This study employed Support Vector Machine (SVM) in the classification and prediction of fire outbreak based on fire outbreak dataset captured from the Fire Outbreak Data Capture Device (FODCD). The fire outbreak data capture device (FODCD) used was developed to capture environmental parameters values used in this work. The FODCD device comprised DHT11 temperature sensor, MQ-2 smoke sensor, LM393 Flame sensor, and ESP8266 Wi-Fi module, connected to Arduino nano v3.0.board. 700 data point were captured using the FODCD device, with 60% of the dataset used for training while 20% was used for testing and validation respectively. The SVM model was evaluated using the True Positive Rate (TPR), False Positive Rate (FPR), Accuracy, Error Rate (ER), Precision, and Recall performance metrics. The performance results show that the SVM algorithm can predict cases of fire outbreak with an accuracy of 80% and a minimal error rate of 0.2%. This system was able to predict cases of fire outbreak with a higher degree of accuracy. It is indicated that the use of sensors to capture real world dataset, and machine learning algorithm such as support vector machine gives a better result to the problem of fire management.
Purpose The purpose of this paper is to apply the earlier enhanced personal profile ontology (e-PPO) developed by the authors as a case study for the appraisal of the lecturers in the department of computer science, University of Uyo, Uyo for the purposes of promotions. The developed e-PPO was a sample smart résumé for the selection of the best among three personnel using linguistic variables and formal rules representing the combination of the criteria and subcriteria was illustrated which was used to allocate competent personnel for software requirement engineering tasks. The need for the use of the smart resume for appraisal purposes was pointed out in the conference paper, calling for the applicant’s data to be inputted into the enhanced personal profile ontology (e-PPO) for personnel appraisa. Design/methodology/approach Appraisal is a regular review of employees’ performances and their overall contribution to the organization they are working for. The availability of a web application for personnel appraisal requires PPO which includes both static and dynamic features. Personal profile is often modified for several purposes calling for augmentation and annotation when needs arise. Resume is one resulting extract from personal profile and often contain slightly different information based on needs. The urgent preparation of resume may introduce bias and incorrect information for the sole aim of projecting the personnel as being qualified for the available job. Religious and gender biases may sometimes be observed during appointments of new personnel, which may not be the case during appraisals for promotions or reassignment of tasks because such biases become insignificant given the fact that job targets and the skills needed are already set and the appraisals passes through several phases that are not determined by a single individual. This work therefore applied the earlier developed e-PPO for appraisal of the academic staff of the department of computer science, university of Uyo, Uyo, Nigeria. A mixed approach of existing ontologies like Methontology and Neon have been followed in the creation of the e-PPO, which is a constraint-based semantic data model tested using Protégé inbuilt reasoner with its updated plugins. Upon application of e-PPO on personnel appraisals, promotion and selection of employee for specific assignments in any organization is possible using the smart resume. Findings The use of the smart resume reduces the numerous task that would have been taken up by the human resource team, thereby reducing the processing time for the appraisals. The appraisal task is done void of biases of any kind such as gender and religion. Originality/value This work is an extension of the original work done by the authors.
The COVID-19 pandemic has reawakened the necessity of wearing a face mask in public places in several countries including Nigeria. The effect of prolonged use of face mask on pregnant women is not yet evaluated. The objective of this study was to assess the impact of wearing a surgical face mask on the cardiopulmonary functions of pregnant women. A prospective and case-control study was conducted among 85 healthy pregnant women at gestational ages between 20 weeks and 37 weeks. Equal number of age and parity-matched healthy non-pregnant women were recruited as controls. Their baseline SpO2 and arterial pulse were measured. The participants were then instructed to wear surgical face masks and remain at a resting position for 1 h; thereafter, the SpO2 and pulse rates were measured using a mobile electronic pulse oximeter. Data analysis was done using SPSS version 23. The level of significance was set at 0.05. There was no significant difference in their mean SpO2 (97.44% ± 3.365) and (98.86% ± 1.014) for the pregnant women and the controls, respectively (P= 0.146). However, the mean pulse rate of the pregnant women was significantly higher than that of the controls (97. 58b/m ± 10.731 and 93.17b/m ± 8.850; P = 0.012). The incidence of hypoxemia (SpO2 < 90%) was very low (2.35%) in the pregnant women but non among the non-pregnant control. The incidence of hypoxia-related symptoms was also very low (1.8%). There was a weak negative correlation between the SpO2 and pulse rate (r = −0.0881; P = 0.464 in the pregnant group compared to the controls (r = −0.309; P = 0.004). A vast majority of healthy pregnant women can safely wear a surgical face mask for a long time.
In today's society, almost all human endeavours depend on software products. Lack of quality software is one of the software industry's most important problems. Hence, it would be beneficial to access the quality of software to improve and enhance software products while increasing customer satisfaction. This paper assesses software product quality using a Support Vector Machine-based ensemble classifier. The ISO/IEC-9126 (International Organization for Standardization 2001) software quality (SQ) framework was adopted in this work. Dimension reduction of the product metric category dataset and the entire PM dataset was conducted using linear discriminant analysis (LDA). SVM kernel functions (linear, quadratic, cubic, fine gaussian, medium gaussian and coarse gaussian) were used to model each classifier. The combinations of the results from the multiple SVMs used AdaBoost, bagging, and random subspace ensemble methods for the assessment of SQ. All three ensemble learning methods performed better than the individual SVM, however, the bagging stood out with an accuracy of 93.0%. Hence, it was adopted in the fusion of the SVM results and classification of SQ into classes. Results from the confusion matrix and receivers’ operating characteristics were greater than 97.99% and confirm significant improvements with an ensemble of homogenous classifiers based on SVM.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.