Characterizing multi-agent team behavior from partial team tracings : evidence from the English Premier League

Real-world AI systems have been recently deployed which can automatically analyze the plan and tactics of tennis players. As the game-state is updated regularly at short intervals (i.e. point-level), a library of successful and unsuccessful plans of a player can be learnt over time. Given the relative strengths and weaknesses of a player’s plans, a set of proven plans or tactics from the library that characterize a player can be identified. For low-scoring, continuous team sports like soccer, such analysis for multi-agent teams does not exist as the game is not segmented into “discretized” plays (i.e. plans), making it difficult to obtain a library that characterizes a team’s behavior. Additionally, as player tracking data is costly and difficult to obtain, we only have partial team tracings in the form of ball actions which makes this problem even more difficult. In this paper, we propose a method to overcome these issues by representing team behavior via play-segments, which are spatio-temporal descriptions of ball movement over fixed windows of time. Using these representations we can characterize team behavior from entropy maps, which give a measure of predictability of team behaviors across the field. We show the efficacy and applicability of our method on the 2010-2011 English Premier League soccer data.

Team communications in surgery - creating a culture of safety

As a key department within a healthcare organisation, the operating room is a hazardous environment, where the consequences of errors are high, despite the relatively low rates of occurrence. Team performance in surgery is increasingly being considered crucial for a culture of safety. The aim of this study was to describe team communication and the ways it fostered or threatened safety culture in surgery. Ethnography was used, and involved a 6-month fieldwork period of observation and 19 interviews with 24 informants from nursing, anaesthesia and surgery. Data were collected during 2009 in the operating rooms of a tertiary care facility in Queensland, Australia. Through analysis of the textual data, three themes that exemplified teamwork culture in surgery were generated: ‘‘building shared understandings through open communication’’; ‘‘managing contextual stressors in a hierarchical environment’’ and ‘‘intermittent membership influences team performance’’. In creating a safety culture in a healthcare organisation, a team’s optimal performance relies on the open discussion of teamwork and team expectation, and significantly depends on how the organisational culture promotes such discussions.

On robust face recognition via sparse encoding : the good, the bad, and the ugly

In the field of face recognition, Sparse Representation (SR) has received considerable attention during the past few years. Most of the relevant literature focuses on holistic descriptors in closed-set identification applications. The underlying assumption in SR-based methods is that each class in the gallery has sufficient samples and the query lies on the subspace spanned by the gallery of the same class. Unfortunately, such assumption is easily violated in the more challenging face verification scenario, where an algorithm is required to determine if two faces (where one or both have not been seen before) belong to the same person. In this paper, we first discuss why previous attempts with SR might not be applicable to verification problems. We then propose an alternative approach to face verification via SR. Specifically, we propose to use explicit SR encoding on local image patches rather than the entire face. The obtained sparse signals are pooled via averaging to form multiple region descriptors, which are then concatenated to form an overall face descriptor. Due to the deliberate loss spatial relations within each region (caused by averaging), the resulting descriptor is robust to misalignment & various image deformations. Within the proposed framework, we evaluate several SR encoding techniques: l1-minimisation, Sparse Autoencoder Neural Network (SANN), and an implicit probabilistic technique based on Gaussian Mixture Models. Thorough experiments on AR, FERET, exYaleB, BANCA and ChokePoint datasets show that the proposed local SR approach obtains considerably better and more robust performance than several previous state-of-the-art holistic SR methods, in both verification and closed-set identification problems. The experiments also show that l1-minimisation based encoding has a considerably higher computational than the other techniques, but leads to higher recognition rates.

Cohort normalization based sparse representation for undersampled face recognition

Abstract. In recent years, sparse representation based classification(SRC) has received much attention in face recognition with multipletraining samples of each subject. However, it cannot be easily applied toa recognition task with insufficient training samples under uncontrolledenvironments. On the other hand, cohort normalization, as a way of mea-suring the degradation effect under challenging environments in relationto a pool of cohort samples, has been widely used in the area of biometricauthentication. In this paper, for the first time, we introduce cohort nor-malization to SRC-based face recognition with insufficient training sam-ples. Specifically, a user-specific cohort set is selected to normalize theraw residual, which is obtained from comparing the test sample with itssparse representations corresponding to the gallery subject, using poly-nomial regression. Experimental results on AR and FERET databases show that cohort normalization can bring SRC much robustness against various forms of degradation factors for undersampled face recognition.

