Kwara State University Journals
Not a member yet
291 research outputs found
Sort by
Assessment of farmers’ perception of organic fertilizer usage in Ondo State, Nigeria
Get PDFThe use of organic fertilizer can keep soil health and fertility sustainable. This use of organic fertilizer can be determined by farmers’ perception of organic fertilizer usage. This study therefore assessed the perception of organic fertilizer usage among farmers in Ondo State, Nigeria. Multistage sampling procedure was used to select 250 farmers and interview schedule was used to elicit information from the farmers on their demographic and social characteristics; awareness of organic fertilizer benefits; and perception of organic fertilizer usage. Data collected were analysed using descriptive and inferential statistics. The results show that 67.2 percent of the farmers had high awareness level of organic fertilizer benefits while 56.8 percent of the farmers had a favourable perception of organic fertilizer usage. The study also revealed that ethnicity (χ2 = 38.174) and family type (χ2 = 11.679) were associated with farmers’ perception of organic fertilizer usage. Also, age of farmers (β = - 0.110) and farmers’ awareness of organic fertilizer benefits (β = 0.686) were determinants of farmers’ perception of organic fertilizer usage at P≤0.05. The study concluded that farmers had favourable perception of organic fertilizer usage and recommended that extension agents should make farmers aware of the benefits of organic fertilizer
Fraud detection in customers’ electricity consumption in Nigeria using machine learning approach
Get PDFElectricity theft is estimated to have cost Nigeria billions of Naira over the years. Electric utilities use data analytics to discover unusual consumption patterns and possible fraud in order to prevent electricity theft. This work uses data analysis to detect electricity theft, as well as a measure that uses this threat model to compare and evaluate anomaly detectors. This study employs machine learning algorithms to categorize fraud detection in customers’ electricity use, as data mining techniques has helped multiple companies and sectors better their various types of technology. Support Vector Machine (SVM) and C4.5 Decision Tree classification algorithms were used to detect fraud using consumer electricity use data. The accuracy of SVM and C4.5 was 63.4 percent and 65.9%, respectively. As a result, the Map-Reduced-ANOVA with SVM attained an accuracy of 77.5 %
Cluster analysis and ethno-botanical studies of some selected tree species in Kwara State University, Malete, Nigeria
Get PDFCluster analysis and ethno-botanical inquiry on some selected trees species in Kwara State University, Malate was carried out. This is with a view to finding out relationship between the morphological features and ethno-botanical uses of tree species in study area. Thirty line transects of 10m x 10m were laid out. Ten tree species were identified and their spatial distributions were studied. The spatial distributions were determined by frequency value, Shannon-Wiener’s diversity and Menhinick’s richness index. Azadiracta indica and Eucalyptus citriodora were the dominant species with frequency value 34.52% and 13.10% respectively. Morphological parameters of the tree species were subjected to hierarchical cluster analyses, vis: single, complete, average and centroid linkages. The complete and average linkages gave the clearest clusters. Tree species that consistently form clusters irrespective of the analysis type are: Delonix regia and Terminalia ivorensis. Others species occurred as outliers with some relationships with the clustered species. Dendrogram generated from morphological features of plant species with true nested relationship in both the complete and average linkages method showed in the results of cluster analysis have correlations with traditional medicinal uses of the tree species
Physical parameters of some varieties of yam tubers relevant in the design of mechanical yam harvester
Get PDFYam harvesting had been identified as one of the crucial and labour-intensive operations in producing the root crop. It involves standing, bending, squatting, and even sitting on the ground sometimes, depending on the size of ridges and depth of penetration of harvested tubers. During the period of harvesting farmers still use simple tools such as hoes, cutlasses and other simple farm tools. An efficient yam harvester is therefore not only necessary but also important to regenerate the production of yam to meet up with ever-increasing demand for the yam exportation. Thus, the knowledge of the physical properties of yams becomes imperative in the design of suitable and appropriate yam harvesters. The properties investigated were length, diameter and weight of different yam species and the height of ridges, space between the ridges and space between the rows. The results revealed that the range of mean values of: (17.34 – 48.66 cm), (7.53 – 14.23 cm) and (9.7 – 27.6 N) for the length, diameter and weight of yam species, respectively, will be useful in the design of space between the blades and adjustment of blades while that of the length of the yam tuber will be useful in the design of depth of penetration and adjustment of the digging device. While the range of mean values of 30.0 – 85.1 cm, 108.9 – 216.0 cm and 106.0 – 195.6 cm for the height of ridges, space between ridges and space between the rows, respectively, this will be useful in the design of spacing between each set of the blade to accommodate two ridges at once
