CNN-Based Multiclass Classification for  COVID-19  in Chest X-ray Images

S.K.Towfek

doi:https://doi.org/10.54216/JAIM.060105

American Journal of Business and Operations Research | 2021

Strategic Integration of Business Intelligence for Sustainable Portfolio Management in the Industry 4.0 Era

The advent of Industry 4.0 has propelled a transformative shift in business paradigms, prompting the strategic integration of business intelligence (BI) for sustainable portfolio management. This study addresses the need to discern optimal strategies in clustering investor portfolios within this dynamic landscape. Leveraging the Gap Statistic Algorithm and Silhouette Coefficient, a systematic methodology was employed to cluster investors based on diverse portfolio attributes, including asset allocation, risk profiles, and historical performance metrics. A feature correlation map elucidated attribute interdependencies, while summary statistics provided a comprehensive snapshot of the investor dataset. Results from the Gap Statistic Algorithm revealed an optimal cluster count, guiding the segmentation of investors into distinct clusters. Subsequent validation using the Silhouette Coefficient affirmed the coherence and quality of the clusters derived. The findings underscore the efficacy of BI-driven approaches in effectively clustering investors based on portfolio characteristics within Industry 4.0, facilitating nuanced insights into investor behaviors and preferences. Conclusively, this research illuminates pathways for informed decision-making in sustainable portfolio management, emphasizing the pivotal role of BI tools in optimizing investor segmentation strategies for contemporary industrial landscapes.

groups

Ahmed M. Ali mail -

Ahmed Abdelhafeez mail -

Shimaa S. Mohamed mail

link https://doi.org/10.54216/AJBOR.030205

Volume & Issue

Vol. Volume 3 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications |

Design PID Controller Tuned by Using Fuzzy Logic for 3 Link Robot Manipulator

Robots are commonly used in industry, but they have limitations like complex dynamics, difficulties with flexibility, and nonlinearity. This research aims to enhance the tracking performance of a three-DOF open-chain robot manipulator. So, the driven dynamic equations will be utilized to identify the nonlinear robot model. The objective of this study is to achieve the desired performance of a three-degree-of-freedom (3-DOF) robot through the implementation of a Fuzzy Logic Self-Tuning Proportional-Integral-Derivative (PID) controller. The proposed PID controller exhibits notable distinctions when compared to the traditional PID controller. In conventional PID control, model parameters are determined by a range of procedures, including Ziegler-Nichols. However, in the context of fuzzy logic self-tuning PID control, these parameters are selected utilizing intelligent methodologies. This paper presents one of the smart methods (Fuzzy logic) as a tuner to obtain the PID parameter value. After the model of the 3-DoF Robot manipulator is driven, The PID controller tuned by Fuzzy logic is created in two scenarios: 1. Using the error and error derivative. 2. Using the error and error integral. The data obtained from the simulation indicate that the proposed controllers have the ability to enhance the overall efficiency of the 3-DoF Robot manipulator.

groups

AliAbdul-Sadahali.muhssen@alkafeel.edu.iq mail

link

Volume & Issue

Details open_in_new

International Journal of Neutrosophic Science | 2024

⃗ȷρ Neutrosophic F Subgroup Over a Finite Group

Neutrosophic set has been developed as a mathematical method for procuring indeterminate and incomplete information. Neutrosophic fuzzy set is a powerful generic system that has been recently developed. In several areas, including data and information analysis, data science, information and decision, have successfully applied neutrosophic concept. Not just that but also the important problems we experience in variety of fields, such as computing, life science, social development, and technical work are represented by neutrosophic fuzzy sets. In this paper, we have presented the idea of an implication-based (ȷρ) neutrosophic fuzzy (F) subgroup over a finite group and a ȷρ neutrosophic F normal subgroup over a finite group. Further, we have established a few fundamental properties of a ȷρ neutrosophic F subgroup over a finite group and ȷρ neutrosophic F normal subgroup over a finite group.

groups

V. Dhanya mail -

M. Selvarathi mail -

M. Ambika mail

link https://doi.org/10.54216/IJNS.230113

Volume & Issue

Vol. Volume 23 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2024

A Neutrosophic Decision-Making Methods of the Key Aspects for Supply Chain Management in International Business Administrations

