Human behaviour recognition in data-scarce domains

This paper presents the novel theory for performing multi-agent activity recognition without requiring large training corpora. The reduced need for data means that robust probabilistic recognition can be performed within domains where annotated datasets are traditionally unavailable. Complex human activities are composed from sequences of underlying primitive activities. We do not assume that the exact temporal ordering of primitives is necessary, so can represent complex activity using an unordered bag. Our three-tier architecture comprises low-level video tracking, event analysis and high-level inference. High-level inference is performed using a new, cascading extension of the Rao–Blackwellised Particle Filter. Simulated annealing is used to identify pairs of agents involved in multi-agent activity. We validate our framework using the benchmarked PETS 2006 video surveillance dataset and our own sequences, and achieve a mean recognition F-Score of 0.82. Our approach achieves a mean improvement of 17% over a Hidden Markov Model baseline.

Hierarchical Task Network Planning with Common-Sense Reasoning for Multiple-People Behaviour Analysis

Safety on public transport is a major concern for the relevant authorities. We
address this issue by proposing an automated surveillance platform which combines data from video, infrared and pressure sensors. Data homogenisation and integration is achieved by a distributed architecture based on communication middleware that resolves interconnection issues, thereby enabling data modelling. A common-sense knowledge base models and encodes knowledge about public-transport platforms and the actions and activities of passengers. Trajectory data from passengers is modelled as a time-series of human activities. Common-sense knowledge and rules are then applied to detect inconsistencies or errors in the data interpretation. Lastly, the rationality that characterises human behaviour is also captured here through a bottom-up Hierarchical Task Network planner that, along with common-sense, corrects misinterpretations to explain passenger behaviour. The system is validated using a simulated bus saloon scenario as a case-study. Eighteen video sequences were recorded with up to six passengers. Four metrics were used to evaluate performance. The system, with an accuracy greater than 90% for each of the four metrics, was found to outperform a rule-base system and a system containing planning alone.

Contextual anomaly detection in crowded surveillance scenes

This work addresses the problem of detecting human behavioural anomalies in crowded surveillance environments. We focus in particular on the problem of detecting subtle anomalies in a behaviourally heterogeneous surveillance scene. To reach this goal we implement a novel unsupervised context-aware process. We propose and evaluate a method of utilising social context and scene context to improve behaviour analysis. We find that in a crowded scene the application of Mutual Information based social context permits the ability to prevent self-justifying groups and propagate anomalies in a social network, granting a greater anomaly detection capability. Scene context uniformly improves the detection of anomalies in both datasets. The strength of our contextual features is demonstrated by the detection of subtly abnormal behaviours, which otherwise remain indistinguishable from normal behaviour.

Applied behavior analysis: What do teachers of students with autism spectrum disorder know?

With rising numbers of school-aged children with autism educated in mainstream classroomsand applied behavior analysis (ABA) considered the basis of best practice, teachers’ knowledgein this field has become a key concern for inclusion. Self-reported knowledge of ABA of specialneeds teachers (n=165) was measured and compared to their actual knowledge of ABAdemonstrated in accurate responses to a multiple-choice test. Findings reported here show thatteachers’ self-perceived knowledge exceeded actual knowledge and that actual knowledge ofABA was not

Combining histology, stable isotope analysis and ZooMS collagen fingerprinting to investigate the taphonomic history and dietary behaviour of extinct giant tortoises from the Mare aux Songes deposit on Mauritius

Taphonomic research of bones can provide additional insight into a site's formation and development, the burial environment and ongoing post-mortem processes. A total of 30 tortoise (Cylindraspis) femur bone samples from the Mare aux Songes site (Mauritius)were studied histologically, assessing parameters such as presence and type of microbial alteration, inclusions, staining/infiltrations, the degree of microcracking and birefringence. The absence of microbial attack in the 4200 year old Mare aux Songes bones suggests the animals rapidly entered the soil whole-bodied and were sealed anoxically, although they suffered frombiological and chemical degradation (i.e. pyrite formation/oxidation, mineral dissolution and staining) related to changes in the site's hydrology. Additionally, carbon and nitrogen stable isotopeswere analysed to obtain information on the animals' feeding behaviour. The results show narrowly distributed δ13C ratios, indicating a terrestrial C3 plant-based diet, combined with a wide range in δ15N ratios. This is most likely related to the tortoises' drought-adaptive ability to change their metabolic processes, which can affect the δ15N ratios. Furthermore, ZooMS collagen fingerprinting analysis successfully identified two tortoise species (C. triserrata and C. inepta) in the bone assemblage,which,when combined with stable isotope data, revealed significantly different δ15N ratios between the two tortoise species. As climatic changes around this period resulted in increased aridity in the Mascarene Islands, this could explain the extremely elevated δ15N ratio in our dataset. The endemic fauna was able to endure the climatic changes 4200 years ago, although human arrival in the 17th century changed the original habitat to such an extent that it resulted in the extinction of several species. Fortunately we are still able to study these extinct tortoises due to the beneficial conditions of their burial environment, resulting in excellent bone preservation.

