External publication lists are avilable in the following locations:
2013
A Tarasov, SJ Delany, B Mac Namee, "Improving Performance by Re-Rating in the Dynamic Estimation of Rater Reliability", In Proceedings of Machine Learning Meets Crowdsourcing Workshop in conjunction with International Conference on Machine Learning. (2013) |Full text|
K Kennedy, B Mac Namee, SJ Delany, M O'Sullivan, N Watson, "A window of opportunity: Assessing behavioural scoring", Expert Systems with Applications, 40(4). (2013) |Full text|
Yan Li, Brian Mac Namee and John D. Kelleher, "Expecting the Unexpected: Measuring Uncertainties in Mobile Robot Path Planning in Dynamic Environments", In Proceedings of the 14th Towards Autonomous Robotic Systems (TAROS 2013). (2013) |pdf| Lindstrom, P., Mac Namee, B. & Delany, S., "Drift detection using uncertainty distribution divergence", Evolving Systems, 4, 13-25. (2013) |Full text|
2012
Tarasov, A , Delany, S. J., Mac Namee, B., "Dynamic Estimation of Rater Reliability in Subjective Tasks using Multi-Armed Bandit Techniques", roceedings of the ASE/IEEE International Conference on Social Computing, pp. 979-980. (2012) |Full text| Tarasov, A , Delany, S. J., Mac Namee, B., "Improving Performance by Re-Rating in the Dynamic Estimation of Rater Reliability", Machine Learning Meets Crowdsourcing Workshop, in conjunction with ICML 2013 . (2012) |Full text| Tarasov, A , Delany, S. J., Mac Namee, B., "Dynamic Estimation of Rater Reliability in Regression Tasks using Multi-Armed Bandit Techniques", Workshop on Machine Learning in Human Computation and Crowdsourcing, in conjunction with ICML 2012 . (2012) |Full text| Dunne, M., Mac Namee, B. & Kelleher, J.D., "Stereoscopic
avatar interfaces: A study to determine what effect, if any, 3d technology has at
increasing the interpretability of an avatar’s gaze into the real-world", In Proceedings of Multimodal Analyses enabling Artificial Agents in Human-Machine Interaction (MA3 2012). (2012) |pdf| Strunkin, D., Mac Namee, B. & Kelleher, J.D.,, "An Investigation into Feature Selection for Oncological Survival Prediction", In Proceedings of the International Conference on Information Technology: New Generations (ITNG-12). (2012) Dunne, M., Mac Namee, B. & Kelleher, J.D., "The Turning, Stretching and Boxing Technique: A Step in the Right Direction", In Proceedings of the 12th International Conference on Intelligent Virtual Agents. (2012) Delany, S.J., Segata, N. & Mac Namee, B., "Profiling Instances in Noise Reduction", Knowledge Based Systems, (31) p28-40. (2012) |Full text| |abstract| The dependency on the quality of the training data has led to significant work in noise reduction for instance-based learning algorithms. This paper presents an empirical evaluation of current noise reduction techniques, not just from the perspective of their comparative performance, but from the perspective of investigating the types of instances that they focus on for removal. A novel instance profiling technique known as RDCL profiling allows the structure of a training set to be analysed at the instance level categorising each instance based on modelling their local competence properties. This profiling approach offers the opportunity of investigating the types of instances removed by the noise reduction techniques that are currently in use in instance-based learning. The paper also considers the effect of removing instances with specific profiles from a dataset and shows that a very simple approach of removing instances that are misclassified by the training set and cause other instances in the dataset to be misclassified is an effective noise reduction technique.[hide] K. Kennedy, B. Mac Namee, S.J. Delany, "Using semi-supervised classifiers for credit scoring", Journal of the
Operational Research Society 64, no. 4 (2012): 513-529. (2012) |pdf| |abstract| In credit scoring, low-default portfolios are those for which very little default history exists. This makes it problematic for financial institutions to estimate a reliable probability of a customer defaulting on a loan. Banking regulation (Basel II Capital Accord), and best practice, however, necessitate an accurate and valid estimate of the probability of default. In this article the suitability of semi-supervised one-class classification algorithms as a solution to the low default portfolio problem are evaluated. The performance of one-class classification algorithms is compared with the performance of supervised two-class classification algorithms. This study also investigates the suitability of oversampling, which is a common