Machine learning techniques to improve software quality

A significant proportion of the cost of software development is due to software testing and maintenance. This is in part the result of the inevitable imperfections due to human error, lack of quality during the design and coding of software, and the increasing need to reduce faults to improve customer satisfaction in a competitive marketplace. Given the cost and importance of removing errors improvements in fault detection and removal can be of significant benefit. The earlier in the development process faults can be found, the less it costs to correct them and the less likely other faults are to develop. This research aims to make the testing process more efficient and effective by identifying those software modules most likely to contain faults, allowing testing efforts to be carefully targeted. This is done with the use of machine learning algorithms which use examples of fault prone and not fault prone modules to develop predictive models of quality. In order to learn the numerical mapping between module and classification, a module is represented in terms of software metrics. A difficulty in this sort of problem is sourcing software engineering data of adequate quality. In this work, data is obtained from two sources, the NASA Metrics Data Program, and the open source Eclipse project. Feature selection before learning is applied, and in this area a number of different feature selection methods are applied to find which work best. Two machine learning algorithms are applied to the data - Naive Bayes and the Support Vector Machine - and predictive results are compared to those of previous efforts and found to be superior on selected data sets and comparable on others. In addition, a new classification method is proposed, Rank Sum, in which a ranking abstraction is laid over bin densities for each class, and a classification is determined based on the sum of ranks over features. A novel extension of this method is also described based on an observed polarising of points by class when rank sum is applied to training data to convert it into 2D rank sum space. SVM is applied to this transformed data to produce models the parameters of which can be set according to trade-off curves to obtain a particular performance trade-off.

Demonstration of closed-­loop airborne sense-­and-­avoid using machine vision

This paper describes a vision-based airborne collision avoidance system developed by the Australian Research Centre for Aerospace Automation (ARCAA) under its Dynamic Sense-and-Act (DSA) program. We outline the system architecture and the flight testing undertaken to validate the system performance under realistic collision course scenarios. The proposed system could be implemented in either manned or unmanned aircraft, and represents a step forward in the development of a “sense-and-avoid” capability equivalent to human “see-and-avoid”.

Self-directed student work groups using blended learning

This paper provides a description of an innovative teaching approach designed to facilitate student work groups using a blended learning approach that incorporates both traditional face-to-face teaching methods and an online student work group facility. The teaching approach is designed to accommodate a large introductory human resource management subject positioned within an undergraduate business degree.

Professional development using informal learning networks : an empirical study in Australia’s digital content industry

Informal learning networks play a key role in the skill and professional development of professionals working in micro-businesses within Australia’s digital content industry as they do not necessarily have access to a learning and development or a human resources section that can assist in mapping their learning pathway. Professionals working in this environment would typically adopt an informal learning approach to their skill and professional development by utilising their social and business networks. The overall aim of this PhD research project is to study how these professionals manage their skill and professional development, and to explore what role informal learning networks play in this professional learning context. This paper will describe the theme of the research project and how it fits with previous research and other relevant studies. Secondly, it will present the study’s research focus, and the research questions. It will also present relevant theories and perspectives, and the methods for empirical data collection. Data collection will be through three distinct phases using a mixed methods research design: an online survey, interviews, and case studies. It should be noted the findings presented in this paper offer some early results of the research project.

Representing and discovering adversarial team behaviors using player roles

In this paper, we describe a method to represent and discover adversarial group behavior in a continuous domain. In comparison to other types of behavior, adversarial behavior is heavily structured as the location of a player (or agent) is dependent both on their teammates and adversaries, in addition to the tactics or strategies of the team. We present a method which can exploit this relationship through the use of a spatiotemporal basis model. As players constantly change roles during a match, we show that employing a "role-based" representation instead of one based on player "identity" can best exploit the playing structure. As vision-based systems currently do not provide perfect detection/tracking (e.g. missed or false detections), we show that our compact representation can effectively "denoise" erroneous detections as well as enabe temporal analysis, which was previously prohibitive due to the dimensionality of the signal. To evaluate our approach, we used a fully instrumented field-hockey pitch with 8 fixed high-definition (HD) cameras and evaluated our approach on approximately 200,000 frames of data from a state-of-the-art real-time player detector and compare it to manually labelled data.

