Social event detection at MediaEval 2013 : challenges, datasets and evaluation

In this paper, we provide an overview of the Social Event Detection (SED) task that is part of the MediaEval Bench mark for Multimedia Evaluation 2013. This task requires participants to discover social events and organize the re- lated media items in event-specific clusters within a collection of Web multimedia. Social events are events that are planned by people, attended by people and for which the social multimedia are also captured by people. We describe the challenges, datasets, and the evaluation methodology.

Evaluation of two-view geometry methods with automatic ground-truth generation

A large number of methods have been published that aim to evaluate various components of multi-view geometry systems. Most of these have focused on the feature extraction, description and matching stages (the visual front end), since geometry computation can be evaluated through simulation. Many data sets are constrained to small scale scenes or planar scenes that are not challenging to new algorithms, or require special equipment. This paper presents a method for automatically generating geometry ground truth and challenging test cases from high spatio-temporal resolution video. The objective of the system is to enable data collection at any physical scale, in any location and in various parts of the electromagnetic spectrum. The data generation process consists of collecting high resolution video, computing accurate sparse 3D reconstruction, video frame culling and down sampling, and test case selection. The evaluation process consists of applying a test 2-view geometry method to every test case and comparing the results to the ground truth. This system facilitates the evaluation of the whole geometry computation process or any part thereof against data compatible with a realistic application. A collection of example data sets and evaluations is included to demonstrate the range of applications of the proposed system.

Product feature taxonomy learning based on user reviews

In recent years, the Web 2.0 has provided considerable facilities for people to create, share and exchange information and ideas. Upon this, the user generated content, such as reviews, has exploded. Such data provide a rich source to exploit in order to identify the information associated with specific reviewed items. Opinion mining has been widely used to identify the significant features of items (e.g., cameras) based upon user reviews. Feature extraction is the most critical step to identify useful information from texts. Most existing approaches only find individual features about a product without revealing the structural relationships between the features which usually exist. In this paper, we propose an approach to extract features and feature relationships, represented as a tree structure called feature taxonomy, based on frequent patterns and associations between patterns derived from user reviews. The generated feature taxonomy profiles the product at multiple levels and provides more detailed information about the product. Our experiment results based on some popularly used review datasets show that our proposed approach is able to capture the product features and relations effectively.

Overview of INEX 2013

INEX investigates focused retrieval from structured documents by providing large test collections of structured documents, uniform evaluation measures, and a forum for organizations to compare their results. This paper reports on the INEX 2013 evaluation campaign, which consisted of four activities addressing three themes: searching professional and user generated data (Social Book Search track); searching structured or semantic data (Linked Data track); and focused retrieval (Snippet Retrieval and Tweet Contextualization tracks). INEX 2013 was an exciting year for INEX in which we consolidated the collaboration with (other activities in) CLEF and for the second time ran our workshop as part of the CLEF labs in order to facilitate knowledge transfer between the evaluation forums. This paper gives an overview of all the INEX 2013 tracks, their aims and task, the built test-collections, and gives an initial analysis of the results

Predicting fault-prone software modules with rank sum classification

The detection and correction of defects remains among the most time consuming and expensive aspects of software development. Extensive automated testing and code inspections may mitigate their effect, but some code fragments are necessarily more likely to be faulty than others, and automated identification of fault prone modules helps to focus testing and inspections, thus limiting wasted effort and potentially improving detection rates. However, software metrics data is often extremely noisy, with enormous imbalances in the size of the positive and negative classes. In this work, we present a new approach to predictive modelling of fault proneness in software modules, introducing a new feature representation to overcome some of these issues. This rank sum representation offers improved or at worst comparable performance to earlier approaches for standard data sets, and readily allows the user to choose an appropriate trade-off between precision and recall to optimise inspection effort to suit different testing environments. The method is evaluated using the NASA Metrics Data Program (MDP) data sets, and performance is compared with existing studies based on the Support Vector Machine (SVM) and Naïve Bayes (NB) Classifiers, and with our own comprehensive evaluation of these methods.

