learning (QML) and classical machine learning (CML) approaches for the analysis of COVID-19 images. The recent developments in quantum computing have led researchers to explore new ideas and approaches using QML. The proposed approach consists of two phases: in phase I, synthetic CT images are generated through the conditional adversarial network (CGAN) to increase the size of the dataset for accurate training and testing. In phase II, the classification of COVID-19/healthy images is performed, in which two models are proposed: CML and QML.

Result: The proposed model achieved 0.94 precision (Pn), 0.94 accuracy (Ac), 0.94 recall (Rl), and 0.94 F1-score (Fe) on POF Hospital dataset while 0.96 Pn, 0.96 Ac, 0.95 Rl, and 0.96 Fe on UCSD-AI4H dataset.

Conclusion: The proposed method achieved better results when compared to the latest published work in this domain.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s12559-021-09926-6DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8353617PMC
August 2021

Impact of autocatalytic chemical reaction in an Ostwald-de-Waele nanofluid flow past a rotating disk with heterogeneous catalysis.

Sci Rep 2021 Jul 30;11(1):15526. Epub 2021 Jul 30.

Department of Mathematics, College of Sciences, King Khalid University, Abha, 61413, Kingdom of Saudi Arabia.

The nanofluids owing to their alluring attributes like enhanced thermal conductivity and better heat transfer characteristics have a vast variety of applications ranging from space technology to nuclear reactors etc. The present study highlights the Ostwald-de-Waele nanofluid flow past a rotating disk of variable thickness in a porous medium with a melting heat transfer phenomenon. The surface catalyzed reaction is added to the homogeneous-heterogeneous reaction that triggers the rate of the chemical reaction. The added feature of the variable thermal conductivity and the viscosity instead of their constant values also boosts the novelty of the undertaken problem. The modeled problem is erected in the form of a system of partial differential equations. Engaging similarity transformation, the set of ordinary differential equations are obtained. The coupled equations are numerically solved by using the bvp4c built-in MATLAB function. The drag coefficient and Nusselt number are plotted for arising parameters. The results revealed that increasing surface catalyzed parameter causes a decline in thermal profile more efficiently. Further, the power-law index is more influential than the variable thickness disk index. The numerical results show that variations in dimensionless thickness coefficient do not make any effect. However, increasing power-law index causing an upsurge in radial, axial, tangential, velocities, and thermal profile.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-021-94918-7DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8324849PMC
July 2021

Optimization of Correlation Filters Using Extended Particle Swarm Optimization Technique.

Comput Math Methods Med 2021 5;2021:6321860. Epub 2021 Jul 5.

Faculty of Applied Computing and Technology, Noroff University College, Kristiansand, Norway.

In the past few decades, the field of image processing has seen a rapid advancement in the correlation filters, which serves as a very promising tool for object detection and recognition. Mostly, complex filter equations are used for deriving the correlation filters, leading to a filter solution in a closed loop. Selection of optimal tradeoff (OT) parameters is crucial for the effectiveness of correlation filters. This paper proposes extended particle swarm optimization (EPSO) technique for the optimal selection of OT parameters. The optimal solution is proposed based on two cost functions. The best result for each target is obtained by applying the optimization technique separately. The obtained results are compared with the conventional particle swarm optimization method for various test images belonging from different state-of-the-art datasets. The obtained results depict the performance of filters improved significantly using the proposed optimization method.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1155/2021/6321860DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8279855PMC
July 2021

Multiple slips impact in the MHD hybrid nanofluid flow with Cattaneo-Christov heat flux and autocatalytic chemical reaction.

Sci Rep 2021 Jul 16;11(1):14625. Epub 2021 Jul 16.

Faculty of Applied Computing and Technology, Noroff University College, Kristiansand, Norway.

The present study deliberates the nanofluid flow containing multi and single-walled carbon nanotubes submerged into Ethylene glycol in a Darcy-Forchheimer permeable media over a stretching cylinder with multiple slips. The innovation of the envisaged mathematical model is enriched by considering the impacts of non-uniform source/sink and modified Fourier law in the energy equation and autocatalytic chemical reaction in the concentration equation. Entropy optimization analysis of the mathematical model is also performed in the present problem. Pertinent transformations procedure is implemented for the conversion of the non-linear system to the ordinary differential equations. The succor of the Shooting technique combined with the bvp4c MATLAB software is utilized for the solution of a highly nonlinear system of equations. The impacts of the leading parameters versus engaged fields are inspected through graphical sketches. The outcomes show that a strong magnetic field strengthens the temperature profile and decays the velocity profile. Also, the fluid velocity is lessened for growing estimates of the parameter of slip. Additionally, it is detected that entropy number augmented for higher thermal relaxation parameter and Reynolds number. To substantiate the existing mathematical model, a comparison table is also added. An excellent correlation is achieved here.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-021-94187-4DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8285399PMC
July 2021

Smart-Contract Aware Ethereum and Client-Fog-Cloud Healthcare System.

Sensors (Basel) 2021 Jun 14;21(12). Epub 2021 Jun 14.

