LAUTECH JOURNAL OF COMPUTING AND INFORMATICS

Multi-Objective Feature Selection Using Non-dominated Sorting Mechanisms and Bi-Directional Elimination for Heart Disease Classification

2024-07-26T15:10:51+00:00

Heart Disease (HD) is the primary cause of death worldwide, and its early detection poses challenges for physicians due to a high probability of false positives resulting from the large number of features. To address this issue, Feature Selection (FS) is being employed to identify the most significant feature subsets for HD classification. FS aims to accomplish two main objectives: (1) reducing the number of features and (2) enhancing the classification performance of the selected features. However, most current approaches treat FS as a single objective, combining these aims into one. Consequently, this research introduces a multi-objective FS approach that treats the number of selected features and classification performance as distinct objectives to avoid conflicts arising from a single objective. The study utilizes the Non-dominated Sorting Genetic Algorithm (NSGA-III), a bi-directional elimination-based method, as the optimization algorithm during the search process. The proposed method is evaluated on nine HD datasets of varying complexity, employing five Machine Learning (ML) classifiers as evaluation measures. The results demonstrate that the proposed method performs favorably on most datasets in terms of both the number of selected features and classification performance. The accuracy of each ML classifier surpasses its respective Sensitivity, Specificity, and F-Measure. Support Vector Machine (SVM) excels in terms of the number of selected features, while Decision Tree Classifier (DTC) exhibits superior classification accuracy. K-Nearest Neighbors (KNN) yields promising results for high-dimensional datasets. Comparative analysis with existing studies establishes the superiority of the proposed method.

Ontology-Driven Information System Design for Women's Reproductive Health Education: Addressing

2024-07-26T15:47:02+00:00

The widespread use of information systems has permeated healthcare, with telemedicine offering solutions for remote areas. This study aims to address knowledge gaps in women's reproductive health (RH) within the South-West region of Nigeria. A mixed-methods approach was employed to assess current knowledge levels and identify areas needing improvement. The first phase involved data acquisition through surveys targeting women of reproductive age (15-49 years) in the region. Statistical analysis was used to evaluate their understanding of key domains like menstrual cycles, family planning, and sexually transmitted infections (STIs). The second phase focused on designing an ontology-driven information system using the Protégé platform and Web Ontology Language (OWL). This system will cater to the identified knowledge gaps by providing readily accessible, accurate content based on user-defined queries. The proposed approach empowers women with the knowledge necessary to make informed decisions about their reproductive health, ultimately contributing to a healthier society.

Enhancing 5G Internet of Things (iot) Connectivity Through Comprehensive Path Loss Modelling: A Systematic Review

2024-07-26T16:12:52+00:00

Optimizing connectivity becomes paramount as the integration of 5G networks and the Internet of Things (IoT) continues to revolutionize communication landscapes. This systematic review digs into the intricacies of path loss modeling, a critical aspect of ensuring robust 5G IoT connectivity. By synthesizing and analyzing diverse research studies, this review aims to provide a comprehensive understanding of the current state of path loss modeling in the context of 5G IoT networks. We explored emerging methodologies and technologies that contribute to the optimization of path loss modeling and ultimately paved the way for enhanced and reliable 5G IoT connectivity. The study presents a comprehensive survey of IoT connectivity in 5G networks, specifically focusing on the different path loss models utilized in designing and installing 5G network infrastructure. Our review contributes by examining the characteristics of 5G networks, detailing the architecture of IoT in the 5G network, exploring diverse path loss models employed in 5G network planning, and highlighting both current challenges and promising research areas for the future of IoT connectivity. This research aims to provide valuable insight for researchers, practitioners, and industry professionals working on optimizing 5G IoT networks.

