KNUSTSpace

Institutional Repository of the Kwame Nkrumah University of Science and Technology

On this portal we showcase the intellectual output of the university..

 

Communities in DSpace

Select a community to browse its collections.

Now showing 1 - 5 of 6

Recent Submissions

No Thumbnail Available
Item
Suicidal behaviours among school-going adolescents in samoa: a secondary analysis of prevalence, protective, and risk factors
(Middle East Current Psychiatry, 2023) Owusu Sarfo, Jacob; Gbordzoe, Newton Isaac; Attigah, Dean; Debrah, Timothy Pritchard; Ofori, Crescens Osei Bonsu; Obeng, Paul; 0000-0002-4503-9211
Background Suicide has become a major threat to achieving Sustainable Development Goals three and four, especially for school-going adolescents worldwide. As part of eforts to prevent suicide, population-based studies regarding the prevalence and variables that predict suicidal behaviours are required to inform decisions. Despite this realisation, Samoa lacks empirical data on suicidal behaviours among adolescents. We conducted a secondary analysis of the 2017 Global School-based Student Health Survey to examine the prevalence of suicidal behaviours (idea, plan, and attempt) of school-going adolescents in Samoa. Results The prevalence of suicidal ideation, plan, and attempt was 24.1%, 23.8%, and 21.8%, respectively. Also, we found that having understanding parents was an important protective factor against all three suicidal behaviours among Samoan in-school adolescents. Suicidal ideation was predicted by cigarette smoking, having someone who smokes in adolescents’ presence, bullying, loneliness, and worrying about things they could not study. Also, cigarette smoking, bullying, having multiple sexual partners, and worrying increased the risk of having suicidal plans. Again, adolescents’ suicidal attempt was predicted by adolescent truancy, alcohol use, cigarette smoking, being bullied, having close friends, loneliness, and worry. Conclusions Rather than focusing on the school setting alone, suicide prevention interventions in Samoa should foster interdisciplinary collaborations to help reduce suicide.
No Thumbnail Available
Item
Severe morbidities associated with induced abortions among misoprostol users and non-users in a tertiary public hospital in Ghana
(BMC Women's Health, 2014) Damalie, Francis J. M.K.; Dassah, Edward T.; Morhe, Emmanuel S. K.; Nakua, Emmanuel K.; Tagbor, Harry K.; Opare-Addo S.
Background: Misoprostol has become a popular over the counter self-administered abortifacient in Ghana. This study aimed to compare the socio-demographic characteristics and clinical complications associated with misoprostol and non-misoprostol induced abortions among patients admitted to a tertiary public health facility in Ghana. Methods: This was a cross sectional study conducted at the gynaecological ward of Komfo Anokye Teaching Hospital (KATH), over a four-month period using a structured pre-tested questionnaire. Data were analysed using Chi-square, Fisher’s exact and student t-tests. Factors associated with severe morbidity were examined using Poisson regression with robust error variance to estimate crude and ad justed relative risks (RRs) with 95% confidence intervals (CIs). P < 0.05 was considered statistically significant. Results: Overall, 126 misoprostol users and 126 misoprostol non-users were recruited into the study. About 71% of the clients had self-induced abortions. Misoprostol users were more likely to be younger (p < 0.001), single (p < 0.001), nulliparous (p = 0.001), of higher educational background (p = 0.001), and unemployed (p < 0.001), than misoprostol non-users. Misoprostol users were more likely than non-users to undergo termination of pregnancy because they wanted to continue schooling (p < 0.001) or were not earning regular income to support a family (p = 0.001). Overall, 182 (72.2%) of the women (79.4% misoprostol users vs. 65.1% misoprostol non-users; p = 0.01) suffered severe morbidity. Nulliparous women (adjusted RR, 1.28; 95% CI, 1.08-1.52) and those who had induced abortion after 12 weeks’ gestation (adjusted RR, 1.36; 95% CI, 1.18-1.57) were at increased risks of experiencing severe morbidity. The association between mode of abortion induction and severe morbidity was not statistically significant (p = 0.06). Conclusion: Self-induced abortions using misoprostol is a common practice among women in this study; nearly three quarters of them suffered severe morbidity. Nonetheless, severe morbidity among misoprostol users and non-users did not differ significantly but was directly related to the gestational age at which the induced abortions occurred. Health education on the dangers of self-induced abortions and appropriate use of medication abortion could help reduce complications associated with induced abortions in Ghana.
No Thumbnail Available
Item