The importance of supply chain management in the field of international business administration is investigated in this study. Global businesses rely heavily on effective supply chain management, which coordinates the international transfer of materials, data, and money. The paper illuminates the critical nature of supply chain management on a worldwide scale. Distance, cultural differences, legal constraints, and logistics are only some of the problems and complexity of international supply chain management that are explored in this article. Topics covered include supplier selection and management, demand forecasting, inventory control, transportation, and distribution network design, as well as other techniques used by businesses to improve their worldwide supply chains. The study also discusses how international supply networks are affected by globalization, free trade agreements, and geopolitical considerations. Organizational strategies for overcoming hurdles such as tariffs, quotas, and political instability in international commerce are discussed. This paper used the neutrosophic sets (NSs) to deal with uncertainty in assessment factors of supply chains in international business. The NS is integrated with the DEMATEL method. The neutrosophic DEMATEL is used to show relationships between factors.

groups

Ather Abdulrahman Ageeli mail

link https://doi.org/10.54216/IJNS.230114

Volume & Issue

Vol. Volume 23 / Iss. Issue 1

Details open_in_new

Prospects for Applied Mathematics and Data Analysis | 2023

A few little steps beyond Knuth’s Boolean Logic Table with Neutrosophic Logic: A Paradigm Shift in Uncertain Computation

The present article delves into the extension of Knuth’s fundamental Boolean logic table to accommodate the complexities of indeterminate truth values through the integration of neutrosophic logic (Smarandache & Christianto, 2008). Neutrosophic logic, rooted in Florentin Smarandache’s groundbreaking work on Neutrosophic Logic (cf. Smarandache, 2005, and his other works), introduces an additional truth value, ‘indeterminate,’ enabling a more comprehensive framework to analyze uncertainties inherent in computational systems. By bridging the gap between traditional boolean operations and the indeterminacy present in various real-world scenarios, this extension redefines logic tables, introducing neutrosophic operators that capture nuances beyond the binary realm. Through a thorough exploration of neutrosophic logic's principles and its implications in computational paradigms, this study proposes a novel approach to logic design that accommodates uncertain, imprecise, and incomplete information. This paradigm shift in logic tables not only broadens the spectrum of computing methodologies but also holds promise in fields such as decision-making systems and data analytics. This article amalgamates insights from over twelve key references encompassing seminal works in boolean logic, neutrosophic logic, and their applications in diverse scientific and computational domains, aiming to pave the way for a more robust and adaptable logic framework in computation.

groups

Florentin Smarandache mail -

Victor Christianto mail

link https://doi.org/10.54216/PAMDA.020201

Volume & Issue

Vol. Volume 2 / Iss. Issue 2

Details open_in_new

Journal of Sustainable Development and Green Technology | 2023

Global Socio-Economic Problems and Approaches to Their Resolution

This article explores the causes, classification, and description of global problems, as well as ways to solve them. It also covers global development, the Millennium Development Goals, and sustainable development goals.

groups

Abdurakhmonov F. Abdufarmonovich mail

link https://doi.org/10.54216/JSDGT.030203

Volume & Issue

Vol. Volume 3 / Iss. Issue 2

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2023

Optical Character Recognition System for Digit Recognition Using Deep Learning

Because it is so difficult to distinguish handwritten digits, digit identification is one of the most critical applications in computer vision. This is one of the reasons why it is so tough. The field of handwritten character recognition is one in which a great deal of application of numerous deep learning models has occurred. The startling parallels that can be drawn between deep learning and the brain are primarily responsible for its meteoric rise in popularity. In this study, the Artificial Neural Network and the Convolutional Neural Network, two of the most used Deep Learning algorithms, were investigated with an eye toward the recognition process's feature extraction and classification phases. With the assistance of the categorical cross-entropy loss and the ADAM optimizer, the models were trained on the MNIST dataset. Backpropagation and gradient descent are the two methods utilized during the training process of neural networks that contain reLU activations and carry out automatic feature extraction. In computer vision, one of the most common and widely used classifiers is the Convolution Neural Network, sometimes referred to as ConvNets or Convolutional neural networks. This network is used for the recognition and categorization of images.

