Polarization of forecast densities : a new approach to time series classification

Time series classification has been extensively explored in many fields of study. Most methods are based on the historical or current information extracted from data. However, if interest is in a specific future time period, methods that directly relate to forecasts of time series are much more appropriate. An approach to time series classification is proposed based on a polarization measure of forecast densities of time series. By fitting autoregressive models, forecast replicates of each time series are obtained via the bias-corrected bootstrap, and a stationarity correction is considered when necessary. Kernel estimators are then employed to approximate forecast densities, and discrepancies of forecast densities of pairs of time series are estimated by a polarization measure, which evaluates the extent to which two densities overlap. Following the distributional properties of the polarization measure, a discriminant rule and a clustering method are proposed to conduct the supervised and unsupervised classification, respectively. The proposed methodology is applied to both simulated and real data sets, and the results show desirable properties.

Unsupervised speaker adaptation for telephone call transcription

The use of the PC and Internet for placing telephone calls will present new opportunities to capture vast amounts of un-transcribed speech for a particular speaker. This paper investigates how to best exploit this data for speaker-dependent speech recognition. Supervised and unsupervised experiments in acoustic model and language model adaptation are presented. Using one hour of automatically transcribed speech per speaker with a word error rate of 36.0%, unsupervised adaptation resulted in an absolute gain of 6.3%, equivalent to 70% of the gain from the supervised case, with additional adaptation data likely to yield further improvements. LM adaptation experiments suggested that although there seems to be a small degree of speaker idiolect, adaptation to the speaker alone, without considering the topic of the conversation, is in itself unlikely to improve transcription accuracy.

Separable and non-separable discrete wavelet transform based texture features and image classification of breast thermograms

Highly sensitive infrared cameras can produce high-resolution diagnostic images of the temperature and vascular changes of breasts. Wavelet transform based features are suitable in extracting the texture difference information of these images due to their scale-space decomposition. The objective of this study is to investigate the potential of extracted features in differentiating between breast lesions by comparing the two corresponding pectoral regions of two breast thermograms. The pectoral regions of breastsare important because near 50% of all breast cancer is located in this region. In this study, the pectoral region of the left breast is selected. Then the corresponding pectoral region of the right breast is identified. Texture features based on the first and the second sets of statistics are extracted from wavelet decomposed images of the pectoral regions of two breast thermograms. Principal component analysis is used to reduce dimension and an Adaboost classifier to evaluate classification performance. A number of different wavelet features are compared and it is shown that complex non-separable 2D discrete wavelet transform features perform better than their real separable counterparts.

No sex difference in body fat in response to supervised and measured exercise

It is often reported that females lose less body weight than males do in response to exercise. These differences are suggested to be a result of females exhibiting a stronger defense of body fat and a greater compensatory appetite response to exercise than males do. Purpose This study aimed to compare the effect of a 12-wk supervised exercise program on body weight, body composition, appetite, and energy intake in males and females. Methods A total of 107 overweight and obese adults (males = 35, premenopausal females = 72, BMI = 31.4 ± 4.2 kg·m−2, age = 40.9 ± 9.2 yr) completed a supervised 12-wk exercise program expending approximately 10.5 MJ·wk−1 at 70% HRmax. Body composition, energy intake, appetite ratings, RMR, and cardiovascular fitness were measured at weeks 0 and 12. Results The 12-wk exercise program led to significant reductions in body mass (males [M] = −3.03 ± 3.4 kg and females [F] = −2.28 ± 3.1 kg), fat mass (M = −3.14 ± 3.7 kg and F = −3.01 ± 3.0 kg), and percent body fat (M = −2.45% ± 3.3% and F = −2.45% ± 2.2%; all P < 0.0001), but there were no sex-based differences (P > 0.05). There were no significant changes in daily energy intake in males or females after the exercise intervention compared with baseline (M = 199.2 ± 2418.1 kJ and F = −131.6 ± 1912.0 kJ, P > 0.05). Fasting hunger levels significantly increased after the intervention compared with baseline values (M = 11.0 ± 21.1 min and F = 14.0 ± 22.9 mm, P < 0.0001), but there were no differences between males and females (P > 0.05). The exercise also improved satiety responses to an individualized fixed-energy breakfast (P < 0.0001). This was comparable in males and females. Conclusions Males and premenopausal females did not differ in their response to a 12-wk exercise intervention and achieved similar reductions in body fat. When exercise interventions are supervised and energy expenditure is controlled, there are no sex-based differences in the measured compensatory response to exercise.