The Ada Beater: Improving the Quality of Handmade Paper in Ghana
(Noyam Journals, 2023) Ayim, Bertha Adjoakuma; https://orcid.org/0009-0003-1391-6480
The School Progression Policy is an intervention strategy to decrease unnecessary, high dropout rates in the South African Education system. It allows learners to move from one grade to another and thus advance in their careers and exit the basic education school system with a qualification. However, due to this intervention, some learners have experienced social and emotional problems at school, which may affect their wellbeing. This study explored the effects of the School Progression Policy on the progressed Grade 12 learners’ well-being in schools. It adopted a qualitative research methodology within a constructivist paradigm and used a case study research design. Thirty-seven learners (23 females and 14 males) and fifteen teachers and SMTs were purposively selected from four schools in the Motheo Education District. Semistructured interviews were employed for data collection. Thematic results revealed that this policy implementation positively and negatively affected progressed Grade 12 learners’ well-being. This study recommended constant empowerment and motivation for the progressed learners and comprehensive orientation at the beginning of the year to prepare and capacitate them to handle the expectations and challenges of Grade 12. Handmade paper has been around for centuries. In Asia, Europe, and other parts of the world, the means of creating handmade paper depend largely on traditional equipment and other industrial machines. In Ghana, the means of creating handmade paper is through a tedious process of hand beating the bast fiber of the Kyenkyen tree. This resulted in the production of a proto-paper known as the bark cloth. This traditional method has almost become extinct with the influx of imported industrial papers. Therefore the purpose of this study was to seek a solution to this problem through the possible design and fabrication of a paper pulp-making machine daubed the Ada Beater. Thus getting vital tools for making art, print, and papermaking. The paper explored practice-based research methodology to fabricate a papermaking machine known as the Ada Beater. The results showed that the machine can be fabricated and made to produce improved papers of archival quality derived from various plant sources in Ghana. It is recommended that this homegrown know-how should be made available to artists and art teachers for the teaching and use of handmade paper for artistic purposes.
No Thumbnail Available
Item
Predictive Maintenance Model Based on Multisensor Data Fusion of Hybrid Fuzzy Rough Set Theory Feature Selection and Stacked Ensemble for Fault Classification
(Hindawi, 2022) Buabeng, Albert; Simons, Anthony; Frempong, Nana Kena; Ziggah, Yao Yevenyo; 0000-0002-7138-3526
With the rising demand for integrated and autonomous systems in the eld of engineering, e cient frameworks for instant detection of performance anomalies are imperative for improved productivity and cost-e ectiveness. is study proposes a systematic predictive maintenance framework based on the hybrid multisensor fusion technique of fuzzy rough set feature selection and stacked ensemble for the e cient classi cation of fault conditions characterised by uncertainties. First, a feature vector of time-domain features was extracted from 17 multiple sensor signals. en, a comparative study of six di erent Fuzzy Rough Set Feature Selection (FRFS) methods was employed to select the various combinations of optimal feature subsets for various faults classi cation tasks. e determined optimal feature subsets then served as inputs for training the stacked ensemble (ESB(STK)). In the ESB(STK), Support Vector Machine (SVM), Multilayer Perceptron (MLP), k-Nearest Neighbour (k-NN), C4.5 Decision Tree (C4.5 DT), Logistic Regression (LR), and Linear Discriminant Analysis (LDA) served as the base classi ers while the LR was selected to be the metaclassi er. e proposed hybrid framework (FRFS-ESB(STK)) improved the classi cation accuracy with the selected combinations of optimal feature subset size whiles reducing the computational cost, over tting, training runtime, and uncertainty in modelling. Overall analyses showed that the FRFS-ESB(STK) proved to be generalisable and versatile in the classi cation of all conditions of four monitored hydraulic components (i.e., cooler, valve, accumulator, and internal pump leakage) when compared with the six base classi ers (standalone) and three existing ensemble classi ers (Stochastic Gradient Boosting (SGB), Ada Boost (ADB), and Bagging (BAG)). e proposed FRFS-ESB(STK) showed an average improvement of 11.28% and 0.88% test accuracies when classifying accumulator and pump conditions, respectively, whiles 100% classi cation rates were obtained for both cooler and valve.
