Robust recognition of human behaviour in challenging environments

Novel techniques have been developed for the automatic recognition of human behaviour in challenging environments using information from visual and infra-red camera feeds. The techniques have been applied to two interesting scenarios: Recognise drivers' speech using lip movements and recognising audience behaviour, while watching a movie, using facial features and body movements. Outcome of the research in these two areas will be useful in the improving the performance of voice recognition in automobiles for voice based control and for obtaining accurate movie interest ratings based on live audience response analysis.

Information security culture : a behaviour compliance conceptual framework

Understanding the complex dynamic and uncertain characteristics of organisational employees who perform authorised or unauthorised information security activities is deemed to be a very important and challenging task. This paper presents a conceptual framework for classifying and organising the characteristics of organisational subjects involved in these information security practices. Our framework expands the traditional Human Behaviour and the Social Environment perspectives used in social work by identifying how knowledge, skills and individual preferences work to influence individual and group practices with respect to information security management. The classification of concepts and characteristics in the framework arises from a review of recent literature and is underpinned by theoretical models that explain these concepts and characteristics. Further, based upon an exploratory study of three case organisations in Saudi Arabia involving extensive interviews with senior managers, department managers, IT managers, information security officers, and IT staff; this article describes observed information security practices and identifies several factors which appear to be particularly important in influencing information security behaviour. These factors include values associated with national and organisational culture and how they manifest in practice, and activities related to information security management.

Robust suspicious behaviour detection for smart surveillance systems

Video surveillance technology, based on Closed Circuit Television (CCTV) cameras, is one of the fastest growing markets in the field of security technologies. However, the existing video surveillance systems are still not at a stage where they can be used for crime prevention. The systems rely heavily on human observers and are therefore limited by factors such as fatigue and monitoring capabilities over long periods of time. To overcome this limitation, it is necessary to have “intelligent” processes which are able to highlight the salient data and filter out normal conditions that do not pose a threat to security. In order to create such intelligent systems, an understanding of human behaviour, specifically, suspicious behaviour is required. One of the challenges in achieving this is that human behaviour can only be understood correctly in the context in which it appears. Although context has been exploited in the general computer vision domain, it has not been widely used in the automatic suspicious behaviour detection domain. So, it is essential that context has to be formulated, stored and used by the system in order to understand human behaviour. Finally, since surveillance systems could be modeled as largescale data stream systems, it is difficult to have a complete knowledge base. In this case, the systems need to not only continuously update their knowledge but also be able to retrieve the extracted information which is related to the given context. To address these issues, a context-based approach for detecting suspicious behaviour is proposed. In this approach, contextual information is exploited in order to make a better detection. The proposed approach utilises a data stream clustering algorithm in order to discover the behaviour classes and their frequency of occurrences from the incoming behaviour instances. Contextual information is then used in addition to the above information to detect suspicious behaviour. The proposed approach is able to detect observed, unobserved and contextual suspicious behaviour. Two case studies using video feeds taken from CAVIAR dataset and Z-block building, Queensland University of Technology are presented in order to test the proposed approach. From these experiments, it is shown that by using information about context, the proposed system is able to make a more accurate detection, especially those behaviours which are only suspicious in some contexts while being normal in the others. Moreover, this information give critical feedback to the system designers to refine the system. Finally, the proposed modified Clustream algorithm enables the system to both continuously update the system’s knowledge and to effectively retrieve the information learned in a given context. The outcomes from this research are: (a) A context-based framework for automatic detecting suspicious behaviour which can be used by an intelligent video surveillance in making decisions; (b) A modified Clustream data stream clustering algorithm which continuously updates the system knowledge and is able to retrieve contextually related information effectively; and (c) An update-describe approach which extends the capability of the existing human local motion features called interest points based features to the data stream environment.

A suspicious behaviour detection using a context space model for smart surveillance systems

Video surveillance systems using Closed Circuit Television (CCTV) cameras, is one of the fastest growing areas in the field of security technologies. However, the existing video surveillance systems are still not at a stage where they can be used for crime prevention. The systems rely heavily on human observers and are therefore limited by factors such as fatigue and monitoring capabilities over long periods of time. This work attempts to address these problems by proposing an automatic suspicious behaviour detection which utilises contextual information. The utilisation of contextual information is done via three main components: a context space model, a data stream clustering algorithm, and an inference algorithm. The utilisation of contextual information is still limited in the domain of suspicious behaviour detection. Furthermore, it is nearly impossible to correctly understand human behaviour without considering the context where it is observed. This work presents experiments using video feeds taken from CAVIAR dataset and a camera mounted on one of the buildings Z-Block) at the Queensland University of Technology, Australia. From these experiments, it is shown that by exploiting contextual information, the proposed system is able to make more accurate detections, especially of those behaviours which are only suspicious in some contexts while being normal in the others. Moreover, this information gives critical feedback to the system designers to refine the system.