approach to dealing with low-default portfolios. Assessment of the performance of one and two-class classification algorithms using nine real-world banking datasets, which have been modified to replicate low-default portfolios, is provided. Our results demonstrate that only in the near or complete absence of defaulters should semi-supervised one-class classification algorithms be used instead of supervised two-class classification algorithms. Furthermore, we demonstrate for data sets whose class labels are unevenly distributed that optimising the threshold value on classifier output yields, in many cases, an improvement in classification performance. Finally, our results suggest that oversampling produces no overall improvement to the best performing two-class classification algorithms.[hide]
2011
Kenneth Kennedy, Sarah Jane Delany and Brian Mac Namee, "A Framework for Generating Data to Simulate Application Scoring", In Proceedings of the Credit Scoring and Credit Control XII
Conference. (2011) |pdf| |abstract| In this paper we propose a framework to generate artificial data that can be used to simulate credit risk scenarios. Artificial data is useful in the credit scoring domain for two reasons. Firstly, the use of artificial data allows for the introduction and control of
variability that can realistically be expected to occur, but has yet to materialise in practice. The ability to control parameters allows for a thorough exploration of the performance of classification models under diff erent conditions. Secondly, due to non-disclosure agreements and commercial sensitivities, obtaining real credit scoring data is a problematic and time consuming task. By the provision of publicly available artificial data, credit scoring is opened to the wider data mining community. This in turn could help enable greater participation, promote replicable experimental findings, and give rise to solution proposals to outstanding credit
scoring problems.
To ensure that our framework is sufficiently grounded in reality, data distributions are generated using a troika of sources: demographic information from the Central Statistics Office, Ireland; housing statistics published by the Irish Government Department of the Environment, Heritage and Local Government; and a profile of loan defaulters developed using a recent report published by a
credit rating agency. By engaging with a credit scoring expert we select characteristics that are typical of most application scorecard models including, amongst others: age, income, loan value, and occupation. Through user controlled settings the conditional prior probabilities of the characteristics can be adjusted over time to simulate di ffering scenarios. In order to assign class labels to the generated data a credit risk score is estimated based on the non-linear interactions between various characteristics. Based on the desired number of defaulters a cut-o score is placed on this monotonic ordering of credit scores to distinguish between those likely to repay and those likely to default on their financial obligation. The classification complexity is controlled by adding user-defined random Gaussian noise.
After discussing the desirable characteristics of artificial data we describe a pseudo-random data generator for credit scoring and provide illustrations on how the framework can be used to generate population drift.[hide] Schutte, N., Kelleher, J & Mac Namee, B., "Automatic Annotation of Referring Expression in Situated Dialogues", International Journal Of Computational Linguistics And Applications, 2 (1-2). (2011) Lindstrom, P., MacNamee, B., Delany, S., "Drift Detection Using Uncertainty Distribution Divergence", In Proceedings of the 2nd International Workshop on Handling Concept Drift in Adaptive Information Systems (HaCDAIS). (2011) |Full text| |abstract| Concept drift is believed to be prevalent inmost data gathered from naturally occurring processes and thus warrants research by the machine learning community.There are a myriad of approaches to concept drift handling which have been shown to handle concept drift with varying degrees of success.
However, most approaches make the key assumption that the labelled data will be available at no labelling cost shortly after classification, an assumption which is often violated. The high labelling cost in many domains provides a strong motivation to reduce the number of labelled instances required to handle concept drift. Explicit detection approaches that do not require labelled instances to detect concept drift show great promise for achieving this.
