Do-Rank: DCG optimization for learning-to-rank in tag-based item recommendation systems

Discounted Cumulative Gain (DCG) is a well-known ranking evaluation measure for models built with multiple relevance graded data. By handling tagging data used in recommendation systems as an ordinal relevance set of {negative,null,positive}, we propose to build a DCG based recommendation model. We present an efficient and novel learning-to-rank method by optimizing DCG for a recommendation model using the tagging data interpretation scheme. Evaluating the proposed method on real-world datasets, we demonstrate that the method is scalable and outperforms the benchmarking methods by generating a quality top-N item recommendation list.

Is the sun too bright in Queensland? An approach to robust outdoor colour beacon detection

Using cameras onboard a robot for detecting a coloured stationary target outdoors is a difficult task. Apart from the complexity of separating the target from the background scenery over different ranges, there are also the inconsistencies with direct and reflected illumination from the sun,clouds, moving and stationary objects. They can vary both the illumination on the target and its colour as perceived by the camera. In this paper, we analyse the effect of environment conditions, range to target, camera settings and image processing on the reported colours of various targets. The analysis indicates the colour space and camera configuration that provide the most consistent colour values over varying environment conditions and ranges. This information is used to develop a detection system that provides range and bearing to detected targets. The system is evaluated over various lighting conditions from bright sunlight, shadows and overcast days and demonstrates robust performance. The accuracy of the system is compared against a laser beacon detector with preliminary results indicating it to be a valuable asset for long-range coloured target detection.

LunaRoo: A Proposal for the Google Lunar XPrize Payload Opportunity with the Part Time Scientists team

This proposal describes the innovative and competitive lunar payload solution developed at the Queensland University of Technology (QUT)–the LunaRoo: a hopping robot designed to exploit the Moon's lower gravity to leap up to 20m above the surface. It is compact enough to fit within a 10cm cube, whilst providing unique observation and mission capabilities by creating imagery during the hop. This first section is deliberately kept short and concise for web submission; additional information can be found in the second chapter.

Evaluation of object detection proposals under condition variations

Object detection is a fundamental task in many computer vision applications, therefore the importance of evaluating the quality of object detection is well acknowledged in this domain. This process gives insight into the capabilities of methods in handling environmental changes. In this paper, a new method for object detection is introduced that combines the Selective Search and EdgeBoxes. We tested these three methods under environmental variations. Our experiments demonstrate the outperformance of the combination method under illumination and view point variations.

RuleOMS: A rule-based online management system

We propose an architecture for a rule-based online management systems (RuleOMS). Typically, many domain areas face the problem that stakeholders maintain databases of their business core information and they have to take decisions or create reports according to guidelines, policies or regulations. To address this issue we propose the integration of databases, in particular relational databases, with a logic reasoner and rule engine. We argue that defeasible logic is an appropriate formalism to model rules, in particular when the rules are meant to model regulations. The resulting RuleOMS provides an efficient and flexible solution to the problem at hand using defeasible inference. A case study of an online child care management system is used to illustrate the proposed architecture.

Negative priming in naming of categorically related objects: An fMRI study

Ignoring an object slows subsequent naming responses to it, a phenomenon known as negative priming (NP). A central issue in NP research concerns the level of representation at which the effect occurs. As object naming is typically considered to involve access to abstract semantic representations, Tipper 1985 proposed that the NP effect occurred at this level of processing, and other researchers supported this proposal by demonstrating a similar result with categorically related objects (e.g., Allport et al., 1985; Murray, 1995), an effect referred to as semantic NP. However, objects within categories share more physical or structural features than objects from different categories. Consequently, the NP effect observed with categorically related objects might occur at a structural rather than semantic level of representation. We used event related fMRI interleaving overt object naming and image acquisition to demonstrate for the first time that the semantic NP effect activates the left posterior-mid fusiform and insular-opercular cortices. Moreover, both naming latencies and left posterior-mid fusiform cortex responses were influenced by the structural similarity of prime-probe object pairings in the categorically related condition, increasing with the number of shared features. None of the cerebral regions activated in a previous fMRI study of the identity NP effect (de Zubicaray et al., 2006) showed similar activation during semantic NP, including the left anterolateral temporal cortex, a region considered critical for semantic processing. The results suggest that the identity and semantic NP effects differ with respect to their neural mechanisms, and the label "semantic NP" might be a misnomer. We conclude that the effect is most likely the result of competition between structurally similar category exemplars that determines the efficiency of object name retrieval.

Text segmentation in unconstrained hand-drawings in whiteboard photos

In this paper we present a robust method to detect handwritten text from unconstrained drawings on normal whiteboards. Unlike printed text on documents, free form handwritten text has no pattern in terms of size, orientation and font and it is often mixed with other drawings such as lines and shapes. Unlike handwritings on paper, handwritings on a normal whiteboard cannot be scanned so the detection has to be based on photos. Our work traces straight edges on photos of the whiteboard and builds graph representation of connected components. We use geometric properties such as edge density, graph density, aspect ratio and neighborhood similarity to differentiate handwritten text from other drawings. The experiment results show that our method achieves satisfactory precision and recall. Furthermore, the method is robust and efficient enough to be deployed in a mobile device. This is an important enabler of business applications that support whiteboard-centric visual meetings in enterprise scenarios. © 2012 IEEE.

