Pollen image classification using the classifynder system: Algorithm comparison and a case study on New Zealand honey

We describe an investigation into how Massey University’s Pollen Classifynder can accelerate the understanding of pollen and its role in nature. The Classifynder is an imaging microscopy system that can locate, image and classify slide based pollen samples. Given the laboriousness of purely manual image acquisition and identification it is vital to exploit assistive technologies like the Classifynder to enable acquisition and analysis of pollen samples. It is also vital that we understand the strengths and limitations of automated systems so that they can be used (and improved) to compliment the strengths and weaknesses of human analysts to the greatest extent possible. This article reviews some of our experiences with the Classifynder system and our exploration of alternative classifier models to enhance both accuracy and interpretability. Our experiments in the pollen analysis problem domain have been based on samples from the Australian National University’s pollen reference collection (2,890 grains, 15 species) and images bundled with the Classifynder system (400 grains, 4 species). These samples have been represented using the Classifynder image feature set.We additionally work through a real world case study where we assess the ability of the system to determine the pollen make-up of samples of New Zealand honey. In addition to the Classifynder’s native neural network classifier, we have evaluated linear discriminant, support vector machine, decision tree and random forest classifiers on these data with encouraging results. Our hope is that our findings will help enhance the performance of future releases of the Classifynder and other systems for accelerating the acquisition and analysis of pollen samples.

A comparison of classification algorithms within the Classifynder pollen imaging system

We describe an investigation into how Massey University's Pollen Classifynder can accelerate the understanding of pollen and its role in nature. The Classifynder is an imaging microscopy system that can locate, image and classify slide based pollen samples. Given the laboriousness of purely manual image acquisition and identification it is vital to exploit assistive technologies like the Classifynder to enable acquisition and analysis of pollen samples. It is also vital that we understand the strengths and limitations of automated systems so that they can be used (and improved) to compliment the strengths and weaknesses of human analysts to the greatest extent possible. This article reviews some of our experiences with the Classifynder system and our exploration of alternative classifier models to enhance both accuracy and interpretability. Our experiments in the pollen analysis problem domain have been based on samples from the Australian National University's pollen reference collection (2890 grains, 15 species) and images bundled with the Classifynder system (400 grains, 4 species). These samples have been represented using the Classifynder image feature set. In addition to the Classifynder's native neural network classifier, we have evaluated linear discriminant, support vector machine, decision tree and random forest classifiers on these data with encouraging results. Our hope is that our findings will help enhance the performance of future releases of the Classifynder and other systems for accelerating the acquisition and analysis of pollen samples. © 2013 AIP Publishing LLC.

On standby? A comparison of online and offline witnesses to bullying and their bystander behaviour

Given their ubiquitous presence as witnesses to school-yard bullying, the role of the ‘bystander’ has been studied extensively. The prevalence and behaviour of bystanders to cyberbullying, however, is less understood. In an anonymous, school-based questionnaire, 716 secondary school students from South-East Queensland reported whether they had witnessed traditional and/or cyberbullying, and how they responded to each type. Overlap in bystander roles between online and offline environments was examined, as was their relationship to age and gender. Students who witnessed traditional bullying were more likely to have witnessed cyberbullying. Bystanders’ behaviour was sometimes similar in both contexts of traditional and cyberbullying, mainly if they were outsiders but half of the 256 students who reported witnessing both traditional and cyberbullying, acted in different roles across the two environments. The implications of the findings are discussed in the context of previous research on cyberbullying and traditional-bystanders. Future research should further explore the role of bystanders online, including examining whether known predictors of traditional-bystander behaviour similarly predict cyber-bystander behaviour.

Classification of inventory data suit for managing Australian railway bridges

With a focus to optimising the life cycle performance of Australian Railway bridges, new bridge classification and environmental classification systems are proposed. The new bridge classification system is mainly to facilitate the implementation of novel Bridge Management System (BMS) which optimise the life cycle cost both at project level and network level while environment classification is mainly to improve accuracy of Remaining Service Potential (RSP) module of the proposed BMS. In fact, limited capacity of the existing BMS to trigger the maintenance intervention point is an indirect result of inadequacies of the existing bridge and environmental classification systems. The proposed bridge classification system permits to identify the intervention points based on percentage deterioration of individual elements and maintenance cost, while allowing performance based rating technique to implement for maintenance optimisation and prioritisation. Simultaneously, the proposed environment classification system will enhance the accuracy of prediction of deterioration of steel components.

