Fusion: Practice and Applications

Journal DOI

https://doi.org/10.54216/FPA

Submit Your Paper

2692-4048ISSN (Online) 2770-0070ISSN (Print)

Enhancing Heart Disease Diagnosis Using Machine Learning Classifiers

Ahmed A. H. Alkurdi

Heart diseases are the primary cause of death worldwide. The approximate mortality rate due to cardiovascular diseases is a staggering 18 million lives per year. many human lives could be saved with early and accurate diagnosis and prediction of such conditions. Thus, the automation of such a process is crucial and achievable with the rise of machine learning and deep learning capabilities. However, patient data is riddled with issues which must be resolved before they can be used for heart disease prediction. This research aims to improve the accuracy of heart disease diagnosis by utilizing data preprocessing techniques and classification algorithms. These techniques may provide an insight into predicting cardiovascular diseases from subtle clues before any major symptoms arise. The study employs the Heart Disease UCI dataset and follows a systematic approach to train machine learning models in the process of heart disease diagnosis. The approach utilizes a variety of data preprocessing techniques to prepare the data for model training such as MEAN missing value imputation, Normalization, Synthetic Minority Over-sampling Technique (SMOTE), and Correlation. Afterward, the preprocessed data is fed into four popular classification algorithms: Decision Tree, Random Forest, Support Vector Machine (SVM), and k-Nearest Neighbors (k-NN). These algorithms provide a broad evaluation of the dataset. The proposed methodology demonstrates promising results which clearly highlight the value and significance of data preprocessing. This is evident from the achieved accuracy, precision, recall, F1 score and ROC AUC results. In summary, the importance of preprocessing and feature selection is distinct when dealing with datasets containing various challenges. These crucial processes play a central role in building a trustworthy and precise model for heart disease prediction.

Read More

Doi: https://doi.org/10.54216/FPA.130101

Vol. 13 Issue. 1 PP. 08-18, (2023)

Fusion of Water Evaporation Optimization and Great Deluge: A Dynamic Approach for Benchmark Function Solving

Saman M. Almufti

The "Water Evaporation Optimization - Great Deluge" explores the synergy between the Water Evaporation Optimization Algorithm (WEOA) and the Great Deluge Algorithm (GDA) to create a novel fusion model. This research investigates the efficacy of combining these two powerful optimization techniques in addressing benchmark problems. The fusion model incorporates WEOA's dynamic exploration-exploitation dynamics and GDA's global search capabilities. By merging their strengths, the fusion model seeks to enhance convergence efficiency and solution quality. The study presents an experimental analysis of the fusion model's performance across a range of benchmark functions, evaluating its ability to escape local optima and converge towards global optima. The results provide insights into the effectiveness of the fusion model and its potential for addressing complex optimization challenges., a comprehensive performance analysis of the application of the proposed fusion model to a curated set of widely acknowledged benchmark functions, renowned for their role in evaluating the capabilities of optimization algorithms, is undertaken. By rigorously evaluating the convergence characteristics, solution quality, and computational efficiency of the algorithm, a thorough understanding of the strengths and limitations of WEOA is aimed to be provided. Through meticulous comparisons with established optimization techniques, illumination of the aptitude of WEOA in addressing diverse optimization challenges across a spectrum of problem landscapes is intended. The analytical insights, not only advancing the understanding of WEOA's applicability, but also furnishing valuable guidance for both researchers and practitioners in search of robust optimization methodologies, are proffered.

Read More

Doi: https://doi.org/10.54216/FPA.130102

Vol. 13 Issue. 1 PP. 19-36, (2023)

Regression Analysis and Artificial Neural Network Approach to Predict of Surface Roughness in Milling Process

Zaineb Hameed Neamah , Ahmad Al-Talabi , Asma A. Mohammed Ali

Surface roughness (Ra) has a significant influence on the fatigue strength, corrosion resistance, and aesthetic appeal of machine components. Ra is hence a crucial manufacturing process parameter. This study predicts Ra of aluminum alloy Al-7024 after milling. Regression analysis and artificial neural network (ANN) modeling approaches are suggested for predicting Ra values. For better surface roughness, the cutting parameter must be set properly. Spindle speed, feed rate, and depth of cut have been chosen as predictors. Through 31 study cases, regression and ANN were used to examine how these parameters affected Ra. The measurement of surface roughness, together with comprehensive Ra analysis and regression analysis. The findings of this investigation indicate that Ra was predicted by both the regression and ANN models. convergent results from model predictions are obtained. This convergence highlights the promising methodology used in this work to forecast Ra in the milling of Al-7024. The findings demonstrated that, in comparison to the regression model, which had an average variation from the actual values of roughly 1%, The surface roughness was accurately predicted by the ANN model.