A virtual radiation therapy workflow training simulation

Aim Simulation forms an increasingly vital component of clinical skills development in a wide range of professional disciplines. Simulation of clinical techniques and equipment is designed to better prepare students for placement by providing an opportunity to learn technical skills in a “safe” academic environment. In radiotherapy training over the last decade or so this has predominantly comprised treatment planning software and small ancillary equipment such as mould room apparatus. Recent virtual reality developments have dramatically changed this approach. Innovative new simulation applications and file processing and interrogation software have helped to fill in the gaps to provide a streamlined virtual workflow solution. This paper outlines the innovations that have enabled this, along with an evaluation of the impact on students and educators. Method Virtual reality software and workflow applications have been developed to enable the following steps of radiation therapy to be simulated in an academic environment: CT scanning using a 3D virtual CT scanner simulation; batch CT duplication; treatment planning; 3D plan evaluation using a virtual linear accelerator; quantitative plan assessment, patient setup with lasers; and image guided radiotherapy software. Results Evaluation of the impact of the virtual reality workflow system highlighted substantial time saving for academic staff as well as positive feedback from students relating to preparation for clinical placements. Students valued practice in the “safe” environment and the opportunity to understand the clinical workflow ahead of clinical department experience. Conclusion Simulation of most of the radiation therapy workflow and tasks is feasible using a raft of virtual reality simulation applications and supporting software. Benefits of this approach include time-saving, embedding of a case-study based approach, increased student confidence, and optimal use of the clinical environment. Ongoing work seeks to determine the impact of simulation on clinical skills.

Practice patterns of radiation therapy technology in Australia: Results of a national audit

This article presents the results of a single-day census of radiation therapy (RT) treatment and technology use in Australia. The primary aim of the study was to ascertain patterns of RT practice and technology in use across Australia. These data were primarily collated to inform curriculum development of academic programs, thereby ensuring that training is matched to workforce patterns of practice. Methods: The study design was a census method with all 59 RT centres in Australia being invited to provide quantitative summary data relating to patient case mix and technology use on a randomly selected but common date. Anonymous and demographic-free data were analysed using descriptive statistics. Results: Overall data were provided across all six Australian States by 29 centres of a possible 59, yielding a response rate of 49% and representing a total of 2743 patients. Findings from this study indicate the increasing use of emerging intensity-modulated radiotherapy (IMRT), image fusion and image-guided radiation therapy (IGRT) technology in Australian RT planning and delivery phases. IMRT in particular was used for 37% of patients, indicating a high uptake of the technology in Australia when compared to other published data. The results also highlight the resource-intensive nature of benign tumour radiotherapy. Conclusions: In the absence of routine national data collection, the single-day census method offers a relatively convenient means of measuring and tracking RT resource utilisation. Wider use of this tool has the potential to not only track trends in technology implementation but also inform evidence-based guidelines for referral and resource planning.

Compact features for birdcall retrieval from environmental acoustic recordings

Bioacoustic data can be used for monitoring animal species diversity. The deployment of acoustic sensors enables acoustic monitoring at large temporal and spatial scales. We describe a content-based birdcall retrieval algorithm for the exploration of large data bases of acoustic recordings. In the algorithm, an event-based searching scheme and compact features are developed. In detail, ridge events are detected from audio files using event detection on spectral ridges. Then event alignment is used to search through audio files to locate candidate instances. A similarity measure is then applied to dimension-reduced spectral ridge feature vectors. The event-based searching method processes a smaller list of instances for faster retrieval. The experimental results demonstrate that our features achieve better success rate than existing methods and the feature dimension is greatly reduced.

Automated topometric graph generation from floor plan analysis

The world is rich with information such as signage and maps to assist humans to navigate. We present a method to extract topological spatial information from a generic bitmap floor plan and build a topometric graph that can be used by a mobile robot for tasks such as path planning and guided exploration. The algorithm first detects and extracts text in an image of the floor plan. Using the locations of the extracted text, flood fill is used to find the rooms and hallways. Doors are found by matching SURF features and these form the connections between rooms, which are the edges of the topological graph. Our system is able to automatically detect doors and differentiate between hallways and rooms, which is important for effective navigation. We show that our method can extract a topometric graph from a floor plan and is robust against ambiguous cases most commonly seen in floor plans including elevators and stairwells.

