Generative models for automatic recognition of human daily activities from a single triaxial accelerometer

In this work, we compare two generative models including Gaussian Mixture Model (GMM) and Hidden Markov Model (HMM) with Support Vector Machine (SVM) classifier for the recognition of six human daily activity (i.e., standing, walking, running, jumping, falling, sitting-down) from a single waist-worn tri-axial accelerometer signals through 4-fold cross-validation and testing on a total of thirteen subjects, achieving an average recognition accuracy of 96.43% and 98.21% in the first experiment and 95.51% and 98.72% in the second, respectively. The results demonstrate that both HMM and GMM are not only able to learn but also capable of generalization while the former outperformed the latter in the recognition of daily activities from a single waist worn tri-axial accelerometer. In addition, these two generative models enable the assessment of human activities based on acceleration signals with varying lengths.

Structural understanding from note-taking within video lectures

 Note-taking during all kinds of lectures is a standard and easy technique for learners of all ages to self-document their thought during learning. Based on a metacognitive rationale, this study investigates the effect of note-taking within different kinds of video-lectures – text-driven presentations versus graphical presentations. The availability of note-taking is experimentally controlled for 54 undergraduate students, and the quality of the nodes is then projected to the learning outcome as compared to the content of the lectures. Our results indicate little direct impact of the note quality, and contra-intuitively, not taking notes helped learners with their knowledge structure. Our study helps to understand the limits of note-taking during learning and with a broader theoretical understanding of idiosyncratic externalization.

Managing the risks from new and emerging infectious disease: the 'one health' paradigm

The global risk from new and emerging infectious diseases continues to grow with recognition that, for the most part, the pathogens involved emerge from animals to infect humans. Recognizing the complexity of these interactions and the need for a strong interdisciplinary approach to effectively manage these risks, new partnerships are being forged under the general umbrella of 'one health'. Involving human health, animal health, and environmental health exponents, solutions are sought for how to prevent as well as respond to the threats. But is this approach working? Whilst a number of key meetings continue to be held under the One Health umbrella, are we really seeing measureable progress in risk prevention and mitigation? Focusing research on the drivers for emergence, on modeling the risks, on improved diagnostics, and on targeted vaccines could considerably enhance our ability to prevent and respond. Ensuring the uptake and applications of new diagnostics and vaccines will be the key to prevention and response, but achieving this will require policies that drive further the One Health collaborations. Such policies should ensure that scant available resources are targeted toward the identified outcomes through research delivery and uptake, and that we genuinely work as "one world" in tackling the very real risks we face

Intelligent facial emotion recognition using a layered encoding cascade optimization model

In this research, we propose a facial expression recognition system with a layered encoding cascade optimization model. Since generating an effective facial representation is a vital step to the success of facial emotion recognition, a modified Local Gabor Binary Pattern operator is first employed to derive a refined initial face representation and we then propose two evolutionary algorithms for feature optimization including (i) direct similarity and (ii) Pareto-based feature selection, under the layered cascade model. The direct similarity feature selection considers characteristics within the same emotion category that give the minimum within-class variation while the Pareto-based feature optimization focuses on features that best represent each expression category and at the same time provide the most distinctions to other expressions. Both a neural network and an ensemble classifier with weighted majority vote are implemented for the recognition of seven expressions based on the selected optimized features. The ensemble model also automatically updates itself with the most recent concepts in the data. Evaluated with the Cohn-Kanade database, our system achieves the best accuracies when the ensemble classifier is applied, and outperforms other research reported in the literature with 96.8% for direct similarity based optimization and 97.4% for the Pareto-based feature selection. Cross-database evaluation with frontal images from the MMI database has also been conducted to further prove system efficiency where it achieves 97.5% for Pareto-based approach and 90.7% for direct similarity-based feature selection and outperforms related research for MMI. When evaluated with 90° side-view images extracted from the videos of the MMI database, the system achieves superior performances with >80% accuracies for both optimization algorithms. Experiments with other weighting and meta-learning combination methods for the construction of ensembles are also explored with our proposed ensemble showing great adpativity to new test data stream for cross-database evaluation. In future work, we aim to incorporate other filtering techniques and evolutionary algorithms into the optimization models to further enhance the recognition performance.

Learning clinical skills during bedside teaching encounters in general practice: a video-observational study with insights from activity theory

Purpose – This paper aims to explore how opportunities for learning clinical skills are negotiated within bedside teaching encounters (BTEs). Bedside teaching, within the medical workplace, is considered essential for helping students develop their clinical skills. Design/methodology/approach – An audio and/or video observational study examining seven general practice BTEs was undertaken. Additionally, audio-recorded, semi-structured interviews were conducted with participants. All data were transcribed. Data analysis comprised Framework Analysis informed by Engeström’s Cultural Historical Activity Theory. Findings – BTEs can be seen to offer many learning opportunities for clinical skills. Learning opportunities are negotiated by the participants in each BTE, with patients, doctors and students playing different roles within and across the BTEs. Tensions emerged within and between nodes and across two activity systems. Research limitations/implications – Negotiation of clinical skills learning opportunities involved shifts in the use of artefacts, roles and rules of participation, which were tacit, dynamic and changing. That learning is constituted in the activity implies that students and teachers cannot be fully prepared for BTEs due to their emergent properties. Engaging doctors, students and patients in refecting on tensions experienced and the factors that infuence judgements in BTEs may be a useful frst step in helping them better manage the roles and responsibilities therein. Originality/value – The paper makes an original contribution to the literature by highlighting the tensions inherent in BTEs and how the negotiation of roles and division of labour whilst juggling two interacting activity systems create or inhibit opportunities for clinical skills learning. This has signifcant implications for how BTEs are conceptualised.

The effect of active video games by ethnicity, sex and fitness: subgroup analysis from a randomised controlled trial

BACKGROUND: The prevention and treatment of childhood obesity is a key public health challenge. However, certain groups within populations have markedly different risk profiles for obesity and related health behaviours. Well-designed subgroup analysis can identify potential differential effects of obesity interventions, which may be important for reducing health inequalities. The study aim was to evaluate the consistency of the effects of active video games across important subgroups in a randomised controlled trial (RCT).

FINDINGS: A two-arm, parallel RCT was conducted in overweight or obese children (n=322; aged 10-14 years) to determine the effect of active video games on body composition. Statistically significant overall treatment effects favouring the intervention group were found for body mass index, body mass index z-score and percentage body fat at 24 weeks. For these outcomes, pre-specified subgroup analyses were conducted among important baseline demographic (ethnicity, sex) and prognostic (cardiovascular fitness) groups. No statistically significant interaction effects were found between the treatment and subgroup terms in the main regression model (p=0.36 to 0.93), indicating a consistent treatment effect across these groups.

CONCLUSIONS: Preliminary evidence suggests an active video games intervention had a consistent positive effect on body composition among important subgroups. This may support the use of these games as a pragmatic public health intervention to displace sedentary behaviour with physical activity in young people.