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.

Oral liquid nutritional supplements for people with dementia in residential aged care facilities

AIM: This systematic review investigated the prescription, administration and effectiveness of oral liquid nutritional supplements (OLNS) for people with dementia in residential aged care facilities (RACF). METHODS: A comprehensive search of relevant databases, hand searching and cross-referencing found 15 relevant articles from a total of 2910 possible results. Articles which met the inclusion criteria were critically appraised by two independent reviewers using the relevant Joanna Briggs Institute (JBI) appraisal checklist. Data were extracted using the relevant JBI extraction instruments. No data synthesis was possible due to clinical and methodological heterogeneity. RESULTS: Included studies examined a range of strategies, issues and results related to OLNS for persons with dementia in RACFs; however there appear to be significant gaps in the current body of research, particularly in relation to examinations of effectiveness. CONCLUSIONS: This review was unable to produce a definitive finding regarding effectiveness. OLNS may improve the nutritional state of residents with dementia and help prevent weight loss, and there is some suggestion that it may slow the rate of cognitive decline. However, in order for OLNS to be effective, nursing and care staff need to ensure that sufficient attention is paid to the issues of prescription and administration.

Transparent, balanced and vigorous: The exercise of the Australian Privacy Commissioner's powers in relation to National Privacy Principle 4

This thesis considers whether the Australian Privacy Commissioner's use of its powers supports compliance with the requirement to 'take reasonable steps' to protect personal information in National Privacy Principle 4 of the Privacy Act 1988 (Cth). Two unique lenses were used. First, the Commissioner's use of powers was assessed against the principles of transparency, balance and vigorousness and secondly against alignment with an industry practice approach to securing information. Following a comprehensive review of publicly available materials, interviews and investigation file records, this thesis found that the Commissioner's use of his powers has not been transparent, balanced or vigorous, nor has it been supportive of an industry practice approach to securing data. Accordingly, it concludes that the Privacy Commissioner's use of its regulatory powers is unlikely to result in any significant improvement to the security of personal information held by organisations in Australia.

Biomarkers of exercise-induced myocardial stress in relation to inflammatory and oxidative stress

Increased concentrations of biomarkers reflecting myocardial stress such as cardiac troponin I and T and brain natriuretic peptide (BNP) have been observed following strenuous, long-lasting endurance exercise. The pathophysiological mechanisms are still not fully elucidated and the interpretations of increased post-exercise concentrations range from (i) evidence for exercise-induced myocardial damage to (ii) non-relevant spurious troponin elevations, presumably caused by assay imprecision or heterophilic antibodies. Several lines of evidence suggest that inflammatory processes or oxidative stress could be involved in the rise of NT-proBNP and Troponin observed in critically ill patients with sepsis or burn injury. We tested the hypothesis that inflammatory or oxidative stress is also responsible for exercise-induced cardiomyocyte strain in a large cohort of triathletes following an Ironman triathlon. However, the post-race increase in cardiac troponin T and NT-proBNP was not associated with several markers of exercise-induced inflammation, oxidative stress or antioxidant vitamins. Therefore, we clearly need more studies with other inflammatory markers and different designs to elucidate the scientific background for increases in myocardial stress markers following strenuous endurance events.

Molecular genetic investigation of mitochondrial dysfunction in relation to migraine susceptibility

The aim of this research was to assess the role of genetic variation in mitochondrial function and how this relates to migraine pathophysiology. Using our unique Norfolk Island population, a custom in-house next generation sequencing methodology was developed. This data for the first time showed that there is a molecular genetic link between mitochondrial dysfunction and migraine susceptibility. This work has provided the foundation for further studies aimed at utilising the identified markers in improved migraine diagnostic and therapeutic strategies.

Reproducible and label-free biosensor for the selective extraction and rapid detection of proteins in biological fluids

Erythropoietin (EPO), a glycoprotein hormone of ∼34 kDa, is an important hematopoietic growth factor, mainly produced in the kidney and controls the number of red blood cells circulating in the blood stream. Sensitive and rapid recombinant human EPO (rHuEPO) detection tools that improve on the current laborious EPO detection techniques are in high demand for both clinical and sports industry. A sensitive aptamer-functionalized biosensor (aptasensor) has been developed by controlled growth of gold nanostructures (AuNS) over a gold substrate (pAu/AuNS). The aptasensor selectively binds to rHuEPO and, therefore, was used to extract and detect the drug from horse plasma by surface enhanced Raman spectroscopy (SERS). Due to the nanogap separation between the nanostructures, the high population and distribution of hot spots on the pAu/AuNS substrate surface, strong signal enhancement was acquired. By using wide area illumination (WAI) setting for the Raman detection, a low RSD of 4.92% over 150 SERS measurements was achieved. The significant reproducibility of the new biosensor addresses the serious problem of SERS signal inconsistency that hampers the use of the technique in the field. The WAI setting is compatible with handheld Raman devices. Therefore, the new aptasensor can be used for the selective extraction of rHuEPO from biological fluids and subsequently screened with handheld Raman spectrometer for SERS based in-field protein detection.

