Fast and accurate hand pose detection for human-robot interaction

[EN]Enabling natural human-robot interaction using computer vision based applications requires fast and accurate hand detection. However, previous works in this field assume different constraints, like a limitation in the number of detected gestures, because hands are highly complex objects difficult to locate. This paper presents an approach which integrates temporal coherence cues and hand detection based on wrists using a cascade classifier. With this approach, we introduce three main contributions: (1) a transparent initialization mechanism without user participation for segmenting hands independently of their gesture, (2) a larger number of detected gestures as well as a faster training phase than previous cascade classifier based methods and (3) near real-time performance for hand pose detection in video streams.

Approaches to Developing Educational Resources Using AI Embedded in Computer Game Technology. A Case Study: Primary School Literacy

In this extended abstract, we discuss recent research at Worcester into the inclusion of AI into ‘Serious Games’. Serious Games research intends to harness the power of computer game technology to produce educational and training materials. We prefer the name ‘Immersive Environments’ (IEs) since this emphasises the human psychological dimension. Creation of compelling and convincing learning software requires a rich engagement of the learner, and a convincing learning experience. We believe that various aspects of the AI tradition can inform the production of such learning.

Creating Educational Immersive Environments Using a Computer Game Engine: Case Studies and Design Theory

This paper aims to crystallize recent research performed at the University of Worcester to investigate the feasibility of using the commercial game engine ‘Unreal Tournament 2004’ (UT2004) to produce ‘Educational Immersive Environments’ (EIEs) suitable for education and training. Our research has been supported by the UK Higher Education Academy. We discuss both practical and theoretical aspects of EIEs. The practical aspects include the production of EIEs to support high school physics education, the education of architects, and the learning of literacy by primary school children. This research is based on the development of our novel instructional medium, ‘UnrealPowerPoint’. Our fundamental guiding principles are that, first, pedagogy must inform technology, and second, that both teachers and pupils should be empowered to produce educational materials. Our work is informed by current educational theories such as constructivism, experiential learning and socio-cultural approaches as well as elements of instructional design and game principles.

Models of the user: designers’ perspectives on influencing sustainable behaviour

Influencing more environmentally friendly and sustainable behaviour is a current focus of many projects, ranging from government social marketing campaigns, education and tax structures to designers’ work on interactive products, services and environments. There is a wide variety of techniques and methods used, intended to work via different sets of cognitive and environmental principles. These approaches make different assumptions about ‘what people are like’: how users will respond to behavioural interventions, and why, and in the process reveal some of the assumptions that designers and other stakeholders, such as clients commissioning a project, make about human nature. This paper discusses three simple models of user behaviour – the pinball, the shortcut and the thoughtful – which emerge from user experience designers’ statements about users while focused on designing for behaviour change. The models are characterised using systems terminology and the application of each model to design for sustainable behaviour is examined via a series of examples.

The Design with Intent Method: a design tool for influencing user behaviour

Using product and system design to influence user behaviour offers potential for improving performance and reducing user error, yet little guidance is available at the concept generation stage for design teams briefed with influencing user behaviour. This article presents the Design with Intent Method, an innovation tool for designers working in this area, illustrated via application to an everyday human–technology interaction problem: reducing the likelihood of a customer leaving his or her card in an automatic teller machine. The example application results in a range of feasible design concepts which are comparable to existing developments in ATM design, demonstrating that the method has potential for development and application as part of a user-centred design process.

Making the user more efficient: Design for sustainable behaviour

User behaviour is a significant determinant of a product’s environmental impact; while engineering advances permit increased efficiency of product operation, the user’s decisions and habits ultimately have a major effect on the energy or other resources used by the product. There is thus a need to change users’ behaviour. A range of design techniques developed in diverse contexts suggest opportunities for engineers, designers and other stakeholders working in the field of sustainable innovation to affect users’ behaviour at the point of interaction with the product or system, in effect ‘making the user more efficient’. Approaches to changing users’ behaviour from a number of fields are reviewed and discussed, including: strategic design of affordances and behaviour-shaping constraints to control or affect energyor other resource-using interactions; the use of different kinds of feedback and persuasive technology techniques to encourage or guide users to reduce their environmental impact; and context-based systems which use feedback to adjust their behaviour to run at optimum efficiency and reduce the opportunity for user-affected inefficiency. Example implementations in the sustainable engineering and ecodesign field are suggested and discussed.