Prediction of Student Academic Performance Using a Multi-Regression and Classification-Based Model

2024-07-26T16:33:25+00:00

The Prediction of students’ performance is a necessity because it forecasts how well a student is expected to perform during a course of study. Over the years, studies have revealed that student performance has been below average, with one of the main causes being that a thorough prediction of a student's academic potential is typically not done. To choose the best model for predicting and categorizing academic achievement, a multi-regression analysis is performed using machine learning models such as Decision Tree, K-Nearest Neighbor, Random Forest, Logistic Regression, and Support Vector Machine. Furthermore, the result shows that Random Forest is the best-performing classifier in this study, with an F1 score and accuracy of 94.9%, as well as the best-performing regression model, with a Mean Absolute Error (MAE) of 0.3711 in predicting academic success.

The Role of Information and Communication Technology on the Effective Implementation of Cashless Policy in Akoko-Edo Local Government Area, Edo State.

2024-07-26T16:49:52+00:00

This study examines the role of Information and Communication Technology in the effective implementation of cashless policy in Akoko-Edo Local Government Area, Edo State. The paper highlights the impact of the cashless policy in the local economy of the local government area under study. Some selected communities of the local government area were used. These are: Ikpeshi, Igara, Ibillo, Ososo communities. Data were collected using structured questionnaire in the four selected communities. Two hundred questionnaires were distributed at fifty questionnaires to each of the four selected communities. The analysis was based on Correlation, Chi-square and t-test via SPSS version 26.0. The finding revealed that 81.7% of respondents agreed that ICT plays an essential role in the cashless policy implementation in Nigeria as it allows citizens to access banking services whenever and wherever they are, but the policy has been badly implemented as a result of non-effectiveness of ICT or digital infrastructures, low level or lack of digital competence, knowledge, skills and attitudes among the citizenry, most especially in the remote or rural areas. The study equally showed that there is a general lack of sensitization and awareness on the implementation of cashless policy by the CBN. More so, most of our rural and remote areas were largely unbanked and under-banked and the ICT infrastructures are scarce or non-existence. Many of the rural dwellers and farmers rely mostly on cash-based economy to transact their businesses and sell their farm produces. The study concluded that the effective use of ICT is a major driver that would greatly improve the implementation of cashless policy and effect much needed growth in the nation economy. Furthermore, the paper recommends that the government should consider introducing policies that promote and strengthen the use of ICT infrastructures, digital competence, knowledge, skills and attitudinal change for the effective implementation of cashless policy in Nigeria and lastly, adequate measures should be undertaken to ensure that our rural areas are provided with access to efficient ICT services and stronger internet penetration.

Development of a Web Based Hospital Emergency Application

2024-07-26T17:23:52+00:00

In this project, a web-based hospital emergency application was developed using the Python programming language and Django frameworks. The primary motivation for this project is to save lives in times of crucial emergency situations, while also providing a user-friendly and efficient solution for individuals in need of immediate medical assistance. The application offers several key features, including the ability to locate nearby hospitals based on the user's current location, request an ambulance, and access a chatbot for basic health issue prescriptions. To accomplish this, we leveraged Python and Django's powerful features to build a robust and user-friendly application. We integrated Google maps API location-based services to enable users to find the closest hospitals and request ambulances with ease. Furthermore, the inclusion of a chatbot feature enhances the application's utility, offering immediate medical advice for common health concerns. The results of this project demonstrate a successful integration of technology to improve emergency medical services, making it easier for users to access critical care in a timely manner. This paper showcases the practical implementation of these features and highlights the potential for enhancing healthcare delivery through web-based applications.

Development of a Phishing Detection System Using Ensemble Machine Learning Method

2024-07-27T07:38:58+00:00

Over the years, phishing has been a major problem and has caused different people to lose sensitive information, hence leading to loss of financial assets. Different machine learning algorithms have been used in the assessment of phishing in different aspects: websites, emails, texts amongst others. However, phishing attacks continue to increase frequency and sophistication despite the numerous attempts to combat it, there is therefore a need for improved detection mechanisms. This study therefore assessed four machine learning algorithms (Random Forest (RF), Logistic Regression (LR), Naive (NB) and Support Vector Machine (SVM)), built an ensemble model with them and developed a system using this model to detect phishing websites. A dataset obtained from Kaggle machine learning repository containing 549,347 records of websites was split into two, 70% to train the ensemble model and 30% to test the model. Two categories of features were selected: Lexical based features and Domain based features of the URL. The performance of the four algorithms were evaluated using accuracy, precision, recall and f1-score. The model was implemented with Python programming language in Jupyter Notebook and 97.42% accuracy was recorded. The results obtained showed that proposed model is comparable to existing models with accuracies of 96%, 98%, 72% and 97% for LR, SVM, RF and NB respectively. The model was used to develop a user-friendly system where users can paste URLs in order to check the safety of the address. The system however is limited to HTTP protocols and might not be equipped to handle short URLs.

