Approximation of Bayesian predictive p-values with regression ABC

In the Bayesian framework a standard approach to model criticism is to compare some function of the observed data to a reference predictive distribution. The result of the comparison can be summarized in the form of a p-value, and it's well known that computation of some kinds of Bayesian predictive p-values can be challenging. The use of regression adjustment approximate Bayesian computation (ABC) methods is explored for this task. Two problems are considered. The first is the calibration of posterior predictive p-values so that they are uniformly distributed under some reference distribution for the data. Computation is difficult because the calibration process requires repeated approximation of the posterior for different data sets under the reference distribution. The second problem considered is approximation of distributions of prior predictive p-values for the purpose of choosing weakly informative priors in the case where the model checking statistic is expensive to compute. Here the computation is difficult because of the need to repeatedly sample from a prior predictive distribution for different values of a prior hyperparameter. In both these problems we argue that high accuracy in the computations is not required, which makes fast approximations such as regression adjustment ABC very useful. We illustrate our methods with several samples.

A Bayesian Framework for the Assessment of Vision-based Weed and Fruit Detection and Classification Algorithms

This paper proposes new metrics and a performance-assessment framework for vision-based weed and fruit detection and classification algorithms. In order to compare algorithms, and make a decision on which one to use fora particular application, it is necessary to take into account that the performance obtained in a series of tests is subject to uncertainty. Such characterisation of uncertainty seems not to be captured by the performance metrics currently reported in the literature. Therefore, we pose the problem as a general problem of scientific inference, which arises out of incomplete information, and propose as a metric of performance the(posterior) predictive probabilities that the algorithms will provide a correct outcome for target and background detection. We detail the framework through which these predicted probabilities can be obtained, which is Bayesian in nature. As an illustration example, we apply the framework to the assessment of performance of four algorithms that could potentially be used in the detection of capsicums (peppers).

Minimizing overprocessing waste in business processes via predictive activity ordering

Overprocessing waste occurs in a business process when effort is spent in a way that does not add value to the customer nor to the business. Previous studies have identied a recurrent overprocessing pattern in business processes with so-called "knockout checks", meaning activities that classify a case into "accepted" or "rejected", such that if the case is accepted it proceeds forward, while if rejected, it is cancelled and all work performed in the case is considered unnecessary. Thus, when a knockout check rejects a case, the effort spent in other (previous) checks becomes overprocessing waste. Traditional process redesign methods propose to order knockout checks according to their mean effort and rejection rate. This paper presents a more fine-grained approach where knockout checks are ordered at runtime based on predictive machine learning models. Experiments on two real-life processes show that this predictive approach outperforms traditional methods while incurring minimal runtime overhead.

Linking Theory and Practice: Performing a Reality Check on a Model of IS Success

The issue of ‘rigour vs. relevance’ in IS research has generated an intense, heated debate for over a decade. It is possible to identify, however, only a limited number of contributions on how to increase the relevance of IS research without compromising its rigour. Based on a lifecycle view of IS research, we propose the notion of ‘reality checks’ in order to review IS research outcomes in the light of actual industry demands. We assume that five barriers impact the efficient transfer of IS research outcomes; they are lack of awareness, lack of understandability, lack of relevance, lack of timeliness, and lack of applicability. In seeking to understand the effect of these barriers on the transfer of mature IS research into practice, we used focus groups. We chose DeLone and McLean’s IS success model as our stimulus because it is one of the more widely researched areas of IS.

Semi-active control for structural vibration based on predictive algorithm [Chinese title = 基于预测算法的结构振动半主动控制]

Based on Newmark-β method, a structural vibration response is predicted. Through finding the appropriate control force parameters within certain ranges to optimize the objective function, the predictive control of the structural vibration is achieved. At the same time, the numerical simulation analysis of a two-storey frame structure with magneto-rheological (MR) dampers under earthquake records is carried out, and the parameter influence on structural vibration reduction is discussed. The results demonstrate that the semi-active control based on Newmark-β predictive algorithm is better than the classical control strategy based on full-state feedback control and has remarkable advantages of structural vibration reduction and control robustness.

Taking a 'reality' check : expanding pre-service teachers' views on pedagogy and diversity

The outcomes of a two-pronged 'real-world' learning project, which aimed to expand the views of pre-service teachers about learning, pedagogy and diversity, will be discussed in this paper. Seventy-two fourth-year and 22 first-year students, enrolled in a Bachelor of Education degree in Queensland, Australia, were engaged in community sites outside of university lectures, and separate from their practicum. Using Butin's conceptual framework for service learning, we show evidence that this approach can enable pre-service teachers to see new realities about the dilemmas and ambiguities of performing as learners and as teachers. We contend that when such 'real-world' experiences have different foci at different times in their four-year degree, pre-service teachers have more opportunities to develop sophisticated understandings of pedagogy in diverse contexts for diverse learners.

Construction projects immediate health check : a CSF & KPI approach

Many factors have the potential to influence human health. These factors need to be monitored to maintain health. As is the case with human health, construction projects have a number of critical factors that can facilitate a broad evaluation of project health. In order to use these factors as an indication of health, they need to be assessed. This assessment can help to achieve desired outcomes for the project. This paper discusses the approach of assessing Critical Success Factors (CSFs) using Key Performance Indicators (KPIs) to ascertain the immediate health of a construction project. This approach is applicable to all phases of construction projects and many construction procurement methods. KPIs have been benchmarked on the basis of industry standards and historical data. The robustness of the KPIs to assess the immediate health of a project has been validated using Australian and international case studies.

Bayesian model averaging for harmful algal bloom prediction

Harmful Algal Blooms (HABs) are a worldwide problem that have been increasing in frequency and extent over the past several decades. HABs severely damage aquatic ecosystems by destroying benthic habitat, reducing invertebrate and fish populations and affecting larger species such as dugong that rely on seagrasses for food. Few statistical models for predicting HAB occurrences have been developed, and in common with most predictive models in ecology, those that have been developed do not fully account for uncertainties in parameters and model structure. This makes management decisions based on these predictions more risky than might be supposed. We used a probit time series model and Bayesian Model Averaging (BMA) to predict occurrences of blooms of Lyngbya majuscula, a toxic cyanophyte, in Deception Bay, Queensland, Australia. We found a suite of useful predictors for HAB occurrence, with Temperature figuring prominently in models with the majority of posterior support, and a model consisting of the single covariate average monthly minimum temperature showed by far the greatest posterior support. A comparison of alternative model averaging strategies was made with one strategy using the full posterior distribution and a simpler approach that utilised the majority of the posterior distribution for predictions but with vastly fewer models. Both BMA approaches showed excellent predictive performance with little difference in their predictive capacity. Applications of BMA are still rare in ecology, particularly in management settings. This study demonstrates the power of BMA as an important management tool that is capable of high predictive performance while fully accounting for both parameter and model uncertainty.