Designing for User-facing Uncertainty in Everyday Sensing and Prediction

Thesis (Ph.D.)--University of Washington, 2016-07

Gaining by Giving? Peer Research into Service User and Carer Perceptions of Inclusivity in Higher Education

Service users and carers (SUAC) have made significant contributions to professional training in social work courses in Higher Education (HE) over the past decade in the UK. Such participation has been championed by government, academics and SUAC groups from a range of theoretical and political perspectives. Most research into the effectiveness of SUAC involvement at HE has come from the perspectives of academics and very little SUAC-led research exists. This qualitative peer research was led by two members of the University of Worcester’s SUAC group. Findings were that SUAC perceived their involvement brought benefits to students, staff, the University and the local community. Significant personal benefits such as finding a new support network, increased self-development and greater confidence to manage their own care were identified in ways that suggested that the benefits that can flow from SUAC involvement at HE are perhaps more far-reaching than previously recognised. Barriers to inclusion were less than previously reported in the literature and the humanising effects of SUAC involvement are presented as a partial antidote to an increasingly marketised HE culture.

User Behavioral Modeling of Web-based Systems for Continuous User Authentication

Authentication plays an important role in how we interact with computers, mobile devices, the web, etc. The idea of authentication is to uniquely identify a user before granting access to system privileges. For example, in recent years more corporate information and applications have been accessible via the Internet and Intranet. Many employees are working from remote locations and need access to secure corporate files. During this time, it is possible for malicious or unauthorized users to gain access to the system. For this reason, it is logical to have some mechanism in place to detect whether the logged-in user is the same user in control of the user's session. Therefore, highly secure authentication methods must be used. We posit that each of us is unique in our use of computer systems. It is this uniqueness that is leveraged to "continuously authenticate users" while they use web software. To monitor user behavior, n-gram models are used to capture user interactions with web-based software. This statistical language model essentially captures sequences and sub-sequences of user actions, their orderings, and temporal relationships that make them unique by providing a model of how each user typically behaves. Users are then continuously monitored during software operations. Large deviations from "normal behavior" can possibly indicate malicious or unintended behavior. This approach is implemented in a system called Intruder Detector (ID) that models user actions as embodied in web logs generated in response to a user's actions. User identification through web logs is cost-effective and non-intrusive. We perform experiments on a large fielded system with web logs of approximately 4000 users. For these experiments, we use two classification techniques; binary and multi-class classification. We evaluate model-specific differences of user behavior based on coarse-grain (i.e., role) and fine-grain (i.e., individual) analysis. A specific set of metrics are used to provide valuable insight into how each model performs. Intruder Detector achieves accurate results when identifying legitimate users and user types. This tool is also able to detect outliers in role-based user behavior with optimal performance. In addition to web applications, this continuous monitoring technique can be used with other user-based systems such as mobile devices and the analysis of network traffic.