Research Group of Embedded Systems and Mobile Application in Health Science, College of Arts, Media and Technology, Chiang Mai University, Chiang Mai 50200, Thailand.

The Internet of Medical Things (IoMT) is increasingly being used for healthcare purposes. IoMT enables many sensors to collect patient data from various locations and send it to a distributed hospital for further study. IoMT provides patients with a variety of paid programmes to help them keep track of their health problems. However, the current system services are expensive, and offloaded data in the healthcare network are insecure. The research develops a new, cost-effective and stable IoMT framework based on a blockchain-enabled fog cloud. The study aims to reduce the cost of healthcare application services as they are processing in the system. The study devises an IoMT system based on different algorithm techniques, such as Blockchain-Enable Smart-Contract Cost-Efficient Scheduling Algorithm Framework (BECSAF) schemes. Smart-Contract Blockchain schemes ensure data consistency and validation with symmetric cryptography. However, due to the different workflow tasks scheduled on other nodes, the heterogeneous, earliest finish, time-based scheduling deals with execution under their deadlines. Simulation results show that the proposed algorithm schemes outperform all existing baseline approaches in terms of the implementation of applications.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3390/s21124093DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8232207PMC
June 2021

Underwater Networked Wireless Sensor Data Collection for Computational Intelligence Techniques: Issues, Challenges, and Approaches.

IEEE Access 2020 6;8:122959-122974. Epub 2020 Jul 6.

Department of Computer Science and EngineeringLovely Professional UniversityPhagwara144411India.

Underwater wireless sensor networks (UWSNs) is emerging as an advance terminology for monitoring and controlling the underwater aquatic life. This technology determines the undiscovered resources present in the water through computational intelligence (CI) techniques. CI here pertains to the capability of a system to acquire a specific task from data or experimental surveillance below the water. In today's time data is considered as the identity for everything that exists in nature, whether that data is related to human beings, machines or any type of device like internet of underwater things (IoUT). The collected data should be correct, complete and fulfill the requirements of a particular task to be done. Underwater data collection is very tough because of sensors mobility due to water drift 3 meters/sec, crest and trough. A lot of packet drop also exists due to underwater conditions that hurdles the data collection process. Various techniques already exists for efficient collection of data below the water but these are not properly classified. This manuscript has summarized the concept of data collection in UWSN along with its classification based on routing. Also, a short discussion about existence of CORONA below the water along with water purification is carried out. Furthermore, some data routing approaches are also analyzed on the basis of quality of service parameters and the current challenges to be tackled during data collection are also discussed.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/ACCESS.2020.3007502DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8051310PMC
July 2020

Internet of things-assisted advanced dynamic information processing system for physical education system.

Technol Health Care 2021 May 26. Epub 2021 May 26.

Wenzhou Kean University, Weizhou, Zhejiang, China.

Background: In recent years the Internet of Things (IoT) has become a popular technological culture in the physical education system. Though several technologies have grown in the physical education system domain, IoT plays a significant role due to its optimized health information processing framework for students during workouts.

Objective: In this paper, an advanced dynamic information processing system (ADIPS) has been proposed with IoT assistance to explore the traditional design architecture for physical activity tracking.

Method: To track and evaluate human physical activity in day-to-day living, a new paradigm has been integrated with wearable IoT devices for effective information processing during physical workouts. Continuous observation and review of the condition and operations of various students by ADIPS helps to evaluate the sensed information to analyze the health condition of the students.

Results: The result of ADIPS has been implemented based on the performance factor correlation with the traditional system.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/THC-213005DOI Listing
May 2021

Detection of diabetic retinopathy using a fusion of textural and ridgelet features of retinal images and sequential minimal optimization classifier.

PeerJ Comput Sci 2021 7;7:e456. Epub 2021 May 7.

Department of Applied Informatics, Vytautas Magnus University, Kaunas, Lithuania.

Diabetes is one of the most prevalent diseases in the world, which is a metabolic disorder characterized by high blood sugar. Diabetes complications are leading to Diabetic Retinopathy (DR). The early stages of DR may have either no sign or cause minor vision problems, but later stages of the disease can lead to blindness. DR diagnosis is an exceedingly difficult task because of changes in the retina during the disease stages. An automatic DR early detection method can save a patient's vision and can also support the ophthalmologists in DR screening. This paper develops a model for the diagnostics of DR. Initially, we extract and fuse the ophthalmoscopic features from the retina images based on textural gray-level features like co-occurrence, run-length matrix, as well as the coefficients of the Ridgelet Transform. Based on the retina features, the Sequential Minimal Optimization (SMO) classification is used to classify diabetic retinopathy. For performance analysis, the openly accessible retinal image datasets are used, and the findings of the experiments demonstrate the quality and efficacy of the proposed method (we achieved 98.87% sensitivity, 95.24% specificity, 97.05% accuracy on DIARETDB1 dataset, and 90.9% sensitivity, 91.0% specificity, 91.0% accuracy on KAGGLE dataset).
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.7717/peerj-cs.456DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8114804PMC
May 2021

Nonlinear radiative Maxwell nanofluid flow in a Darcy-Forchheimer permeable media over a stretching cylinder with chemical reaction and bioconvection.