Our approach Confidence Distribution Batch Detection (CDBD)provides a signal correlated to changes in concept without using labelled data. We also show how this signal combined with a trigger and a rebuild policy can maintain classifier accuracy while using a limited amount of labelled data.[hide] Sloan, C., Mac Namee, B. & Kelleher, J.D., "Utility-Directed Goal-Oriented Action Planning: A Utility-Based Control System for Computer Game Agents", In Proceedings of the 22nd Irish Conference on Artificial Intelligence and Cognitive Science. (2011) Kelleher, J.D., Ross, R.J., Sloan, C. & Mac Namee, B., "The effect of occlusion on the semantics of projective spatial terms: a case study in grounding language in perception.", Cognitive Processing 12(1): 95-108. (2011) Sloan, C., J. D. Kelleher, B. Mac Namee, "Feeling the Ambiance: Using Smart Ambiance to Increase
Contextual Awareness in Game Agents", In proceedings of the Sixth International ACM Conference on the Foundations of Digital Games. (2011)
2010
Yan Li, Brian Mac Namee and John D. Kelleher, "Navigating the Corridors of Power: Using RFID and Compass Sensors for Robot Localisation and Navigation", In Proceedings of the 11th Towards Autonomous Robotic Systems (TAROS 2010). (2010) |pdf| Yan Li, Brian Mac Namee and John D. Kelleher, "Helmsman, Set a Course: Using a Compass and RFID Tags for Indoor Localisation and Navigation", In Proceedings of the 21st Irish Conference on Artificial Intelligence and Cognitive Science (AICS 2010). (2010) |pdf| Brian Mac Namee, Rong Hu, and Sarah Jane Delany, "Inside the Selection Box: Visualising active learning selection strategies", In Proceedings of the Challenges of Data Visualization Neural Information Processing Systems (NIPS) 2010 Workshop. (2010) |abstract| Visualisations can be used to provide developers with insights into the inner workings of interactive machine learning techniques. In active learning, an inherently interactive machine learning technique, the design of selection strategies is the key research question and this paper demonstrates how spring model based visualisations can be used to provide insight into the precise operation of various selection strategies. Using sample datasets, this paper provides detailed examples of the differences between a range of selection strategies.[hide] Kelleher, J.D., Ross, R.J., Mac Namee, B. and Sloan, C., "Situating Spatial Templates for Human-Robot Interaction", In Proc. of the AAAI Symposium on Dialog with Robots. (2010) |abstract| People often refer to objects by describing the object's spatial location relative to another object. Due to their ubiquity in situated discourse, the ability to use 'locative expressions' is fundamental to human-robot dialogue systems. A key component of this ability are computational models of spatial term semantics. These models bridge the grounding gap between spatial language and sensor data. Within the Artificial Intelligence and Robotics communities, spatial template based accounts, such as the Attention Vector Sum model (Regier and Carlson, 2001), have found considerable application in mediating situated human-machine communication (Gorniak, 2004; Brenner et a., 2007; Kelleher and Costello, 2009). Through empirical validation and computational application these template based models have proven their usefulness. We argue, however, that these models ignore important contextual features; resulting in their over-generalization and failure to account for actual usage in situated context. Such over-simplifications are a natural consequence of the experimental design taken in acquiring these models. That is, the data behind and hence the subsequent modelling of template based accounts used simplified scenes and reduced 2-dimensional survey based object configurations. While this is understandable given the original aims of these studies, we nevertheless believe that this is not sufficient justification for the direct application of idealized spatial templates to situated communication. This critique of template based models is similar in spirit to critiques already put forward by a number of researchers: Coventry and Garrod (2004) have stressed the need to account for functional effects; Kelleher and Costello (2009) highlighted the need to account for the effects introduced by distractors. Here, we argue that the models must also be extended to incorporate perspective effects.[hide] Schutte, N., Kelleher, J.D. and Mac Namee, B., "Visual Salience and Reference Resolution in Situated Dialogues: A Corpus-based Evaluation", In Proc. of the AAAI Symposium on Dialog with Robots. (2010) |abstract| Dialogues between humans and robots are necessarily situated. Exophoric references to objects in the shared visual context are very frequent in situated dialogues, for example when a human is verbally guiding a tele-operated mobile robot. We present an approach to automatically resolving exophoric referring expressions in a situated dialogue based on the visual salience of possible referents. We evaluate the effectiveness of this approach and a range of different salience metrics using data from the SCARE corpus which we have augmented with visual information. The results of our evaluation show that our computationally lightweight approach is successful, and so promising for use in human-robot dialogue systems.[hide] Mark Dunne, Brian Mac Namee & John Kelleher, "TSB Technique: Increasing a User's Sense of Immersion with Intelligent Virtual Agents", The 21st National Conference on Artificial Intelligence and Cognitive Science Student Symposium. (2010) |pdf| |abstract| The field of Intelligent Virtual Agent (IVA) research depends heavily on immersive techniques when presenting virtual agents to end-users. This sense of immersion relies on the user believing the agent to be real and present in their environment, creating the “Illusion of Life”. This poster describes the on-going research into using a combination of three rendering techniques, Twisting, Stretching and Boxing (TSB), to create a fully immersive 3D illusion for an end-user from any viewpoint, as they move freely in front of displays distributed across large populated environments. The novel approach outlined in this poster, uses head tracking, face detection and the TSB technique to increase the user’s sense of immersion and subsequently their sense of the agent’s presence within the environment. Using only web-cameras, our approach is a hardware-light solution which does not require the end-user to wear any additional apparatus, such as the LED headset used previously. The poster primarily discusses our Approach, the Preliminary Experiments & Results, Proposed Evaluation Process and Future Work.