Using text-spotting to query the world

The world we live in is well labeled for the benefit of humans but to date robots have made little use of this resource. In this paper we describe a system that allows robots to read and interpret visible text and use it to understand the content of the scene. We use a generative probabilistic model that explains spotted text in terms of arbitrary search terms. This allows the robot to understand the underlying function of the scene it is looking at, such as whether it is a bank or a restaurant. We describe the text spotting engine at the heart of our system that is able to detect and parse wild text in images, and the generative model, and present results from images obtained with a robot in a busy city setting.

Microorganisms within human follicular fluid : effects on IVF

Our previous study reported microorganisms in human follicular fluid. The objective of this study was to test human follicular fluid for the presence of microorganisms and to correlate these findings with the in vitro fertilization (IVF) outcomes. In this study, 263 paired follicular fluids and vaginal swabs were collected from women undergoing IVF cycles, with various causes for infertility, and were cultured to detect microorganisms. The cause of infertility and the IVF outcomes for each woman were correlated with the microorganisms detected within follicular fluid collected at the time of trans-vaginal oocyte retrieval. Microorganisms isolated from follicular fluids were classified as: (1) ‘colonizers’ if microorganisms were detected within the follicular fluid, but not within the vaginal swab (at the time of oocyte retrieval); or (2) ‘contaminants’ if microorganisms detected in the vagina at the time of oocyte retrieval were also detected within the follicular fluid. The presence of Lactobacillus spp. in ovarian follicular fluids was associated with embryo maturation and transfer. This study revealed microorganisms in follicular fluid itself and that the presence of particular microorganisms has an adverse affect on IVF outcomes as seen by an overall decrease in embryo transfer rates and pregnancy rates in both fertile and infertile women, and live birth rates in women with idiopathic infertility. Follicular fluid microorganisms are a potential cause of adverse pregnancy outcomes in IVF in both infertile women and in fertile women with infertile male partners.

Learning spatial concepts from RatSLAM representations

RatSLAM is a biologically-inspired visual SLAM and navigation system that has been shown to be effective indoors and outdoors on real robots. The spatial representation at the core of RatSLAM, the experience map, forms in a distributed fashion as the robot learns the environment. The activity in RatSLAM’s experience map possesses some geometric properties, but still does not represent the world in a human readable form. A new system, dubbed RatChat, has been introduced to enable meaningful communication with the robot. The intention is to use the “language games” paradigm to build spatial concepts that can be used as the basis for communication. This paper describes the first step in the language game experiments, showing the potential for meaningful categorization of the spatial representations in RatSLAM.

Rethinking public service media and citizenship: digital strategies for news and current affairs at Australia’s Special Broadcasting Service

This article considers the concept of media citizenship in relation to the digital strategies of the Special Broadcasting Service (SBS). At SBS, Australia’s multicultural public broadcaster, there is a critical appraisal of its strategies to harness user-created content (UCC) and social media to promote greater audience participation through its news and current affairs Web sites. The article looks at the opportunities and challenges that user-created content presents for public service media organizations as they consolidate multiplatform service delivery. Also analyzed are the implications of radio and television broadcasters’ moves to develop online services. It is proposed that case study methodologies enable an understanding of media citizenship to be developed that maintains a focus on the interaction between delivery technologies, organizational structures and cultures, and program content that is essential for understanding the changing focus of 21st-century public service media.

Representing USDL for humans and tools

This chapter deals with technical aspects of how USDL service descriptions can be read from and written to different representations for use by humans and tools. A combination of techniques for representing and exchanging USDL have been drawn from Model-Driven Engineering and Semantic Web technologies. The USDL language's structural definition is specified as a MOF meta-model, but some modules were originally defined using the OWL language from the Semantic Web community and translated to the meta-model format. We begin with the important topic of serializing USDL descriptions into XML, so that they can be exchanged beween editors, repositories, and other tools. The following topic is how USDL can be made available through the Semantic Web as a network of linked data, connected via URIs. Finally, consideration is given to human-readable representations of USDL descriptions, and how they can be generated, in large part, from the contents of a stored USDL model.

