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.

The use of acoustic emission monitoring to rank paper materials with respect to their fracture toughness

In this study, a simplified Acoustic Emission (AE) equipment, in essence an AE signal conditioner and a USB (Universal Serial Bus) data acquisition system, is used to study what happens in paper structures during mechanical loading. By the use of such equipment, some parameters that can be extracted are e.g. the stress and strain at onset of AE, the stress and strain at the onset of rapid AE defined as some numerical factor (larger then one) times the initial emission rate, the emission rate at the first stage of loading and the stress and strain at final failure i.e. when the specimen loses its load carrying ability.In this study however, the interest is focused on one particular parameter i.e. the elastic strain energy density W c at onset of AE. This is a parameter with a clear physical meaning and in this study, the correlation between this parameter and a fracture toughness measure, is investigated.The conclusion is that when nine different paper materials (with a large span regarding properties) are considered, there is a correlation (however not linear) between these two parameters.