Full Text Available
Access Full Text at Repository
Search Results - Classification reduction
Search alternatives:
- reduction »
- Go to Previous Page
- Showing 121 - 121 results of 121
Search Tools:
Refine Results
Page will reload when a filter is selected or excluded.- "The nurse’s role has long been regarded as stress filled based on the physical labour human suffering, work hours, staffing and interpersonal relationships that are central to the work nurses do. Occupational stress is thus, a recognized problem among health care workers in general. Nursing has therefore been identified as an occupation that has high level of risks and stress in the work place environment. Therefore the study investigated the effects of occupational health intervention programme on environmental risks and stress management of staff nurses in South-west Nigeria. A pretest, posttest, control group, quasi-experimental research design was adopted. Two hundred and twenty five (225) respondents were selected for the study. One hundred and twelve (112) respondents were used as experimental group while one hundred and thirteen (113) respondents were used as control group. Fish bowl method was used for grouping the participants into experimental and control groups respectively. A self-developed questionnaire tagged ‘Occupational Health Intervention Programme, Environmental Risks and Stress Management Questionnaire OHIPERSMQ’ with a reliability coefficient of 0.88 was used. The experimentation lasted 8 weeks. Analysis was done using ANCOVA and Multiple Classification Analysis. Hypotheses were tested at 0.05 alpha level. Findings revealed that occupational health intervention programme has significant effect on risk management knowledge of staff nurses. The experimental group had mean = 4.44, better than the control group that had mean = 2.92. Also, occupational health intervention programme had significant effect on stress management knowledge of nurses with experimental group mean = 7.78, better than the control group mean = 2.36. Based on these findings, it was recommended that medical social workers should ensure that nurses participate in educational training in skills associated with risk reduction, stress reduction and safety promotion so as to guarantee their wellbeing and good job performance." 1 results 1
- Classification is the process of finding a set of models that distinguish data classes to predict unknown class label in data mining. The class imbalance problem occurs when standard classifiers are majority-biased while the minority class is ignored. Existing classifiers tend to maximise overall prediction accuracy and minimise error at the expense of the minority class. However, research had shown that misclassification cost of the minority class is higher and should not be ignored since it is the class of interest. This work was therefore designed to develop advanced data sampling schemes that improve the classification performance of imbalance datasets with the view of increasing the recall of the minority class. Synthetic Minority Oversampling Technique (SMOTE) was extended to SMOTE+300% and combined with existing under-sampling schemes: Random Under-Sampling (RUS), Neighbourhood Cleaning Rule (NCL), Wilson’s Edited Nearest Neighbour (ENN) and Condense Nearest Neighbour (CNN). Five advanced data sampling scheme algorithms: SMOTE300ENN, SMOTE300RUS, SMOTE300NCL, SMOTENCL and SMOTERUS were coded using JAVA and implemented in WEKA, a data mining tool as an Application Programming Interface. The existing and developed schemes were applied to 886 Diabetes Mellitus (DM), 1,163 Senior Secondary School Certificate Result (SSSCR) and 786 Contraceptive Methods (CM) datasets. The datasets were collected in Ilesha and Ibadan, Nigeria. Their performances were determined with different classification algorithms using Receiver Operating Characteristics (ROC), recall of the minority class and performance gain metrics. Friedman’s Test at p = 0.05 was used to analyse these schemes against the classification algorithms. The ROC metric revealed that the mean rank values for DM, SSSCR and CM datasets treated with the advanced schemes ranged from 6.9-13.8, 3.8-12.8 and 6.6-13.5, respectively when compared with the existing schemes which ranged from 3.4-7.8, 2.6-12.6 and 