A randomised controlled trial of an online theory-based intervention to improve adult Australians' sun-protective behaviours

Objective. To evaluate the effectiveness of a single-session online theory of planned behaviour (TPB)-based intervention to improve sun-protective attitudes and behaviour among Australian adults. Methods. Australian adults (N = 534; 38.7% males; Mage = 39.3 years) from major cities (80.9%), regional (17.6%) and remote areas (1.5%)were recruited and randomly allocated to an intervention (N=265) and information only group (N = 267). The online intervention focused on fostering positive attitudes, perceptions of normative support, and control perceptions for sun protection. Participants completed questionnaires assessing standard TPB measures (attitude, subjective norm, perceived behavioural control, intention, behaviour) and extended TPB constructs of group norm (friends, family), personal norm, and image norm, pre-intervention (Time 1) and one week (Time 2) and one month post-intervention (Time 3). Repeated Measures Multivariate Analysis of Variance tested intervention effects across time. Results. Intervention participants reported more positive attitudes towards sun protection and used sunprotective measures more often in the subsequent month than participants receiving information only. The intervention effects on control perceptions and norms were non-significant. Conclusions. A theory-based online intervention fostering more favourable attitudes towards sun safety can increase sun protection attitudes and self-reported behaviour among Australian adults in the short term.

Improving the police response to online fraud

Online fraud poses a significant problem to society in terms of its monetary losses and the devastating impact on victims. It also poses significant challenges to law enforcement agencies, regarding their ability to investigate crimes which are complex, occur in a virtual environment, incorporate multiple (often international) jurisdictions, and have a very low reporting rate. This paper examines the police response to online fraud. It argues that traditionally, fraud has received little attention and priority from police agencies and this is exacerbated in the online context. In contrast to this, the paper presents the example of Project Sunbird, a partnership between the West Australian Police and the West Australian Department of Commerce which has embraced the use of financial intelligence to proactively contact suspected victims of online fraud. This paper argues that a proactive approach to policing online fraud can have substantial positive effects for police and victims alike.

Adaptive online gradient descent

We study the rates of growth of the regret in online convex optimization. First, we show that a simple extension of the algorithm of Hazan et al eliminates the need for a priori knowledge of the lower bound on the second derivatives of the observed functions. We then provide an algorithm, Adaptive Online Gradient Descent, which interpolates between the results of Zinkevich for linear functions and of Hazan et al for strongly convex functions, achieving intermediate rates between [square root T] and [log T]. Furthermore, we show strong optimality of the algorithm. Finally, we provide an extension of our results to general norms.

Enhancements to dielectric response measurements of oil-paper insulation for online and offline applications

The research introduces a promising technique for monitoring the degradation status of oil-paper insulation systems of large power transformers in an online mode and innovative enhancements are also made on the existing offline measurements, which afford more direct understanding of the insulation degradation process. Further, these techniques benefit from a quick measurement owing to the chirp waveform signal application. The techniques are improved and developed on the basis of measuring the impedance response of insulation systems. The feasibility and validity of the techniques was supported by the extensive simulation works as well as experimental investigations.

Fine-grained plant classification using convolutional neural networks for feature extraction

We present an overview of the QUT plant classification system submitted to LifeCLEF 2014. This system uses generic features extracted from a convolutional neural network previously used to perform general object classification. We examine the effectiveness of these features to perform plant classification when used in combination with an extremely randomised forest. Using this system, with minimal tuning, we obtained relatively good results with a score of 0:249 on the test set of LifeCLEF 2014.

Love hurts: The costly reality of online romance fraud

Online dating and romance scams continue to lure in Australians with figures this week showing people have lost more than A$23 million this year alone, with average individual losses at A$21,000 – three times higher than other types of fraud. The Australian Competition and Consumer Commission (ACCC) set up the Scam Disruption Project in August to help target those it believes have been caught in such scams. Over three months it sent 1,500 letters to potential victims in New South Wales and the Australian Capital Territory. The figures released this week show that 50 people have been scammed, losing a total A$1.7 million – that’s an average of A$34,000 per victim. Almost three quarters of the scams were dating and romance related, which saw it evolve into the number one category of fraud victimisation. Romance scams continue to pose a problem – despite the efforts of the police and ACCC – so why is it that people continue to fall for them?

Injury narrative text classification using factorization model

Narrative text is a useful way of identifying injury circumstances from the routine emergency department data collections. Automatically classifying narratives based on machine learning techniques is a promising technique, which can consequently reduce the tedious manual classification process. Existing works focus on using Naive Bayes which does not always offer the best performance. This paper proposes the Matrix Factorization approaches along with a learning enhancement process for this task. The results are compared with the performance of various other classification approaches. The impact on the classification results from the parameters setting during the classification of a medical text dataset is discussed. With the selection of right dimension k, Non Negative Matrix Factorization-model method achieves 10 CV accuracy of 0.93.