Handling Heterogeneity in Collaborative Networked Surgical Simulators

Stand-alone and networked surgical virtual reality based simulators have been proposed as means to train surgical skills with or without a supervisor nearby the student or trainee -- However, surgical skills teaching in medicine schools and hospitals is changing, requiring the development of new tools to focus on: (i) importance of mentors role, (ii) teamwork skills and (iii) remote training support -- For these reasons, a surgical simulator should not only allow the training involving a student and an instructor that are located remotely, but also the collaborative training of users adopting different medical roles during the training sesión -- Collaborative Networked Virtual Surgical Simulators (CNVSS) allow collaborative training of surgical procedures where remotely located users with different surgical roles can take part in the training session -- To provide successful training involving good collaborative performance, CNVSS should handle heterogeneity factors such as users’ machine capabilities and network conditions, among others -- Several systems for collaborative training of surgical procedures have been developed as research projects -- To the best of our knowledge none has focused on handling heterogeneity in CNVSS -- Handling heterogeneity in this type of collaborative sessions is important because not all remotely located users have homogeneous internet connections, nor the same interaction devices and displays, nor the same computational resources, among other factors -- Additionally, if heterogeneity is not handled properly, it will have an adverse impact on the performance of each user during the collaborative sesión -- In this document, the development of a context-aware architecture for collaborative networked virtual surgical simulators, in order to handle the heterogeneity involved in the collaboration session, is proposed -- To achieve this, the following main contributions are accomplished in this thesis: (i) Which and how infrastructure heterogeneity factors affect the collaboration of two users performing a virtual surgical procedure were determined and analyzed through a set of experiments involving users collaborating, (ii) a context-aware software architecture for a CNVSS was proposed and implemented -- The architecture handles heterogeneity factors affecting collaboration, applying various adaptation mechanisms and finally, (iii) A mechanism for handling heterogeneity factors involved in a CNVSS is described, implemented and validated in a set of testing scenarios

A Binary Classifier for Test Case Feasibility Applied to Automatically Generated Tests of Event-Driven Software

Modern software application testing, such as the testing of software driven by graphical user interfaces (GUIs) or leveraging event-driven architectures in general, requires paying careful attention to context. Model-based testing (MBT) approaches first acquire a model of an application, then use the model to construct test cases covering relevant contexts. A major shortcoming of state-of-the-art automated model-based testing is that many test cases proposed by the model are not actually executable. These \textit{infeasible} test cases threaten the integrity of the entire model-based suite, and any coverage of contexts the suite aims to provide. In this research, I develop and evaluate a novel approach for classifying the feasibility of test cases. I identify a set of pertinent features for the classifier, and develop novel methods for extracting these features from the outputs of MBT tools. I use a supervised logistic regression approach to obtain a model of test case feasibility from a randomly selected training suite of test cases. I evaluate this approach with a set of experiments. The outcomes of this investigation are as follows: I confirm that infeasibility is prevalent in MBT, even for test suites designed to cover a relatively small number of unique contexts. I confirm that the frequency of infeasibility varies widely across applications. I develop and train a binary classifier for feasibility with average overall error, false positive, and false negative rates under 5\%. I find that unique event IDs are key features of the feasibility classifier, while model-specific event types are not. I construct three types of features from the event IDs associated with test cases, and evaluate the relative effectiveness of each within the classifier. To support this study, I also develop a number of tools and infrastructure components for scalable execution of automated jobs, which use state-of-the-art container and continuous integration technologies to enable parallel test execution and the persistence of all experimental artifacts.

An assessment of data leakage in Firefox under different conditions.

Data leakage is a serious issue and can result in the loss of sensitive data, compromising user accounts and details, potentially affecting millions of internet users. This paper contributes to research in online security and reducing personal footprint by evaluating the levels of privacy provided by the Firefox browser. The aim of identifying conditions that would minimize data leakage and maximize data privacy is addressed by assessing and comparing data leakage in the four possible browsing modes: normal and private modes using a browser installed on the host PC or using a portable browser from a connected USB device respectively. To provide a firm foundation for analysis, a series of carefully designed, pre-planned browsing sessions were repeated in each of the various modes of Firefox. This included low RAM environments to determine any effects low RAM may have on browser data leakage. The results show that considerable data leakage may occur within Firefox. In normal mode, all of the browsing information is stored within the Mozilla profile folder in Firefox-specific SQLite databases and sessionstore.js. While passwords were not stored as plain text, other confidential information such as credit card numbers could be recovered from the Form history under certain conditions. There is no difference when using a portable browser in normal mode, except that the Mozilla profile folder is located on the USB device rather than the host's hard disk. By comparison, private browsing reduces data leakage. Our findings confirm that no information is written to the Firefox-related locations on the hard disk or USB device during private browsing, implying that no deletion would be necessary and no remnants of data would be forensically recoverable from unallocated space. However, two aspects of data leakage occurred equally in all four browsing modes. Firstly, all of the browsing history was stored in the live RAM and was therefore accessible while the browser remained open. Secondly, in low RAM situations, the operating system caches out RAM to pagefile.sys on the host's hard disk. Irrespective of the browsing mode used, this may include Firefox history elements which can then remain forensically recoverable for considerable time.

