Human identification from video using advanced gait recognition techniques

The solutions proposed in this thesis contribute to improve gait recognition performance in practical scenarios that further enable the adoption of gait recognition into real world security and forensic applications that require identifying humans at a distance. Pioneering work has been conducted on frontal gait recognition using depth images to allow gait to be integrated with biometric walkthrough portals. The effects of gait challenging conditions including clothing, carrying goods, and viewpoint have been explored. Enhanced approaches are proposed on segmentation, feature extraction, feature optimisation and classification elements, and state-of-the-art recognition performance has been achieved. A frontal depth gait database has been developed and made available to the research community for further investigation. Solutions are explored in 2D and 3D domains using multiple images sources, and both domain-specific and independent modality gait features are proposed.

Dalby Shopping Precinct Survey Report : Consumer Attitudes towards Proposed Extended Trading Hours at Dalby

Data was collected to measure shopper’s attitudes toward the proposed Sunday and limited public holiday trading in Dalby. Survey questionnaires were conducted between 29th August to 31st August at Coles Dalby and Dalby Shoppingtown Plaza. In total, 150 respondents participated in the survey. Overall, the findings suggest that most respondents, especially males, couples with children, fulltime workers and those under the age of 49 years, embrace the proposed Sunday and limited holiday trading in Dalby. While there are concerns over increasing competition for smaller retailers who already trade on Sundays, a majority of respondents indicated it would suit their lifestyle, be convenient, provide more jobs, increase trade for smaller retailers within the area, reduce queues and congestion observed on Saturdays. The majority of those shoppers that indicated they currently did some shopping on a Sunday reported they would continue to support smaller retailers who currently trade on Sundays and some public holidays, if changes came about. Those opposed to changes to trading hours indicated a belief that existing trading hours were sufficient. Most people indicated the proposed extension of trading hours would not harm the community or have a negative, detrimental effect on themselves or their family. The main findings presented in the report are as follows: - 96.8% of respondents surveyed reported to be local, permanent residents of Dalby. - Residents of Dalby visited shopping centres and stores on average 2.8 times per week. This frequency is proportionately higher than the average Australian shopping behaviour at 2.5 times per week (Roy Morgan Supermarket Monitor). - It was determined that weekday evenings (after 5 pm) were the busiest times for shopping, with Saturday the next most popular day to shop. - 68% of respondents support the proposal of the extended trading hours at supermarkets, department stores and the shopping centre in Dalby, 26% oppose and 6% are unsure. - 90% of the respondents agreed that residents of Dalby should be allowed the same choice as other regional towns and cities in supporting/opposing changes to trading hours. The remaining 10% expressed a disagreement. - A larger percentage of males supported the proposal for Sunday and limited holiday trading. Of all the males surveyed, 80% were in support, 15% were opposed and 5% unsure. 60% of female respondents support the proposal, while 33% oppose it and 5% were unsure. - The highest percentage of support exists in fulltime workers with 90% of those respondents supporting the proposal. - In contrast, the lowest percentage of support was found in the non-working (retired/unemployed) respondents, where 67% opposed the application. - It was noted that 71% of respondents employed casually also indicated opposition against proposed changes. Further questioning identified an underlying concern from casually employed persons that Sunday trade would force them onto Sunday work rosters. - 92% of shared households expressed support for Sunday and limited public holiday trading, while 83% of both couples with children and single parent with children at home also supported the application. - 72% of the respondents often find it necessary to do some grocery shopping in Dalby on a Sunday. 76% of shoppers who indicated they already undertook some shopping on Sunday, indicated would continue to shop and support smaller retailers. - Of the respondents surveyed, 44% have travelled outside of Dalby on a Sunday to shop. This indicates that such residents find it necessary to undertake some shopping on a Sunday and in order to do so, drive an hour to Toowoomba in order to access a range of retailers. - The most cited reasons for supporting Sunday and limited public holiday trade were; ‘More choice about when I shop and that is convenient’ (69%), ‘Sunday trade will create job opportunities’ (71%), ‘Sunday trade will be helpful when preparing school lunches and getting ready for the working week’ (62%), and ‘Sunday trade will reduce shopping congestion during peak shopping periods’ (62%) - The most cited reasons for opposing the proposed changes are that ‘Sunday trade may increase competition for small retailers who already trade on Sunday’ (41%), ‘Shops are already open 6 days a week which is enough’ (31%), and ‘Sunday is a day of rest or a religious day and shopping should not be allowed’ (23%). - 97% of respondents indicated they would not change their sporting or social commitment if changes to trading hours were implemented.