Sci Rep 2021 04 30;11(1):9391. Epub 2021 Apr 30.

Division of Computational Science, Faculty of Science, Prince of Songkla University, Hat Yai, Songkhla, 90110, Thailand.

Studies accentuating nanomaterials suspensions and flow traits in the view of their applications are the focus of the present study. Especially, the usage of such materials in biomedical rheological models has achieved great importance. The nanofluids' role is essential in the cooling of small electronic gizmos like microchips and akin devices. Having such exciting and practical applications of nanofluids our goal is to scrutinize the Maxwell MHD nanofluid flow over an extended cylinder with nonlinear thermal radiation amalgamated with chemical reaction in a Darcy-Forchheimer spongy media. The presence of gyrotactic microorganisms is engaged to stabilize the nanoparticles in the fluid. The partial slip condition is considered at the boundary of the stretching cylinder. The Buongiorno nanofluid model is betrothed with impacts of the Brownian motion and thermophoresis. The analysis of entropy generation is also added to the problem. The highly nonlinear system is tackled numerically is addressed by the bvp4c built-in function of the MATLAB procedure. The outcomes of the prominent parameters versus embroiled profiles are portrayed and conversed deeming their physical significance. It is perceived that fluid temperature is augmented for large estimates of the radiation and Darcy parameters. Moreover, it is noticed that the magnetic and wall roughness parameters lower the fluid velocity. To corroborate the presented results, a comparison of the current study with a previously published paper is also executed. An outstanding correlation in this regard is attained.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-021-88947-5DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8087771PMC
April 2021

Analyzing the impact of induced magnetic flux and Fourier's and Fick's theories on the Carreau-Yasuda nanofluid flow.

Sci Rep 2021 Apr 29;11(1):9230. Epub 2021 Apr 29.

Faculty of Applied Computing and Technology, Noroff University College, Kristiansand, 4608, Norway.

The current study analyzes the effects of modified Fourier and Fick's theories on the Carreau-Yasuda nanofluid flow over a stretched surface accompanying activation energy with binary chemical reaction. Mechanism of heat transfer is observed in the occurrence of heat source/sink and Newtonian heating. The induced magnetic field is incorporated to boost the electric conductivity of nanofluid. The formulation of the model consists of nonlinear coupled partial differential equations that are transmuted into coupled ordinary differential equations with high nonlinearity by applying boundary layer approximation. The numerical solution of this coupled system is carried out by implementing the MATLAB solver bvp4c package. Also, to verify the accuracy of the numerical scheme grid-free analysis for the Nusselt number is presented. The influence of different parameters, for example, reciprocal magnetic Prandtl number, stretching ratio parameter, Brownian motion, thermophoresis, and Schmidt number on the physical quantities like velocity, temperature distribution, and concentration distribution are addressed with graphs. The Skin friction coefficient and local Nusselt number for different parameters are estimated through Tables. The analysis shows that the concentration of nanoparticles increases on increasing the chemical reaction with activation energy and also Brownian motion efficiency and thermophoresis parameter increases the nanoparticle concentration. Opposite behavior of velocity profile and the Skin friction coefficient is observed for increasing the stretching ratio parameter. In order to validate the present results, a comparison with previously published results is presented. Also, Factors of thermal and solutal relaxation time effectively contribute to optimizing the process of stretchable surface chilling, which is important in many industrial applications.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-021-87831-6DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8085058PMC
April 2021

An Efficient DenseNet-Based Deep Learning Model for Malware Detection.

Entropy (Basel) 2021 Mar 15;23(3). Epub 2021 Mar 15.

Faculty of Applied Mathematics, Silesian University of Technology, 44-100 Gliwice, Poland.

Recently, there has been a huge rise in malware growth, which creates a significant security threat to organizations and individuals. Despite the incessant efforts of cybersecurity research to defend against malware threats, malware developers discover new ways to evade these defense techniques. Traditional static and dynamic analysis methods are ineffective in identifying new malware and pose high overhead in terms of memory and time. Typical machine learning approaches that train a classifier based on handcrafted features are also not sufficiently potent against these evasive techniques and require more efforts due to feature-engineering. Recent malware detectors indicate performance degradation due to class imbalance in malware datasets. To resolve these challenges, this work adopts a visualization-based method, where malware binaries are depicted as two-dimensional images and classified by a deep learning model. We propose an efficient malware detection system based on deep learning. The system uses a reweighted class-balanced loss function in the final classification layer of the DenseNet model to achieve significant performance improvements in classifying malware by handling imbalanced data issues. Comprehensive experiments performed on four benchmark malware datasets show that the proposed approach can detect new malware samples with higher accuracy (98.23% for the Malimg dataset, 98.46% for the BIG 2015 dataset, 98.21% for the MaleVis dataset, and 89.48% for the unseen Malicia dataset) and reduced false-positive rates when compared with conventional malware mitigation techniques while maintaining low computational time. The proposed malware detection solution is also reliable and effective against obfuscation attacks.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3390/e23030344DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7998822PMC
March 2021

Nonclinical Features in Predictive Modeling of Cardiovascular Diseases: A Machine Learning Approach.

