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.

Common-sense reasoning for human action recognition

This paper presents a novel method that leverages reasoning capabilities in a computer vision system dedicated to human action recognition. The proposed methodology is decomposed into two stages. First, a machine learning based algorithm - known as bag of words - gives a first estimate of action classification from video sequences, by performing an image feature analysis. Those results are afterward passed to a common-sense reasoning system, which analyses, selects and corrects the initial estimation yielded by the machine learning algorithm. This second stage resorts to the knowledge implicit in the rationality that motivates human behaviour. Experiments are performed in realistic conditions, where poor recognition rates by the machine learning techniques are significantly improved by the second stage in which common-sense knowledge and reasoning capabilities have been leveraged. This demonstrates the value of integrating common-sense capabilities into a computer vision pipeline. © 2012 Elsevier B.V. All rights reserved.

The Developing Habitus of the Anti-Social Behaviour Practitioner: From Expansion in Years of Plenty to Surviving the Age of Austerity

Specialist anti-social behaviour units are common within social housing providers, with many established in response to the policies of the New Labour governments of 1997–2010. These units now find themselves operating in a different political and financial environment. Following the English riots of 2011, the Coalition government, whilst imposing budgetary cuts across the public sector, called on social housing providers to intensify their role in tackling disorder. This article explores the habitus or working cultures within anti-social behaviour units post-New Labour. It does so through empirical research conducted in the aftermath of the English riots. The research finds that practitioners view their work as a core function of social housing provision. They have developed an understanding of human behaviour, which crosses the criminal and social policy fields with a wide skillset to match. A number of factors including national policy, community expectations, and multi-partnership engagement influence their dynamic working culture.

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.

Towards Educational Inclusion in a Transforming Society: Some Lessons from Community Relations and Special Needs Education in Northern Ireland

This paper takes an original approach to an important aspect of educational research and its role in transforming societies, namely that of educational inclusion. It brings together what some might consider two rather strange bedfellows i.e. community relations and special needs education. It also draws upon new tools for theorising educational inclusion, which give a central role to the discursive nature of human conduct and which take a view of human behaviour as socially embedded and meaningful.

“ Humanitarian Competition: An Intellectual History in Perspective”.

Competition has become the mantra for survival in a globalised world where meaningful existence is fraught with demands, which go beyond the material to the immaterial ‘byte-size’. This has been exemplified by our obsession with illusions of immediate fame and fortune. This paper contextualises and extends the debate about the role of competition in general. Here the four major myths of competition are explored and deconstructed, from a Darwinian perspective to a more demonstrably engaged perspective on ‘capabilities’ (Sen, 1999). The second section deals particularly with the key debates, theories that influenced Tsunesaburo Makiguchi’s seminal ideas of ‘humanitarian competition’ in 1903. The final part of the paper seeks to decipher the relevance of the key ideas of ‘humanitarian competition’ as proposed by Dr Daisaku Ikeda in his 2009 peace proposal. Here the transition from competition to cooperation is explored by tying together the key principles of global coexistence enunciated by both Makiguchi and Ikeda in the context of expanding spiritual influence by the forces of culture, morality and virtue. To engage with humanitarian competition calls for a major shift from hard power to soft power, from subordination to one of engagement. In other words this concept advances the Buddhist principle of peaceful co-existence, or Panchsheel, as a norm for human behaviour of love, kindness, sacrifice and peace through cooperation, where equality and mutual benefit are critical. Humanitarian competition provides the essential framework to establish a new world order as highlighted by both Makiguchi and Ikeda.

The emergence of bone technologies at the end of the pleistocene in Southeast Asia:Regional and evolutionary implications

For many decades Palaeolithic research viewed the development of early modern human behaviour as largely one of progress down a path towards the modernity of the present. The European Palaeolithic sequence the most extensively studied was for a long time the yard-stick against which records from other regions were judged. Recent work undertaken in Africa and increasingly Asia, however, now suggests that the European evidence may tell a story that is more parochial and less universal than previously thought. While tracking developments at the large scale (the grand narrative) remains important, there is growing appreciation that to achieve a comprehensive understanding of human behavioural evolution requires an archaeologically regional perspective to balance this. One of the apparent markers of human modernity that has been sought in the global Palaeolithic record, prompted by finds in the European sequence, is innovation in bonebased technologies. As one step in the process of re-evaluating and contextualizing such innovations, in this article we explore the role of prehistoric bone technologies within the Southeast Asian sequence, where they have at least comparable antiquity to Europe and other parts of Asia. We observe a shift in the technological usage of bone from a minor component to a medium of choice during the second half of the Last Termination and into the Holocene. We suggest that this is consistent with it becoming a focus of the kinds of inventive behaviour demanded of foraging communities as they adapted to the far-reaching environmental and demographic changes that were reshaping this region at that time. This record represents one small element of a much wider, much longerterm adaptive process, which we would argue is not confined to the earliest instances of a particular technology or behaviour, but which forms part of an on-going story of our behavioural evolution. © 2012 The McDonald Institute for Archaeological Research.

Social housing tenants, Climate Change and sustainable living: A study of awareness, behaviours and willingness to adapt

Despite a focus in the UK on providing sustainable housing in recent years, it is unlikely that targets set to reduce resource consumption in housing will be achieved without a greater focus on human behaviour. It is necessary to understand the actions of people occupying dwellings, as it is invariably the occupants rather than the buildings that decided whether or not to consume resources. In this paper the authors present a pilot study where 53 social housing tenant households in Northern Ireland were interviewed to ascertain their perceptions of Climate Change, their current behaviours and their willingness to reduce energy and water consumption in the home. The intention was to explore links between perceptions and reported behaviour as well as perceptions and willingness to reduce resource consumption. Results show that 77% of tenants believed Climate Change to be an important issue; 57% accepted that it is up to the individual to take responsibility for tackling Climate Change; and demonstrated a strong desire to make a difference to reduce their impact. The researchers identified both passive (devices) and active (behaviours) resource savings currently in place and established where further resource reduction was feasible based on tenants' willingness to alter their behaviours.