An interactive and adaptive building layer : strategies for allowing people to become advanced building-users

This paper reports outcomes of a pilot study to develop a conceptual framework to allow people to retrofit a building-layer to gain better control of their own built- environments. The study was initiated by the realisation that discussions surrounding the improvement of building performances tend to be about top-down technological solutions rather than to help and encourage bottom-up involvement of building-users. While users are the ultimate beneficiaries and their feedback is always appreciated, their direct involvements in managing buildings would often be regarded as obstruction or distraction. This is largely because casual interventions by uninformed building-users tend to disrupt the system. Some earlier researches showed however that direct and active participation of users could improve the building performance if appropriate training and/or systems were introduced. We also speculate this in long run would also make the built environment more sustainable. With this in mind, we looked for opportunities to retrofit our own office with an interactive layer to study how we could introduce ad-hoc systems for building-users. The aim of this paper is to describe our vision and initial attempts followed by discussion.

Designing locative and social media technologies for community collaboration and social benefit : PetSearch

The convergence of locative and social media with collaborative interfaces and data visualisation has expanded the potential of online information provision. Offering new ways for communities to share contextually specific information, it presents the opportunity to expand social media’s current focus on micro self-publishing with applications that support communities to actively address areas of local need. This paper details the design and development of a prototype application that illustrates this potential. Entitled PetSearch, it was designed in collaboration with the Animal Welfare League of Queensland to support communities to map and locate lost, found and injured pets, and to build community engagement in animal welfare issues. We argue that, while established approaches to social and locative media provide a useful foundation for designing applications to harness social capital, they must be re-envisaged if they are to effectively facilitate community collaboration. We conclude by arguing that the principles of user engagement and co-operation employed in this project can be extrapolated to other online approaches that aim to facilitate co-operative problem solving for social benefit.

The backfilled GEI : a cross-capture modality gait feature for frontal and side-view gait recognition

In this paper, we propose a novel direction for gait recognition research by proposing a new capture-modality independent, appearance-based feature which we call the Back-filled Gait Energy Image (BGEI). It can can be constructed from both frontal depth images, as well as the more commonly used side-view silhouettes, allowing the feature to be applied across these two differing capturing systems using the same enrolled database. To evaluate this new feature, a frontally captured depth-based gait dataset was created containing 37 unique subjects, a subset of which also contained sequences captured from the side. The results demonstrate that the BGEI can effectively be used to identify subjects through their gait across these two differing input devices, achieving rank-1 match rate of 100%, in our experiments. We also compare the BGEI against the GEI and GEV in their respective domains, using the CASIA dataset and our depth dataset, showing that it compares favourably against them. The experiments conducted were performed using a sparse representation based classifier with a locally discriminating input feature space, which show significant improvement in performance over other classifiers used in gait recognition literature, achieving state of the art results with the GEI on the CASIA dataset.

Mobile Q&A for enhancing online discussion

In this study, we explore the design and evaluation of a mobile online discussion system for motivating students to share their learning experiences. The system supports interaction with peers and academic staff anytime and anywhere using mobile devices. The application introduces a set of features that enables customisation for different purposes. This paper describes the application and explains the motivation for developing the application. We describe the methods and results of a case study that explores usage of the application among a small group of localised participants. Finally, we discuss the implications of this work and outline future areas of research and development.

Anomalous event detection using a semi-two dimensional hidden Markov model

The rapid increase in the deployment of CCTV systems has led to a greater demand for algorithms that are able to process incoming video feeds. These algorithms are designed to extract information of interest for human operators. During the past several years, there has been a large effort to detect abnormal activities through computer vision techniques. Typically, the problem is formulated as a novelty detection task where the system is trained on normal data and is required to detect events which do not fit the learned `normal' model. Many researchers have tried various sets of features to train different learning models to detect abnormal behaviour in video footage. In this work we propose using a Semi-2D Hidden Markov Model (HMM) to model the normal activities of people. The outliers of the model with insufficient likelihood are identified as abnormal activities. Our Semi-2D HMM is designed to model both the temporal and spatial causalities of the crowd behaviour by assuming the current state of the Hidden Markov Model depends not only on the previous state in the temporal direction, but also on the previous states of the adjacent spatial locations. Two different HMMs are trained to model both the vertical and horizontal spatial causal information. Location features, flow features and optical flow textures are used as the features for the model. The proposed approach is evaluated using the publicly available UCSD datasets and we demonstrate improved performance compared to other state of the art methods.

Spatio temporal feature evaluation for action recognition

Spatio-Temporal interest points are the most popular feature representation in the field of action recognition. A variety of methods have been proposed to detect and describe local patches in video with several techniques reporting state of the art performance for action recognition. However, the reported results are obtained under different experimental settings with different datasets, making it difficult to compare the various approaches. As a result of this, we seek to comprehensively evaluate state of the art spatio- temporal features under a common evaluation framework with popular benchmark datasets (KTH, Weizmann) and more challenging datasets such as Hollywood2. The purpose of this work is to provide guidance for researchers, when selecting features for different applications with different environmental conditions. In this work we evaluate four popular descriptors (HOG, HOF, HOG/HOF, HOG3D) using a popular bag of visual features representation, and Support Vector Machines (SVM)for classification. Moreover, we provide an in-depth analysis of local feature descriptors and optimize the codebook sizes for different datasets with different descriptors. In this paper, we demonstrate that motion based features offer better performance than those that rely solely on spatial information, while features that combine both types of data are more consistent across a variety of conditions, but typically require a larger codebook for optimal performance.

