Oduntan O.E.,Federal Polytechnic |
Olabiyisi S.O.,LAUTECH |
Adeyanju I.A.,Federal University, Oye-Ekiti |
FTC 2016 - Proceedings of Future Technologies Conference | Year: 2016
This study investigates the relative efficacy of using n-grams extracted terms, the aggregation of such terms, and a combination of feature extraction techniques in building an automated essay-type grading (AETG) system. The paper focused on the modification of the Principal Component Analysis (PCA) by integrating n-grams terms as input into the PCA algorithm. Hardcopies of examiners' marking schemes and softcopies of students' answers for two courses, Management Information System (COM 317) and Research Methodology (COM 325), offered at the Department of Computer Science, Federal Polytechnic, Ilaro, during 2013/2014 academic session were used as case studies. The textual contents of the marking schemes were transcripted into electronic documents using same file format as the students' answers. The documents were pre-processed for stopwords removal and each keyword stemmed to address morphological variations. N-gram terms (N=2, 3) were then extracted across all students' answer scripts and marking scheme documents for each of the two courses. The documents were represented in the vector space model as a Document Term Matrix. Principal Component Analysis (PCA) algorithm was modified by integrating n-gram terms as input into existing PCA to derive Modified Principal Component Analysis (MPCA) algorithm. The MPCA was used to reduce the sparseness of the matrix. Document similarity was measured using cosine similarity measure which compared each student's answer script document vector with the marking scheme document vector. The MPCA based AETG system outperformed the PCA equivalent having a high positive correlation and lower mean absolute error when the human marker scores are compared to those of the system. We intend to explore other approaches that will able to capture non-textual contents in our future work. © 2016 IEEE.
Oke M.O.,LAUTECH |
Awonorin S.O.,UNAAB |
Sanni L.O.,UNAAB |
Asiedu R.,International Institute Of Tropical Agriculture |
Journal of Food Processing and Preservation | Year: 2013
Water yam (Dioscorea alata) flour was processed using standard wet milling procedure prior to the extrusion process, which led to the determination of extrudate properties of the flours. A single-screw extruder (DCE 330, NJ) was used in evaluating the extrudate properties, which included torque, mass flow rate, residence time, specific mechanical energy and expansion ratio of the flours from the water yam samples. The effect of extrusion and process variables: feed moisture content, screw speed and barrel temperature on the extruder torque, residence time, mass flow rate, specific mechanical energy and expansion ratio for the variety were determined and predictive models were also developed using response surface methodology. It was observed that changing the feed moisture content, barrel temperature and screw speed significantly (P<0.05) affected expansion ratio, torque, mass flow rate, residence time and specific mechanical energy of all the extrudates. Increasing the feed moisture content (18-28% db) and screw speed (80-180rpm) resulted in a substantial decrease in expansion ratio (46.6%), residence time (27.5%) and specific mechanical energy (83.6%); whereas, increasing the screw speed significantly increased the mass flow rate (64.5%) of extrudates. Regression analysis indicated that screw speed and feed moisture content were the major process variables showing significant (P<0.05) linear, quadratic and interaction influences on mass flow rate, expansion ratio and specific mechanical energy. © 2012 Wiley Periodicals, Inc.
Fenwa O.D.,LAUTECH |
Ajala F.A.,LAUTECH |
Proceedings - International Conference on Computer Vision and Image Analysis Applications, ICCVIA 2015 | Year: 2015
Medical image classification scheme has been on the increase in order to help physicians, and medical practitioners in their evaluation and analysis of diseases. Several classification schemes such as Artificial Neural Network (ANN), Bayes Classification, Support Vector Machine (SVM), K-Means Nearest Neighbor have been used. In this paper, we evaluate and compared the performance of ANN and SVM by analyzing Cirrhosis and Hemachromatosis-two major diseases of the liver. Corresponding results showed support vector machine is of better classification strength than neural network by achieving a percentage accuracy of 87.5%, while ANN was 71.25%. © 2015 IEEE.
Abioye A.O.,Lautech |
Oyeyinka S.A.,University Of Ilorin |
Oyeyinka A.T.,University of Leeds |
Pakistan Journal of Scientific and Industrial Research Series B: Biological Sciences | Year: 2012
In this study, possibility of making jam from two underutilized fruits (baobab and hogplum fruits) known to have high pectin content was investigated. This will increase their consumption and further promote the popularity of jam among rural dwellers where these crops are found. Baobab and Hogplum fruits were cleaned, sorted, weighed and their pulps were extracted in each case using a mesh. Formulation was made in different proportions (100:0, 0:100, 70:30, 30:70, and 50:50) using both fruits. Dissolved sugar and acidifying agent (lime) were added to the mixture and heated at 80°C until it sets. Samples were stored, under refrigeration till analysis. The jam samples were analyzed for pH, total soluble solids (°Brix), titratable acidity (TTA), ascorbic acid, β-carotene and moisture content (MC). Sensory attributes of the samples were compared with a commercial jam (apricot jam (APJ).
PubMed | LAUTECH
Type: Journal Article | Journal: South African medical journal = Suid-Afrikaanse tydskrif vir geneeskunde | Year: 2010
Impaired fasting or glucose tolerance and/or diabetes can occur with hypertension, which theoretically predicts a worse cardiovascular risk profile, and consequently requires intensive cardiovascular risk management.To characterise the frequency of the occurrence of conventional cardiovascular risk factors among hypertensive subjects with impaired fasting blood glucose.We studied 120 hypertensive subjects and 80 age- and sex-matched normotensive controls. Relevant history, clinical examination, laboratory and other tests were undertaken. Body mass index was determined. Informed consent was obtained from all participants, and ethical approval was obtained.There was no statistically significant difference between the age and gender of the hypertensive subjects and the controls (55.1+/-10.83 v. 54.7+/-10.89 years, p=0.76). The serum fasting lipids were higher, but not statistically significantly, among the hypertensives than the controls (triglycerides 1.23+/-0.50 v. 1.22+/-0.48, p=0.900; total cholesterol 4.51+/-1.52 v. 4.38+/-0.84, p=0.842; LDL 2.51+/-1.41 v. 2.4+/-0.63, p=0.811, respectively). The prevalence of impaired glucose tolerance among newly presenting hypertensive subjects was 30.0%. Hypertriglyceridaemia (38.9% v. 6.0%, p=0.038), hypo-HDL cholesterolaemia (52.7% v. 31.0%, p=0.028) and visceral obesity (52.8% v. 27.4%, p=0.036) were statistically more prevalent among hypertensive subjects with impaired glucose tolerance than among those with normal glucose tolerance.The prevalence of impaired glucose tolerance among newly presenting hypertensive subject is very high, and they have more clusters of cardiovascular risks than those without impaired glucose tolerance. The former therefore need intensive cardiovascular assessment and appropriate preventive and treatment modalities. Glucose parameters of newly presenting hypertensive subjects must be determined to evaluate their cardiovascular risk profile.