Mt Isa Shopping Precinct Survey Report : Consumer Attitudes towards Proposed Extended Trading Hours at Mt Isa

Data was collected to measure shopper’s attitudes toward the proposed Sunday and limited public holiday trading in Mt Isa. Survey questionnaires were conducted between 15th August to 17th August at Kmart Plaza, Woolworths, Miles St. and Mt Isa Plaza. In total, 300 respondents participated in the survey. Overall, the findings suggest that most respondents, especially males, couples with children and fulltime workers, embrace the proposed Sunday and limited holiday trading in Mt Isa. While there are concerns over increasing competition for smaller retailers who already trade on Sundays, a majority of respondents indicated it would suit their lifestyle, be convenient, provide more jobs, increase trade for smaller retailers within the area, reduce queues and congestion, and offer a less expensive grocery shopping. The majority of those shoppers that indicated they currently did some shopping on a Sunday reported they would continue to support smaller retailers who currently trade on Sundays and some public holidays, if changes came about. Those opposed to changes to trading hours also indicated a belief that existing trading hours were sufficient. Most people indicated the proposed extension of trading hours would not harm the community or have a negative, detrimental effect on themselves or their family. The main findings presented in the report are as follows: - 96% of respondents surveyed reported to be local, permanent residents of Mt Isa. - Residents of Mt Isa visited shopping centres and stores on average 2.4 times per week. This mirrors the average Australian shopping behaviour at 2.5 times per week (Roy Morgan Supermarket Monitor) - It was determined that Saturday was the busiest day for shopping with a majority of respondents indicating they visited stores on that day of the week. - 71% of respondents support the proposal of extended trading hours at shopping centres in Mt Isa, 25% oppose and 4% are unsure. - 87% of the respondents agreed that residents of Mt Isa should be allowed the same choice as other regional towns and cities in supporting/opposing changes to trading hours. The remaining 13% expressed a disagreement. - A larger percentage of males supported the proposal for Sunday and limited holiday trading. Of all the males surveyed, 81% were in support, 17% were opposed and 2% unsure. By contrast, 64% of female respondents support the proposal, while 31% oppose it and 5% are unsure. - The highest percentage of support exists in fulltime workers with 85% of those respondents supporting the proposal. In contrast, the lowest percentage of support was found in the non-working respondents, where 62% opposed the application. - 78% of couples living with children at home expressed support for Sunday and limited public holiday trading, while 60% of couples without children also supported the application. - Of the respondents surveyed, virtually none (less than 1%) have travelled outside of Mt Isa on a Sunday to shop. This indicates that due to the remote and isolated location of this town, residents do not have the option to travel reasonable distances in order to access a range of retailers. - 70% of the respondents often find it necessary to do some grocery shopping in Mt Isa on a Sunday. - Convenience is cited as the major reason for support (79%) followed by lifestyle (75%). - The most cited reasons for supporting ‘it would be convenient’ (81%), ‘It may create more jobs’ (77%), ‘It may reduce congestion during busy shopping periods’ (74%, and ‘It would make it easier for working families with kids’ (74%). - The most cited reasons for opposing the proposed changes are that ‘It will disadvantage smaller businesses’ (44%), ‘It is unnecessary’ (29%). - 72% of shoppers who indicated they already undertook some shopping on Sunday, indicated would continue to shop and support smaller retailers. - 98% of respondents indicated they would not change their sporting or social commitment if changes to trading hours were implemented.

B-lactamase-mediated resistance to antimicrobials : the relationship between genotype and phenotype

This thesis examined the ability to predict the emergence of bacteria resistant to antibiotics using genetic markers in the bacteria. Bacteria containing the genetic markers were able to become resistant to antibiotics, whereas bacteria that did not have the genetic markers remained susceptible. Existing techniques can identify the presence of resistance by looking at the characteristics of the bacteria during growth. However, having the ability to predict antibiotic resistance before it emerges could improve the preservation of currently available antibiotics and minimise treatment failure.

Optimal HMM filtering and decision feedback equalisation for differential encoded transmission systems

In this paper conditional hidden Markov model (HMM) filters and conditional Kalman filters (KF) are coupled together to improve demodulation of differential encoded signals in noisy fading channels. We present an indicator matrix representation for differential encoded signals and the optimal HMM filter for demodulation. The filter requires O(N3) calculations per time iteration, where N is the number of message symbols. Decision feedback equalisation is investigated via coupling the optimal HMM filter for estimating the message, conditioned on estimates of the channel parameters, and a KF for estimating the channel states, conditioned on soft information message estimates. The particular differential encoding scheme examined in this paper is differential phase shift keying. However, the techniques developed can be extended to other forms of differential modulation. The channel model we use allows for multiplicative channel distortions and additive white Gaussian noise. Simulation studies are also presented.