Strength and fracture resistance of cellulose fiber reinforced cement composite
Get PDFThis study presents the production and experimental assessment of the strengths and fracture resistance of cellulose fiber-reinforced cementitious composite material. The composite, which consists of mixture of recycled fibers obtained from waste carton boxes, was stabilized with measured level of Ordinary Portland Cement. The effects of constituent’s composition on compressive strength, flexural strength and fracture toughness were elucidated. Compressive strengths and flexural strengths were measured using uniaxial compressive and three-point bend loading conditions respectively while a single edge notch bend test (SENB) condition was employed for the fracture toughness measurement. The results obtained from experiments showed that the composite properties are significantly improved by the fiber reinforcement with optimum properties obtained at fiber composition of 5wt. % with compressive strength of 24.4 MPa, flexural strength of 8.0 MPa and fracture toughness of 1.36 MPa√m. The results were discussed for possible applications of robust cellulose fiber reinforced cement composite materials suitable for interior structural applications and to provide potential opportunities for waste management and/or recycling of carton boxes and other related wastes
Convolutional neural network based approach for dermatological disease prediction
Get PDFThe fast growing application of Artificial Intelligence in the field of medicine has led to an improvement in the detection and treatment of many kinds of ailments including skin diseases. However, there exists deficiency in the performances of the existing image pixel scaling techniques when applied to skin diseases detection. Pixel scaling is a major preprocessing tool in the classification of images. To improve the performance of skin disease detection and classification model, this paper proposes a new pixel scaling technique called Mean Pixel Division. At the preprocessing stage, each pixel value in the skin diseases images is divided by the mean of the entire channel pixel values. This reduces the range of the pixel values to a manageable level. A synthetic minority oversampling technique (SMOTE) was used to overcome the challenge of unbalanced classes’ distribution in the dataset. Then, a CNN architecture was designed and trained with the earlier pre-processed images. The evaluation of the proposed approach compared with some existing scaling techniques shows that our approach outperformed the existing techniques, having recorded 99.62%, 98.66% and 99.78% in terms of performance accuracy, sensitivity and specificity respectively
Determinants of cashew farmers’ willingness to adopt bee pollination technology in Kwara State, Nigeria
Get PDFThe consistent drop in cashew nuts production due to decline in the population of animal pollinators is a growing concern for farmers and other actors in the cashew sector. Improving production through the use of technologies has been identified as a strategic way to combat the situation. This study is designed to assess the determinants of farmers’ willingness to adopt assisted bee pollination technology in Kwara State, Nigeria. A multi-stage sampling procedure was used to select one hundred and sixty-two respondents for the study. The data collected using structured interview schedule were presented and analysed using descriptive statistics and binary logistic regression. Findings of the study revealed that the mean age of the respondents was 52.3 years, mostly males (94.4%) and were married (95.1%) with an average household size of 8 persons and 24.2 years of farming experience. Only 11.7% of the farmers had high level of awareness of the bee pollination practices and 63.5% are willing to adopt the technology. The logistic regression analysis revealed that marital status, household size and years of farming experience had significant contribution to the farmers’ willingness to adopt the innovation at 0.05 level of significance. The study concluded that the cashew farmers are willing to adopt the technology despite their poor level of awareness suggesting they are high risk takers. It was recommended that adequate information should be made available to guide them in their adoption decisions
Malathion and Pirimiphosmethyl susceptibility of bendiocarb resistant Anopheles gambiae s.l. mosquito populations in urban Lagos, Nigeria
Get PDFThis study assessed susceptibility status of Anopheles mosquito populations to organophosphate insecticides in selected areas within Lagos metropolis. The study also provides an update on the earlier established Anopheles mosquito resistance to some insecticides such as pyrethroids and carbamate. Adult Anopheles mosquito populations reared from larval collections at natural breeding sites in Yaba and Lekki areas in Lagos were exposed to World Health Organization (WHO) insecticide test papers. The insecticides used for the test include: two organophosphates (Malathion and Pirimiphos methyl), two pyrethroids (deltamethrin and permethrin) and one carbamate (bendiocarb). All the mosquitoes used in this study were identified as An. gambiae sensu lato. Results from the study showed that Anopheles populations from the two sites were fully susceptible (100% mortality rates) to the organophosphates (Malathion and Pirimiphos methyl). The Anopheles populations exhibited resistance to pyrethroid (permethrin and deltamethrin) (≤ 60% mortality rates) and carbamate bendiocarb (≤ 38% mortality rates). The resistance levels were higher compared to the reports of earlier studies