Developing a Novel Cardiac Disease Prediction Framework Utilizing Advanced Machine Learning Algorithms

2024-07-27T07:55:49+00:00

Predicting and diagnosing cardiac disease has long been a crucial and difficult responsibility for medical professionals. Hospitals and other medical facilities provide pricey medicines and procedures to address cardiac ailments. Predicting cardiac disease in its early stages will thus be beneficial to the global population, allowing them to adopt preventative measures before the condition becomes serious. The study aims to revolutionize cardiac disease prediction and diagnosis through innovative machine learning methodologies. Addressing the challenge of early detection, which is crucial yet complex, the research seeks to implement a groundbreaking approach using advanced machine learning techniques. The novelty of this study lies in its use of two distinct machine learning algorithms - Logistic Regression and Random Forest - to analyze healthcare data. The obtained result shows that logistic regression model on the other hand had an accuracy of 80.48%, which is a fair performance, but still falls short of the random forest model's level of accuracy. This study will not only contribute to reducing mortality rates but also foster environments conducive to human development by enabling early intervention and effective treatment strategies. Data for this study is sourced from Kaggle, with Google Colab serving as the development platform, ensuring a robust and data-driven approach to cardiac healthcare.

Enhancing Loan Default Prediction Accuracy in Nigerian Banks: A Hybrid ANN-LSTM Approach

2024-07-27T08:12:02+00:00

Loan defaults pose a significant challenge to Nigerian banks, threatening financial stability and profitability. Existing predictive models often lack the accuracy needed for effective risk management. This study proposes a hybrid Artificial Neural Network-Long Short-Term Memory (ANN-LSTM) model to enhance loan default prediction accuracy. Leveraging a dataset of 148,670 loan records with 37 features from Nigerian banks, the model integrates ANN's ability to capture complex patterns with LSTM's proficiency in processing sequential data. Performance evaluation using accuracy, precision, recall, F1-score, and Area Under the ROC Curve (AUC) demonstrates the hybrid model's superiority over traditional approaches. The ANN-LSTM model achieved 99.7% accuracy and 100% AUC, significantly outperforming Naive Bayes and Logistic Regression models. These results suggest that the proposed hybrid approach can substantially improve risk assessment and decision-making processes in Nigerian banks, potentially reducing loan default rates and enhancing overall financial stability.

An Enhanced Singular Value Decomposition System for Facial Feature Extraction Using Residue Number System (RNS)

2024-07-27T08:30:29+00:00

Facial Expression (FE) is a technique of extracting facial feature to identify people. There have been several investigations on how to speed up the SVD algorithm's computations for facial feature extraction and offer other improvements. Several technologies have been created that do facial expression recognition. However, it is a difficult task to realize the balance between computing time and accuracy of each approach in these systems In contrast, further research is still needed to speed up calculation and increase accuracy of the facial expressions technique. This study offers improved singular value decomposition using the residue number technique for the extraction of facial features. After the feature extraction procedure, the Manhattan classifier was utilized to categorize the facial features. Local database was setup which contained 90 facial images of 30 persons frontal faces with 3 images of each individual. The training set consisted of 60 images, whereas the testing set had 30 images. The experimental results indicated an average training time of 2.045 seconds for SVD and average training time of 1.045 seconds for SVD-RNS. Bar chart was used to show the graphical relationship between SVD and SVD-RNS Training time. The research revealed that RNS reduce SVD computational time.