Computer Sciences Commons^™

Widening The Evaluation Net, Brian Mac Namee, Mark Dunne

Conference papers

Intelligent Virtual Agent (IVA) systems are notoriously difficult to evaluate, particularly due to the subjectivity involved. From the various efforts to develop standard evaluation schemes for IVA systems the scheme proposed by Isbister & Doyle, which evaluates systems across five categories, seems particularly appropriate. To examine how these categories are being used, the evaluations presented in the proceedings of IVA '07 and IVA '08 are summarised and the extent to which the five categories in the Isbister & Doyle scheme are used is highlighted. Finally, to illustrate how the full scheme can be used, an evaluation of an IVA system …

Sampling With Confidence: Using K-Nn Confidence Measures In Active Learning, Rong Hu, Sarah Jane Delany, Brian Macnamee

Conference papers

Active learning is a process through which classifiers can be built from collections of unlabelled examples through the cooperation of a human oracle who can label a small number of examples selected as most informative. Typically the most informative examples are selected through uncertainty sampling based on classification scores. However, previous work has shown that, contrary to expectations, there is not a direct relationship between classification scores and classification confidence. Fortunately, there exists a collection of particularly effective techniques for building measures of classification confidence from the similarity information generated by k-NN classifiers. This paper investigates using these confidence measures …

Forked:A Demonstration Of Physics Realism In Augmented Reality, David Beaney, Brian Mac Namee

Conference papers

In making fully immersive augmented reality (AR) applications, real and virtual objects will have to be seen to physically interact together in a realistic and believable way. This paper describes Forked! a system that has been developed to show how physical interactions between real and virtual objects can be simulated re- alistically and believably through appropriate use of a physics en- gine. The system allows users control a robotic forklift to manipu- late virtual crates in an AR environment. The paper also describes a evaluation experiment in which it is shown that the physical inter- actions between the forklift and …

Toward Social Search: From Explicit To Implicit Collaboration To Predict Users' Interests, Luca Longo, Stephen Barrett

Conference papers

Inspection methods and cheap self-reporting procedures have been significantly employed in the field of Human- Computer Interaction for assessing the usability of interfaces, systems and technologies. However, there is a tendency to overlook aspects related to the context and features of the users during the usability assessment process. This research introduces the concept of mental workload as an aid to enhance usability measurement. A user-study has been designed and executed in the context of human-web interaction. The aim was to investigate the relationship between the perception of usability of three popular web-sites, and the mental workload imposed by a set …

An Enhanced Data Mining Life Cycle, Markus Hofmann, Brendan Tierney

Conference papers

Data mining projects are complex and can have a high failure rate. In order to improve project management and success rates of such projects a life cycle is vital to the overall success of the project. This paper reports on a research project that was concerned with the life cycle development for data mining projects, its team members and their role. The paper provides a detailed view of the design and development of the data mining life cycle called DMLC. The life cycle aims to support all members of data mining project teams as well as IT managers and academic …

Stepping Off The Stage, Brian Mac Namee, John D. Kelleher

Conference papers

Mixed-reality virtual agents are an attractive solution to the problems associated with human-robot interaction, allowing all the expressiveness of virtual characters to be married with the advantages of a physical artifact which exists in a shared environment with the user. However, common approaches to achieving this restrict the virtual characters appearing on top of, or encompassing the robot. This paper describes the Stepping Off the Stage system in which mixed-reality agents are allowed to step off the robot stage and move to other parts of the environment, offering compelling new interaction possibilities.

Enabling Adaptation In Trust Computations, Luca Longo, Pierpaolo Dondio, Bresciani Riccardo, Andrew Butterfield, Stephen Barrett

Conference papers

Digital systems have been rapidly evolving within highly dynamic and unstructured environments, where the lack of a central authority forces entities to interact with each other through collaboration and negotiation. Digital agents often use Trust models in order to compute the level of trustworthiness of the partner they want to collaborate with. Unfortunately, due to the evolution speed of open and collaborative environments, the trustworthiness of an agent varies over time, and as a result, Trust models must be continuously adapted to the changing context. In this work we address the problem by presenting a self-adaptive model for Trust computations. …

Storage, Manipulation, And Visualization Of Lidar Data, Bianca Schoen-Phelan, M. Bertolotto, D. F. Laefer, Sean W. Corish