Digital human modelling for vehicle design and manufacturing

Digital human modelling (DHM) has today matured from research into industrial application. In the automotive domain, DHM has become a commonly used tool in virtual prototyping and human-centred product design. While this generation of DHM supports the ergonomic evaluation of new vehicle design during early design stages of the product, by modelling anthropometry, posture, motion or predicting discomfort, the future of DHM will be dominated by CAE methods, realistic 3D design, and musculoskeletal and soft tissue modelling down to the micro-scale of molecular activity within single muscle fibres. As a driving force for DHM development, the automotive industry has traditionally used human models in the manufacturing sector (production ergonomics, e.g. assembly) and the engineering sector (product ergonomics, e.g. safety, packaging). In product ergonomics applications, DHM share many common characteristics, creating a unique subset of DHM. These models are optimised for a seated posture, interface to a vehicle seat through standardised methods and provide linkages to vehicle controls. As a tool, they need to interface with other analytic instruments and integrate into complex CAD/CAE environments. Important aspects of current DHM research are functional analysis, model integration and task simulation. Digital (virtual, analytic) prototypes or digital mock-ups (DMU) provide expanded support for testing and verification and consider task-dependent performance and motion. Beyond rigid body mechanics, soft tissue modelling is evolving to become standard in future DHM. When addressing advanced issues beyond the physical domain, for example anthropometry and biomechanics, modelling of human behaviours and skills is also integrated into DHM. Latest developments include a more comprehensive approach through implementing perceptual, cognitive and performance models, representing human behaviour on a non-physiologic level. Through integration of algorithms from the artificial intelligence domain, a vision of the virtual human is emerging.

A Context Space Model for Detecting Anomalous Behaviour in Video Surveillance

Having a good automatic anomalous human behaviour detection is one of the goals of smart surveillance systems’ domain of research. The automatic detection addresses several human factor issues underlying the existing surveillance systems. To create such a detection system, contextual information needs to be considered. This is because context is required in order to correctly understand human behaviour. Unfortunately, the use of contextual information is still limited in the automatic anomalous human behaviour detection approaches. This paper proposes a context space model which has two benefits: (a) It provides guidelines for the system designers to select information which can be used to describe context; (b)It enables a system to distinguish between different contexts. A comparative analysis is conducted between a context-based system which employs the proposed context space model and a system which is implemented based on one of the existing approaches. The comparison is applied on a scenario constructed using video clips from CAVIAR dataset. The results show that the context-based system outperforms the other system. This is because the context space model allows the system to considering knowledge learned from the relevant context only.

STALKERBOT : learning to navigate dynamic human environments by following people

Service robots that operate in human environments will accomplish tasks most efficiently and least disruptively if they have the capability to mimic and understand the motion patterns of the people in their workspace. This work demonstrates how a robot can create a humancentric navigational map online, and that this map re ects changes in the environment that trigger altered motion patterns of people. An RGBD sensor mounted on the robot is used to detect and track people moving through the environment. The trajectories are clustered online and organised into a tree-like probabilistic data structure which can be used to detect anomalous trajectories. A costmap is reverse engineered from the clustered trajectories that can then inform the robot's onboard planning process. Results show that the resultant paths taken by the robot mimic expected human behaviour and can allow the robot to respond to altered human motion behaviours in the environment.

Life on the edge : the effects of building facade three dimensionality on public social behaviour

Links between the built environment and human behaviour have long been of interest to those involved in the fields of urban planning and architecture, but direct assessments of the links between the three-dimensional building façade form and human behaviour are rare. Much work has been completed on subjects’ responses to the aesthetic of architectural frontages but this has generally been conducted using two-dimensional images of structures and in no way assesses human responses when in the presence of these structures. This research has set about observing the behaviour of individuals and groups in the public realm and recording their reactions to architecture which has a distinct three-dimensional character, with particular reference to the street level façade. The behaviour was recorded and quantified and indicated that there is significant differences in human behaviour around these various types of architecture.