Metabolic signatures of Huntington's disease (HD): 1H NMR analysis of the polar metabolome in post mortem human brain

Huntington’s disease (HD) is an autosomal neurodegenerative disorder affecting approximately 5-10 persons per 100,000 worldwide. The pathophysiology of HD is not fully understood but the age of onset is known to be highly dependent on the number of CAG triplet repeats in the huntingtin gene. Using 1H NMR spectroscopy this study biochemically profiled 39 brain metabolites in post-mortem striatum (n=14) and frontal lobe (n=14) from HD sufferers and controls (n=28). Striatum metabolites were more perturbed with 15 significantly affected in HD cases, compared with only 4 in frontal lobe (P<0.05; q<0.3). The metabolite which changed most overall was urea which decreased 3.25-fold in striatum (P<0.01). Four metabolites were consistently affected in both brain regions. These included the neurotransmitter precursors tyrosine and L-phenylalanine which were significantly depleted by 1.55-1.58-fold and 1.48-1.54-fold in striatum and frontal lobe, respectively (P=0.02-0.03). They also included L-leucine which was reduced 1.54-1.69-fold (P=0.04-0.09) and myo-inositol which was increased 1.26-1.37-fold (P<0.01). Logistic regression analyses performed with MetaboAnalyst demonstrated that data obtained from striatum produced models which were profoundly more sensitive and specific than those produced from frontal lobe. The brain metabolite changes uncovered in this first 1H NMR investigation of human HD offer new insights into the disease pathophysiology. Further investigations of striatal metabolite disturbances are clearly warranted.

Ethical reasoning through simulation: a phenomenological analysis of student experience

Background
Medical students transitioning into professional practice feel underprepared to deal with the emotional complexities of real-life ethical situations. Simulation-based learning (SBL) may provide a safe environment for students to probe the boundaries of ethical encounters. Published studies of ethics simulation have not generated sufficiently deep accounts of student experience to inform pedagogy. The aim of this study was to understand students’ lived experiences as they engaged with the emotional challenges of managing clinical ethical dilemmas within a SBL environment.

Methods
This qualitative study was underpinned by an interpretivist epistemology. Eight senior medical students participated in an interprofessional ward-based SBL activity incorporating a series of ethically challenging encounters. Each student wore digital video glasses to capture point-of-view (PoV) film footage. Students were interviewed immediately after the simulation and the PoV footage played back to them. Interviews were transcribed verbatim. An interpretative phenomenological approach, using an established template analysis approach, was used to iteratively analyse the data.

Results
Four main themes emerged from the analysis: (1) ‘Authentic on all levels?’, (2)‘Letting the emotions flow’, (3) ‘Ethical alarm bells’ and (4) ‘Voices of children and ghosts’. Students recognised many explicit ethical dilemmas during the SBL activity but had difficulty navigating more subtle ethical and professional boundaries. In emotionally complex situations, instances of moral compromise were observed (such as telling an untruth). Some participants felt unable to raise concerns or challenge unethical behaviour within the scenarios due to prior negative undergraduate experiences.

Conclusions
This study provided deep insights into medical students’ immersive and embodied experiences of ethical reasoning during an authentic SBL activity. By layering on the human dimensions of ethical decision-making, students can understand their personal responses to emotion, complexity and interprofessional working. This could assist them in framing and observing appropriate ethical and professional boundaries and help smooth the transition into clinical practice.

Reducing child conduct disordered behaviour and improving parent mental health in disadvantaged families: a 12 month follow-up and cost analysis of a parenting intervention

The effectiveness of the Incredible Years Basic parent programme (IYBP) in reducing child conduct problems and improving parent competencies and mental health was examined in a 12-month follow-up. Pre- to post-intervention service use and related costs were also analysed. A total of 103 families and their children (aged 32–88 months), who previously participated in a randomised controlled trial of the IYBP, took part in a 12-month follow-up assessment. Child and parent behaviour and well-being were measured using psychometric and observational measures. An intention-to-treat analysis was carried out using a one-way repeated measures ANOVA. Pairwise comparisons were subsequently conducted to determine whether treatment outcomes were sustained 1 year post-baseline assessment. Results indicate that post-intervention improvements in child conduct problems, parenting behaviour and parental mental health were maintained. Service use and associated costs continued to decline. The results indicate that parent-focused interventions, implemented in the early years, can result in improvements in child and parent behaviour and well-being 12 months later. A reduced reliance on formal services is also indicated.

Exploring the effects of a universal classroom management training programme on teacher and child behaviour: a group randomised controlled trial and cost analysis

Teachers frequently struggle to cope with conduct problems in the classroom. The aim of this study was to assess the effectiveness of the Incredible Years Teacher Classroom Management Training Programme for improving teacher competencies and child adjustment. The study involved a group randomised controlled trial which included 22 teachers and 217 children (102 boys and 115 girls). The average age of children included in the study was 5.3 years (standard deviation = 0.89). Teachers were randomly allocated to an intervention group (n = 11 teachers; 110 children) or a waiting-list control group (n = 11; 107 children). The sample also included 63 ‘high-risk’ children (33 intervention; 30 control), who scored above the cut-off (>12) on the Strengths and Difficulties Questionnaire for abnormal socioemotional and behavioural difficulties. Teacher and child behaviours were assessed at baseline and 6 months later using psychometric and observational measures. Programme delivery costs were also analysed. Results showed positive changes in teachers’ self-reported use of positive classroom management strategies (effect size = 0.56), as well as negative classroom management strategies (effect size = −0.43). Teacher reports also highlight improvements in the classroom behaviour of the high-risk group of children, while the estimated cost of delivering the Incredible Years Teacher Classroom Management Training Programme was modest. However, analyses of teacher and child observations were largely non-significant. A need for further research exploring the effectiveness and cost-effectiveness of the Incredible Years Teacher Classroom Management Training Programme is indicated.