Interdiscip Sci 2021 Jun 6;13(2):201-211. Epub 2021 Mar 6.

Department of Computer Science and Engineering, SRM Institute of Science & Technology, Kattankulathur, Chengalpattu (D.t), 603 203, Tamilnadu, India.

Background: In the broader healthcare domain, the prediction bears more value than an explanation considering the cost of delays in its services. There are various risk prediction models for cardiovascular diseases (CVDs) in the literature for early risk assessment. However, the substantial increase in CVDs-related mortality is challenging global health systems, especially in developing countries. This situation allows researchers to improve CVDs prediction models using new features and risk computing methods. This study aims to assess nonclinical features that can be easily available in any healthcare systems, in predicting CVDs using advanced and flexible machine learning (ML) algorithms.

Methods: A gender-matched case-control study was conducted in the largest public sector cardiac hospital of Pakistan, and the data of 460 subjects were collected. The dataset comprised of eight nonclinical features. Four supervised ML algorithms were used to train and test the models to predict the CVDs status by considering traditional logistic regression (LR) as the baseline model. The models were validated through the train-test split (70:30) and tenfold cross-validation approaches.

Results: Random forest (RF), a nonlinear ML algorithm, performed better than other ML algorithms and LR. The area under the curve (AUC) of RF was 0.851 and 0.853 in the train-test split and tenfold cross-validation approach, respectively. The nonclinical features yielded an admissible accuracy (minimum 71%) through the LR and ML models, exhibiting its predictive capability in risk estimation.

Conclusion: The satisfactory performance of nonclinical features reveals that these features and flexible computational methodologies can reinforce the existing risk prediction models for better healthcare services.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s12539-021-00423-wDOI Listing
June 2021

Irreversibility minimization analysis of ferromagnetic Oldroyd-B nanofluid flow under the influence of a magnetic dipole.

Sci Rep 2021 Feb 26;11(1):4810. Epub 2021 Feb 26.

Department of Mathematics, Huzhou University, Huzhou, 313000, People's Republic of China.

Studies highlighting nanoparticles suspensions and flow attributes in the context of their application are the subject of current research. In particular, the utilization of these materials in biomedical rheological models has gained great attention. Magneto nanoparticles have a decisive role in the ferrofluid flows to regulate their viscoelastic physiognomies. Having such substantial interest in the flow of ferrofluids our objective is to elaborate the melting heat transfer impact in a stretched Oldroyd-B flow owing to a magnetic dipole in the presence of entropy generation optimization. Buongiorno nanofluid model expounding thermophoretic and Brownian features are considered. Moreover, activation energy with chemical reaction is also considered. The Cattaneo-Christov heat flux model is affianced instead of conventional Fourier law. The renowned bvp4c function of MATLAB is utilized to handle the nonlinearity of the system. Impacts of miscellaneous parameters are portrayed through graphical fallouts and numeric statistics. Results divulge that the velocity and temperature profiles show the opposite trend for growing estimates of the ferromagnetic parameter. It is also noticed that the temperature ratio parameter diminishes the entropy profile. Moreover, it is seen that the concentration profile displays a dwindling trend for the Brownian motion parameter and the opposite trend is witnessed for the thermophoretic parameter.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-021-84254-1DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7910595PMC
February 2021

Industrial Internet of Things for smart manufacturing applications using Hierarchical Trustful Resource Assignment.

Work 2021 ;68(3):955-965

Beirut Arab University, Beirut, Lebanon.

Background: The manufacturing industry undergoes a new age, with significant changes taking place on several fronts. Companies devoted to digital transformation take their future plants inspired by the Internet of Things (IoT). The IoT is a worldwide network of interrelated physical devices, which is an essential component of the internet, including sensors, actuators, smart apps, computers, mechanical machines, and people. The effective allocation of the computing resources and the carrier is critical in the Industrial Internet of Things (IIoT) for smart production systems. Indeed, the existing assignment method in the smart production system cannot guarantee that resources meet the inherently complex and volatile requirements of the user are timely. Many research results on resource allocations in auction formats which have been implemented to consider the demand and real-time supply for smart development resources, but safety privacy and trust estimation issues related to these outcomes are not actively discussed.

Objectives: The paper proposes a Hierarchical Trustful Resource Assignment (HTRA) and Trust Computing Algorithm (TCA) based on Vickrey Clarke-Groves (VGCs) in the computer carriers necessary resources to communicate wirelessly among IIoT devices and gateways, and the allocation of CPU resources for processing information at the CPC.

Results: Finally, experimental findings demonstrate that when the IIoT equipment and gateways are valid, the utilities of each participant are improved.

Conclusion: This is an easy and powerful method to guarantee that intelligent manufacturing components genuinely work for their purposes, which want to integrate each element into a system without interactions with each other.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/WOR-203429DOI Listing
June 2021

Application of response surface methodology on the nanofluid flow over a rotating disk with autocatalytic chemical reaction and entropy generation optimization.