Conference papers

In recent years, three-dimensional (3D) data has become increasingly available, in part as a result of significant technological progresses in Light Detection and Ranging (LiDAR). LiDAR provides longitude and latitude information delivered in conjunction with a GPS device, and elevation information generated by a pulse or phase laser scanner, which together provide an effective way of acquiring accurate 3D information of a terrestrial or manmade feature. The main advantages of LiDAR over conventional surveying methods lie in the high accuracy of the data and the relatively little time needed to scan large geographical areas. LiDAR scans provide a vast amount …

Sentiment Classification Of Reviews Using Sentiwordnet, Bruno Ohana, Brendan Tierney

Conference papers

Sentiment classification concerns the use of automatic methods for predicting the orientation of subjective content on text documents, with applications on a number of areas including recommender and advertising systems, customer intelligence and information retrieval. SentiWordNet is an opinion lexicon derived from the WordNet database where each term is associated with numerical scores indicating positive and negative sentiment information. This research presents the results of applying the SentiWordNet lexical resource to the problem of automatic sentiment classification of film reviews. Our approach comprises counting positive and negative term scores to determine sentiment orientation, and an improvement is presented by building …

A Covert Encryption Method For Applications In Electronic Data Interchange, Jonathan Blackledge, Dmitry Dubovitskiy

Articles

A principal weakness of all encryption systems is that the output data can be ‘seen’ to be encrypted. In other words, encrypted data provides a ‘flag’ on the potential value of the information that has been encrypted. In this paper, we provide a new approach to ‘hiding’ encrypted data in a digital image.

In conventional (symmetric) encryption, the plaintext is usually represented as a binary stream and encrypted using an XOR type operation with a binary cipher. The algorithm used is ideally designed to: (i) generate a maximum entropy cipher so that there is no bias with regard to any …

Development Of A Workflow For The Comparison Of Classification Techniques, Zanifa Omary

Masters

As the interest in machine learning and data mining springs up, the problem of how to assess learning algorithms and compare classifiers become more pressing. This has been associated with the lack of comprehensive and complete workflow depending on the project scale to provide guidance to its users. This means the success or failure of the project can be highly dependent on the person or team carrying it. The standard practice adopted by many researchers and experimenters has been to follow steps or phases from existing workflows such as CRISP-DM, KDD and SASSEMMA. However, as machine learning and data mining …

A Web-Based And Mobile Environmental Management System, James Carswell, Keith Gardiner, Michela Bertolotto, Andrea Rizzini, A Mandrak

Articles

This paper describes a Web-based and mobile system specifically developed to monitor fish species at risk. Such a system integrates spatial functionality to allow users not only to visualise maps and metadata of the area of concern but also to perform context-aware queries and updating of spatial datasets. The spatial datasets are provided by the Canadian Department of Fisheries and Oceans (DFO) and the prototype is customised to the specific needs of the Great Lakes Laboratory for Fisheries and Aquatic Sciences (GLLFAS) Fish Habitat Section requirements for fish species at risk assessment. Currently, researchers, habitat biologists and enforcement officers have …

A Generic Approach And Framework For Managing Complex Information, Essam Mansour

Doctoral

Several application domains, such as healthcare, incorporate domain knowledge into their day-to-day activities to standardise and enhance their performance. Such incorporation produces complex information, which contains two main clusters (active and passive) of information that have internal connections between them. The active cluster determines the recommended procedure that should be taken as a reaction to specific situations. The passive cluster determines the information that describes these situations and other descriptive information plus the execution history of the complex information. In the healthcare domain, a medical patient plan is an example for complex information produced during the disease management activity from …

Knowledge Management For Disparate Etruscan Cultural Heritage, John Mcauley, James Carswell

Conference papers

This paper introduces the TARCHNA approach to managing and presenting contextualised heritage content. The system uses the CIDOC CRM ontology to consolidate a virtual repository of geographically disparate heritage databases and present a holistic view of a fragmented heritage. While previous approaches to presenting heritage collections have focused on the browse and search paradigm, the TARCHNA system uses narrative concepts as a means of presenting and re-using contextualised heritage artefacts within a broader cultural setting.

Medical Language Processing For Patient Diagnosis Using Text Classification And Negation Labelling, Brian Mac Namee, John D. Kelleher, Sarah Jane Delany

Conference papers

This paper describes the approach of the DIT AIGroup to the i2b2 Obesity Challenge to build a system to diagnose obesity and related co-morbidities from narrative, unstructured patient records. Based on experimental results a system was developed which used knowledge-light text classification using decision trees, and negation labelling.