Active learning: A step towards automating medical concept extraction

Objective This paper presents an automatic active learning-based system for the extraction of medical concepts from clinical free-text reports. Specifically, (1) the contribution of active learning in reducing the annotation effort, and (2) the robustness of incremental active learning framework across different selection criteria and datasets is determined. Materials and methods The comparative performance of an active learning framework and a fully supervised approach were investigated to study how active learning reduces the annotation effort while achieving the same effectiveness as a supervised approach. Conditional Random Fields as the supervised method, and least confidence and information density as two selection criteria for active learning framework were used. The effect of incremental learning vs. standard learning on the robustness of the models within the active learning framework with different selection criteria was also investigated. Two clinical datasets were used for evaluation: the i2b2/VA 2010 NLP challenge and the ShARe/CLEF 2013 eHealth Evaluation Lab. Results The annotation effort saved by active learning to achieve the same effectiveness as supervised learning is up to 77%, 57%, and 46% of the total number of sequences, tokens, and concepts, respectively. Compared to the Random sampling baseline, the saving is at least doubled. Discussion Incremental active learning guarantees robustness across all selection criteria and datasets. The reduction of annotation effort is always above random sampling and longest sequence baselines. Conclusion Incremental active learning is a promising approach for building effective and robust medical concept extraction models, while significantly reducing the burden of manual annotation.

External knowledge and query strategies in active learning: A study in clinical information extraction

This paper presents a new active learning query strategy for information extraction, called Domain Knowledge Informativeness (DKI). Active learning is often used to reduce the amount of annotation effort required to obtain training data for machine learning algorithms. A key component of an active learning approach is the query strategy, which is used to iteratively select samples for annotation. Knowledge resources have been used in information extraction as a means to derive additional features for sample representation. DKI is, however, the first query strategy that exploits such resources to inform sample selection. To evaluate the merits of DKI, in particular with respect to the reduction in annotation effort that the new query strategy allows to achieve, we conduct a comprehensive empirical comparison of active learning query strategies for information extraction within the clinical domain. The clinical domain was chosen for this work because of the availability of extensive structured knowledge resources which have often been exploited for feature generation. In addition, the clinical domain offers a compelling use case for active learning because of the necessary high costs and hurdles associated with obtaining annotations in this domain. Our experimental findings demonstrated that 1) amongst existing query strategies, the ones based on the classification model’s confidence are a better choice for clinical data as they perform equally well with a much lighter computational load, and 2) significant reductions in annotation effort are achievable by exploiting knowledge resources within active learning query strategies, with up to 14% less tokens and concepts to manually annotate than with state-of-the-art query strategies.

Relation between variants in the neurotrophin receptor gene, NTRK3, and white matter integrity in healthy young adults

The NTRK3 gene (also known as TRKC) encodes a high affinity receptor for the neurotrophin 3'-nucleotidase (NT3), which is implicated in oligodendrocyte and myelin development. We previously found that white matter integrity in young adults is related to common variants in genes encoding neurotrophins and their receptors. This underscores the importance of neurotrophins for white matter development. NTRK3 variants are putative risk factors for schizophrenia, bipolar disorder, and obsessive-compulsive disorder hoarding, suggesting that some NTRK3 variants may affect the brain.To test this, we scanned 392 healthy adult twins and their siblings (mean age, 23.6. ±. 2.2. years; range: 20-29. years) with 105-gradient 4-Tesla diffusion tensor imaging (DTI). We identified 18 single nucleotide polymorphisms (SNPs) in the NTRK3 gene that have been associated with neuropsychiatric disorders. We used a multi-SNP model, adjusting for family relatedness, age, and sex, to relate these variants to voxelwise fractional anisotropy (FA) - a DTI measure of white matter integrity.FA was optimally predicted (based on the highest false discovery rate critical p), by five SNPs (rs1017412, rs2114252, rs16941261, rs3784406, and rs7176429; overall FDR critical p=. 0.028). Gene effects were widespread and included the corpus callosum genu and inferior longitudinal fasciculus - regions implicated in several neuropsychiatric disorders and previously associated with other neurotrophin-related genetic variants in an overlapping sample of subjects. NTRK3 genetic variants, and neurotrophins more generally, may influence white matter integrity in brain regions implicated in neuropsychiatric disorders.

A reproducible method for automated extraction of brain volumes from 3D human head MR images

An automated method for extracting brain volumes from three commonly acquired three-dimensional (3D) MR images (proton density, T1 weighted, and T2-weighted) of the human head is described. The procedure is divided into four levels: preprocessing, segmentation, scalp removal, and postprocessing. A user-provided reference point is the sole operator-dependent input required. The method's parameters were first optimized and then fixed and applied to 30 repeat data sets from 15 normal older adult subjects to investigate its reproducibility. Percent differences between total brain volumes (TBVs) for the subjects' repeated data sets ranged from .5% to 2.2%. We conclude that the method is both robust and reproducible and has the potential for wide application.

Utility of web content blocks in content extraction

Currently we are facing an overburdening growth of the number of reliable information sources on the Internet. The quantity of information available to everyone via Internet is dramatically growing each year [15]. At the same time, temporal and cognitive resources of human users are not changing, therefore causing a phenomenon of information overload. World Wide Web is one of the main sources of information for decision makers (reference to my research). However our studies show that, at least in Poland, the decision makers see some important problems when turning to Internet as a source of decision information. One of the most common obstacles raised is distribution of relevant information among many sources, and therefore need to visit different Web sources in order to collect all important content and analyze it. A few research groups have recently turned to the problem of information extraction from the Web [13]. The most effort so far has been directed toward collecting data from dispersed databases accessible via web pages (related to as data extraction or information extraction from the Web) and towards understanding natural language texts by means of fact, entity, and association recognition (related to as information extraction). Data extraction efforts show some interesting results, however proper integration of web databases is still beyond us. Information extraction field has been recently very successful in retrieving information from natural language texts, however it is still lacking abilities to understand more complex information, requiring use of common sense knowledge, discourse analysis and disambiguation techniques.