Sci Rep 2021 Feb 17;11(1):4021. Epub 2021 Feb 17.

Department of Mathematics, Huzhou University, Huzhou, 313000, People's Republic of China.

The role of nanofluids is of fundamental significance in the cooling process of small electronic devices including microchips and other associated gadgets in microfluidics. With such astounding applications of nanofluids in mind, it is intended to examine the flow of magnetohydrodynamic nanofluid comprising a novel combination of multi-walled carbon nanotubes and engine oil over a stretched rotating disk. The concentration equation is modified by considering the autocatalytic chemical reaction. The succor of the bvp4c numerical technique amalgamated with the response surface methodology is secured for the solution of a highly nonlinear system of equations. The sensitivity analysis is performed using a response surface methodology. The significant impacts of the prominent arising parameters versus involved fields are investigated through graphical illustrations. It is observed that the skin friction coefficient and local Nusselt number are positively sensitive to nanoparticle volume fraction while it is positively sensitive to the suction parameter. It is negatively sensitive to the Magnetic parameter. The skin friction coefficient is negatively sensitive to all input parameters.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-021-81755-xDOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7890068PMC
February 2021

Cloud Computing-Based Framework for Breast Cancer Diagnosis Using Extreme Learning Machine.

Diagnostics (Basel) 2021 Feb 4;11(2). Epub 2021 Feb 4.

Department of Electrical-Electronics Engineering, Trakya University, Edirne 22030, Turkey.

Globally, breast cancer is one of the most significant causes of death among women. Early detection accompanied by prompt treatment can reduce the risk of death due to breast cancer. Currently, machine learning in cloud computing plays a pivotal role in disease diagnosis, but predominantly among the people living in remote areas where medical facilities are scarce. Diagnosis systems based on machine learning act as secondary readers and assist radiologists in the proper diagnosis of diseases, whereas cloud-based systems can support telehealth services and remote diagnostics. Techniques based on artificial neural networks (ANN) have attracted many researchers to explore their capability for disease diagnosis. Extreme learning machine (ELM) is one of the variants of ANN that has a huge potential for solving various classification problems. The framework proposed in this paper amalgamates three research domains: Firstly, ELM is applied for the diagnosis of breast cancer. Secondly, to eliminate insignificant features, the gain ratio feature selection method is employed. Lastly, a cloud computing-based system for remote diagnosis of breast cancer using ELM is proposed. The performance of the cloud-based ELM is compared with some state-of-the-art technologies for disease diagnosis. The results achieved on the Wisconsin Diagnostic Breast Cancer (WBCD) dataset indicate that the cloud-based ELM technique outperforms other results. The best performance results of ELM were found for both the standalone and cloud environments, which were compared. The important findings of the experimental results indicate that the accuracy achieved is 0.9868, the recall is 0.9130, the precision is 0.9054, and the F1-score is 0.8129.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3390/diagnostics11020241DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7913821PMC
February 2021

Prediction of COVID-19 - Pneumonia based on Selected Deep Features and One Class Kernel Extreme Learning Machine.

Comput Electr Eng 2021 Mar 30;90:106960. Epub 2020 Dec 30.

College of Computer and Information Sciences, Prince Sultan University, SA.

In this work, we propose a deep learning framework for the classification of COVID-19 pneumonia infection from normal chest CT scans. In this regard, a 15-layered convolutional neural network architecture is developed which extracts deep features from the selected image samples - collected from the Radiopeadia. Deep features are collected from two different layers, global average pool and fully connected layers, which are later combined using the max-layer detail (MLD) approach. Subsequently, a Correntropy technique is embedded in the main design to select the most discriminant features from the pool of features. One-class kernel extreme learning machine classifier is utilized for the final classification to achieving an average accuracy of 95.1%, and the sensitivity, specificity & precision rate of 95.1%, 95%, & 94% respectively. To further verify our claims, detailed statistical analyses based on standard error mean (SEM) is also provided, which proves the effectiveness of our proposed prediction design.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.compeleceng.2020.106960DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7832028PMC
March 2021

Impact of Newtonian heating and Fourier and Fick's laws on a magnetohydrodynamic dusty Casson nanofluid flow with variable heat source/sink over a stretching cylinder.

Sci Rep 2021 Jan 27;11(1):2357. Epub 2021 Jan 27.

College of Natural and Health Sciences, Zayed University, 144543, Abu Dhabi, UAE.

The present investigation aims to deliberate the magnetohydrodynamic (MHD) dusty Casson nanofluid with variable heat source/sink and modified Fourier's and Fick's laws over a stretching cylinder. The novelty of the flow model is enhanced with additional effects of the Newtonian heating, activation energy, and an exothermic chemical reaction. In an exothermic chemical reaction, the energy of the reactants is higher than the end products. The solution to the formulated problem is attained numerically by employing the MATLAB software function bvp4c. The behavior of flow parameters versus involved profiles is discussed graphically at length. For large values of momentum dust particles, the velocity field for the fluid flow declines, whereas an opposite trend is perceived for the dust phase. An escalation is noticed for the Newtonian heating in the temperature profile for both the fluid and dust-particle phase. A comparison is also added with an already published work to check the validity of the envisioned problem.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-021-81747-xDOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7841187PMC
January 2021

Time series forecasting of COVID-19 transmission in Asia Pacific countries using deep neural networks.