Comparison of Radiation Doses for Catheter Ablation Procedures for Atrial Fibrillation with Percutaneous Coronary Intervention Cases

Background: Catheter ablation procedures for atrial fibrillation (AF) may frequently require long fluoroscopic times. We sought to undertake a review of radiation safety practice in our Cardiac Electrophysiology Laboratory and implement changes to minimize fluoroscopic doses. We also sought to compare the results with radiation doses for percutaneous coronary intervention (PCI) cases performed in our hospital. Methods: Fluoroscopic times and doses for AF ablation procedures performed by a single operator on a Philips Integris H3000 image-intensifier were analysed for 11-month period. Results were compared with all PCI procedures performed over a similar period by multiple operators on a Philips Integris Allura FD system. Comprehensive review of radiation practice in the Electrophysiology laboratory identified the potential to reduce pulse frame rates and doses, and to narrow the field of interest without impacting the performance of the procedure. These changes were implemented and results analysed after a further 11 months. Results: In the pre-intervention period 50 AF catheter ablations had a mean fluoroscopic time of 86.4 min and mean fluoroscopic dose 68.4 Gy/cm2. Post-intervention 75 procedures had a mean fluorosocopic time of 68.9 min (p < 0.0001) and mean dose of 14.3 Gy/cm2 (p < 0.0001) 128 PCI procedures had a mean combined fluoroscopic and image acquisition time of 10.0 min and mean total dose 38.8 Gy/cm2. Conclusions: Catheter ablation procedures for AF may require lengthy use of fluoroscopy but simple modifications to radiation practice can result in marked reductions in radiation dose that compare favourably with PCI case doses

De Profundis (Theatre Soundtrack)

This creative work is an original soundtrack for the multimedia performance adaptation of Oscar Wilde’s De Profundis, led by David Fenton and Brian Lucas and produced by Metro Arts. Intermediality offers unique challenges to the composer creating towards live performance. Given the text-based nature of the piece, and the prevalence of screen content, music had a distinct role to play in supporting the intermedial performance environment. Drawing from Oscar Wilde’s own writings in the initial stages [“...richer cadences…more curious effects” “…the cry of Marysas” and the “deferred resolution of Chopin”] , the deliberately risky compositional process experimented with improvised location recordings and found sounds, random and fragmented assemblages of vintage recordings, rough methods and obsolete recording technology, and the sonic kinship of the hissing sibilances of the sea, theatrical applause and the crackle of antique recording devices (which had just been invented in Wilde’s time) worked into wefts of sound. As the soundtrack emerged, is was clearly resistant to ‘concepts’ imposed from the outside, and as the field of possibilities expanded and engaged in dialogue with the other elements of the performance (live and projected) certain pieces were selected by the director and curated into the emerging work. Thus leitmotifs emerged, rather than being imposed from the outset, with a particular through line holding: if it was too obviously like ‘music’, (which is usually used in theatre as emotional lubrication and narrative signpost) it didn’t work, and if it sounded like avant-garde sound-art, it was too grating and detracted from the primacy of the text. As a composer I worked this sweet spot inbetween these two poles as well as serving David Fenton’s curation: he determined which compositions to incorporate, reiterate and omit as part of the process of writing text, action and image and the compositional process responded with organic elaborations and variations on these selections. Musical resolution was mostly deferred until the closing stages of the performance. The soundtrack was present for the duration of the show, and Artshub reviewed the musical component thus: “...the score by David Megarrity is a refined, understated ambient scaffolding.” It premiered at the Visy Theatre, Brisbane Powerhouse, on 22 April 2015.

Unsupervised Domain Adaptation by Domain Invariant Projection

Domain-invariant representations are key to addressing the domain shift problem where the training and test exam- ples follow different distributions. Existing techniques that have attempted to match the distributions of the source and target domains typically compare these distributions in the original feature space. This space, however, may not be di- rectly suitable for such a comparison, since some of the fea- tures may have been distorted by the domain shift, or may be domain specific. In this paper, we introduce a Domain Invariant Projection approach: An unsupervised domain adaptation method that overcomes this issue by extracting the information that is invariant across the source and tar- get domains. More specifically, we learn a projection of the data to a low-dimensional latent space where the distance between the empirical distributions of the source and target examples is minimized. We demonstrate the effectiveness of our approach on the task of visual object recognition and show that it outperforms state-of-the-art methods on a stan- dard domain adaptation benchmark dataset

Enhancing human action recognition with region proposals

Deep convolutional network models have dominated recent work in human action recognition as well as image classification. However, these methods are often unduly influenced by the image background, learning and exploiting the presence of cues in typical computer vision datasets. For unbiased robotics applications, the degree of variation and novelty in action backgrounds is far greater than in computer vision datasets. To address this challenge, we propose an “action region proposal” method that, informed by optical flow, extracts image regions likely to contain actions for input into the network both during training and testing. In a range of experiments, we demonstrate that manually segmenting the background is not enough; but through active action region proposals during training and testing, state-of-the-art or better performance can be achieved on individual spatial and temporal video components. Finally, we show by focusing attention through action region proposals, we can further improve upon the existing state-of-the-art in spatio-temporally fused action recognition performance.