Petrology and textural classification of the Jericho kimberlite, northern Slave Province, Nunavut, Canada

The paper presents data on petrology, bulk rock and mineral compositions, and textural classification of the Middle Jurassic Jericho kimberlite (Slave craton, Canada). The kimberlite was emplaced as three steep-sided pipes in granite that was overlain by limestones and minor soft sediments. The pipes are infilled with hypabyssal and pyroclastic kimberlites and connected to a satellite pipe by a dyke. The Jericho kimberlite is classified as a Group Ia, lacking groundmass tetraferriphlogopite and containing monticellite pseudomorphs. The kimberlite formed, during several consecutive emplacement events of compositionally different batches of kimberlite magma. Core-logging and thin-section observations identified at least two phases of hypabyssal kimberlites and three phases of pyroclastic kimberlites. Hypabyssal kimberlites intruded as a main dyke (HK1) and as late small-volume aphanitic and vesicular dykes. Massive pyroclastic kimberlite (MPK1) predominantly filled the northern and southern lobes of the pipe and formed from magma different from the HK1 magma. The MPK1 magma crystallized Ti-, Fe-, and Cr-rich phlogopite without rims of barian phlogopite, and clinopyroxene and spinel without atoll structures. MPK1 textures, superficially reminiscent of tuffisitic kimberlite, are caused by pervasive contamination by granite xenoliths. The next explosive events filled the central lobe with two varieties of pyroclastic kimberlite: (1) massive and (2) weakly bedded, normally graded pyroclastic kimberlite. The geology of the Jericho pipe differs from the geology of South African or the Prairie kimberlites, but may resemble Lac de Gras pipes, in which deeper erosion removed upper fades of resedimented kimberlites.

Applying SVMs and weight-based factor analysis to unsupervised adaptation for speaker verification

This paper presents an extended study on the implementation of support vector machine(SVM) based speaker verification in systems that employ continuous progressive model adaptation using the weight-based factor analysis model. The weight-based factor analysis model compensates for session variations in unsupervised scenarios by incorporating trial confidence measures in the general statistics used in the inter-session variability modelling process. Employing weight-based factor analysis in Gaussian mixture models (GMM) was recently found to provide significant performance gains to unsupervised classification. Further improvements in performance were found through the integration of SVM-based classification in the system by means of GMM supervectors. This study focuses particularly on the way in which a client is represented in the SVM kernel space using single and multiple target supervectors. Experimental results indicate that training client SVMs using a single target supervector maximises performance while exhibiting a certain robustness to the inclusion of impostor training data in the model. Furthermore, the inclusion of low-scoring target trials in the adaptation process is investigated where they were found to significantly aid performance.

Improving deep convultional neural networks with unsupervised feature learning

The latest generation of Deep Convolutional Neural Networks (DCNN) have dramatically advanced challenging computer vision tasks, especially in object detection and object classification, achieving state-of-the-art performance in several computer vision tasks including text recognition, sign recognition, face recognition and scene understanding. The depth of these supervised networks has enabled learning deeper and hierarchical representation of features. In parallel, unsupervised deep learning such as Convolutional Deep Belief Network (CDBN) has also achieved state-of-the-art in many computer vision tasks. However, there is very limited research on jointly exploiting the strength of these two approaches. In this paper, we investigate the learning capability of both methods. We compare the output of individual layers and show that many learnt filters and outputs of the corresponding level layer are almost similar for both approaches. Stacking the DCNN on top of unsupervised layers or replacing layers in the DCNN with the corresponding learnt layers in the CDBN can improve the recognition/classification accuracy and training computational expense. We demonstrate the validity of the proposal on ImageNet dataset.

Mapping semantic knowledge for unsupervised text categorisation

Text categorisation is challenging, due to the complex structure with heterogeneous, changing topics in documents. The performance of text categorisation relies on the quality of samples, effectiveness of document features, and the topic coverage of categories, depending on the employing strategies; supervised or unsupervised; single labelled or multi-labelled. Attempting to deal with these reliability issues in text categorisation, we propose an unsupervised multi-labelled text categorisation approach that maps the local knowledge in documents to global knowledge in a world ontology to optimise categorisation result. The conceptual framework of the approach consists of three modules; pattern mining for feature extraction; feature-subject mapping for categorisation; concept generalisation for optimised categorisation. The approach has been promisingly evaluated by compared with typical text categorisation methods, based on the ground truth encoded by human experts.

Vision-based classification of solder joint defects

Inspection of solder joints has been a critical process in the electronic manufacturing industry to reduce manufacturing cost, improve yield, and ensure product quality and reliability. The solder joint inspection problem is more challenging than many other visual inspections because of the variability in the appearance of solder joints. Although many research works and various techniques have been developed to classify defect in solder joints, these methods have complex systems of illumination for image acquisition and complicated classification algorithms. An important stage of the analysis is to select the right method for the classification. Better inspection technologies are needed to fill the gap between available inspection capabilities and industry systems. This dissertation aims to provide a solution that can overcome some of the limitations of current inspection techniques. This research proposes two inspection steps for automatic solder joint classification system. The “front-end” inspection system includes illumination normalisation, localization and segmentation. The illumination normalisation approach can effectively and efficiently eliminate the effect of uneven illumination while keeping the properties of the processed image. The “back-end” inspection involves the classification of solder joints by using Log Gabor filter and classifier fusion. Five different levels of solder quality with respect to the amount of solder paste have been defined. Log Gabor filter has been demonstrated to achieve high recognition rates and is resistant to misalignment. Further testing demonstrates the advantage of Log Gabor filter over both Discrete Wavelet Transform and Discrete Cosine Transform. Classifier score fusion is analysed for improving recognition rate. Experimental results demonstrate that the proposed system improves performance and robustness in terms of classification rates. This proposed system does not need any special illumination system, and the images are acquired by an ordinary digital camera. In fact, the choice of suitable features allows one to overcome the problem given by the use of non complex illumination systems. The new system proposed in this research can be incorporated in the development of an automated non-contact, non-destructive and low cost solder joint quality inspection system.