The evaluation of a clinical scar scale for porcine burn scars

This study describes the evaluation of a clinical scar scale for our porcine burn scars, which includes scar cosmetic outcome, colour, height and hair, supplemented with reference porcine scar photographs representing each scar outcome and scar colour scores. A total of 72 porcine burn scars at week 6 after burn were rated in vivo and/or on photographs. Good agreements were achieved for both intra-rater reliability (correlation is 0.86-0.98) and inter-rater reliability (ICC=80-85%). The results showed statistically significant correlations for each pair in this clinical scar scale (p<0.01), with the best correlation found between scar cosmetic outcome and scar colour. A multivariate principle components analysis revealed that this clinical scar assessment was highly correlated with scar histology, wound size, and re-epithelialisation data (p<0.001). More severe scars are clinically characterised by darker purple colouration, more elevation, no presence of hair, histologically by thicker scar tissue, thinner remaining normal dermis, are more likely to have worse contraction, and slower re-epithelialisation. This study demonstrates that our clinical scar scale is a reliable, independent and valuable tool for assessing porcine burn outcome and truthfully reflects scar appearance and function. To our knowledge, this is the first study demonstrating a high correlation between clinical scar assessment and scar histology, wound contraction and re-epithelialisation data on porcine burn scars. We believe that the successful use of porcine scar scales is invaluable for assessing potential human burn treatments.

Systematic evaluation of GoSoapBox in tertiary education : a student response system for improving learning experiences and outcomes

There is currently a wide range of research into the recent introduction of student response systems in higher education and tertiary settings (Banks 2006; Kay and Le Sange, 2009; Beatty and Gerace 2009; Lantz 2010; Sprague and Dahl 2009). However, most of this pedagogical literature has generated ‘how to’ approaches regarding the use of ‘clickers’, keypads, and similar response technologies. There are currently no systematic reviews on the effectiveness of ‘GoSoapBox’ – a more recent, and increasingly popular student response system – for its capacity to enhance critical thinking, and achieve sustained learning outcomes. With rapid developments in teaching and learning technologies across all undergraduate disciplines, there is a need to obtain comprehensive, evidence-based advice on these types of technologies, their uses, and overall efficacy. This paper addresses this current gap in knowledge. Our teaching team, in an undergraduate Sociology and Public Health unit at the Queensland University of Technology (QUT), introduced GoSoapBox as a mechanism for discussing controversial topics, such as sexuality, gender, economics, religion, and politics during lectures, and to take opinion polls on social and cultural issues affecting human health. We also used this new teaching technology to allow students to interact with each other during class – both on both social and academic topics – and to generate discussions and debates during lectures. The paper reports on a data-driven study into how this interactive online tool worked to improve engagement and the quality of academic work produced by students. This paper will firstly, cover the recent literature reviewing student response systems in tertiary settings. Secondly, it will outline the theoretical framework used to generate this pedagogical research. In keeping with the social and collaborative features of Web 2.0 technologies, Bandura’s Social Learning Theory (SLT) will be applied here to investigate the effectiveness of GoSoapBox as an online tool for improving learning experiences and the quality of academic output by students. Bandura has emphasised the Internet as a tool for ‘self-controlled learning’ (Bandura 2001), as it provides the education sector with an opportunity to reconceptualise the relationship between learning and thinking (Glassman & Kang 2011). Thirdly, we describe the methods used to implement the use of GoSoapBox in our lectures and tutorials, and which aspects of the technology we drew on for learning purposes, as well as the methods for obtaining feedback from the students about the effectiveness or otherwise of this tool. Fourthly, we report cover findings from an examination of all student/staff activity on GoSoapBox as well as reports from students about the benefits and limitations of it as a learning aid. We then display a theoretical model that is produced via an iterative analytical process between SLT and our data analysis for use by academics and teachers across the undergraduate curriculum. The model has implications for all teachers considering the use of student response systems to improve the learning experiences of their students. Finally, we consider some of the negative aspects of GoSoapBox as a learning aid.

An evaluation of clinical procedures used in dental implant treatment in posterior maxilla using flapless technique

This study was a measure forward in cultivating the scientific basis for an approach to examine clinical procedure in Flapless dental implant surgery. The thesis is based on: the systematic review, retrospective study of flapless implants, and in vivo study on the osseo-integration in osteoporotic rats. Dr Doan investigated "clinical procedures used in dental implant treatment in posterior maxilla using flapless technique". The work has yielded significant contributions to the area of implant flapless surgery and its effects on osteoporotic patients having implants in the posterior maxilla.

