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.

Tracking the defining moments of crisis process and practice

Crisis holds the potential for profound change in organizations and industries. The past 50 years of crisis management highlight key shifts in crisis practice, creating opportunities for multiple theories and research tracks. Defining crises such as Tylenol, Exxon Valdez, and September 11 terrorist attacks have influenced or challenged the principles of best practice of crisis communication in public relations. This study traces the development of crisis process and practice by identifying shifts in crisis research and models and mapping these against key management theories and practices. The findings define three crisis domains: crisis planning, building and testing predictive models, and mapping and measuring external environmental influences. These crisis domains mirror but lag the evolution of management theory, suggesting challenges for researchers to reshape the research agenda to close the gap and lead the next stage of development in the field of crisis communication for effective organizational outcomes.

The effect of juice composition on the scaling rate and scale composition in sugar mill evaporators

To date, the formation of deposits on heat exchanger surfaces is the least understood problem in the design of heat exchangers for processing industries. Dr East has related the structure of the deposits to solution composition and has developed predictive models for composite fouling of calcium oxalate and silica in sugar factory evaporators.

Psychological predictors of injury among elite athletes

Objectives: To establish injury rates among a population of elite athletes, to provide normative data for psychological variables hypothesised to be predictive of sport injuries, and to establish relations between measures of mood, perceived life stress, and injury characteristics as a precursor to introducing a psychological intervention to ameliorate the injury problem. Methods: As part of annual screening procedures, athletes at the Queensland Academy of Sport report medical and psychological status. Data from 845 screenings (433 female and 412 male athletes) were reviewed. Population specific tables of normative data were established for the Brunel mood scale and the perceived stress scale. Results: About 67% of athletes were injured each year, and about 18% were injured at the time of screening. Fifty percent of variance in stress scores could be predicted from mood scores, especially for vigour, depression, and tension. Mood and stress scores collectively had significant utility in predicting injury characteristics. Injury status (current, healed, no injury) was correctly classified with 39% accuracy, and back pain with 48% accuracy. Among a subset of 233 uninjured athletes (116 female and 117 male), five mood dimensions (anger, confusion, fatigue, tension, depression) were significantly related to orthopaedic incidents over the preceding 12 months, with each mood dimension explaining 6–7% of the variance. No sex differences in these relations were found. Conclusions: The findings support suggestions that psychological measures have utility in predicting athletic injury, although the relatively modest explained variance highlights the need to also include underlying physiological indicators of allostatic load, such as stress hormones, in predictive models.

Toward a model for predicting magnetic susceptibility of bedrock regolith and soils

One of the Department of Defense's most pressing environmental problems is the efficient detection and identification of unexploded ordnance (UXO). In regions of highly magnetic soils, magnetic and electromagnetic sensors often detect anomalies that are of geologic origin, adding significantly to remediation costs. In order to develop predictive models for magnetic susceptibility, it is crucial to understand modes of formation and the spatial distribution of different iron oxides. Most rock types contain iron and their magnetic susceptibility is determined by the amount and form of iron oxides present. When rocks weather, the amount and form of the oxides change, producing concomitant changes in magnetic susceptibility. The type of iron oxide found in the weathered rock or regolith is a function of the duration and intensity of weathering, as well as the original content of iron in the parent material. The rate of weathering is controlled by rainfall and temperature; thus knowing the climate zone, the amount of iron in the lithology and the age of the surface will help predict the amount and forms of iron oxide. We have compiled analyses of the types, amounts, and magnetic properties of iron oxides from soils over a wide climate range, from semi arid grasslands, to temperate regions, and tropical forests. We find there is a predictable range of iron oxide type and magnetic susceptibility according to the climate zone, the age of the soil and the amount of iron in the unweathered regolith.