The development and validation of two complementary measures of drivers' hazard perception ability

Hazard perception in driving involves a number of different processes. This paper reports the development of two measures designed to separate these processes. A Hazard Perception Test was developed to measure how quickly drivers could anticipate hazards overall, incorporating detection, trajectory prediction, and hazard classification judgements. A Hazard Change Detection Task was developed to measure how quickly drivers can detect a hazard in a static image regardless of whether they consider it hazardous or not. For the Hazard Perception Test, young novices were slower than mid-age experienced drivers, consistent with differences in crash risk, and test performance correlated with scores in pre-existing Hazard Perception Tests. For drivers aged 65 and over, scores on the Hazard Perception Test declined with age and correlated with both contrast sensitivity and a Useful Field of View measure. For the Hazard Change Detection Task, novices responded quicker than the experienced drivers, contrary to crash risk trends, and test performance did not correlate with measures of overall hazard perception. However for drivers aged 65 and over, test performance declined with age and correlated with both hazard perception and Useful Field of View. Overall we concluded that there was support for the validity of the Hazard Perception Test for all ages but the Hazard Change Detection Task might only be appropriate for use with older drivers.

Position, rotation, and scale invariant recognition of images using higher-order spectra

A new approach to recognition of images using invariant features based on higher-order spectra is presented. Higher-order spectra are translation invariant because translation produces linear phase shifts which cancel. Scale and amplification invariance are satisfied by the phase of the integral of a higher-order spectrum along a radial line in higher-order frequency space because the contour of integration maps onto itself and both the real and imaginary parts are affected equally by the transformation. Rotation invariance is introduced by deriving invariants from the Radon transform of the image and using the cyclic-shift invariance property of the discrete Fourier transform magnitude. Results on synthetic and actual images show isolated, compact clusters in feature space and high classification accuracies

Classification—Content Regulation and Convergent Media

On 24 March 2011, Attorney-General Robert McClelland referred the National Classification Scheme to the ALRC and asked it to conduct widespread public consultation across the community and industry. The review considered issues including: existing Commonwealth, State and Territory classification laws the current classification categories contained in the Classification Act, Code and Guidelines the rapid pace of technological change the need to improve classification information available to the community the effect of media on children and the desirability of a strong content and distribution industry in Australia. During the inquiry, the ALRC conducted face-to-face consultations with stakeholders, hosted two online discussion forums, and commissioned pilot community and reference group forums into community attitudes to higher level media content. The ALRC published two consultation documents—an Issues Paper and a Discussion Paper—and invited submissions from the public. The Final Report was tabled in Parliament on 1 March 2012. Recommendations: The report makes 57 recommendations for reform. The net effect of the recommendations would be the establishment of a new National Classification Scheme that: applies consistent rules to content that are sufficiently flexible to be adaptive to technological change; places a regulatory focus on restricting access to adult content, helping to promote cyber-safety and protect children from inappropriate content across media platforms; retains the Classification Board as an independent classification decision maker with an essential role in setting benchmarks; promotes industry co-regulation, encouraging greater industry content classification, with government regulation more directly focused on content of higher community concern; provides for pragmatic regulatory oversight, to meet community expectations and safeguard community standards; reduces the overall regulatory burden on media content industries while ensuring that content obligations are focused on what Australians most expect to be classified; and harmonises classification laws across Australia, for the benefit of consumers and content providers.

Development and implementation of the Australian universities radiation therapy student clinical assessment form

Purpose: Prior to 2009, one of the problems faced by radiation therapists who supervised and assessed students on placement in Australian clinical centres, was that each of the six Australian universities where Radiation Therapy (RT) programmes were conducted used different clinical assessment and reporting criteria. This paper describes the development of a unified national clinical assessment and reporting form that was implemented nationally by all six universities in 2009. Methods: A four phase methodology was used to develop the new assessment form and user guide. Phase 1 included university consensus around domains of student practice and assessment, and alignment with national competency standards; Phase 2 was a national consensus workshop attended by radiation therapists involved in student supervision and assessment; Phase 3 was an action research re-iterative Delphi technique involving two rounds of a mail-out to gain further expert consensus; and stage 4 was national piloting of the developed assessment form. Results: The new assessment form includes five main domains of practice and 19 sub-domain criteria which students are assessed against during placement. Feedback from the pilot centre participants was positive, with the new form being assessed to be comprehensive and complemented by the accompanying user guide. Conclusion: The new assessment form has improved both the formative and summative assessment of students on placement, as well as enhancing the quality of feedback to students and the universities. The new national form has high acceptance from the Australian universities and has been subject to wide review by the profession.