Follow the leader if you can, hedge if you must

Follow-the-Leader (FTL) is an intuitive sequential prediction strategy that guarantees constant regret in the stochastic setting, but has poor performance for worst-case data. Other hedging strategies have better worst-case guarantees but may perform much worse than FTL if the data are not maximally adversarial. We introduce the FlipFlop algorithm, which is the first method that provably combines the best of both worlds. As a stepping stone for our analysis, we develop AdaHedge, which is a new way of dynamically tuning the learning rate in Hedge without using the doubling trick. AdaHedge refines a method by Cesa-Bianchi, Mansour, and Stoltz (2007), yielding improved worst-case guarantees. By interleaving AdaHedge and FTL, FlipFlop achieves regret within a constant factor of the FTL regret, without sacrificing AdaHedge’s worst-case guarantees. AdaHedge and FlipFlop do not need to know the range of the losses in advance; moreover, unlike earlier methods, both have the intuitive property that the issued weights are invariant under rescaling and translation of the losses. The losses are also allowed to be negative, in which case they may be interpreted as gains.

Large scale read classification for next generation sequencing

Next Generation Sequencing (NGS) has revolutionised molecular biology, resulting in an explosion of data sets and an increasing role in clinical practice. Such applications necessarily require rapid identification of the organism as a prelude to annotation and further analysis. NGS data consist of a substantial number of short sequence reads, given context through downstream assembly and annotation, a process requiring reads consistent with the assumed species or species group. Highly accurate results have been obtained for restricted sets using SVM classifiers, but such methods are difficult to parallelise and success depends on careful attention to feature selection. This work examines the problem at very large scale, using a mix of synthetic and real data with a view to determining the overall structure of the problem and the effectiveness of parallel ensembles of simpler classifiers (principally random forests) in addressing the challenges of large scale genomics.

Document clustering algorithms, representations and evaluation for information retrieval

This thesis presents new methods for classification and thematic grouping of billions of web pages, at scales previously not achievable. This process is also known as document clustering, where similar documents are automatically associated with clusters that represent various distinct topic. These automatically discovered topics are in turn used to improve search engine performance by only searching the topics that are deemed relevant to particular user queries.

Unusual event detection in crowded scenes

Novel computer vision techniques have been developed to automatically detect unusual events in crowded scenes from video feeds of surveillance cameras. The research is useful in the design of the next generation intelligent video surveillance systems. Two major contributions are the construction of a novel machine learning model for multiple instance learning through compressive sensing, and the design of novel feature descriptors in the compressed video domain.

STAR : Predicting recombination sites from amino acid sequence

Background Designing novel proteins with site-directed recombination has enormous prospects. By locating effective recombination sites for swapping sequence parts, the probability that hybrid sequences have the desired properties is increased dramatically. The prohibitive requirements for applying current tools led us to investigate machine learning to assist in finding useful recombination sites from amino acid sequence alone. Results We present STAR, Site Targeted Amino acid Recombination predictor, which produces a score indicating the structural disruption caused by recombination, for each position in an amino acid sequence. Example predictions contrasted with those of alternative tools, illustrate STAR'S utility to assist in determining useful recombination sites. Overall, the correlation coefficient between the output of the experimentally validated protein design algorithm SCHEMA and the prediction of STAR is very high (0.89). Conclusion STAR allows the user to explore useful recombination sites in amino acid sequences with unknown structure and unknown evolutionary origin. The predictor service is available from http://pprowler.itee.uq.edu.au/star.

Predicting structural disruption of proteins caused by crossover

We present a machine learning model that predicts a structural disruption score from a protein s primary structure. SCHEMA was introduced by Frances Arnold and colleagues as a method for determining putative recombination sites of a protein on the basis of the full (PDB) description of its structure. The present method provides an alternative to SCHEMA that is able to determine the same score from sequence data only. Circumventing the need for resolving the full structure enables the exploration of yet unresolved and even hypothetical sequences for protein design efforts. Deriving the SCHEMA score from a primary structure is achieved using a two step approach: first predicting a secondary structure from the sequence and then predicting the SCHEMA score from the predicted secondary structure. The correlation coefficient for the prediction is 0.88 and indicates the feasibility of replacing SCHEMA with little loss of precision.

A convolutional neural network for automatic analysis of aerial imagery

This paper introduces a new method to automate the detection of marine species in aerial imagery using a Machine Learning approach. Our proposed system has at its core, a convolutional neural network. We compare this trainable classifier to a handcrafted classifier based on color features, entropy and shape analysis. Experiments demonstrate that the convolutional neural network outperforms the handcrafted solution. We also introduce a negative training example-selection method for situations where the original training set consists of a collection of labeled images in which the objects of interest (positive examples) have been marked by a bounding box. We show that picking random rectangles from the background is not necessarily the best way to generate useful negative examples with respect to learning.

Anomaly detection in online social networks : using data-mining techniques and fuzzy logic

This research is a step forward in improving the accuracy of detecting anomaly in a data graph representing connectivity between people in an online social network. The proposed hybrid methods are based on fuzzy machine learning techniques utilising different types of structural input features. The methods are presented within a multi-layered framework which provides the full requirements needed for finding anomalies in data graphs generated from online social networks, including data modelling and analysis, labelling, and evaluation.

The Catlin Seaview Survey – kilometre-scale seascape assessment, and monitoring of coral reef ecosystems

1.Marine ecosystems provide critically important goods and services to society, and hence their accelerated degradation underpins an urgent need to take rapid, ambitious and informed decisions regarding their conservation and management. 2.The capacity, however, to generate the detailed field data required to inform conservation planning at appropriate scales is limited by time and resource consuming methods for collecting and analysing field data at the large scales required. 3.The ‘Catlin Seaview Survey’, described here, introduces a novel framework for large-scale monitoring of coral reefs using high-definition underwater imagery collected using customized underwater vehicles in combination with computer vision and machine learning. This enables quantitative and geo-referenced outputs of coral reef features such as habitat types, benthic composition, and structural complexity (rugosity) to be generated across multiple kilometre-scale transects with a spatial resolution ranging from 2 to 6 m2. 4.The novel application of technology described here has enormous potential to contribute to our understanding of coral reefs and associated impacts by underpinning management decisions with kilometre-scale measurements of reef health. 5.Imagery datasets from an initial survey of 500 km of seascape are freely available through an online tool called the Catlin Global Reef Record. Outputs from the image analysis using the technologies described here will be updated on the online repository as work progresses on each dataset. 6.Case studies illustrate the utility of outputs as well as their potential to link to information from remote sensing. The potential implications of the innovative technologies on marine resource management and conservation are also discussed, along with the accuracy and efficiency of the methodologies deployed.

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.