Human action recognition from video sequences

This PhD research has proposed new machine learning techniques to improve human action recognition based on local features. Several novel video representation and classification techniques have been proposed to increase the performance with lower computational complexity. The major contributions are the construction of new feature representation techniques, based on advanced machine learning techniques such as multiple instance dictionary learning, Latent Dirichlet Allocation (LDA) and Sparse coding. A Binary-tree based classification technique was also proposed to deal with large amounts of action categories. These techniques are not only improving the classification accuracy with constrained computational resources but are also robust to challenging environmental conditions. These developed techniques can be easily extended to a wide range of video applications to provide near real-time performance.

Structuring time and questioning to achieve tactical awareness in games lessons

Background: A paradigm shift in educational policy to create problem solvers and critical thinkers produced the games concept approach (GCA) in Singapore's Revised Syllabus for Physical Education (1999). A pilot study (2001) conducted on 11 primary school student teachers (STs) using this approach identified time management and questioning as two of the major challenges faced by novice teachers. Purpose: To examine the GCA from three perspectives: structure—lesson form in terms of teacher-time and pupil-time; product—how STs used those time fractions; and process—the nature of their questioning (type, timing, and target). Participants and setting: Forty-nine STs from three different PETE cohorts (two-year diploma, four-year degree, two-year post-graduate diploma) volunteered to participate in the study conducted during the penultimate week of their final practicum in public primary and secondary schools. Intervention: Based on the findings of the pilot study, PETE increased the emphasis on GCA content specific knowledge and pedagogical procedures. To further support STs learning to actualise the GCA, authentic micro-teaching experiences that were closely monitored by faculty were provided in schools nearby. Research design: This is a descriptive study of time-management and questioning strategies implemented by STs on practicum. Each lesson was segmented into a number of sub-categories of teacher-time (organisation, demonstration and closure) and pupil-time (practice time and game time). Questions were categorised as knowledge, technical, tactical or affective. Data collection: Each ST was video-taped teaching a GCA lesson towards the end of their final practicum. The STs individually determined the timing of the data collection and the lesson to be observed. Data analysis: Each lesson was segmented into a number of sub-categories of both teacher- and pupil-time. Duration recording using Noldus software (Observer 4.0) segmented the time management of different lesson components. Questioning was coded in terms of type, timing and target. Separate MANOVAs were used to measure the difference between programmes and levels (primary and secondary) in relation to time-management procedures and questioning strategies. Findings: No differences emerged between the programmes or levels in their time-management or questioning strategies. Using the GCA, STs generated more pupil time (53%) than teacher time (47%). STs at the primary level provided more technical practice, and those in secondary schools more small-sided game play. Most questions (58%) were asked during play or practice but were substantially low-order involving knowledge or recall (76%) and only 6.7% were open-ended or divergent and capable of developing tactical awareness. Conclusions: Although STs are delivering more pupil time (practice and game) than teacher-time, the lesson structure requires further fine-tuning to extend the practice task beyond technical drills. Many questions are being asked to generate knowledge about games but lack sufficient quality to enhance critical thinking and tactical awareness, as the GCA intends.

Video-stimulated recall in cross-cultural research in education: A case study in Vietnam

This paper examines incorporating video-stimulated recall (VSR) as a data collection technique in cross-cultural research. With VSR, participants are invited to watch video-recordings of particular events that they are involved in; they then recall their thoughts in relation to their observations of their behaviour in relation the event. The research draws on a larger PhD project completed at an Australian university that explored Vietnamese lecturers’ beliefs about learner autonomy. In cross-cultural research using the VSR technique provided significant challenges including time constraints of participants, misunderstandings of the VSR protocol and the possibility of participants’ losing face when reflecting on their teaching episodes. Adaptations to the VSR technique were required to meet the cultural challenges specific to this population, indicating a need for flexibility and awareness of the cultural context for research.

