Assessment of existing soakaways for reuse

This paper describes a practical approach for the investigation, assessment and design of existing soakaways. This method can be utilised for measuring the performance and capacity of the systems and examining whether the systems are suitable for reuse when information about the design and installation of the systems is not available. The requirements for field observations and the procedure for a soil infiltration test for the installed system are suggested for successful assessment. The soil infiltration rate of the system is estimated from the field test data without requiring information on the design and construction details of the system. The system's working condition is measured by a performance indicator related to the time taken to empty the soakaway. This is then employed to evaluate the potential reuse of the system. The system's drain capacity is determined by the design principles of current practice and the effect of climate change on its drain capacity is considered. Contamination of soils around the systems after long-term use of discharge service and the water present in soakaway chambers are also investigated. A detailed case study for the reuse of four installed soakaways for a new housing development demonstrates how the proposed approach provides a straightforward process for the infiltration performance and drain capacity assessment of the existing systems. The effectiveness and applicability of the proposed approach are further demonstrated from the assessments for a number of installed systems over various sites

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.