Background: Cardiovascular diseases are recognized generally to be among the number one illnesscausing death across the globe. Predicting heart disease using a computer-aided technique makes it easier for medical practitioners to diagnose and thereby savinglives andreducingcosts. Feature selection has become an essential component for developing Machinelearning models. It chooses the most relevant features from the available dataset,thereby shortening the training period, making the model easier to train, improving generalization and decreasing overfitting without necessarily compromising the system’s accuracy. Aim:The purpose of this work is to design and build an optimal model forthe prediction of heart diseases,especially at an early stage by considering certain features that are most relevant forthe prediction without compromising the system’s accuracy. Method: The Cleveland UCI dataset with 303 instances wereused in trainingthe model and the findings showthat selectKBest is an effective tool in improving the prediction of heart diseases. The performance metrics Accuracy, Sensitivity, Precision were measured.Results: the study found that when hybridizing k-Nearest Neighbor Bagging, Decision TreeBagging, Gradient Boosting generated the highest accuracy of 90%, 85% and 88% respectively.
{"title":"Enhancing Heart Disease Prediction Using Ensemble Techniques","authors":"Wasilah Sada, Celinus Kiyea","doi":"10.56471/slujst.v4i.277","DOIUrl":"https://doi.org/10.56471/slujst.v4i.277","url":null,"abstract":"Background: Cardiovascular diseases are recognized generally to be among the number one illnesscausing death across the globe. Predicting heart disease using a computer-aided technique makes it easier for medical practitioners to diagnose and thereby savinglives andreducingcosts. Feature selection has become an essential component for developing Machinelearning models. It chooses the most relevant features from the available dataset,thereby shortening the training period, making the model easier to train, improving generalization and decreasing overfitting without necessarily compromising the system’s accuracy. Aim:The purpose of this work is to design and build an optimal model forthe prediction of heart diseases,especially at an early stage by considering certain features that are most relevant forthe prediction without compromising the system’s accuracy. Method: The Cleveland UCI dataset with 303 instances wereused in trainingthe model and the findings showthat selectKBest is an effective tool in improving the prediction of heart diseases. The performance metrics Accuracy, Sensitivity, Precision were measured.Results: the study found that when hybridizing k-Nearest Neighbor Bagging, Decision TreeBagging, Gradient Boosting generated the highest accuracy of 90%, 85% and 88% respectively.","PeriodicalId":299818,"journal":{"name":"SLU Journal of Science and Technology","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115256792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Online shopping websites in Nigeria were assumed to be associated with security challenges such as intrusion, and abuse of users’ privacy. This study assessed users’ perception on the security challenges of selected e-commerce websites in Nigeria. The study was conducted in the Sokoto metropolis. The survey was based on ten (10) selected e-commerce websites, viz: Jumia, Konga, Olx, Jiji, Deal Dey, Taafoo, Adibba, Yudala, Kaymu, and Wakanow. A total of 200 Structured questionnaire was administered on the participants of the study based on their online shopping experience and their access to the Internet within the Sokoto metropolis. 296 responses were found usable for data analysis at the end of the survey. A descriptive analysis in form of frequency was conducted to achieve the main objective of the study. It was found that Konga, Jiji, Jumia, and OLX are the most visited e-commerce websites in Nigeria. The study discovered that privacy and security challenges are of great concern to these e-commerce websites in Nigeria. They also provide high-quality and very cheap products, provides up-to-date adverts on their websites and very easy pick-up and home delivery services. Based on the findings of this study, the following recommendations were made. Stronger security measures should be taken by e-commerce websites to earn users' trust; the e-commerce sites should engage in user awareness programs to familiarize users with security measures.
{"title":"Assessing User’s Perception on Security Challenges of Selected E-Commerce Websites in Nigeria","authors":"M. Aliyu","doi":"10.56471/slujst.v4i.280","DOIUrl":"https://doi.org/10.56471/slujst.v4i.280","url":null,"abstract":"Online shopping websites in Nigeria were assumed to be associated with security challenges such as intrusion, and abuse of users’ privacy. This study assessed users’ perception on the security challenges of selected e-commerce websites in Nigeria. The study was conducted in the Sokoto metropolis. The survey was based on ten (10) selected e-commerce websites, viz: Jumia, Konga, Olx, Jiji, Deal Dey, Taafoo, Adibba, Yudala, Kaymu, and Wakanow. A total of 200 Structured questionnaire was administered on the participants of the study based on their online shopping experience and their access to the Internet within the Sokoto metropolis. 296 responses were found usable for data analysis at the end of the survey. A descriptive analysis in form of frequency was conducted to achieve the main objective of the study. It was found that Konga, Jiji, Jumia, and OLX are the most visited e-commerce websites in Nigeria. The study discovered that privacy and security challenges are of great concern to these e-commerce websites in Nigeria. They also provide high-quality and very cheap products, provides up-to-date adverts on their websites and very easy pick-up and home delivery services. Based on the findings of this study, the following recommendations were made. Stronger security measures should be taken by e-commerce websites to earn users' trust; the e-commerce sites should engage in user awareness programs to familiarize users with security measures.","PeriodicalId":299818,"journal":{"name":"SLU Journal of Science and Technology","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127749456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Salisu Garba, Marzuk Abdullahi, Umar Abdullahi Umar, Nura Tijjani Wurnor
This paper proposed an approach for obesity levels classification. The main contribution of this work is the use of boosting and bagging techniques in the decision tree (DT) and naïve Bayes (NB) classification model to improve the accuracy of obesity levels classification. This is achieved by introducing a boosting and bagging technique to further improve the recognition rate of obesity levels in the DT model, eliminating the correlated features, and eliminating the zero observations problem in the NB model. To validate the accuracy of the proposed approach, empirical evaluation was carried out using WEKA to determine the accuracy, precision, and recall. The results show that the DT classification model performs better in terms of accuracy and average precision. The proposed approach can help in software development for the classification of individuals with obesity
{"title":"Sule Lamido University Journal of Science and Technology (SLUJST) Vol. 3 No. 1&2 [June, 2022], pp. 113-121113Obesity Level ClassificationBased on Decision Tree and Naïve Bayes Classifiers","authors":"Salisu Garba, Marzuk Abdullahi, Umar Abdullahi Umar, Nura Tijjani Wurnor","doi":"10.56471/slujst.v3i.175","DOIUrl":"https://doi.org/10.56471/slujst.v3i.175","url":null,"abstract":"This paper proposed an approach for obesity levels classification. The main contribution of this work is the use of boosting and bagging techniques in the decision tree (DT) and naïve Bayes (NB) classification model to improve the accuracy of obesity levels classification. This is achieved by introducing a boosting and bagging technique to further improve the recognition rate of obesity levels in the DT model, eliminating the correlated features, and eliminating the zero observations problem in the NB model. To validate the accuracy of the proposed approach, empirical evaluation was carried out using WEKA to determine the accuracy, precision, and recall. The results show that the DT classification model performs better in terms of accuracy and average precision. The proposed approach can help in software development for the classification of individuals with obesity","PeriodicalId":299818,"journal":{"name":"SLU Journal of Science and Technology","volume":"216 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127405651","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：