An evaluation of the Australian ‘reconceptualising early mathematics learning’ project : key findings and implications

The Pattern and Structure Mathematics Awareness Project (PASMAP) has investigated the development of patterning and early algebraic reasoning among 4 to 8 year olds over a series of related studies. We assert that an awareness of mathematical pattern and structure (AMPS) enables mathematical thinking and simple forms of generalization from an early age. This paper provides an overview of key findings of the Reconceptualizing Early Mathematics Learning empirical evaluation study involving 316 Kindergarten students from 4 schools. The study found highly significant differences on PASA scores for PASMAP students. Analysis of structural development showed increased levels for the PASMAP students; those categorised as low ability developed improved structural responses over a short period of time.

Perception Quality Evaluation with Visual and Infrared Cameras in Challenging Environmental Conditions

This work aims to contribute to the reliability and integrity of perceptual systems of unmanned ground vehicles (UGV). A method is proposed to evaluate the quality of sensor data prior to its use in a perception system by utilising a quality metric applied to heterogeneous sensor data such as visual and infrared camera images. The concept is illustrated specifically with sensor data that is evaluated prior to the use of the data in a standard SIFT feature extraction and matching technique. The method is then evaluated using various experimental data sets that were collected from a UGV in challenging environmental conditions, represented by the presence of airborne dust and smoke. In the first series of experiments, a motionless vehicle is observing a ’reference’ scene, then the method is extended to the case of a moving vehicle by compensating for its motion. This paper shows that it is possible to anticipate degradation of a perception algorithm by evaluating the input data prior to any actual execution of the algorithm.

Visual metrics for the evaluation of sensor data quality in outdoor perception

This paper proposes an experimental study of quality metrics that can be applied to visual and infrared images acquired from cameras onboard an unmanned ground vehicle (UGV). The relevance of existing metrics in this context is discussed and a novel metric is introduced. Selected metrics are evaluated on data collected by a UGV in clear and challenging environmental conditions, represented in this paper by the presence of airborne dust or smoke. An example of application is given with monocular SLAM estimating the pose of the UGV while smoke is present in the environment. It is shown that the proposed novel quality metric can be used to anticipate situations where the quality of the pose estimate will be significantly degraded due to the input image data. This leads to decisions of advantageously switching between data sources (e.g. using infrared images instead of visual images).

Visual metrics for the evaluation of sensor data quality in outdoor perception

This paper proposes an experimental study of quality metrics that can be applied to visual and infrared images acquired from cameras onboard an unmanned ground vehicle (UGV). The relevance of existing metrics in this context is discussed and a novel metric is introduced. Selected metrics are evaluated on data collected by a UGV in clear and challenging environmental conditions, represented in this paper by the presence of airborne dust or smoke.

Datasets for the evaluation of multi-sensor perception in natural environments with challenging conditions

This paper presents large, accurately calibrated and time-synchronised datasets, gathered outdoors in controlled environmental conditions, using an unmanned ground vehicle (UGV), equipped with a wide variety of sensors. It discusses how the data collection process was designed, the conditions in which these datasets have been gathered, and some possible outcomes of their exploitation, in particular for the evaluation of performance of sensors and perception algorithms for UGVs.

From “anytime, anywhere” to “here and now”: place and time restrictions in mobile narratives to enhance situated engagement of mobile users

The usage of the mobile Internet has increased tremendously within the last couple of years, and thereby the vision of accessing information anytime, anywhere has become more realistic and a dominant design principle for providing content. However, this study challenges this paradigm of unlimited and unrestricted access, and explores the question whether constraints and restrictions can positively influence the motivation and enticement of mobile users to engage with location-specific content. Restrictions, such as a particular time or location that gives a user access to content, may be used to foster participation and engagement, as well as to support content production and to enhance the user’s experience. In order to explore this, a Mobile Narrative and a Narrative Map have been created. For the former, the access to individual chapters of the story was restricted. Authors can specify constraints, such as a location or time, which need to be met by the reader if they want to read the story. This concept allows creative writers of the story to exploit the fact that the reader’s context is known, by intensifying the user experience and integrating this knowledge into the writing process. The latter, the Narrative Map, provides users with extracts from stories or information snippets about authors at relevant locations. In both concepts, a feedback channel was also integrated, on which location, time, and size constraints were imposed. In a user-centred design process involving authors and potential readers, those concepts have been implemented, followed by an evaluation comprising four user studies. The results show that restrictions and constraints can indeed lead to more enticing and engaging user experiences, and restricted contribution opportunities can lead to a higher motivation to participate as well as to an improved quality of submissions. These findings are relevant for future developments in the area of mobile narratives and creative writing, as well as for common mobile services that aim for enticing user experiences.