Pers Ubiquitous Comput 2021 Jan 10:1-18. Epub 2021 Jan 10.

Department of Mathematics and Computer Science, Faculty of Science, University of Jeddah, Jeddah, Saudi Arabia.

The novel human coronavirus disease COVID-19 has become the fifth documented pandemic since the 1918 flu pandemic. COVID-19 was first reported in Wuhan, China, and subsequently spread worldwide. Almost all of the countries of the world are facing this natural challenge. We present forecasting models to estimate and predict COVID-19 outbreak in Asia Pacific countries, particularly Pakistan, Afghanistan, India, and Bangladesh. We have utilized the latest deep learning techniques such as Long Short Term Memory networks (LSTM), Recurrent Neural Network (RNN), and Gated Recurrent Units (GRU) to quantify the intensity of pandemic for the near future. We consider the time variable and data non-linearity when employing neural networks. Each model's salient features have been evaluated to foresee the number of COVID-19 cases in the next 10 days. The forecasting performance of employed deep learning models shown up to July 01, 2020, is more than 90% accurate, which shows the reliability of the proposed study. We hope that the present comparative analysis will provide an accurate picture of pandemic spread to the government officials so that they can take appropriate mitigation measures.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s00779-020-01494-0DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7797027PMC
January 2021

Upshot of heterogeneous catalysis in a nanofluid flow over a rotating disk with slip effects and Entropy optimization analysis.

Sci Rep 2021 Jan 8;11(1):120. Epub 2021 Jan 8.

College of Natural and Health Sciences, Zayed University, 144543, Abu Dhabi, United Arab Emirates.

The present study examines homogeneous (HOM)-heterogeneous (HET) reaction in magnetohydrodynamic flow through a porous media on the surface of a rotating disk. Preceding investigations mainly concentrated on the catalysis for the rotating disk; we modeled the impact of HET catalysis in a permeable media over a rotating disk with slip condition at the boundary. The HOM reaction is followed by isothermal cubic autocatalysis, however, the HET reactions occur on the surface governed by first-order kinetics. Additionally, entropy minimization analysis is also conducted for the envisioned mathematical model. The similarity transformations are employed to convert the envisaged model into a non-dimensional form. The system of the modeled problem with ordinary differential equations is analyzed numerically by using MATLAB built-in bvp4c function. The behavior of the emerging parameters versus the thermal, concentration, and velocity distributions are depicted graphically with requisite discussion abiding the thumb rules. It is learned that the rate of the surface catalyzed reaction is strengthened if the interfacial area of the permeable media is enhanced. Thus, a spongy medium can significantly curtail the reaction time. It is also noticed that the amplitude of velocity and thermal profile is maximum for the smallest value of the velocity slip parameter. Heat transfer rate declines for thermophoresis and the Brownian motion parameter with respect to the thermal slip parameter. The cogency of the developed model is also validated by making a comparison of the existing results with a published article under some constraints. Excellent harmony between the two results is noted.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-020-80553-1DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7794536PMC
January 2021

Novel framework of GIS based automated monitoring process on environmental biodegradability and risk analysis using Internet of Things.

Environ Res 2021 03 9;194:110621. Epub 2021 Jan 9.

Department of Software, Sejong University, 209 Neungdong-ro, Gwangjin-gu, Seoul, Republic of Korea. Electronic address:

A proper method on real-time monitoring of organic biomass degradation and its evaluation for safeguarding the ecosystem is the need of the hour. The work process designed in this study is to demarcate the anaerobic digestion potential using kinetic modelling and web GIS application methods. Wastewater source that causes pollution are identified through satellite maps such as solid earth, drain system, surface of earth structure, land filling and land use. The grabbed data are utilized for identifying the concentration of sludge availability. Based on literature resource multi influencing factor techniques are introduced along with overlay method to differentiate digestion potential of sludge source. This study optimizes the biodegradation potential of domestic sewage at different sludge concentrations in a pilot model operated with the samples identified through topographical drainage survey. The materialization of devices is using the Internet of Things (IoTs), that is pragmatic to be the promising tendency. Kinetic study, methanogenic assay test are performed with three different cation binding agents to find its solubilization potential and methane evolution, which is further subjected to digestion potential in anaerobic conditions for possible application in the field of environmental science. Risk analysis reveals that land filling method will have highest impact on maintaining sustainable environment. The results outcome on natural biodegradation may be used for individual house hold wastewater management for the locality.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.envres.2020.110621DOI Listing
March 2021

Effects of Chemical Species and Nonlinear Thermal Radiation with 3D Maxwell Nanofluid Flow with Double Stratification-An Analytical Solution.