Effect of haptic guidance and error amplification robotic training interventions on the immediate improvement of timing among individuals that had a stroke

Abstract : Many individuals that had a stroke have motor impairments such as timing deficits that hinder their ability to complete daily activities like getting dressed. Robotic rehabilitation is an increasingly popular therapeutic avenue in order to improve motor recovery among this population. Yet, most studies have focused on improving the spatial aspect of movement (e.g. reaching), and not the temporal one (e.g. timing). Hence, the main aim of this study was to compare two types of robotic rehabilitation on the immediate improvement of timing accuracy: haptic guidance (HG), which consists of guiding the person to make the correct movement, and thus decreasing his or her movement errors, and error amplification (EA), which consists of increasing the person’s movement errors. The secondary objective consisted of exploring whether the side of the stroke lesion had an effect on timing accuracy following HG and EA training. Thirty-four persons that had a stroke (average age 67 ± 7 years) participated in a single training session of a timing-based task (simulated pinball-like task), where they had to activate a robot at the correct moment to successfully hit targets that were presented a random on a computer screen. Participants were randomly divided into two groups, receiving either HG or EA. During the same session, a baseline phase and a retention phase were given before and after each training, and these phases were compared in order to evaluate and compare the immediate impact of HG and EA on movement timing accuracy. The results showed that HG helped improve the immediate timing accuracy (p=0.03), but not EA (p=0.45). After comparing both trainings, HG was revealed to be superior to EA at improving timing (p=0.04). Furthermore, a significant correlation was found between the side of stroke lesion and the change in timing accuracy following EA (r[subscript pb]=0.7, p=0.001), but not HG (r[subscript pb]=0.18, p=0.24). In other words, a deterioration in timing accuracy was found for participants with a lesion in the left hemisphere that had trained with EA. On the other hand, for the participants having a right-sided stroke lesion, an improvement in timing accuracy was noted following EA. In sum, it seems that HG helps improve the immediate timing accuracy for individuals that had a stroke. Still, the side of the stroke lesion seems to play a part in the participants’ response to training. This remains to be further explored, in addition to the impact of providing more training sessions in order to assess any long-term benefits of HG or EA.

Aplicación de SPEA2 al cálculo de esquemas de dosificación para el tratamiento quimioterapéutico del cáncer

En este trabajo se aborda la aplicación de SPEA2, un método para optimización multiobjetivo, al cálculo de un esquema de dosificación para el tratamiento quimioterapéutico de una masa tumoral; entiéndase por esquema de dosificación la especificación del o de los agentes cito-tóxicos, sus dosis y tiempos en que deben administrarse. El problema de optimización aquí resuelto es uno multiobjetivo, pues el esquema de dosificación a calcularse debe minimizar no solo el tamaño del tumor, sino también la toxicidad remanente al término del tratamiento, su costo, etc. El SPEA2 es un algoritmo genético que aplica el criterio de Pareto; por lo tanto, lo que calcula es una aproximación a la frontera de Pareto, soluciones de entre las cuales el usuario puede escoger la “mejor”. En el proceso de esta investigación se construyó SoT-Q, una herramienta de software que consiste de dos módulos principales: un optimizador para calcular los esquemas de dosificación óptimos, y un simulador para aplicar dichos esquemas a un paciente (simulado) con masa tumoral; el funcionamiento del simulador se basa en un modelo fármaco-dinámico que representa el tumor. El programa SoT-Q podría en el futuro -una vez extensamente probado y depurado- asistir a médicos oncólogos en la toma de decisiones respecto a tratamientos quimioterapéuticos; o podría servir también como ayuda pedagógica en el entrenamiento de nuevos profesionales de la salud. Los resultados obtenidos fueron muy buenos; en todos los casos de prueba utilizados se logró reducir de manera significativa tanto el tamaño del tumor como la toxicidad remanente al término del tratamiento; en algunos casos la reducción fue de tres órdenes de magnitud.

User Interface Abstraction for enabling TV set based Inclusive Access to the Information Society

199 p.