Support vector machines for regression and applications to software quality prediction

Software metrics are the key tool in software quality management. In this paper, we propose to use support vector machines for regression applied to software metrics to predict software quality. In experiments we compare this method with other regression techniques such as Multivariate Linear Regression, Conjunctive Rule and Locally Weighted Regression. Results on benchmark dataset MIS, using mean absolute error, and correlation coefficient as regression performance measures, indicate that support vector machines regression is a promising technique for software quality prediction. In addition, our investigation of PCA based metrics extraction shows that using the first few Principal Components (PC) we can still get relatively good performance.

Artificial neural networks in modelling osmotic dehydration of foods

Artificial neural network (ANN) models for water loss (WL) and solid gain (SG) were evaluated as potential alternative to multiple linear regression (MLR) for osmotic dehydration of apple, banana and potato. The radial basis function (RBF) network with a Gaussian function was used in this study. The RBF employed the orthogonal least square learning method. When predictions of experimental data from MLR and ANN were compared, an agreement was found for ANN models than MLR models for SG than WL. The regression coefficient for determination (R2) for SG in MLR models was 0.31, and for ANN was 0.91. The R2 in MLR for WL was 0.89, whereas ANN was 0.84.Osmotic dehydration experiments found that the amount of WL and SG occurred in the following descending order: Golden Delicious apple > Cox apple > potato > banana. The effect of temperature and concentration of osmotic solution on WL and SG of the plant materials followed a descending order as: 55 > 40 > 32.2C and 70 > 60 > 50 > 40%, respectively.

Age and gender influences on sensory perceptions of novel low cost nutrient-rich food products developed using traditional Ghanaian food ingredients

Background: A number of factors are known to influence food preferences and acceptability of new products. These include their sensory characteristics and strong, innate neural influences. In designing foods for any target group, it is important to consider intrinsic and extrinsic characteristics which may contribute to palatability, and acceptability of foods. Objective: To assess age and gender influences on sensory perceptions of novel low cost nutrient-rich food products developed using traditional Ghanaian food ingredients. Materials and Methods: In this study, a range of food products were developed from Ghanaian traditional food sources using the Food Multimix (FMM) concept. These products were subjected to sensory evaluation to assess the role of sensory perception on their acceptability among different target age groups across the life cycle (aged 11-68 years olds) and to ascertain any possible influences of gender on preference and choice. Variables including taste, odour, texture, flavour and appearance were tested and the results captured on a Likert scale and scores of likeness and acceptability analysed. Multivariate analyses were used to develop prediction models for targeted recipe development for different target groups. Multiple factor analysis of variance (ANOVA) and logistic linear regression were employed to test the strength of acceptability and to ascertain age and gender influences on product preference. Results: The results showed a positive trend in acceptability (r = 0.602) which tended towards statistical significance (p = 0.065) with very high product favourability rating (91% acceptability; P=0.005). However, age [odds ratios=1.44 (11-15 years old) odds ratios=2.01 (18-68 years old) and gender (P=0.000)] were major influences on product preference with children and females (irrespective of age) showing clear preferences or dislike of products containing certain particular ingredients. Conclusion: These findings are potentially useful in planning recipes for feeding interventions involving different vulnerable and target groups.