Joint evaluation of multiple speech patterns for speech recognition and training

We are addressing the novel problem of jointly evaluating multiple speech patterns for automatic speech recognition and training. We propose solutions based on both the non-parametric dynamic time warping (DTW) algorithm, and the parametric hidden Markov model (HMM). We show that a hybrid approach is quite effective for the application of noisy speech recognition. We extend the concept to HMM training wherein some patterns may be noisy or distorted. Utilizing the concept of ``virtual pattern'' developed for joint evaluation, we propose selective iterative training of HMMs. Evaluating these algorithms for burst/transient noisy speech and isolated word recognition, significant improvement in recognition accuracy is obtained using the new algorithms over those which do not utilize the joint evaluation strategy.

Blended learning in medical imaging pre-clinical skills training – does it work?

Undergraduate Medical Imaging (MI)students at QUT attend their first clinical placement towards the end of semester two. Students undertake two (pre)clinical skills development units – one theory and one practical. Students gain good contextual and theoretical knowledge during these units via a blended learning model with multiple learning methods employed. Students attend theory lectures, practical sessions, tutorial sessions in both a simulated and virtual environment and also attend pre-clinical scenario based tutorial sessions. The aim of this project is to evaluate the use of blended learning in the context of 1st year Medical Imaging Radiographic Technique and its effectiveness in preparing students for their first clinical experience. It is hoped that the multiple teaching methods employed within the pre-clinical training unit at QUT builds students clinical skills prior to the real situation. A quantitative approach will be taken, evaluating via pre and post clinical placement surveys. This data will be correlated with data gained in the previous year on the effectiveness of this training approach prior to clinical placement. In 2014 59 students were surveyed prior to their clinical placement demonstrated positive benefits of using a variety of learning tools to enhance their learning. 98.31%(n=58)of students agreed or strongly agreed that the theory lectures were a useful tool to enhance their learning. This was followed closely by 97% (n=57) of the students realising the value of performing role-play simulation prior to clinical placement. Tutorial engagement was considered useful for 93.22% (n=55) whilst 88.14% (n=52) reasoned that the x-raying of phantoms in the simulated radiographic laboratory was beneficial. Self-directed learning yielded 86.44% (n=51). The virtual reality simulation software was valuable for 72.41% (n=42) of the students. Of the 4 students that disagreed or strongly disagreed with the usefulness of any tool they strongly agreed to the usefulness of a minimum of one other learning tool. The impact of the blended learning model to meet diverse student needs continues to be positive with students engaging in most offerings. Students largely prefer pre -clinical scenario based practical and tutorial sessions where 'real-world’ situations are discussed.

Location of Pathogenic Bacteria during Persistent Infections: Insights from an Analysis Using Game Theory

Bacterial persistent infections are responsible for a significant amount of the human morbidity and mortality. Unlike acute bacterial infections, it is very difficult to treat persistent bacterial infections (e.g. tuberculosis). Knowledge about the location of pathogenic bacteria during persistent infection will help to treat such conditions by designing novel drugs which can reach such locations. In this study, events of bacterial persistent infections were analyzed using game theory. A game was defined where the pathogen and the host are the two players with a conflict of interest. Criteria for the establishment of Nash equilibrium were calculated for this game. This theoretical model, which is very simple and heuristic, predicts that during persistent infections pathogenic bacteria stay in both intracellular and extracellular compartments of the host. The result of this study implies that a bacterium should be able to survive in both intracellular and extracellular compartments of the host in order to cause persistent infections. This explains why persistent infections are more often caused by intracellular pathogens like Mycobacterium and Salmonella. Moreover, this prediction is in consistence with the results of previous experimental studies.

Functional Imagery Training to reduce snacking: Testing a novel motivational intervention based on Elaborated Intrusion theory

Functional Imagery Training (FIT) is a new theory-based, manualized intervention that trains positive goal imagery. Multisensory episodic imagery of proximal personal goals is elicited and practised, to sustain motivation and compete with less functional cravings. This study tested the impact of a single session of FIT plus a booster phone call on snacking. In a stepped-wedge design, 45 participants who wanted to lose weight or reduce snacking were randomly assigned to receive a session of FIT immediately or after a 2-week delay. High-sugar and high-fat snacks were recorded using timeline follow back for the previous 3 days, at baseline, 2 and 4 weeks. At 2 weeks, snacking was lower in the immediate group than in the delayed group, and the reduction after FIT was replicated in the delayed group between 2 and 4 weeks. Frequencies of motivational thoughts about snack reduction rose following FIT for both groups, and this change correlated with reductions in snacking and weight loss. By showing that FIT can support change in eating behaviours, these findings show its potential as a motivational intervention for weight management.