Deformable face ensemble alignment with robust grouped-L1 anchors

Many methods exist at the moment for deformable face fitting. A drawback to nearly all these approaches is that they are (i) noisy in terms of landmark positions, and (ii) the noise is biased across frames (i.e. the misalignment is toward common directions across all frames). In this paper we propose a grouped $\mathcal{L}1$-norm anchored method for simultaneously aligning an ensemble of deformable face images stemming from the same subject, given noisy heterogeneous landmark estimates. Impressive alignment performance improvement and refinement is obtained using very weak initialization as "anchors".

Efficient real-time face detection for high resolution surveillance applications

This paper presents an efficient face detection method suitable for real-time surveillance applications. Improved efficiency is achieved by constraining the search window of an AdaBoost face detector to pre-selected regions. Firstly, the proposed method takes a sparse grid of sample pixels from the image to reduce whole image scan time. A fusion of foreground segmentation and skin colour segmentation is then used to select candidate face regions. Finally, a classifier-based face detector is applied only to selected regions to verify the presence of a face (the Viola-Jones detector is used in this paper). The proposed system is evaluated using 640 x 480 pixels test images and compared with other relevant methods. Experimental results show that the proposed method reduces the detection time to 42 ms, where the Viola-Jones detector alone requires 565 ms (on a desktop processor). This improvement makes the face detector suitable for real-time applications. Furthermore, the proposed method requires 50% of the computation time of the best competing method, while reducing the false positive rate by 3.2% and maintaining the same hit rate.

Accelerated professional development and peer consultation : two strategies for continuing professional education for nurses

A comparison was made of accelerated professional development (APD) for nurses (n=64), involving peer consultation and reflective practice, and peer consultation alone (n=30). Although APD participants had a higher completion rate, improvements in caregiver behaviors and work environment were not significantly different.

Perceived social support and community adaptation in schizophrenia

Prompted by the continuing transition to community care, mental health nurses are considering the role of social support in community adaptation. This article demonstrates the importance of distinguishing between kinds of social support and presents findings from the first round data of a longitudinal study of community adaptation in 156 people with schizophrenia conducted in Brisbane, Australia. All clients were interviewed using the relevant subscales of the Diagnostic Interview Schedule to confirm a primary diagnosis of schizophrenia. The study set out to investigate the relationship between community adaptation and social support. Community adaptation was measured with the Brief Psychiatric Rating Scale (BPRS), the Life Skills Profile (LSP) and measures of dissatisfaction with life and problems in daily living developed by the authors. Social support was measured with the Arizona Social Support Interview Schedule (ASSIS). The BPRS and ASSIS were incorporated into a client interview conducted by trained interviewers. The LSP was completed on each client by an informal carer (parent, relative or friend) or a professional carer (case manager or other health professional) nominated by the client. Hierarchical regression analysis was used to examine the relationship between community adaptation and four sets of social support variables. Given the order in which variables were entered in regression equations, a set of perceived social support variables was found to account for the largest unique variance of four measures of community adaptation in 96 people with schizophrenia for whom complete data are available from the first round of the three-wave longitudinal study. A set of the subjective experiences of the clients accounted for the largest unique variance in measures of symptomatology, life skills, dissatisfaction with life, and problems in daily living. Sets of community support, household support and functional variables accounted for less variance. Implications for mental health nursing practice are considered.

Perceptions of stressors and reported coping strategies in nurses caring for residents with Alzheimer's disease in a dementia unit

A study was undertaken on the perceptions of stressors and coping behaviours in a group of nurses caring for residents with Alzheimer's disease in a dementia unit. The purpose of this paper is to report on the preliminary findings of the study. Repertory grid data were used to explore how nurses perceive residents, the stressors nurses experience in their work, and the coping strategies nurses use when caring for residents. The nurses identified 92 sources of stress, 683 coping behaviours and 708 coping strategies. Analyses of selected repertory grid data are presented and the stressors reported by the nurses are summarized. The coping strategies the nurses report using are classified into categories of adaptive and maladaptive responses to stress. In addition, the nursing implications of the coping strategies used by the nurses are also considered.

On the statistical determination of optimal camera configurations in large scale surveillance networks

The selection of optimal camera configurations (camera locations, orientations etc.) for multi-camera networks remains an unsolved problem. Previous approaches largely focus on proposing various objective functions to achieve different tasks. Most of them, however, do not generalize well to large scale networks. To tackle this, we introduce a statistical formulation of the optimal selection of camera configurations as well as propose a Trans-Dimensional Simulated Annealing (TDSA) algorithm to effectively solve the problem. We compare our approach with a state-of-the-art method based on Binary Integer Programming (BIP) and show that our approach offers similar performance on small scale problems. However, we also demonstrate the capability of our approach in dealing with large scale problems and show that our approach produces better results than 2 alternative heuristics designed to deal with the scalability issue of BIP.