Eight weeks of episodic visual navigation inside a non-stationary environment using adaptive spherical views

This paper presents a long-term experiment where a mobile robot uses adaptive spherical views to localize itself and navigate inside a non-stationary office environment. The office contains seven members of staff and experiences a continuous change in its appearance over time due to their daily activities. The experiment runs as an episodic navigation task in the office over a period of eight weeks. The spherical views are stored in the nodes of a pose graph and they are updated in response to the changes in the environment. The updating mechanism is inspired by the concepts of long- and short-term memories. The experimental evaluation is done using three performance metrics which evaluate the quality of both the adaptive spherical views and the navigation over time.

Application of machine learning technique in wind turbine fault diagnosis

In this study, a machine learning technique called anomaly detection is employed for wind turbine bearing fault detection. Basically, the anomaly detection algorithm is used to recognize the presence of unusual and potentially faulty data in a dataset, which contains two phases: a training phase and a testing phase. Two bearing datasets were used to validate the proposed technique, fault-seeded bearing from a test rig located at Case Western Reserve University to validate the accuracy of the anomaly detection method, and a test to failure data of bearings from the NSF I/UCR Center for Intelligent Maintenance Systems (IMS). The latter data set was used to compare anomaly detection with SVM, a previously well-known applied method, in rapidly finding the incipient faults.

‘Hiring a Nashville sensation’ : using narrative learning to develop the problem solving skills of contract law students

This article discusses the design of interactive online activities that introduce problem solving skills to first year law students. They are structured around the narrative framework of ‘Ruby’s Music Festival’ where a young business entrepreneur encounters various issues when organising a music festival and students use a generic problem solving method to provide legal solutions. These online activities offer students the opportunity to obtain early formative feedback on their legal problem solving abilities prior to undertaking a later summative assessment task. The design of the activities around the Ruby narrative framework and the benefits of providing students with early formative feedback will be discussed.

Process studies of odour emissions from effluent ponds using machine-based odour measurement

Replicable experimental studies using a novel experimental facility and a machine-based odour quantification technique were conducted to demonstrate the relationship between odour emission rates and pond loading rates. The odour quantification technique consisted of an electronic nose, AromaScan A32S, and an artificial neural network. Odour concentrations determined by olfactometry were used along with the AromaScan responses to train the artificial neural network. The trained network was able to predict the odour emission rates for the test data with a correlation coefficient of 0.98. Time averaged odour emission rates predicted by the machine-based odour quantification technique, were strongly correlated with volatile solids loading rate, demonstrating the increased magnitude of emissions from a heavily loaded effluent pond. However, it was not possible to obtain the same relationship between volatile solids loading rates and odour emission rates from the individual data. It is concluded that taking a limited number of odour samples over a short period is unlikely to provide a representative rate of odour emissions from an effluent pond. A continuous odour monitoring instrument will be required for that more demanding task.

Modeling dynamic demand response using Monte Carlo simulation and interval mathematics for boundary estimation

With the rapid development of various technologies and applications in smart grid implementation, demand response has attracted growing research interests because of its potentials in enhancing power grid reliability with reduced system operation costs. This paper presents a new demand response model with elastic economic dispatch in a locational marginal pricing market. It models system economic dispatch as a feedback control process, and introduces a flexible and adjustable load cost as a controlled signal to adjust demand response. Compared with the conventional “one time use” static load dispatch model, this dynamic feedback demand response model may adjust the load to a desired level in a finite number of time steps and a proof of convergence is provided. In addition, Monte Carlo simulation and boundary calculation using interval mathematics are applied for describing uncertainty of end-user's response to an independent system operator's expected dispatch. A numerical analysis based on the modified Pennsylvania-Jersey-Maryland power pool five-bus system is introduced for simulation and the results verify the effectiveness of the proposed model. System operators may use the proposed model to obtain insights in demand response processes for their decision-making regarding system load levels and operation conditions.

Active vibration suppression of non-linear beams using optimal dynamic inversion

Euler–Bernoulli beams are distributed parameter systems that are governed by a non-linear partial differential equation (PDE) of motion. This paper presents a vibration control approach for such beams that directly utilizes the non-linear PDE of motion, and hence, it is free from approximation errors (such as model reduction, linearization etc.). Two state feedback controllers are presented based on a newly developed optimal dynamic inversion technique which leads to closed-form solutions for the control variable. In one formulation a continuous controller structure is assumed in the spatial domain, whereas in the other approach it is assumed that the control force is applied through a finite number of discrete actuators located at predefined discrete locations in the spatial domain. An implicit finite difference technique with unconditional stability has been used to solve the PDE with control actions. Numerical simulation studies show that the beam vibration can effectively be decreased using either of the two formulations.