Entropy (Basel) 2020 Apr 16;22(4). Epub 2020 Apr 16.

Department of Computer Science and Engineering, Soonchunhyang University, Asan 31538, Korea.

This article elucidates the magnetohydrodynamic 3D Maxwell nanofluid flow with heat absorption/generation effects. The impact of the nonlinear thermal radiation with a chemical reaction is also an added feature of the presented model. The phenomenon of flow is supported by thermal and concentration stratified boundary conditions. The boundary layer set of non-linear PDEs (partial differential equation) are converted into ODEs (ordinary differential equation) with high nonlinearity via suitable transformations. The homotopy analysis technique is engaged to regulate the mathematical analysis. The obtained results for concentration, temperature and velocity profiles are analyzed graphically for various admissible parameters. A comparative statement with an already published article in limiting case is also added to corroborate our presented model. An excellent harmony in this regard is obtained. The impact of the Nusselt number for distinct parameters is also explored and discussed. It is found that the impacts of Brownian motion on the concentration and temperature distributions are opposite. It is also comprehended that the thermally stratified parameter decreases the fluid temperature.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3390/e22040453DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7516935PMC
April 2020

Radiative MHD Nanofluid Flow over a Moving Thin Needle with Entropy Generation in a Porous Medium with Dust Particles and Hall Current.

Entropy (Basel) 2020 Mar 18;22(3). Epub 2020 Mar 18.

Department of Computer Science and Engineering, Soonchunhyang University, Asan 31538, Korea.

This paper investigated the behavior of the two-dimensional magnetohydrodynamics (MHD) nanofluid flow of water-based suspended carbon nanotubes (CNTs) with entropy generation and nonlinear thermal radiation in a Darcy-Forchheimer porous medium over a moving horizontal thin needle. The study also incorporated the effects of Hall current, magnetohydrodynamics, and viscous dissipation on dust particles. The said flow model was described using high order partial differential equations. An appropriate set of transformations was used to reduce the order of these equations. The reduced system was then solved by using a MATLAB tool bvp4c. The results obtained were compared with the existing literature, and excellent harmony was achieved in this regard. The results were presented using graphs and tables with coherent discussion. It was comprehended that Hall current parameter intensified the velocity profiles for both CNTs. Furthermore, it was perceived that the Bejan number boosted for higher values of Darcy-Forchheimer number.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3390/e22030354DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7516827PMC
March 2020

Comparative analysis of magnetized partially ionized copper, copper oxide-water and kerosene oil nanofluid flow with Cattaneo-Christov heat flux.

Sci Rep 2020 Nov 9;10(1):19300. Epub 2020 Nov 9.

Department of Mathematics, Huzhou University, Huzhou, 313000, People's Republic of China.

This comparative analysis studies the impact of two different nanoparticles Copper and Copper Oxide in two different partially ionized magnetofluid (water and kerosene oil mixed with Copper/Copper Oxide) flows over a linearly stretching surface. The impacts of electrons and ions collisions in the presence of the Cattaneo-Christov heat transfer model are also investigated. The effects of prominent parameters on velocity and temperature fields are depicted through graphical illustrations. A similarity transformation procedure is applied to transform the nonlinear partial differential equations to the ordinary one. Our numerical methodology is based upon the Finite difference method that is the default method in the bvp4c built-in function of the MATLAB scheme. Nusselt number and Skin drag coefficient are computed numerically and presented in tabular form for both types of nanofluids over a linear stretched surface. Our results demonstrate that the effects of CuO are dominant in comparison to the Cu on fluid velocity. The fluid temperature is more prominent in the case of Cu-water nanofluid when we increase nanoparticles concentration.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-020-74865-5DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7653961PMC
November 2020

Nanofluid flow containing carbon nanotubes with quartic autocatalytic chemical reaction and Thompson and Troian slip at the boundary.

Sci Rep 2020 Oct 30;10(1):18710. Epub 2020 Oct 30.

FAST School of Management, National University of Computer & Emerging Sciences, A.K.Brohi Road, H-11/4, Islamabad, Pakistan.

A mathematical model is envisioned to discourse the impact of Thompson and Troian slip boundary in the carbon nanotubes suspended nanofluid flow near a stagnation point along an expanding/contracting surface. The water is considered as a base fluid and both types of carbon nanotubes i.e., single-wall (SWCNTs) and multi-wall (MWCNTs) are considered. The flow is taken in a Dacry-Forchheimer porous media amalgamated with quartic autocatalysis chemical reaction. Additional impacts added to the novelty of the mathematical model are the heat generation/absorption and buoyancy effect. The dimensionless variables led the envisaged mathematical model to a physical problem. The numerical solution is then found by engaging MATLAB built-in bvp4c function for non-dimensional velocity, temperature, and homogeneous-heterogeneous reactions. The validation of the proposed mathematical model is ascertained by comparing it with a published article in limiting case. An excellent consensus is accomplished in this regard. The behavior of numerous dimensionless flow variables including solid volume fraction, inertia coefficient, velocity ratio parameter, porosity parameter, slip velocity parameter, magnetic parameter, Schmidt number, and strength of homogeneous/heterogeneous reaction parameters are portrayed via graphical illustrations. Computational iterations for surface drag force are tabulated to analyze the impacts at the stretched surface. It is witnessed that the slip velocity parameter enhances the fluid stream velocity and diminishes the surface drag force. Furthermore, the concentration of the nanofluid flow is augmented for higher estimates of quartic autocatalysis chemical.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-020-74855-7DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7603354PMC
October 2020

Nanofluid flow with autocatalytic chemical reaction over a curved surface with nonlinear thermal radiation and slip condition.