Tracking spatio temporal movement of human in terms of space utilization using media access control address data

Using Media-Access-Control (MAC) address for data collection and tracking is a capable and cost effective approach as the traditional ways such as surveys and video surveillance have numerous drawbacks and limitations. Positioning cell-phones by Global System for Mobile communication was considered an attack on people's privacy. MAC addresses just keep a unique log of a WiFi or Bluetooth enabled device for connecting to another device that has not potential privacy infringements. This paper presents the use of MAC address data collection approach for analysis of spatio-temporal dynamics of human in terms of shared space utilization. This paper firstly discuses the critical challenges and key benefits of MAC address data as a tracking technology for monitoring human movement. Here, proximity-based MAC address tracking is postulated as an effective methodology for analysing the complex spatio-temporal dynamics of human movements at shared zones such as lounge and office areas. A case study of university staff lounge area is described in detail and results indicates a significant added value of the methodology for human movement tracking. By analysis of MAC address data in the study area, clear statistics such as staff’s utilisation frequency, utilisation peak periods, and staff time spent is obtained. The analyses also reveal staff’s socialising profiles in terms of group and solo gathering. The paper is concluded with a discussion on why MAC address tracking offers significant advantages for tracking human behaviour in terms of shared space utilisation with respect to other and more prominent technologies, and outlines some of its remaining deficiencies.

Challenges for implementation of a new model of collaborative design management: Analyzing the impact of human factor

The ineffectiveness of current design processes has been well studied and has resulted in widespread calls for the evolution and development of new management processes. Even following the advent of BIM, we continue to move from one stage to another without necessarily having resolved all the issues. CAD design technology, if well handled, could have significantly raised the level of quality and efficiency of current processes, but in practice this was not fully realized. Therefore, technology alone can´t solve all the problems and the advent of BIM could result in a similar bottleneck. For a precise definition of the problem to be solved we should start by understanding what are the main current bottlenecks that have yet to be overcome by either new technologies or management processes, and the impact of human behaviour-related issues which impact the adoption and utilization of new technologies. The fragmented and dispersed nature of the AEC sector, and the huge number of small organizations that comprise it, are a major limiting factor. Several authors have addressed this issue and more recently IDDS has been defined as the highest level of achievement. However, what is written on IDDS shows an extremely ideal situation on a state to be achieved; it shows a holistic utopian proposition with the intent to create the research agenda to move towards that state. Key to IDDS is the framing of a new management model which should address the problems associated with key aspects: technology, processes, policies and people. One of the primary areas to be further studied is the process of collaborative work and understanding, together with the development of proposals to overcome the many cultural barriers that currently exist and impede the advance of new management methods. The purpose of this paper is to define and delimit problems to be solved so that it is possible to implement a new management model for a collaborative design process.

Human mating in the informal market for sperm donation: Preferences and decision making

Choosing a mate is one of the largest (economic) decisions humans make. This thesis investigates this large scale decision and how the process is changing with the advent of the internet and the growing market for online informal sperm donation. This research identifies individual factors that influence female mating preferences. It explores the roles of behavioural traits and physical appearance, preferences for homogamy and hypergamy, and personality, and how these impact the decision to choose a donor. Overall, this thesis makes contributions to both the literature on human behaviour, and that on decision-making in extreme and highly important situations.

My place through my eyes : a social constructionist approach to researching the relationships between socioeconomic living contexts and physical activity

There is a growing evidence-base in the epidemiological literature that demonstrates significant associations between people’s living circumstances – including their place of residence – and their health-related practices and outcomes (Leslie, 2005; Karpati, Bassett, & McCord, 2006; Monden, Van Lenthe, & Mackenbach, 2006; Parkes & Kearns, 2006; Cummins, Curtis, Diez-Roux, & Macintyre, 2007; Turrell, Kavanagh, Draper, & Subramanian, 2007). However, these findings raise questions about the ways in which living places, such as households and neighbourhoods, figure in the pathways connecting people and health (Frolich, Potvin, Chabot, & Corin, 2002; Giles-Corti, 2006; Brown et al, 2006; Diez Roux, 2007). This thesis addressed these questions via a mixed methods investigation of the patterns and processes connecting people, place, and their propensity to be physically active. Specifically, the research in this thesis examines a group of lower-socioeconomic residents who had recently relocated from poorer suburbs to a new urban village with a range of health-related resources. Importantly, the study contrasts their historical relationship with physical activity with their reactions to, and everyday practices in, a new urban setting designed to encourage pedestrian mobility and autonomy. The study applies a phenomenological approach to understanding living contexts based on Berger and Luckman’s (1966) conceptual framework in The Social Construction of Reality. This framework enables a questioning of the concept of context itself, and a treatment of it beyond environmental factors to the processes via which experiences and interactions are made meaningful. This approach makes reference to people’s histories, habituations, and dispositions in an exploration between social contexts and human behaviour. This framework for thinking about context is used to generate an empirical focus on the ways in which this residential group interacts with various living contexts over time to create a particular construction of physical activity in their lives. A methodological approach suited to this thinking was found in Charmaz’s (1996; 2001; 2006) adoption of a social constructionist approach to grounded theory. This approach enabled a focus on people’s own constructions and versions of their experiences through a rigorous inductive method, which provided a systematic strategy for identifying patterns in the data. The findings of the study point to factors such as ‘childhood abuse and neglect’, ‘early homelessness’, ‘fear and mistrust’, ‘staying indoors and keeping to yourself’, ‘conflict and violence’, and ‘feeling fat and ugly’ as contributors to an ongoing core category of ‘identity management’, which mediates the relationship between participants’ living contexts and their physical activity levels. It identifies barriers at the individual, neighbourhood, and broader ecological levels that prevent this residential group from being more physically active, and which contribute to the ways in which they think about, or conceptualise, this health-related behaviour in relationship to their identity and sense of place – both geographic and societal. The challenges of living well and staying active in poorer neighbourhoods and in places where poverty is concentrated were highlighted in detail by participants. Participants’ reactions to the new urban neighbourhood, and the depth of their engagement with the resources present, are revealed in the context of their previous life-experiences with both living places and physical activity. Moreover, an understanding of context as participants’ psychological constructions of various social and living situations based on prior experience, attitudes, and beliefs was formulated with implications for how the relationship between socioeconomic contextual effects on health are studied in the future. More detailed findings are presented in three published papers with implications for health promotion, urban design, and health inequalities research. This thesis makes a substantive, conceptual, and methodological contribution to future research efforts interested in how physical activity is conceptualised and constructed within lower socioeconomic living contexts, and why this is. The data that was collected and analysed for this PhD generates knowledge about the psychosocial processes and mechanisms behind the patterns observed in epidemiological research regarding socioeconomic health inequalities. Further, it highlights the ways in which lower socioeconomic living contexts tend to shape dispositions, attitudes, and lifestyles, ultimately resulting in worse health and life chances for those who occupy them.