2.8-7.9, respectively. These results signifies improved classification performance. The Recall metric analysis for the DM, SSSCR and CM datasets in the advanced schemes ranged from 9.4-13.0, 6.3-14.0 and 7.3-13.6, respectively when compared with the existing schemes 2.0-7.5, 2.5-8.9 and 2.1-7.4, respectively. These results show increased detection of the minority class. Performance gains by the advanced UNIVERSITY OF IBADAN LIBRARY vii schemes over the original dataset (DM, SSCE and CM) were: SMOTE300ENN (27.1%), SMOTE300RUS (11.6%), SMOTE300NCL (15.5%), SMOTENCL (8.3%) and SMOTERUS (7.3%). Significant difference was observed amongst all the schemes. The higher the mean rank value and performance gain, the better the scheme. The SMOTE300ENN scheme gave the highest ROC and recall values in the three datasets which were 13.8, 12.8, 12.3 and 13.0, 14.0, 13.6, respectively. The developed Synthetic Minority Oversampling Technique 300 Wilson’s Edited Nearest Neighbour scheme significantly improved classification performance and increased the recall of the minority class over the existing schemes using the same dataset. It is therefore recommended for classification of imbalanced datasets. Keywords: Imbalanced dataset, Receiver operating characteristics, Data reduction techniques, Data reduction techniques Word count: 445 1 results 1
- Data reduction techniques 1 results 1
- Imbalanced dataset 1 results 1
- Juveniles� Offending Behaviour 1 results 1
- Life Coaching Skills 1 results 1
- Occupational health, intervention programme, work place environmental risk, stress management, Nurses 1 results 1
- Offending behaviour among adolescents is on the increase, and is of concern to social welfare practitioners and the criminal justice system because such behaviour represents a significant measure of adolescents� well-being and future personality. Often, adolescents are at logger-heads with significant others when they engage in different types of activities like stealing, truancy, bullying, murder and gangsterism. The consequence is collision with the criminal justice system for discipline, correction and rehabilitation. Correctional psychologists have called for special intervention programmes like Risk-Focused Technique (RFT) and Life Coaching Skills (LCS) in rehabilitating such offending adolescents. Previous studies have concentrated more on opinionated studies with a view to finding solutions to the causal factors of offending behaviour among adolescents than on experimenting with social intervention programmes. This study, therefore, investigated the effectiveness of Risk-Focused Technique (RFT) and Life Coaching Skills (LCS) on the reduction of offending behaviour among inmates of remand homes in Southwestern Nigeria. The moderating effects of gender and self esteem were also determined. The study adopted pretest-posttest, control group, quasi-experimental design with a 3x2x3 factorial matrix. Participants were assigned into RFT, LCS and Control groups. Treatment lasted eight weeks. Fifty-two participants (41 males and 11females) out of (52 males and 16 females) were purposively selected from three remand homes in Oyo (19), Ogun (24) and Osun (9) States. The samples were stratified into two experimental conditions - RFT and LCS and the control group. Two instruments were used: Self-Report Measures of Offending Behaviour Scale (r = 0.78) and Rosenberg Self-esteem Scale (r = 0.77). Seven hypotheses were tested at a 0.05 level of significance. Data were analysed with Analysis of Covariance, and Multiple Classification Analysis. There was significant main effect of treatment on the reduction of offending behaviour of participants (F2,39 = 135.991; ?2 = 0.88). The experimental participants: LCS (x = 43.83) and RFT (x = 48.99), performed better than the control group (x = 57.37) on offending behaviour reduction. Also, self-esteem had a significant main effect on the reduction of participants� offending behaviour (F2,39 = 3.827; ?2 = 0.16). The experimental participants: LCS(x = 42.35) and RFT (x = 38.28) had higher self-esteem than those in control group(x = 20.98). However, gender had no significant main effect on reduction of offending behaviour. There was also no significant interaction effect of treatment and gender on participants� offending behaviour. Further, there was no