From vision to actions: Towards adaptive and autonomous humanoid robots

Although robotics research has seen advances over the last decades robots are still not in widespread use outside industrial applications. Yet a range of proposed scenarios have robots working together, helping and coexisting with humans in daily life. In all these a clear need to deal with a more unstructured, changing environment arises. I herein present a system that aims to overcome the limitations of highly complex robotic systems, in terms of autonomy and adaptation. The main focus of research is to investigate the use of visual feedback for improving reaching and grasping capabilities of complex robots. To facilitate this a combined integration of computer vision and machine learning techniques is employed. From a robot vision point of view the combination of domain knowledge from both imaging processing and machine learning techniques, can expand the capabilities of robots. I present a novel framework called Cartesian Genetic Programming for Image Processing (CGP-IP). CGP-IP can be trained to detect objects in the incoming camera streams and successfully demonstrated on many different problem domains. The approach requires only a few training images (it was tested with 5 to 10 images per experiment) is fast, scalable and robust yet requires very small training sets. Additionally, it can generate human readable programs that can be further customized and tuned. While CGP-IP is a supervised-learning technique, I show an integration on the iCub, that allows for the autonomous learning of object detection and identification. Finally this dissertation includes two proof-of-concepts that integrate the motion and action sides. First, reactive reaching and grasping is shown. It allows the robot to avoid obstacles detected in the visual stream, while reaching for the intended target object. Furthermore the integration enables us to use the robot in non-static environments, i.e. the reaching is adapted on-the- fly from the visual feedback received, e.g. when an obstacle is moved into the trajectory. The second integration highlights the capabilities of these frameworks, by improving the visual detection by performing object manipulation actions.

Food(ing): between human-computer and human-food-experience

This workshop is a continuation and extension to the successful past workshops exploring the intersection of food, technology, place, and people, namely 2009 OZCHI workshop, Hungry 24/7? HCI Design for Sustainable Food Culture and Sustainable Interaction with Food, Technology, and the City [1] and 2010 CHI panel Making Food, Producing Sustainability [3]. The workshop aims to bring together experts from diverse backgrounds including academia, government, industry, and non-for-profit organisations. It specifically aims to create a space for discussion and design of innovative approaches to understanding and cultivating sustainable food practices via human-computer-interaction (HCI) as well as addressing the wider opportunities for the HCI community to engage with food as a key issue for sustainability The workshop addresses environmental, health, and social domains of sustainability in particular, by looking at various conceptual and design approaches in orchestrating sustainable interaction of people and food in and through dynamic techno-social networks.

Unsupervised multi-label text classification using a world knowledge ontology

The development of text classification techniques has been largely promoted in the past decade due to the increasing availability and widespread use of digital documents. Usually, the performance of text classification relies on the quality of categories and the accuracy of classifiers learned from samples. When training samples are unavailable or categories are unqualified, text classification performance would be degraded. In this paper, we propose an unsupervised multi-label text classification method to classify documents using a large set of categories stored in a world ontology. The approach has been promisingly evaluated by compared with typical text classification methods, using a real-world document collection and based on the ground truth encoded by human experts.

Legal, cultural and practical developments in responding to female genital mutilation : can an absolute human right emerge?

Female genital mutilation (FGM) is a cultural practice involving the deliberate, non-therapeutic physical modification of young girls’ genitalia. FGM can take several forms, ranging from smaller incisions, to removal of the clitoris and labia, and narrowing or even closing of the vagina. FGM predates and has no basis in the Koran, or any other religious text. Rather, it is a cultural tradition, particularly common in Islamic societies in regions of Africa, motivated by a patriarchal society’s desire to control female bodies and lives. The primary reason for this desire for control is to ensure virginity at marriage, thereby preserving family honour, within a patriarchal social structure where females’ value as persons is intrinsically connected to, and limited to, their worth as virgin brides. Recent efforts at legal prohibition and practical eradication in a growing number of African nations mark a significant turning point in how societies treat females. This shift in cultural power has been catalysed by a concern for female health, but it has also been motivated by an impulse to promote the human rights of girls and women. Although FGM remains widely practiced and there is much progress yet to be made before its eradication, the rights-based approach which has grown in strength embodies a marked shift in cultural power which reflects progress in women’s and children’s rights in the Western world, but which is now being applied in a different cultural context. This chapter reviews the nature of FGM, its prevalence, and health consequences. It discusses recent legal, cultural and practical developments, especially in African nations. Finally, this chapter raises the possibility that an absolute human right against FGM may emerge.

Ideal victims in human trafficking awareness campaigns

Amidst a proliferation of bestseller books, blockbuster films, television documentaries and sensational news reports, public awareness campaigns have claimed their place in a growing chorus of concern about the crime of human trafficking. These campaigns aim to capture the public’s support in efforts to eliminate a ‘modern slave trade’ in which individuals seeking a better life are transported across borders and forced into exploitative labour conditions. Constrained by the limitations of primary campaign materials (posters, print ads, billboards) typically allowing for only a single image and minimal text, it is unlikely that these awareness campaigns can accurately convey the complexity of the trafficking problem. This chapter explores how the depictions of trafficking victims in awareness campaigns can exclude those who do not fit a restrictive narrative mould. Nils Christie’s pivotal work on the construction of society’s ideal victim is the lens through which this paper examines the literal ‘poster child’ of the anti-trafficking movement.