Development and validation of a multilevel model for predicting workload under routine and nonroutine conditions in an air traffic management center

Objective: The aim of this study was to develop a model capable of predicting variability in the mental workload experienced by frontline operators under routine and nonroutine conditions. Background: Excess workload is a risk that needs to be managed in safety-critical industries. Predictive models are needed to manage this risk effectively yet are difficult to develop. Much of the difficulty stems from the fact that workload prediction is a multilevel problem. Method: A multilevel workload model was developed in Study 1 with data collected from an en route air traffic management center. Dynamic density metrics were used to predict variability in workload within and between work units while controlling for variability among raters. The model was cross-validated in Studies 2 and 3 with the use of a high-fidelity simulator. Results: Reported workload generally remained within the bounds of the 90% prediction interval in Studies 2 and 3. Workload crossed the upper bound of the prediction interval only under nonroutine conditions. Qualitative analyses suggest that nonroutine events caused workload to cross the upper bound of the prediction interval because the controllers could not manage their workload strategically. Conclusion: The model performed well under both routine and nonroutine conditions and over different patterns of workload variation. Application: Workload prediction models can be used to support both strategic and tactical workload management. Strategic uses include the analysis of historical and projected workflows and the assessment of staffing needs. Tactical uses include the dynamic reallocation of resources to meet changes in demand.

Predicting the temporal response of seagrass meadows to dredging using Dynamic Bayesian Networks

Predicting temporal responses of ecosystems to disturbances associated with industrial activities is critical for their management and conservation. However, prediction of ecosystem responses is challenging due to the complexity and potential non-linearities stemming from interactions between system components and multiple environmental drivers. Prediction is particularly difficult for marine ecosystems due to their often highly variable and complex natures and large uncertainties surrounding their dynamic responses. Consequently, current management of such systems often rely on expert judgement and/or complex quantitative models that consider only a subset of the relevant ecological processes. Hence there exists an urgent need for the development of whole-of-systems predictive models to support decision and policy makers in managing complex marine systems in the context of industry based disturbances. This paper presents Dynamic Bayesian Networks (DBNs) for predicting the temporal response of a marine ecosystem to anthropogenic disturbances. The DBN provides a visual representation of the problem domain in terms of factors (parts of the ecosystem) and their relationships. These relationships are quantified via Conditional Probability Tables (CPTs), which estimate the variability and uncertainty in the distribution of each factor. The combination of qualitative visual and quantitative elements in a DBN facilitates the integration of a wide array of data, published and expert knowledge and other models. Such multiple sources are often essential as one single source of information is rarely sufficient to cover the diverse range of factors relevant to a management task. Here, a DBN model is developed for tropical, annual Halophila and temperate, persistent Amphibolis seagrass meadows to inform dredging management and help meet environmental guidelines. Specifically, the impacts of capital (e.g. new port development) and maintenance (e.g. maintaining channel depths in established ports) dredging is evaluated with respect to the risk of permanent loss, defined as no recovery within 5 years (Environmental Protection Agency guidelines). The model is developed using expert knowledge, existing literature, statistical models of environmental light, and experimental data. The model is then demonstrated in a case study through the analysis of a variety of dredging, environmental and seagrass ecosystem recovery scenarios. In spatial zones significantly affected by dredging, such as the zone of moderate impact, shoot density has a very high probability of being driven to zero by capital dredging due to the duration of such dredging. Here, fast growing Halophila species can recover, however, the probability of recovery depends on the presence of seed banks. On the other hand, slow growing Amphibolis meadows have a high probability of suffering permanent loss. However, in the maintenance dredging scenario, due to the shorter duration of dredging, Amphibolis is better able to resist the impacts of dredging. For both types of seagrass meadows, the probability of loss was strongly dependent on the biological and ecological status of the meadow, as well as environmental conditions post-dredging. The ability to predict the ecosystem response under cumulative, non-linear interactions across a complex ecosystem highlights the utility of DBNs for decision support and environmental management.