A FR.E.S.H idea

This paper explores the possibility of including human factoring in a business process model. The importance of doing so is twofold: (1) The organization becomes transparent in its processes as all participants (human, activities and events) are identifiable. (2) Including human factoring allows organizations to hire accordingly to the process needs. (3) Human factoring alleviates the current work related stress that is being encountered. (4) Enable quicker transition for newer employees into job scope. This was made possible by including a human behaviour layer in between pools within a process to depict human behaviour and feeling. Future work includes having a human thought symbol and a human interaction symbol included into the Business Process Modelling Notation (BPMN).

Suicide plays

Suicide is a uniquely human behaviour and has always elicited strong - usually negative - opinions. Thus I would like to state from the very outset that this morbid collection of writing (all separately published elsewhere previously) should not be seen as an attempt to glamorise the act of felo-de-se. Nevertheless, one needs to recognise the inherent theatricality of suicide: too often it is a petulant, peevish performance intended to convey a bitter message to the audience of those left behind. Unfortunately, it is also a performance that many similarly unhappy souls try to emulate, and this phenomenon, known as “The Werther Effect”, is the subject of the first paper, which serves as a most appropriate introduction to the four plays that follow it. The first play, entitled “Hamlet + Ophelia = ?”, is deliberately provocative, and may easily be misunderstood as a call to commit self-murder. It is hoped, however, that the protagonists of this angry little piece are seen to be impetuous and childish, rather than noble or deep. The second play, “Games for Married Couples”, is less about seppuku than it is about the despair of child-less marriage. It is not much happier than the first, but may nevertheless raise a smile or two. “His ... or Her ... Suicide”, on the other hand, is utterly frivolous. I am sure no reader will take it seriously. Finally, and circuitously, is the stage adaptation (and translation) of Goethe’s classic 1774 novella "Die Leiden des jungen Werthers". This piece was produced as part of my 2005 Master of Creative Arts at the University of Melbourne in Australia. Many thanks must go to my supervisor, Associate Professor Angela O’Brien, for prodding and poking me until the thesis was of an acceptable standard.

Ecological approaches to cognition and action in sport and exercise : ask not only what you do, but where you do it

In recent decades, concepts and ideas from James J. Gibson’s theory of direct perception in ecological psychology have been applied to the study of how perception and action regulate sport performance. This article examines the influence of different streams of thought in ecological psychology for studying cognition and action in the diverse behavioural contexts of sport and exercise. In discussing the origins of ecological psychology it can be concluded that psychologists such as Lewin, and to some extent Heider, provided the initial impetus for the development of key ideas. We argue that the papers in this special issue clarify that the different schools of thinking in ecological psychology have much to contribute to theoretical and practical developments in sport and exercise psychology. For example, Gibson emphasized and formalized how the individual is coupled with the environment; Brunswik raised the issue of the ontology of probability in human behaviour and the problem of representative design for experimental task constraints; Barker looked carefully into extra-individual behavioural contexts and Bronfenbrenner presented insights pertinent to the relations between behaviour contexts, and macro influences on behaviour. In this overview, we highlight essential issues from the main schools of thought of relevance to the contexts of sport and exercise, and we consider some potential theoretical linkages with dynamical systems theory.