Playing the policy game: A review of the barriers and enablers of nutrition policy change

- Objective To progress nutrition policy change and develop more effective advocates, it is useful to consider real-world factors and practical experiences of past advocacy efforts to determine the key barriers and enablers to nutrition policy change. This review aimed to identify and synthesize the enablers and barriers to public policy change within the field of nutrition. - Design Electronic databases were searched systematically for studies examining policymaking in public health nutrition. An interpretive synthesis was undertaken. Setting: International, national, state and local government jurisdictions within high-income, democratic countries. - Results Sixty-three studies were selected for inclusion. Numerous themes were identified explaining the barriers and enablers to policy change, all of which fell under the overarching category, ‘political will’, underpinned by a second major category, ‘public will’. Sub-themes, including pressure from industry; neoliberal ideology; use of emotions and values, and being visible were prevalent in describing links between public will, political will and policy change. - Conclusions The frustration around lack of public policy change in nutrition frequently stems from a belief that policymaking is a rational process in which evidence is used to assess the relative costs and benefits of options. The findings from this review confirm that evidence is only one component of influencing policy change. For policy change to occur there needs to be the political will, and often the public will, for the proposed policy problem and solution. This review presents a suite of enablers which can assist health professionals to influence political and public will in future advocacy efforts.

Cooperative game play with avatars and agents: Differences in brain activity and the experience of play

The current study sought to identify the impact of whether teammates in a cooperative videogame were controlled by other humans (avatars) or by the game (agents). The impact on player experience was explored through both subjective questionnaire measures and brain wave activity measurement (electroencephalography). Play with human teammates was associated with a greater sense of relatedness, but less competence and flow than play with other computer-controlled teammates. In terms of brain activity, play with human teammates was associated with greater activity in the alpha, theta and beta power bands than play with computer-controlled teammates. Overall, the results suggest that play with human teammates involves greater cognitive activity in terms of 'mentalising' than play with computer-controlled teammates. Additionally, the associations between subjective measures of player experience and brain activity are described. Limitations of the current study are identified and key directions for future research are discussed.

An adaptive decomposition method for video

Scalable video coding (SVC) is an emerging standard built on the success of advanced video coding standard (H.264/AVC) by the Joint video team (JVT). Motion compensated temporal filtering (MCTF) and Closed loop hierarchical B pictures (CHBP) are two important coding methods proposed during initial stages of standardization. Either of the coding methods, MCTF/CHBP performs better depending upon noise content and characteristics of the sequence. This work identifies other characteristics of the sequences for which performance of MCTF is superior to that of CHBP and presents a method to adaptively select either of MCTF and CHBP coding methods at the GOP level. This method, referred as "Adaptive Decomposition" is shown to provide better R-D performance than of that by using MCTF or CRBP only. Further this method is extended to non-scalable coders.

A cooperative game theoretic approach to prototype selection

In this paper we consider the task of prototype selection whose primary goal is to reduce the storage and computational requirements of the Nearest Neighbor classifier while achieving better classification accuracies. We propose a solution to the prototype selection problem using techniques from cooperative game theory and show its efficacy experimentally.

Cluster based training for scaling non-linear support vector machines

Support Vector Machines(SVMs) are hyperplane classifiers defined in a kernel induced feature space. The data size dependent training time complexity of SVMs usually prohibits its use in applications involving more than a few thousands of data points. In this paper we propose a novel kernel based incremental data clustering approach and its use for scaling Non-linear Support Vector Machines to handle large data sets. The clustering method introduced can find cluster abstractions of the training data in a kernel induced feature space. These cluster abstractions are then used for selective sampling based training of Support Vector Machines to reduce the training time without compromising the generalization performance. Experiments done with real world datasets show that this approach gives good generalization performance at reasonable computational expense.