A proposal to use the inverse problem for determining parameters in a constitutive model for concrete

Junior, Wanderlei Malaquias Pereira; Borges, Romes Antonio; Araújo, Daniel de Lima; Pituba, José Julio de Cerqueira

doi:10.1007/s00500-021-05745-x

Cited by 4 publications

(1 citation statement)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural networks combined with FA are adopted in [92] to restore a power network. FA integrated by bee colony algorithm is presented to find variables of a concrete damage model [93]. To enhance the rate of convergence and accuracy of FA optimizer, the FA is combined with deep learning [94].…”

Section: Introductionmentioning

confidence: 99%

Development of a COVID-19 Patients’ Fatality Prediction System Using Swarm Intelligent Convolution Neural Network

Kareem

Odeniyi

Lawal

2023

AJRCoS

View full text Add to dashboard Cite

Aims: This work aims to develop a system that can be used to accurately and timely predict the fatality of a positively tested COVID-19 patient through the use of a deep learning technique – a swarm intelligent convolutional neural network. Methodology: The dataset used in this study was acquired from the Kaggle repository database. The dataset contains the Lung Chest X-Ray images of COVID-19 patients. The images were pre- processed to obtain the desired image quality for further processing. This was followed by segmenting the pre-processed images. An Enhanced Firefly Algorithm (EFA) was formulated by applying the roulette wheel selection procedure to model the movement process of the firefly as a deterministic process to assist the standard Firefly Algorithm (FA) and application of Chaotic Sinusoidal Map Function to model the attractive process of the firefly which establishes a balance between exploration and exploitation in FA. The EFA was applied to optimize Convolution Neural Network (CNN) hyper-parameters (number of layers, number of filters per layer, filter size and batch size). The segmented result was subsequently presented to EFA-CNN feature extraction and prediction of COVID-19 patient fatality cases. The formulated deep learning models (EFA-CNN and CNN) were implemented using Matrix Laboratory 2020a software. The implemented models were evaluated using specificity, sensitivity, false positive rate, accuracy, and recognition time/rate to determine the performance of the developed models. Results: The findings revealed that the EFA-CNN model performs better in the prediction of COVID-19 patients’ fatality compared to the CNN model. It was also discovered that the formulated EFA applied to select optimal values of the hyper-parameters for the CNN architecture accounted for improved recognition accuracy and reduced recognition time of the developed COVID-19 Patients’ Fatality Prediction System. Conclusion: The system developed will assist both the government and healthcare workers in providing the needed computational capability for the prediction of the fatality level of a positively tested COVID-19 patient.

show abstract

Section: Introductionmentioning

confidence: 99%