Autonomous underwater vehicle trajectory design coupled with predictive ocean models : a case study

Data collection using Autonomous Underwater Vehicles (AUVs) is increasing in importance within the oceano- graphic research community. Contrary to traditional moored or static platforms, mobile sensors require intelligent planning strategies to manoeuvre through the ocean. However, the ability to navigate to high-value locations and collect data with specific scientific merit is worth the planning efforts. In this study, we examine the use of ocean model predictions to determine the locations to be visited by an AUV, and aid in planning the trajectory that the vehicle executes during the sampling mission. The objectives are: a) to provide near-real time, in situ measurements to a large-scale ocean model to increase the skill of future predictions, and b) to utilize ocean model predictions as a component in an end-to-end autonomous prediction and tasking system for aquatic, mobile sensor networks. We present an algorithm designed to generate paths for AUVs to track a dynamically evolving ocean feature utilizing ocean model predictions. This builds on previous work in this area by incorporating the predicted current velocities into the path planning to assist in solving the 3-D motion planning problem of steering an AUV between two selected locations. We present simulation results for tracking a fresh water plume by use of our algorithm. Additionally, we present experimental results from field trials that test the skill of the model used as well as the incorporation of the model predictions into an AUV trajectory planner. These results indicate a modest, but measurable, improvement in surfacing error when the model predictions are incorporated into the planner.

Model-predictive control and closed-loop stability considerations for nonlinear plants described by local ARX-type models

In this paper, a model-predictive control (MPC) method is detailed for the control of nonlinear systems with stability considerations. It will be assumed that the plant is described by a local input/output ARX-type model, with the control potentially included in the premise variables, which enables the control of systems that are nonlinear in both the state and control input. Additionally, for the case of set point regulation, a suboptimal controller is derived which has the dual purpose of ensuring stability and enabling finite-iteration termination of the iterative procedure used to solve the nonlinear optimization problem that is used to determine the control signal.

Comparison of eight published static finite element models of the intact lumbar spine : predictive power of models improves when combined together

Finite element (FE) model studies have made important contributions to our understanding of functional biomechanics of the lumbar spine. However, if a model is used to answer clinical and biomechanical questions over a certain population, their inherently large inter-subject variability has to be considered. Current FE model studies, however, generally account only for a single distinct spinal geometry with one set of material properties. This raises questions concerning their predictive power, their range of results and on their agreement with in vitro and in vivo values. Eight well-established FE models of the lumbar spine (L1-5) of different research centres around the globe were subjected to pure and combined loading modes and compared to in vitro and in vivo measurements for intervertebral rotations, disc pressures and facet joint forces. Under pure moment loading, the predicted L1-5 rotations of almost all models fell within the reported in vitro ranges, and their median values differed on average by only 2° for flexion-extension, 1° for lateral bending and 5° for axial rotation. Predicted median facet joint forces and disc pressures were also in good agreement with published median in vitro values. However, the ranges of predictions were larger and exceeded those reported in vitro, especially for the facet joint forces. For all combined loading modes, except for flexion, predicted median segmental intervertebral rotations and disc pressures were in good agreement with measured in vivo values. In light of high inter-subject variability, the generalization of results of a single model to a population remains a concern. This study demonstrated that the pooled median of individual model results, similar to a probabilistic approach, can be used as an improved predictive tool in order to estimate the response of the lumbar spine.