[hide] Mark Dunne, Brian Mac Namee & John Kelleher, "Scalable Multi-modal Avatar Interface for Multi-user Environments", In Proceedings of the International Conference on Computer Animation and Social Agents 2010 (CASA 2010). (2010) |pdf| |abstract| This research outlines an Intelligent Virtual Agent (IVA) interface, where multiple users will be able to interact with 3D avatars. This will take place in a distributed multi-modal environment where the LOK8 Avatar System (AS) will need to locate it’s users from a crowd, using face tracking and novel 3D animation techniques.[hide] Patrick Lindstrom, Sarah Jane Delany, Brian Mac Namee, "Handling Concept Drift in Text Data Streams Constrained by High Labelling Cost", In Proceedings of the 23rd Florida Artificial Intelligence Research Society Conference (FLAIRS). (2010) |Full text| |abstract| In many real-world classification problems the concept being modelled is not static but rather changes over time - a situation known as concept drift. Most techniques for handling concept drift rely on the true classifications of test instances being available shortly after classification so that classifiers can be retrained to handle the drift. However, in applications where labelling instances with their true class has a high cost this is not reasonable. In this paper we present an approach for keeping a classifier up-to-date in a concept drift domain which is constrained by a high cost of labelling. We use an active learning type approach to select those examples for labelling that are most useful in handling changes in concept. We show how this approach can adequately handle concept drift in a text filtering scenario requiring just 15% of the documents to be manually categorised and labelled.[hide] Mac Namee, B., Beaney, D., and Dong, Q., "Motion in Augmented Reality Games: An Engine for Creating Plausible Physical Interactions in Augmented Reality Games", International Journal of Computer Games Technology, vol. 2010, Article ID 979235. (2010) |Full text| |abstract| The next generation of Augmented Reality (AR) games will require real and
virtual objects to coexist in motion in immersive game environments. This will require the illusion that real and virtual objects interact physically together in a plausible way. The Motion in Augmented Reality Games (MARG) engine described in this paper has been developed to allow these kinds of game environments. The paper describes the design and implementation of the MARG engine and presents two proof-of-concept AR games that have been developed using it. Evaluations of these games have been performed and are presented to show that the MARG engine takes an important step in developing the next generation of motion-rich AR games.[hide] Patrick Lindstrom, Rong Hu, Sarah Jane Delany, and Brian Mac Namee, "SVM Based Active Learning with Exploration", AISTATS 2010 Active Learning and Experimental Design Workshop. (2010) |Full text| |abstract| This paper proposes using exploration guided approaches to select both informative and representative instances to present for labelling in an active learning process.[hide] Rong Hu, Patrick Lindstrom, Sarah Jane Delany, and Brian Mac Namee, "Exploring the Frontier of Uncertainty Space", AISTATS 2010 Active Learning and Experimental Design Workshop. (2010) |Full text| |abstract| We aim to investigate methods balancing exploitation with exploration in active learning to improve the performance of uncertainty sampling. Two exploration guided sampling methods are compared to uncertainty sampling on various real-life datasets from the 2010 Active Learning Challenge. Our initial experiments seems to indicate that combining exploration with uncertainty sampling improves performance on certain datasets but not all.[hide] Rong Hu, Brian Mac Namee, and Sarah Jane Delany, "Off to a good start: Using clustering to select the initial training set in active learning", In: Proceedings of the Twenty-Third International Florida Artificial Intelligence Research Society Conference (FLAIRS 2010). pp. 26-31. (2010) |Full text| |abstract| Active learning (AL) is used in textual classification to alleviate the cost of labelling documents for training. An important issue in AL is the selection of a representative sample of documents to label for the initial training set that seeds the process, and clustering techniques have been successfully used in this regard. However, the clustering techniques used are nondeterministic which causes inconsistent behaviour in the AL process. In this paper we first illustrate the problems associated with using non-deterministic clustering for initial training set selection in AL. We then examine the performance of three deterministic clustering techniques for this task and show that performance comparable to the non-deterministic approaches can be achieved without variations in behaviour.[hide] Rong Hu, Sarah Jane Delany, Brian Mac Namee, "EGAL: Exploration Guided Active Learning for TCBR", In Proceedings of International Conference on Case-based Reasoning (ICCBR) 2010. (2010) |abstract| The task of building labelled case bases can be approached
using active learning (AL), a process which facilitates the labelling of
large collections of examples with minimal manual labelling effort. The
main challenge in designing AL systems is the development of a selection
strategy to choose the most informative examples to manually label.
