Software warehouse and software mining : the impact of data mining to software engineering

Automating Software Engineering is the dream of software Engineers for decades. To make this dream to come to true, data mining can play an important role. Our recent research has shown that to increase the productivity and to reduce the cost of software development, it is essential to have an effective and efficient mechanism to store, manage and utilize existing software resources, and thus to automate software analysis, testing, evaluation and to make use of existing software for new problems. This paper firstly provides a brief overview of traditional data mining followed by a presentation on data mining in broader sense. Secondly, it presents the idea and the technology of software warehouse as an innovative approach in managing software resources using the idea of data warehouse where software assets are systematically accumulated, deposited, retrieved, packaged, managed and utilized driven by data mining and OLAP technologies. Thirdly, we presented the concepts and technology and their applications of data mining and data matrix including software warehouse to software engineering. The perspectives of the role of software warehouse and software mining in modern software development are addressed. We expect that the results will lead to a streamlined high efficient software development process and enhance the productivity in response to modern challenges of the design and development of software applications.

An examination on the performance of MML causal induction

This paper presents an examination report on the performance of the improved MML based causal model discovery algorithm. In this paper, We firstly describe our improvement to the causal discovery algorithm which introduces a new encoding scheme for measuring the cost of describing the causal structure. Stiring function is also applied to further simplify the computational complexity and thus works more efficiently. It is followed by a detailed examination report on the performance of our improved discovery algorithm. The experimental results of the current version of the discovery system show that: (l) the current version is capable of discovering what discovered by previous system; (2) current system is capable of discovering more complicated causal networks with large number of variables; (3) the new version works more efficiently compared with the previous version in terms of time complexity.

Discovering linear causal model from incomplete data

One common drawback in algorithms for learning Linear Causal Models is that they can not deal with incomplete data set. This is unfortunate since many real problems involve missing data or even hidden variable. In this paper, based on multiple imputation, we propose a three-step process to learn linear causal models from incomplete data set. Experimental results indicate that this algorithm is better than the single imputation method (EM algorithm) and the simple list deletion method, and for lower missing rate, this algorithm can even find models better than the results from the greedy learning algorithm MLGS working in a complete data set. In addition, the method is amenable to parallel or distributed processing, which is an important characteristic for data mining in large data sets.

Ensemble parameter estimation for graphical models

Parameter Estimation is one of the key issues involved in the discovery of graphical models from data. Current state of the art methods have demonstrated their abilities in different kind of graphical models. In this paper, we introduce ensemble learning into the process of parameter estimation, and examine ensemble parameter estimation methods for different kind of graphical models under complete data set and incomplete data set. We provide experimental results which show that ensemble method can achieve an improved result over the base parameter estimation method in terms of accuracy. In addition, the method is amenable to parallel or distributed processing, which is an important characteristic for data mining in large data sets.

Modelling of porosity defects in high pressure die casting with a neural network

High Pressure Die Casting (HPDC) is a complex process that results in casting defects if configured improperly. However, finding out the optimal configuration is a non-trivial task as eliminating one of the casting defects (for example, porosity) can result in occurrence of other casting defects. The industry generally tries to eliminate the defects by trial and error which is an expensive and error -prone process. This paper aims to improve current modelling and understanding of defects formation in HPDC machines. We have conducted conventional die casting tests with a neural network model of HPDC machine and compared the obtained results with the current understanding of formation of porosity. While most of our findings correspond well to established knowledge in the field, some of our findings are in conflict with the previous studies of die casting.

Disparity estimation using TI multi-wavelet transform

A multi-resolution image matching technique based on translation invariant discrete multi-wavelet transform followed by a coarse to fine matching strategy is presented. The technique addresses the estimation of optimal corresponding points and the corresponding disparity maps in the presence of occlusion, ambiguity and illuminative variations in the two perspective views taken by two different cameras or at different lighting conditions. The problem of occlusion and ambiguity is addressed explicitly by a geometric optimization approach along with the uniqueness constraint whereas the illuminative variation is dealt with by using windowed normalized correlation on the discrete multi-wavelet coefficients.

Developing the A+B/online virtual gallery

The a+b/online project is an exemplar of a comprehensive online resource that includes Virtual Galleries, resources, digital case studies and an image repository (http://www.ab.deakin.edu.au/online). Throughout its development since 2001, the project has expanded to include several thousand digital objects. This paper discusses the development of the a+b/online site and outlines some of the issues associated with its development. The current state of the project is discussed in relation to the current paradigm of citizen media including blogs.

A novel sensing technique for monitoring pitting corrosion of stainless steel type 316L

A novel electrochemically integrated multi-electrode array namely the wire beam electrode(WBE) in combination with noise signatures analysis has been designed to monitor pittingcorrosion of one of the best corrosion resistance ferrous alloys, stainless steel type 316L.From the direct correlation of electrochemical potential noise signatures and galvanic currentdistribution maps during pitting corrosion processes, two characteristic noise patterns wereobserved prior to stable pit formation: (i) the characteristic ‘peak’ of rapid potential transient,towards less negative direction, followed by recovery (termed noise signature I) was found tocorrelate with the disappearance of unstable anode; (ii) the characteristic noise pattern ofquick potential changes towards less negative direction followed by no recovery (termed noisesignature II) was found to correspond with the massive disappearance of minor anodes leadingto formation of highly localized major anodes in the galvanic current distribution maps.

The influence of protective and risk factors in individual, peer and school domains on Thai adolescents' alcohol and illicit drug use: a survey

This study investigates risk and protective factors for substance abuse in a sample of 1778 students attending technical colleges in Bangkok and Nakhon Ratchasima provinces of Thailand using a self-report questionnaire modified from the Communities That Care youth survey. Low school commitment was strongly associated with illicit drug use, with adjusted odds ratios ranging from 2.84 (glue sniffing) to 10.06 (ecstasy). Having friends using drugs, and friends with delinquent behaviors increased the risk of using alcohol and illegal drugs, with adjusted odds ratios of 6.84 and 6.72 respectively for marijuana use. For protective factors, approximately 40-60% of students with high levels of moral belief, participation in religious activities, and social skills were less likely to use alcohol. It is concluded that peer influence is a significant contributor to Thai adolescents' participation in substance abuse and that engaging in religiosity may assist adolescents to internalize negative aspects of harmful drugs into positive perceptions and encourage them to avoid alcohol and illegal drugs.