A prospective study of personality features predictive of early adolescent alcohol misuse

Personality factors implicated in alcohol misuse have been extensively investigated in adult populations. Fewer studies have clarified the robustness of personality dimensions in predicting early onset alcohol misuse in adolescence. The aim of this study was to examine the predictive utility of two prominent models of personality (Cloninger, 1987; Eysenck & Eysenck, 1975) in emergent alcohol misuse in adolescence. One hundred and 92 secondary school students (mean age = 13.8 years, SD = 0.5) were administered measures of personality (Revised Junior Eysenck Personality Questionnaire – abbreviated; Temperament scale of Junior Temperament and Character Inventory) and drinking behavior (quantity and frequency of consumption, Alcohol Use Disorders Identification Test) at Time 1. At 12-month follow-up, 170 students (88.5%) were retained. Hierarchical multiple regressions revealed the dimensions of psychoticism, extraversion, and Novelty-Seeking to be the most powerful predictors of future alcohol misuse in adolescents. Results provide support for the etiological relevance of these dimensions in the development of early onset alcohol misuse. Findings can be used to develop early intervention programs that target personality risk factors for alcohol misuse in high-risk youth.

Beyond statistical procedures for predictive modelling: Data mining algorithms and support for university research at QUT

In a seminal data mining article, Leo Breiman [1] argued that to develop effective predictive classification and regression models, we need to move away from the sole dependency on statistical algorithms and embrace a wider toolkit of modeling algorithms that include data mining procedures. Nevertheless, many researchers still rely solely on statistical procedures when undertaking data modeling tasks; the sole reliance on these procedures has lead to the development of irrelevant theory and questionable research conclusions ([1], p.199). We will outline initiatives that the HPC & Research Support group is undertaking to engage researchers with data mining tools and techniques; including a new range of seminars, workshops, and one-on-one consultations covering data mining algorithms, the relationship between data mining and the research cycle, and limitations and problems with these new algorithms. Organisational limitations and restrictions to these initiatives are also discussed.

A comparison of alternative bankruptcy prediction models

Early models of bankruptcy prediction employed financial ratios drawn from pre-bankruptcy financial statements and performed well both in-sample and out-of-sample. Since then there has been an ongoing effort in the literature to develop models with even greater predictive performance. A significant innovation in the literature was the introduction into bankruptcy prediction models of capital market data such as excess stock returns and stock return volatility, along with the application of the Black–Scholes–Merton option-pricing model. In this note, we test five key bankruptcy models from the literature using an upto- date data set and find that they each contain unique information regarding the probability of bankruptcy but that their performance varies over time. We build a new model comprising key variables from each of the five models and add a new variable that proxies for the degree of diversification within the firm. The degree of diversification is shown to be negatively associated with the risk of bankruptcy. This more general model outperforms the existing models in a variety of in-sample and out-of-sample tests.

Predictive compensation for variable network delays and packet losses in networked control systems

Networked control systems (NCSs) offer many advantages over conventional control; however, they also demonstrate challenging problems such as network-induced delay and packet losses. This paper proposes an approach of predictive compensation for simultaneous network-induced delays and packet losses. Different from the majority of existing NCS control methods, the proposed approach addresses co-design of both network and controller. It also alleviates the requirements of precise process models and full understanding of NCS network dynamics. For a series of possible sensor-to-actuator delays, the controller computes a series of corresponding redundant control values. Then, it sends out those control values in a single packet to the actuator. Once receiving the control packet, the actuator measures the actual sensor-to-actuator delay and computes the control signals from the control packet. When packet dropout occurs, the actuator utilizes past control packets to generate an appropriate control signal. The effectiveness of the approach is demonstrated through examples.

Jackknife for bias reduction in predictive regressions

One of the fundamental econometric models in finance is predictive regression. The standard least squares method produces biased coefficient estimates when the regressor is persistent and its innovations are correlated with those of the dependent variable. This article proposes a general and convenient method based on the jackknife technique to tackle the estimation problem. The proposed method reduces the bias for both single- and multiple-regressor models and for both short- and long-horizon regressions. The effectiveness of the proposed method is demonstrated by simulations. An empirical application to equity premium prediction using the dividend yield and the short rate highlights the differences between the results by the standard approach and those by the bias-reduced estimator. The significant predictive variables under the ordinary least squares become insignificant after adjusting for the finite-sample bias. These discrepancies suggest that bias reduction in predictive regressions is important in practical applications.