Mapping semantic knowledge for unsupervised text categorisation

Text categorisation is challenging, due to the complex structure with heterogeneous, changing topics in documents. The performance of text categorisation relies on the quality of samples, effectiveness of document features, and the topic coverage of categories, depending on the employing strategies; supervised or unsupervised; single labelled or multi-labelled. Attempting to deal with these reliability issues in text categorisation, we propose an unsupervised multi-labelled text categorisation approach that maps the local knowledge in documents to global knowledge in a world ontology to optimise categorisation result. The conceptual framework of the approach consists of three modules; pattern mining for feature extraction; feature-subject mapping for categorisation; concept generalisation for optimised categorisation. The approach has been promisingly evaluated by compared with typical text categorisation methods, based on the ground truth encoded by human experts.

Interference in text categorisation experiments

This article examines manual textual categorisation by human coders with the hypothesis that the law of total probability may be violated for difficult categories. An empirical evaluation was conducted to compare a one step categorisation task with a two step categorisation task using crowdsourcing. It was found that the law of total probability was violated. Both a quantum and classical probabilistic interpretations for this violation are presented. Further studies are required to resolve whether quantum models are more appropriate for this task.

Formalising human recognition : a fundamental building block for security proofs

A fundamental part of many authentication protocols which authenticate a party to a human involves the human recognizing or otherwise processing a message received from the party. Examples include typical implementations of Verified by Visa in which a message, previously stored by the human at a bank, is sent by the bank to the human to authenticate the bank to the human; or the expectation that humans will recognize or verify an extended validation certificate in a HTTPS context. This paper presents general definitions and building blocks for the modelling and analysis of human recognition in authentication protocols, allowing the creation of proofs for protocols which include humans. We cover both generalized trawling and human-specific targeted attacks. As examples of the range of uses of our construction, we use the model presented in this paper to prove the security of a mutual authentication login protocol and a human-assisted device pairing protocol.

Help-seeking strategies of victim/survivors of human trafficking involving partner migration

Victim/survivors of human trafficking involving partner migration employ diverse help-seeking strategies, both formal and informal, to exit their exploitative situations. Drawing on primary research conducted by Lyneham and Richards (forthcoming), the authors highlight the importance of educating the community and professionals from a wide range of sectors—including health, mental health, child protection, social welfare, social work, domestic violence, migration, legal and law enforcement services—about human trafficking and the help-seeking strategies of victims/survivors in order to support them to leave exploitative situations. Enhancing Australia’s knowledge of victim/survivors’ help-seeking strategies will better inform government and community responses to this crime, improve detection and identification of human trafficking matters and subsequent referral to appropriate victim services.

Using automated text analysis to evaluate students’ conceptual understanding

Background: A major challenge for assessing students’ conceptual understanding of STEM subjects is the capacity of assessment tools to reliably and robustly evaluate student thinking and reasoning. Multiple-choice tests are typically used to assess student learning and are designed to include distractors that can indicate students’ incomplete understanding of a topic or concept based on which distractor the student selects. However, these tests fail to provide the critical information uncovering the how and why of students’ reasoning for their multiple-choice selections. Open-ended or structured response questions are one method for capturing higher level thinking, but are often costly in terms of time and attention to properly assess student responses. Purpose: The goal of this study is to evaluate methods for automatically assessing open-ended responses, e.g. students’ written explanations and reasoning for multiple-choice selections. Design/Method: We incorporated an open response component for an online signals and systems multiple-choice test to capture written explanations of students’ selections. The effectiveness of an automated approach for identifying and assessing student conceptual understanding was evaluated by comparing results of lexical analysis software packages (Leximancer and NVivo) to expert human analysis of student responses. In order to understand and delineate the process for effectively analysing text provided by students, the researchers evaluated strengths and weakness for both the human and automated approaches. Results: Human and automated analyses revealed both correct and incorrect associations for certain conceptual areas. For some questions, that were not anticipated or included in the distractor selections, showing how multiple-choice questions alone fail to capture the comprehensive picture of student understanding. The comparison of textual analysis methods revealed the capability of automated lexical analysis software to assist in the identification of concepts and their relationships for large textual data sets. We also identified several challenges to using automated analysis as well as the manual and computer-assisted analysis. Conclusions: This study highlighted the usefulness incorporating and analysing students’ reasoning or explanations in understanding how students think about certain conceptual ideas. The ultimate value of automating the evaluation of written explanations is that it can be applied more frequently and at various stages of instruction to formatively evaluate conceptual understanding and engage students in reflective