Sci Rep 2020 Oct 27;10(1):18339. Epub 2020 Oct 27.

Department of Mathematics, Huzhou University, Huzhou, 313000, People's Republic of China.

The study of nanofluids is the most debated subject for the last two decades. Researchers have shown great interest owing to the amazing features of nanofluids including heat transfer and thermal conductivity enhancement capabilities. Having such remarkable features of nanofluids in mind we have envisioned a mathematical model that discusses the flow of nanofluid comprising Nickel-Zinc Ferrite-Ethylene glycol (Ni-ZnFeO-CHO) amalgamation past an elongated curved surface with autocatalytic chemical reaction. The additional impacts added to the flow model are the heat generation/absorption with nonlinear thermal radiation. At the boundary, the slip and the convective conditions are added. Pertinent transformations are affianced to get the system of ordinary differential equations from the governing system in curvilinear coordinates. A numerical solution is found by applying MATLAB build-in function bvp4c. Graphical illustrations and the numerically computed estimates are discussed and analyzed properly. It is comprehended that velocity and temperature distributions have varied trends near and away from the curve when the curvature parameter is enhanced. Further, it is comprehended that the concentration field declines for both homogeneous and heterogeneous reaction parameters.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-020-73142-9DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7591526PMC
October 2020

Significance of Hall effect and Ion slip in a three-dimensional bioconvective Tangent hyperbolic nanofluid flow subject to Arrhenius activation energy.

Sci Rep 2020 10 27;10(1):18342. Epub 2020 Oct 27.

Department of Mathematics, Huzhou University, Huzhou, 313000, People's Republic of China.

The dynamics of partially ionized fluid flow subjected to the magnetic field are altogether distinct in comparison to the flow of natural fluids. Fewer studies are available in the literature discussing the alluring characteristics of the Hall effect and the Ion slip in nanofluid flows. Nevertheless, the flow of nanofluid flow with Hall and Ion slip effect integrated with activation energy, gyrotactic microorganisms, and Cattaneo-Christov heat flux is still scarce. To fill in this gap, our aim here is to examine the three dimensional electrically conducting Tangent hyperbolic bioconvective nanofluid flow with Hall and Ion slip under the influence of magnetic field and heat transmission phenomenon past a stretching sheet. Impacts of Cattaneo-Christov heat flux, Arrhenius activation energy, and chemical reaction are also considered here. For the conversion of a non-linear system to an ordinary one, pertinent transformations procedure is implemented. By using the bvp4c MATLAB function, these equations with the boundary conditions are worked out numerically. The significant impacts of prominent parameters on velocity, temperature, and concentration profiles are investigated through graphical illustrations. The results show that the velocity of the fluid is enhanced once the Ion slip and Hall parameters values are improved. Furthermore, the concentration is improved when the values of the activation energy parameter are enhanced.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-020-73365-wDOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7591580PMC
October 2020

Impact of hall and ion slip in a thermally stratified nanofluid flow comprising Cu and AlO nanoparticles with nonuniform source/sink.

Sci Rep 2020 Oct 22;10(1):18064. Epub 2020 Oct 22.

Department of Mathematics, Huzhou University, Huzhou, 313000, People's Republic of China.

Nanofluids play a pivotal role in the heat transport phenomenon and are essential in the cooling process of small gadgets like computer microchips and other related applications in microfluidics. Having such amazing applications of nanofluids, we intend to present a theoretical analysis of the thermally stratified 3D flow of nanofluid containing nano solid particles (Cu and AlO) over a nonlinear stretchable sheet with Ion and Hall slip effects. Moreover, the features of buoyance effect and non-uniform heat source/skin are also analyzed. For the study of numerically better results, Tawari and Das model is adopted here. For the conversion of the system of partial differential equations into ordinary differential equations, apposite transformations are engaged and are tackled by utilizing the bvp4c scheme of MATLAB software. The effects of dimensionless parameters on velocity and temperature profiles are depicted with the help of graphs. Additionally, the Skin friction coefficient and Nusselt number for the practical applications are examined in the tabular form. Verification of the current study by comparing it with an already published work in a special case is also a part of this study. Results show that the thermal performance of copper nanoparticles is more than alumina nanoparticles. An upsurge in the temperature of nanofluid is observed when the strength of the magnetic field is enhanced. However, the temperature of partially ionized nanofluid is significantly lowered because of the collisions of electrons and ions.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-020-74510-1DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7582187PMC
October 2020
-->