groups

Mona Awad mail -

Marwa M. Eid mail

link https://doi.org/10.54216/JAIM.060102

Volume & Issue

Vol. Volume 6 / Iss. Issue 1

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2023

Develop application for prediction COVID-19 using artificial intelligence

The subset of manufactured insights (AI) known as machine learning starts in design acknowledgment, where information can be organized for human comprehension. For a long time, various applications utilizing machine learning have been created in healthcare, fund, military gear, and space investigation; presently, machine learning is a zone that's extending and progressing quickly. It utilizes information to optimize computer execution. AI is vital in combating modern coronaviruses in 2019 (COVID-19) -related matters and is used additionally in computer-assisted blend-making plans. Computer programs' settings are optimized based on preparing information or past encounters. It can moreover make future forecasts utilizing the information. With the assistance of machine learning, we are creating a numerical demonstration based on the data's measurements. Numerous illustrations outline the viability of machine learning and counterfeit insights in this field. Counterfeit insights strategies can improve the consistency of forecasts and choices by making valuable calculations. AI is useful not for foreseeing people with COVID-19 but for assessing general wellbeing. It can screen the COVID-19 episode at different levels; in our paper, we use three machine learning calculations to analyze and predict. The leading precision was in XGP= 99%, but SVM and RF gave great precision at 98%.

groups

Noor abdulmuttaleb jaafar mail -

Noor Razzaq Abbas mail -

Ammar Kadi mail -

Abdelhameed Ibrahim mail -

Abdelaziz A. Abdelhamid mail

link https://doi.org/10.54216/JAIM.060103

Volume & Issue

Vol. Volume 6 / Iss. Issue 1

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2023

An Optimized Architecture for COVID‑19 Prediction Using Chest X‑Ray Images

In modern times, a disease known as COVID-19 that is highly contagious is continuing to have a profoundly negative influence on the people of the entire world. The fundamental purpose of the model that has been proposed is to improve its predictive capabilities while also providing an effective model for predicting COVID-19 that has a robust diagnostic. Image scaling and noise reduction are two examples of the types of pre-processing techniques that are used at the very first step. The adoption of picture scaling and median filtering techniques, both of which work to enhance the quality of the input data in preparation for further processing steps, allows this goal to be accomplished. Several distinct data augmentation strategies, like flipping and rotation, are utilized to improve the model's performance on a limited dataset and assist it in better comprehending the differences present in the training data. In this article, we will provide a unique Optimized Architecture for COVID-19 Prediction (OACP) model to classify COVID-19 situations as either positive or negative effectively. Using CXR pictures, this novel method, based on a tunable deep learning technique called DenseNet, may predict the presence of COVID-19-positive patients. Based on the findings, it was determined that the proposed model utilized achieved better outcomes, with an accuracy of 98%.

groups

Yasser Fouad mail -

Ahmed M. Osman mail -

Ibrahim E. Abdelmaged mail -

Ahmed Mohamed Zaki mail -

Ahmed M. Elshewey mail

link https://doi.org/10.54216/JAIM.060104

Volume & Issue

Vol. Volume 6 / Iss. Issue 1

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2023

CNN-Based Multiclass Classification for COVID-19 in Chest X-ray Images

Managing the increasing number of patients requiring first screening can be significantly aided by real-time automated detection of COVID-19. It's feasible that Deep CNN models that have been trained on sufficiently large datasets will emerge as the most promising options for achieving the goal. This study aims to automatically detect and classify COVID-19 and viral pneumonia infections in chest X-ray images using a deep CNN model. Our proposed model relies on multiclass labeling to accomplish our aims. Design and Organization: Using the ImageNet pre-trained weights, the proposed model is built on top of the VGG16 framework. Additional custom layers were used to fine-tune the model and produce a better overall performance that is more specific to the goal. In terms of its subjects and methods, this study uses 15,153 samples in total. There are X-rays of the lungs from patients with COVID-19, those with viral pneumonia, and healthy volunteers. The entire dataset was split into an 80:20 split for the train and test sets before the model was trained. Image preprocessing and augmentation were used to enhance crucial parts of the photos before they were sent to the model in batches. We measure the model's efficacy with accuracy, precision, recall, and the F1 score. The analysis that was performed statistically was. The model's output is compared to the results of other recent research that have set the standard in the field. The proposed model has a 98% accuracy in multiclass classification on the test dataset, as measured by 98% precision, 96% recall, and 97% F1 score. Receiver operating characteristic curve area scores of 0.99 were achieved in all three multiclass classification situations. Finally, the proposed categorization model may show to be highly useful in the first diagnosis of COVID-19 and viral pneumonia patients, especially when dealing with heavy workloads and large volumes.

groups

S.K.Towfek mail

link https://doi.org/10.54216/JAIM.060105

Volume & Issue

Vol. Volume 6 / Iss. Issue 1

Details open_in_new