No Thumbnail Available
Item
Modelling the volatility of the Ghana stock market: A comparative study
(International Journal of Statistics and Applied Mathematics, 2023) Agyarko, Kofi; Wiah, Eric Neebo; Frempong, Nana Kena; Odoi, Benjamin; 0000-0002-7138-3526
The Ghana stock market is considered attractive to both local and international investors, as it is a developing market with potential for growth. The volatility of stock returns is one of the crucial features of Ghana's stock market that should be carefully taken into account by any investor or policymaker. As a result, the GARCH, TGARCH, and EGARCH models were used in this study to analyze the volatility of the Ghanaian stock market. The models were assessed using Akaike Information Criterion (AIC), RMSE and MAPE. The TGARCH (1,1) with generalized error distribution was the model that suited the data the best based on the AIC, RMSE, and MAPE values.
No Thumbnail Available
Item
Hybrid Intelligent Predictive Maintenance Model for Multiclass Fault Classi
(Research Square, 2021) Buabeng, Albert; Simons, Anthony; Frimpong, Nana Kena; Ziggah, Yao Yevenyo; 0000-0002-7138-3526
Data recorded from monitoring the health condition of industrial equipment are often high-dimensional, nonlinear, nonstationary and characterised by high levels of uncertainty. These factors limit the efficiency of machine learning techniques to produce desirable results when developing effective fault classification frameworks. This paper sought to propose a hybrid artificial intelligent predictive maintenance model based on Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN), Principal Component Analysis (PCA) and Least Squares Support Vector Machine (LSSVM) optimised by the combination of Coupled Simulated Annealing and Nelder-Mead Simplex optimisation algorithms (ICEEMDAN-PCA-LSSVM). Here, ICEEMDAN was first employed as a denoising technique to decompose signals into series of Intrinsic Mode Functions (IMFs) of which only relevant IMFs containing the relevant fault features were retained for signal reconstruction. PCA was then employed as a dimension reduction technique through which the resulting set of uncorrelated features extracted served as input for LSSVM for classifying various fault types. The proposed technique is compared with three established methods (Linear Discriminant Analysis (LDA), Support Vector Machine (SVM) and Artificial Neural Network (ANN)) with multiclass classification capabilities. The various techniques were tested on an experimental UCI machine learning benchmark data obtained from multi-sensors of a hydraulic test rig. The results from the analysis revealed that the proposed ICEEMDAN-PCA-LSSVM technique is versatile and outperformed all the compared classifiers in terms of accuracy, error rate and other evaluation metrics considered. The proposed hybrid technique drastically reduced the redundancies and the dimension of features, allowing for the efficient consideration of relevant features for the enhancement of classification accuracy and convergence speed.
No Thumbnail Available
Item
Generalization of Odd Ramos-Louzada generated family of distributions: Properties, characterizations, and applications to diabetes and cancer survival datasets
(Elsevier, 2024) Okutu, John Kwadey; Frempong, Nana Kena; Appiah, Simon K.; Adebanji, Atinuke O.; 0000-0002-7138-3526
Probability distributions offer the best description of survival data and as a result, various lifetime models have been proposed. However, some of these survival datasets are not followed or suf ficiently fitted by the existing proposed probability distributions. This paper presents a novel Kumaraswamy Odd Ramos-Louzada-G (KumORL-G) family of distributions together with its statistical features, including the quantile function, moments, probability-weighted moments, order statistics, and entropy measures. Some relevant characterizations were obtained using the hazard rate function and the ratio of two truncated moments. In light of the proposed KumORL-G family, a five-parameter sub-model, the Kumaraswamy Odd Ramos-Louzada Burr XII (KumORLBXII) distribution was introduced and its parameters were determined with the maximum likelihood estimation (MLE) technique. Monte Carlo simulation was performed and the numerical results were used to evaluate the MLE technique. The proposed probability distribu tion’s significance and applicability were empirically demonstrated using various complete and censored datasets on the survival times of cancer and diabetes patients. The analytical results showed that the KumORLBXII distribution performed well in practice in comparison to its sub models and several other competing distributions. The new KumORL-G for diabetes and cancer survival data is found extremely efficient and offers an enhanced and novel technique for modeling survival datasets.