Heteroscedastic probabilistic linear discriminant analysis for manifold learning in video-based face recognition

To recognize faces in video, face appearances have been widely modeled as piece-wise local linear models which linearly approximate the smooth yet non-linear low dimensional face appearance manifolds. The choice of representations of the local models is crucial. Most of the existing methods learn each local model individually meaning that they only anticipate variations within each class. In this work, we propose to represent local models as Gaussian distributions which are learned simultaneously using the heteroscedastic probabilistic linear discriminant analysis (PLDA). Each gallery video is therefore represented as a collection of such distributions. With the PLDA, not only the within-class variations are estimated during the training, the separability between classes is also maximized leading to an improved discrimination. The heteroscedastic PLDA itself is adapted from the standard PLDA to approximate face appearance manifolds more accurately. Instead of assuming a single global within-class covariance, the heteroscedastic PLDA learns different within-class covariances specific to each local model. In the recognition phase, a probe video is matched against gallery samples through the fusion of point-to-model distances. Experiments on the Honda and MoBo datasets have shown the merit of the proposed method which achieves better performance than the state-of-the-art technique.

Multidisciplinary team approach for a peer-support based cardiac-diabetes self-management program

Background: Cardiac patients with diabetes are at higher readmission rates (22%) compared to only 6% for those patients without diabetes. Evidence shows benefits of peer support and using information technology to improve chronic illness and achieve better health outcomes. However limited evidence suggests that cardiac or diabetes self-management programs incorporating peer supporters (patients with similar conditions) or telephone and text-messaging, have improved health outcomes and reduce health care utilisations. A multidisciplinary research team approach is crucial to accommodate the complex aspects of delivering intervention programs for these at-risk patients. However, challenges such as the inconsistency in significance of key concepts across research fields, as well as practical and operational issues within different contexts are often experienced. Aims: To develop an effective multidisciplinary team approach to deliver a peer support based cardiac-diabetes self-management program incorporating the preparation of lay personnel to provide telephone and text-messaging follow up support. Methods: The approach was used for a multidisciplinary project using randomised controlled trial. Results: The findings from multidisciplinary team approach reveal the feasibility of a Peer support based cardiac-diabetes self-management program.

Applying quality management to project delivery in Hong Kong : A field study of management perceptions

The concept of market-driven rather than product-driven quality management has been given prominence through the report of a recent inquiry into the performance of the Hong Kong construction industry. The report submitted to the Government of Hong Kong in 2001 establishes a new vision of ‘an integrated industry that is capable of continuous improvement towards excellence in the market-driven environment’. Given the current economic downturn, major contractors are facing many challenges to realize this new quality oriented vision. This paper addresses the critical and timely issue of applying quality management to the project delivery process in Hong Kong. The paper attempts to capture and critically examine management perceptions of quality management aspects as applied to a local large-scale road construction project. Based on the analysis of questionnaire feedback and face-to-face interviews, the paper reveals key attributes of a successful application of quality management approaches, and identifies a mechanism for facilitating such implementation.

‘Working with the team’ : an exploratory study of improved type 2 diabetes management in a new model of integrated primary/secondary care

This study aimed to explore how a new model of integrated primary/secondary care for type 2 diabetes management, the Brisbane South Complex Diabetes Service (BSCDS), related to improved diabetes management in a selected group of patients. We used a qualitative research design to obtain detailed accounts from the BSCDS via semi-structured interviews with 10 patients. The interviews were fully transcribed and systematically coded using a form of thematic analysis. Participants’ responses were grouped in relation to: (1) Patient-centred care; (2) Effective multiprofessional teamwork; and (3) Empowering patients. The key features of this integrated primary/secondary care model were accessibility and its delivery within a positive health care environment, clear and supportive interpersonal communication between patients and health care providers, and patients seeing themselves as being part of the team-based care. The BSCDS delivered patient-centred care and achieved patient engagement in ways that may have contributed to improved type 2 diabetes management in these participants.

The great divide : bridging the gap

Learning Objective: To describe a collaborative system of clinical allocations using a dedicated, discipline specific administrative coordinator. Methods: The Clinical Placement Coordinator is the liaison person between the student, the academic staff and the clinical sites, and fills an important role in bridging the gap to enhance the student learning experience. With this in mind the Coordinator is very discipline focused and works closely with the academic staff who coordinate the clinical units within the program. This person is the ‘‘face’’ of QUT to the external stakeholders, and ensures that all parties experience a smooth process. This no mean feat given that there are over 350 students to be placed annually, across 14 separate clinical blocks ranging from 1 to 6 weeks in length at various sites. The processes involved in clinical placement allocation will be presented, and the roles of the staff in facilitating students’ placement preferences and matching with clinical site offers will be described. In many allied health programs in Australia, the clinical placement activity is carried out by an academic member of staff. However, this can result in delays in communications due to other workload requirements such as lecture, tutorial and practical class commitments. Having a dedicated knowledgeable administration officer has resulted in a person being available to take calls from clinical staff, meet with students to discuss allocation needs and ensure that academic staff are consulted if and when necessary. The Clinical Placement Coordinator is very much a part of the course team and attends professional meetings and conferences as an avenue of networking and meeting clinical staff. Results: The success in having a dedicated administrative officer as the Clinical Placement Coordinator acting as the conduit between academic staff and students, and the university and clinical staff has been highly successful to date. This was noted in commendations from the 2010 Course Accreditation Panel Report which stated: ‘‘The very positive perception in the professional community of Ms Margaret McBurney’s effective and efficient organization of student clinical placements. Students and clinical professionals commented favourably on the approachability of staff. There is confidence that program staff will follow up on issues raised urgently in clinical centres.’’