significant interaction effect of treatment and self-esteem on offending behaviour of the participants. However, there was significant interaction effect of self-esteem and gender on participants� offending behaviour (F2,39 = 5.991; ?2 = 0.24). Finally there was no significant interaction effect of treatment, gender and self-esteem on participants� offending behaviour. Risk-focused technique and life coaching skills were effective in the reduction of offending behaviour among inmates of remand homes in Southwestern Nigeria. Therefore, it is recommended that the two interventions should be utilised by officials of youth agencies and social welfare practitioners involved in correctional psychology. 1 results 1
- Poverty rate 1 results 1
- Poverty reduction programmes in Nigeria have not had significant intended effects. This can be attributed to the non-consideration of the heterogeneous nature of poverty and spatial contiguity of geographical units in their designs. There is scarce information on spatial decomposition and spillover of poverty across the Senatorial Districts (SD) in Nigeria. Therefore, the spatial concentration of poverty and its determinants were investigated. The study employed secondary data from Nigeria Living Standard Survey (NLSS) and Core Welfare Indicators Questionnaire (CWIQ) survey conducted by National Bureau of Statistics (NBS), Independent National Electoral Commission (INEC) and Food and Agriculture Organization (FAO). The NLSS and CWIQ were conducted in 2004 and 2006 respectively. The national sample sizes for NLSS and CWIQ were 22,200 and 77,400 household units respectively. Following the elimination of households with missing values, samples considered for the study were 18,760 and 54,536 households for NLSS and CWIQ respectively. The Poverty Rate (PR) per SD was obtained from household consumption expenditure data sourced from NLSS. Data on Household Size (HS), Household Membership of Association (HMA), Households’ Access to Health Facilities (AHF), People Employed in Agriculture (PEA), Access to Credit Facilities (ACF) and Literate Adult (LA) were obtained from CWIQ. Data on Number of Years Spent in the National Assembly by Senators (NYSNAS) (1999 – 2004) and soil fertility classification of Nigeria were sourced from INEC and FAO respectively. These variables and spatial dimension were hypothesized to influence PR. Data were analysed using descriptive statistics, Foster Greer and Thorbeck model, spatial regression, local indicator of spatial association and spatial probit at p = 0.05. Mean annual household per capita consumption expenditure was N28475.01 ± N11967.5. Percentage of PEA in the SD was 44.2 ± 18.4% while mean HS was 6.5 ± 1.5. Mean values of NYSNAS, ACF and AHF were 4.3 ± 0.5years, 10.5 ± 7.4% and 51.6 ± 18.2% respectively. Fifty-six percent of the SD had fertile soils. Average national PR of the SD was 56.03 ± 24.1%. Fifty three of the SD had PR below the national average. The Moran’s I value (3.4) indicated that spillover of poverty existed among SD. Ten percent increase in PR in one SD resulted in 3.1% increase in PR in the neighbouring SD ( = 0.3). Fifty-two percent of the SD with significant spatial association had low PR neighboured by low PR SD, 41.03% of the SD with high PR were neighboured by high PR SD. The PR in high-high SD was significantly reduced by HMA (-0.9), AHF (-0.3), ACF (-0.9), LA (-1.1), fertile soil (-5.2) and NYSNAS (-6.6). Poverty rate was significantly increased by PEA (0.4) UNIVERSITY OF IBADAN LIBRARY iv and HS (5.5). Mean PR in high-high and low-low SD was 82.6% and 31.8% respectively. Household’s probability of being poor was higher in high-high SD (0.8) compared to low-low (0.08). Poverty incidence in a senatorial district influenced the neighbouring senatorial district. Reduction in poverty incidence would be achieved through households’ membership of associations, improved access to health and credit facilities. Keywords: Spatial concentration, Poverty rate, Spatial probit, Senatorial district Word count: 491 1 results 1
- Receiver operating characteristics 1 results 1
- Remand Homes 1 results 1
- Risk-Focused Technique 1 results 1
- Senatorial district 1 results 1
- Southwestern Nigeria 1 results 1
- Spatial concentration 1 results 1
- Spatial probit 1 results 1
- see all…