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.

Prediction of activity type in preschool children using machine learning techniques

Objectives Recent research has shown that machine learning techniques can accurately predict activity classes from accelerometer data in adolescents and adults. The purpose of this study is to develop and test machine learning models for predicting activity type in preschool-aged children. Design Participants completed 12 standardised activity trials (TV, reading, tablet game, quiet play, art, treasure hunt, cleaning up, active game, obstacle course, bicycle riding) over two laboratory visits. Methods Eleven children aged 3–6 years (mean age = 4.8 ± 0.87; 55% girls) completed the activity trials while wearing an ActiGraph GT3X+ accelerometer on the right hip. Activities were categorised into five activity classes: sedentary activities, light activities, moderate to vigorous activities, walking, and running. A standard feed-forward Artificial Neural Network and a Deep Learning Ensemble Network were trained on features in the accelerometer data used in previous investigations (10th, 25th, 50th, 75th and 90th percentiles and the lag-one autocorrelation). Results Overall recognition accuracy for the standard feed forward Artificial Neural Network was 69.7%. Recognition accuracy for sedentary activities, light activities and games, moderate-to-vigorous activities, walking, and running was 82%, 79%, 64%, 36% and 46%, respectively. In comparison, overall recognition accuracy for the Deep Learning Ensemble Network was 82.6%. For sedentary activities, light activities and games, moderate-to-vigorous activities, walking, and running recognition accuracy was 84%, 91%, 79%, 73% and 73%, respectively. Conclusions Ensemble machine learning approaches such as Deep Learning Ensemble Network can accurately predict activity type from accelerometer data in preschool children.

Deterrence of drug driving : the impact of the ACT drug driving legislation and detection techniques

Overarching Research Questions Are ACT motorists aware of roadside saliva based drug testing operations? What is the perceived deterrent impact of the operations? What factors are predictive of future intentions to drug drive? What are the differences between key subgroups

Landform characterization using geophysics—Recent advances, applications, and emerging tools

This paper presents an overview of the strengths and limitations of existing and emerging geophysical tools for landform studies. The objectives are to discuss recent technical developments and to provide a review of relevant recent literature, with a focus on propagating field methods with terrestrial applications. For various methods in this category, including ground-penetrating radar (GPR), electrical resistivity (ER), seismics, and electromagnetic (EM) induction, the technical backgrounds are introduced, followed by section on novel developments relevant to landform characterization. For several decades, GPR has been popular for characterization of the shallow subsurface and in particular sedimentary systems. Novel developments in GPR include the use of multi-offset systems to improve signal-to-noise ratios and data collection efficiency, amongst others, and the increased use of 3D data. Multi-electrode ER systems have become popular in recent years as they allow for relatively fast and detailed mapping. Novel developments include time-lapse monitoring of dynamic processes as well as the use of capacitively-coupled systems for fast, non-invasive surveys. EM induction methods are especially popular for fast mapping of spatial variation, but can also be used to obtain information on the vertical variation in subsurface electrical conductivity. In recent years several examples of the use of plane wave EM for characterization of landforms have been published. Seismic methods for landform characterization include seismic reflection and refraction techniques and the use of surface waves. A recent development is the use of passive sensing approaches. The use of multiple geophysical methods, which can benefit from the sensitivity to different subsurface parameters, is becoming more common. Strategies for coupled and joint inversion of complementary datasets will, once more widely available, benefit the geophysical study of landforms.Three cases studies are presented on the use of electrical and GPR methods for characterization of landforms in the range of meters to 100. s of meters in dimension. In a study of polygonal patterned ground in the Saginaw Lowlands, Michigan, USA, electrical resistivity tomography was used to characterize differences in subsurface texture and water content associated with polygon-swale topography. Also, a sand-filled thermokarst feature was identified using electrical resistivity data. The second example is on the use of constant spread traversing (CST) for characterization of large-scale glaciotectonic deformation in the Ludington Ridge, Michigan. Multiple CST surveys parallel to an ~. 60. m high cliff, where broad (~. 100. m) synclines and narrow clay-rich anticlines are visible, illustrated that at least one of the narrow structures extended inland. A third case study discusses internal structures of an eolian dune on a coastal spit in New Zealand. Both 35 and 200. MHz GPR data, which clearly identified a paleosol and internal sedimentary structures of the dune, were used to improve understanding of the development of the dune, which may shed light on paleo-wind directions.