2692-4048ISSN (Online)
2770-0070ISSN (Print)
This study presents a comprehensive analysis of the existing techniques and applications of artificial intelligence (AI) to cardiovascular disease diagnosis. The application of AI to the diagnosis of cardiac diseases can enhance diagnostic precision, diagnostic throughput, and patient outcomes. This literature survey analyzes state-of-the-art AI-based methods, rates their efficiency, examines potential future research and development avenues, and finds challenges and limitations, providing a foundational overview of main developments in AI, machine learning, deep learning, and quantum computing in relation to heart disease prevention. This study seeks to guide the use of AI-based techniques for heart disease detection, having an ultimate objective of enhancing patient outcomes through research and development. This review mainly emphasizes the significance of further studying and advancing AI for its ability to revolutionize the diagnosis and management of heart diseases.
Read MoreDoi: https://doi.org/10.54216/FPA.110101
Vol. 11 Issue. 1 PP. 08-25, (2023)
The expression “COVID-19” has been the fiercest but most trending Google search since it first appeared in November 2019. Due to advances in mobile technology and sensors, Healthcare systems based on the Internet of Things are conceivable. Instead of the traditional reactive healthcare systems, these new healthcare systems can be proactive and preventive. This paper suggested a framework for real-time suspect detection based on the Internet of Things. In the early phases of predicting COVID-19, the framework evaluates the existence of the virus by extracting health variables obtained in real-time from sensors and other IoT devices, in order to better understand the behavior of the virus by collecting symptom data of COVID-19, In this paper, four machine learning models (Random Forest, Decision Tree, K-Nearest Neural Network, and Artificial Neural Network) are proposed, these data and applied as a machine learning model to obtain high diagnostic accuracy, however, it is noted that there is a problem when collecting clinical fusion data that is scarce and unbalanced, so a dataset augmented by Generative Adversarial Network (GAN) was used. Several algorithms achieved high levels of accuracy (ACC), including Random Forest (99%), and Decision Tree (99%), K-Nearest Neighbour (98%), and Artificial Neural Network (99%). These results show the ability of GANs to generate data and their ability to provide relevant data to efficiently manage Covid-19 and reduce the risk of its spread through accurate diagnosis of patients and informing health authorities of suspected cases.
Read MoreDoi: https://doi.org/10.54216/FPA.110102
Vol. 11 Issue. 1 PP. 26-36, (2023)
Data storage, software services, infrastructure services, and platform services are only some of the benefits of today's widespread use of cloud computing. Since most cloud services run via the internet, they are vulnerable to a comprehensive range of attacks that might end it the disclosure of sensitive information. The distributed denial-of-service (DDoS) is amongst the attacks that pose an active threat to the cloud environment and disrupts the provided services for the legitimate participants. The main aim of this review paper is to present the recent trends on sophisticated flooding attacks detection methods for cloud computing systems. The review only considers the papers published within the period of 2014 until 2022.This study aims to examine the various deep learning-based DDoS detection algorithms and machine learning used across different cloud environments. Also, the study covers the Sophisticated types of Flooding Attacks and the testing dataset. The review outcomes several research challenges, gaps and future research guidelines related to protection of DDoS attack in cloud computing environment.
Read MoreDoi: https://doi.org/10.54216/FPA.110103
Vol. 11 Issue. 1 PP. 37-56, (2023)
This paper investigates the process of selecting a hyperparameter for use in a kernel semiparametric regression model for fusion data, which is an important tool in various scientific study fields. The selection of the best model to use in advance is not a simple task, and one of the most fascinating current advances in the application is the use of hybrid metaheuristics algorithms to increase the exploration and exploitation capacity of traditional meta-heuristic algorithms. In this study, a hybrid optimization method that combines the pelican algorithm with the black hole algorithm is presented, which achieves a lower mean squared error (MSE) in comparison to other competing techniques. Data merging through the suggested hybrid metaheuristics algorithm gives superior performance in terms of computing time when compared to both the CV-method and the GCV-method. This work has practical implications for researchers and practitioners who use statistical modeling techniques in their work, especially those dealing with data merging for improved accuracy and efficiency.
Read MoreDoi: https://doi.org/10.54216/FPA.110104
Vol. 11 Issue. 1 PP. 57-69, (2023)
This paper presents an improved penalized regression-based clustering algorithm using a nature-inspired approach. Clustering is an unsupervised learning method widely used in data fusion mining, including gene analysis, to group unclassified fusion data based on their features. The proposed algorithm is an extension of the "Sum of Norms" model and aims to better estimate the data by fusing information from various sources. The performance of the proposed algorithm is evaluated on gene expression data. Results show that our approach outperforms other methods, indicating its potential impact on clustering research with data fusion.
Read MoreDoi: https://doi.org/10.54216/FPA.110105
Vol. 11 Issue. 1 PP. 70-76, (2023)