Standing brave in the face of rapid curriculum change : EAL/D teachers speak about critical literacy and its place in senior English teaching

Critical literacy (CL) has been the subject of much debate in the Australian public and education arenas since 2002. Recently, this debate has dissipated as literacy education agendas and attendant policies shift to embrace more hybrid models and approaches to the teaching of senior English. This paper/presentation reports on the views expressed by four teachers of senior English about critical literacy and it’s relevance to students who are from culturally and linguistically diverse backgrounds who are learning English while undertaking senior studies in high school. Teachers’ understandings of critical literacy are important, esp. given the emphasis on Critical and Creative Thinking and Literacy as two of the General Capabilities underpinning the Australian national curriculum. Using critical discourse analysis, data from four specialist ESL teachers in two different schools were analysed for the ways in which these teachers construct critical literacy. While all four teachers indicated significant commitment to critical literacy as an approach to English language teaching, the understandings they articulated varied from providing forms of access to powerful genres, to rationalist approaches to interrogating text, to a type of ‘critical-aesthetic’ analysis of text construction. Implications are also discussed.

Validation and consistency in the application of a trauma team activation system at a level 1 trauma centre

- The RAH was activated over 2500 trauma calls in 2009. This figure is over twice the number of calls put out by similar services. - Many trauma calls (in particular L2 trauma calls) from the existing system do not warrant activation of the trauma team - Sometimes trauma calls are activated for nontrauma reasons (eg rapid access to radiology, departmental pressures etc) - The excess of trauma calls has several deleterious effects particularly on time management for the trauma service staff: ward rounds/tertiary survey rounds, education, quality improvement, research

Liveness detection based on 3D face shape analysis

In recent years face recognition systems have been applied in various useful applications, such as surveillance, access control, criminal investigations, law enforcement, and others. However face biometric systems can be highly vulnerable to spoofing attacks where an impostor tries to bypass the face recognition system using a photo or video sequence. In this paper a novel liveness detection method, based on the 3D structure of the face, is proposed. Processing the 3D curvature of the acquired data, the proposed approach allows a biometric system to distinguish a real face from a photo, increasing the overall performance of the system and reducing its vulnerability. In order to test the real capability of the methodology a 3D face database has been collected simulating spoofing attacks, therefore using photographs instead of real faces. The experimental results show the effectiveness of the proposed approach.

Visual front-end wars : Viola-Jones face detector vs Fourier Lucas-Kanade

The performance of visual speech recognition (VSR) systems are significantly influenced by the accuracy of the visual front-end. The current state-of-the-art VSR systems use off-the-shelf face detectors such as Viola- Jones (VJ) which has limited reliability for changes in illumination and head poses. For a VSR system to perform well under these conditions, an accurate visual front end is required. This is an important problem to be solved in many practical implementations of audio visual speech recognition systems, for example in automotive environments for an efficient human-vehicle computer interface. In this paper, we re-examine the current state-of-the-art VSR by comparing off-the-shelf face detectors with the recently developed Fourier Lucas-Kanade (FLK) image alignment technique. A variety of image alignment and visual speech recognition experiments are performed on a clean dataset as well as with a challenging automotive audio-visual speech dataset. Our results indicate that the FLK image alignment technique can significantly outperform off-the shelf face detectors, but requires frequent fine-tuning.

Human identification at a distance using iris and face

This research has successfully applied super-resolution and multiple modality fusion techniques to address the major challenges of human identification at a distance using face and iris. The outcome of the research is useful for security applications.

Recognising team activities from noisy data

Recently, vision-based systems have been deployed in professional sports to track the ball and players to enhance analysis of matches. Due to their unobtrusive nature, vision-based approaches are preferred to wearable sensors (e.g. GPS or RFID sensors) as it does not require players or balls to be instrumented prior to matches. Unfortunately, in continuous team sports where players need to be tracked continuously over long-periods of time (e.g. 35 minutes in field-hockey or 45 minutes in soccer), current vision-based tracking approaches are not reliable enough to provide fully automatic solutions. As such, human intervention is required to fix-up missed or false detections. However, in instances where a human can not intervene due to the sheer amount of data being generated - this data can not be used due to the missing/noisy data. In this paper, we investigate two representations based on raw player detections (and not tracking) which are immune to missed and false detections. Specifically, we show that both team occupancy maps and centroids can be used to detect team activities, while the occupancy maps can be used to retrieve specific team activities. An evaluation on over 8 hours of field hockey data captured at a recent international tournament demonstrates the validity of the proposed approach.