Referring Expression Generation Challenge 2008 Dit System Descriptions (Dit-Fbi, Dit-Tvas, Dit-Cbsr, Dit-Rbr, Dit-Fbi-Cbsr, Dit-Tvas-Rbr), John D. Kelleher, Brian Mac Namee

Conference papers

This papers desibes a set of systems developed at DIT for the Referring Expression Generation challenage at INLG 2008.In Proceedings of the 5th International Natural Language Generation Conference (INLG-08)

A Translation Mechanism For Recommendations, Pierpaolo Dondio, Luca Longo, Stephen Barrett

Conference papers

An important class of distributed Trust-based solutions is based on the information sharing. A basic requirement of such systems is the ability of participating agents to effectively communicate, receiving and sending messages that can be interpreted correctly. Unfortunately, in open systems it is not possible to postulate a common agreement about the representation of a rating, its semantic meaning and cognitive and computational mechanisms behind a trust-rating formation. Social scientists agree to consider unqualified trust values not transferable, but a more pragmatic approach would conclude that qualified trust judgments are worth being transferred as far as decisions taken considering others’ …

Object Detection And Classification With Applications To Skin Cancer Screening, Jonathan Blackledge, Dmitryi Dubovitskiy

Articles

This paper discusses a new approach to the processes of object detection, recognition and classification in a digital image. The classification method is based on the application of a set of features which include fractal parameters such as the Lacunarity and Fractal Dimension. Thus, the approach used, incorporates the characterisation of an object in terms of its texture.

The principal issues associated with object recognition are presented which includes two novel fast segmentation algorithms for which C++ code is provided. The self-learning procedure for designing a decision making engine using fuzzy logic and membership function theory is also presented and …

Covert Encryption And Document Authentication Using Texture Coding, Jonathan Blackledge, Mary Hallot

Articles

With the improvements in the quality of Commercial-Off-The-Shelf (COTS) printing and scanning devices, the ability to counterfeit documents has become a widespread problem. Consequently, there has been an increasing demand to develop digital watermarking techniques which can be applied to both electronic and printed images (and documents) that can be authenticated, prevent unauthorized copying and withstand abuse and degradation. In this paper , a new approach to digital watermarking is presented and a range of possible applications are considered. The process is defined by using concepts and techniques borrowed from Cryptography. It is based on computing a 'scramble image' by …

Anti-Phishing Models: Main Challenges, Edina Hatunic-Webster

Conference papers

Phishing is a form of online identity theft in which the attacker attempts to fraudulently retrieve a legitimate user's account information, logon credentials or identity information in general. The compromised information is then used for withdrawing money online, taking out cash advances, or making purchases of goods and services on the accounts. Various solutions have been proposed and developed in response to phishing. As phishing is a business problem, the solutions target both non-technical and technical areas. This paper investigates the current anti-phishing solutions and critically reviews their usage, security weaknesses and their effectiveness. The analysis of these models points …

Evaluation Of Robocode As A Teaching Tool For Computer Programming, Arnold Hensman

Conference Papers

Robocode began as an educational tool to aid in learning Java programming. It has since evolved into something of a phenomenon, as the prospect of creating simple to complex virtual tanks appears to pose an attractive challenge to both novice and expert programmers alike. What started out as a teaching tool has grown into a worldwide network of competitors, all keen to prove that their ‘bot’ stands out from the crowd. Competitions are well organised and many Robocode events are a PR dream for the computing companies that sponsor them. Without a doubt, this easy to use application has sparked …

Temporal Factors To Evaluate Trustworthiness Of Virtual Identities, Luca Longo, Pierpaolo Dondio, Stephen Barrett

Conference papers

In this paper we investigate how temporal factors (i.e. factors computed by considering only the time-distribution of interactions) can be used as an evidence of an entity’s trustworthiness. While reputation and direct experience are the two most widely used sources of trust in applications, we believe that new sources of evidence and new applications should be investigated [1]. Moreover, while these two classical techniques are based on evaluating the outcomes of interactions (direct or indirect), temporal factors are based on quantitative analysis, representing an alternative way of assessing trust. Our presumption is that, even with this limited information, temporal factors …

Proceedings Of The 18th Irish Conference On Artificial Intelligence And Cognitive Science, Sarah Jane Delany, Michael Madden

Books/Book Chapters

These proceedings contain the papers that were accepted for publication at AICS-2007, the 18th Annual Conference on Artificial Intelligence and Cognitive Science, which was held in the Technological University Dublin; Dublin, Ireland; on the 29th to the 31st August 2007. AICS is the annual conference of the Artificial Intelligence Association of Ireland (AIAI).