Read More

Doi: https://doi.org/10.54216/FPA.130103

Vol. 13 Issue. 1 PP. 37-48, (2023)

Design of High-Performance Intelligent WSN based-IoT using Time Synchronized Channel Hopping and Spatial Correlation Model

Hamza M. Ridha Al-Khafaji , Refed Adnan Jaleel

Wireless Sensor Network (WSN) is one of the most significant contributors to the Internet of Things (IoT), and it plays a significant role in the lives of individuals. There are three main problems in the design of traditional WSN based-IoT. First problem about data; the WSN transmits a huge volume of data to the IoT for processing. The second problem is the energy; since sensor nodes rely on their limited battery, conserving energy is crucial, and the third problem about efficiency of transmission. This paper presents new WSN based IoT framework that integrate important techniques to solve these problems; To increase the effectiveness of data processing and storing, the intelligent Adaptive Boosting stochastic algorithm is applied. IEEE 802.15.4e time slotted channel hopping (TSCH) protocol is used because it has the benefits such as collision-free transmission and multi-hop transmission.  Data reduction at the Gateway (GW) level of the network is achieved through spatial correlation between sensors with the goal of conserving energy. Principle idea of this new framework is to identify the advantages of integrating the important techniques; intelligent Adaptive Boosting Stochastic diffusion search algorithm, TSCH, and Special correlation model. As a result, the proposed framework can thereby satisfy the need for a long battery life of low-rate applications and at the same time, the need for high throughput for high-rate uses also for testing it in achieved efficient classification of data, the important performance measures are used.

Read More

Doi: https://doi.org/10.54216/FPA.130104

Vol. 13 Issue. 1 PP. 49-58, (2023)

Fusion Methodologies of the Assessment of the Effectiveness of Digital Technologies in Commercial Banks

Muyassarzoda Fayzieva

The introduction and active use of modern digital technologies in commercial banks is becoming a modern trend in the banking sector and allows for improved quality of service to customers. At this point, the importance of assessing the effectiveness of the introduction of digital technologies in industries is increasing. Foreign methodologies for assessing the effectiveness of the introduction of digital technologies in various fields were studied, compared, analyzed, and identified. There are a few methodologies for assessing the effectiveness of digital technologies in the banking industry. The novelty of this research is the fusion of methodologies for assessing the development of digital technologies in commercial banks and determining the level of use of digital technologies offered by commercial banks. To increasing the effectiveness of the introduction of digital technologies in commercial banks, measures of a strategy are developed and recommended by the researcher for the effective development of digital technology offers by commercial banks in Uzbekistan.

Read More

Doi: https://doi.org/10.54216/FPA.130105

Vol. 13 Issue. 1 PP. 69-78, (2023)

Students’ Performance Prediction in Higher Education During COVID-19 Pandemic Based on Recurrent Forecasting and Singular Spectrum Analysis

Kismiantini , Shazlyn M. Shaharudin , Adi Setiawan , Rasyidhani Aditya Rizky , Salsa-Billa Syahida Al-Hasania , Murugan Rajoo , Hairulnizam Mahdin , Salama A Mostafa

The COVID-19 pandemic is a virus that is changing habits in human life worldwide. The COVID-19 outbreaks in Indonesia have forced educational activities such as teaching and learning to be conducted online. Teaching and learning activities using the online method are familiar, but the effectiveness of this method still needs to be investigated to be applied in all educational systems. This study used the predictive modeling of Recurrent Forecasting (RF) derived from Singular Spectrum Analysis (SSA) to know the online learning method's practicality on the student's academic performance. The fundamental notion of the predictive fusion model is to improve the effectiveness of several forms of forecast models in SSA by employing a fusion method of two parameters, a window length (L), and a number of leading components (r). This study used undergraduate students' grade point averages (GPA) from a public university in Indonesia through online classes during the COVID-19 epidemic. The experiments unveiled that a parameter of L = 14 ( ) yielded the finest prediction using the RF-SSA model with a root mean square error (RMSE) value of 0.20. Such a finding signified the ability of the RF-SSA to project the students' academic performance according to the GPA for the forthcoming semester. Nonetheless, developing the RF-SSA algorithm for greater effectiveness is essential to acquiring more datasets, such as by gathering a bigger group of respondents from several Indonesian universities.

Read More

Doi: https://doi.org/10.54216/FPA.130106

Vol. 13 Issue. 1 PP. 79-88, (2023)