Task-Based Mood Induction Procedures For The Elicitation Of Natural Emotional Responses., Brian Vaughan, Charlie Cullen, Spyros Kousidis, Yi Wang

Other resources

This paper details experimental procedures designed to elicit real emotional responses from participants within a controlled acoustic environment. The experiments use Mood Induction Procedures (MIP’s), specifically MIP 4, to implement a co-operative task using two participants. These cooperative tasks are designed to engender emotional responses of activation and evaluation from the participants who are situated in separate isolation booths, thus reducing unwanted noise in the signal, preventing the participants from being distracted and ensuring a cleanly recorded audio signal. The audio is recorded at a professional level of quality (24bit/192Khz). The emotional dimensions of each audio recording will be evaluated …

An Open Source Approach To Wireless Positioning Techniques, Seamus Rooney, Keith Gardiner, James Carswell

Conference papers

There are several problems encountered when trying to determine the location of a mobile phone, including weather you are in an urban or rural environment. Also, it is well known that different positioning technologies can work better than others depending on the environment they are in. For example, GPS works well in rural areas but not as well in urban areas, GSM positioning accuracy can be acceptable in urban areas with the right triangulation technology, but is less accurate in rural areas. Positioning with other technologies such as WiFi, Bluetooth, and Semacode all have their own advantages and disadvantages also, …

An Open Approach To Contextualising Heterogeneous Cultural Heritage Datasets, John Mcauley, James Carswell

Conference papers

This paper describes a semantic museum application, which aims to present a holistic impression of the Etruscan civilisation. Through the use of a distributed computing paradigm and the CIDOC CRM ontology, the system presents a unified view of a fragmented heritage, while supporting browse and search at a semantic level. Within the cultural heritage world, however, much value is placed on ‘context’, both in describing and presenting heritage artefacts. From this perspective, a platform built upon the distributed search paradigm, although useful in many respects, does not convey how an artefact sits within a broader setting. Narrative concepts are proposed …

Urban Location Based Services Using Mobile Clients: The Icing Approach, Eoin Kilfeather, James Carswell, Keith Gardiner, Seamus Rooney

Conference papers

The ICING project is conducting research into eGovernment and Location Based Services and also into two-way interaction with the physical environment. The research focuses on the areas of embedded intelligence, tighter integration of operator platforms and city infrastructure to enable novel services, empowerment of citizens to evolve systems of interaction with the city via social software, input from citizens and sensors for management systems and decision modelling, and a combination of city systems and multi-modal, multi-device communications to provide enhanced services. The technology platforms are gathering indicators from the City, processing the information, proposing actions to be taken with human …

Destination Website Effectiveness – A Delphi-Based Emetric Approach – A Dms Perspective, Patrick Horan, Andrew Frew

Conference papers

This paper outlines the development and evaluation of a comprehensive set of eMetrics for measuring the effectiveness of a Destination Management Systems’ (DMS) websites from the perspective of small and medium-sized hotel enterprises. Ultimately, from a hotel’s viewpoint, website effectiveness depends on how well a site performs with respect to the related business goals. The priority of the research is thus to establish which criteria are important for destination websites and to determine a mechanism for their measurement. These criteria are divided into both macro- and micro- level metrics which each combine to provide information that is actionable from a …

Catching The Drift : Using Feature-Free Case-Based Reasoning For Spam Filtering., Sarah Jane Delany, Derek Bridge

Conference papers

n this paper, we compare case-based spam filters, focusing on their resilience to concept drift. In particular, we evaluate how to track concept drift using a case-based spam filter that uses a feature-free distance measure based on text compression. In our experiments, we compare two ways to normalise such a distance measure, finding that the one proposed in [1] performs better. We show that a policy as simple as retaining misclassified examples has a hugely beneficial effect on handling concept drift in spam but, on its own, it results in the case base growing by over 30%. We then compare …

Using Computer Vision To Create A 3d Representation Of A Snooker Table For Televised Competition Broadcasting, Hao Guo, Brian Mac Namee

Conference papers

The Snooker Extraction and 3D Builder (SE3DB) is designed to be used as a viewer aid in televised snooker broadcasting. Using a single camera positioned over a snooker table, the system creates a virtual 3D model of the table which can be used to allow audiences view the table from any angle. This would be particularly useful in allowing viewers to determine if particular shots are possible or not. This paper will describe the design, development and evaluation of this system. Particular focus in the paper will be given to the techniques used to recognise and locate the balls on …