Typical selection strategies use exploitation techniques which attempt
to refine uncertain areas of the decision space based on the output of
a classifier. Other approaches tend to balance exploitation with exploration,
selecting examples from dense and interesting regions of the domain
space. In this paper we present a simple but effective explorationonly
selection strategy for AL in the textual domain. Our approach is
inherently case-based, using only nearest-neighbour-based density and
diversity measures. We show how its performance is comparable to the
more computationally expensive exploitation-based approaches and that
it offers the opportunity to be classifier independent.[hide] Brian Mac Namee & Sarah Jane Delany, "CBTV: Visualising Case Bases for Similarity Measure Design and Selection", In Proceedings of the International Conference on Case-based Reasoning (ICCBR) 2010. (2010) |pdf| |abstract| In CBR the design and selection of similarity measures is paramount. Selection can bene fit from the use of exploratory visualisation based techniques in parallel with techniques such as cross-validation accuracy comparison. In this paper we present the Case Base Topology Viewer (CBTV) which allows the application of diff erent similarity measures to a case base to be visualised so that system designers can explore the case base and the associated decision boundary space. We show, using a range of datasets and similarity measure types, how the idiosyncrasies of particular similarity measures can be illustrated and compared in CBTV allowing CBR system designers to make more informed choices.[hide]
2009
Pauline Rooney, Kevin O'Rourke, Greg Burke, Brian Mac Namee, and Claudia Igbrude, "Cross-disciplinary approaches for developing serious games in Higher Education: frameworks for food safety and environmental health education", In Proceedings of the First International IEEE Conference in Serious Games and Virtual Worlds (VS-GAmes '09). (2009) |Full text| |abstract| While some educators have adopted commercial off- the-shelf games for use in the classroom, such games may not always meet the individual requirements of lecturers whose courses are tied to specific learning outcomes. An alternative is to capitalise on in-house expertise in Higher Education and create serious games through cross-disciplinary team projects. This paper outlines such a project within one Higher Education institution. It describes synergies created across disciplines as a result of the collaboration on game design and implementation. It looks at tensions generated between the pedagogical requirements (of lecturers), entertainment objectives (of games designers) and technical excellence (sought by developers). Additionally, this paper looks at two serious games designed within this framework. Through reflections on the process and the product, this paper examines whether the collaborative process adopted within a Higher Education context can generate a product good enough to sit beside professionally designed games.[hide] Niels Schutte, John Kelleher, and Brian Mac Namee, "A mobile multimodal dialogue system for location based services", In Proceedings of the 9th Annual Information Technology & Telecommunication Conference (IT&T \'09). (2009) |Full text| |abstract| This paper describes ongoing work on the dialogue management components for LOK8, a multi- modal dialogue system. We describe our plans for a basic architecture of the system, the rough modules and outline the kinds of models in the project, as well as the next steps in our work.[hide] David Beaney and Brian Mac Namee, "Forked! A Demonstration of Physics Realism in Augmented Reality", In Proceedings of the International Symposium on Mixed and Augmented Reality (ISMAR 2009). (2009) |pdf| |abstract| 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 realistically
and believably through appropriate use of a physics engine.
The system allows users control a robotic forklift to manipulate
virtual crates in an AR environment. The paper also describes
a evaluation experiment in which it is shown that the physical interactions
between the forklift and the virtual creates are realistic and
believable enough to be comparable with the physical interactions
between a forklift and real crates.[hide] John Kelleher, Colm Sloan & Brian Mac Namee, "An investigation into the semantics of English topological prepositions", Cognitive Processing, vol 10(2), pp233-236, Springer, 2009. (2009) |Full text| |abstract| The topological prepositions ‘‘at’’, ‘‘on’’ and ‘‘in’’ constitute
a fundamental set of prepositions in English. The primary
constraint on the applicability of these prepositions is the
proximity of the object they locate to the landmark being
used. This shared constraint often results in an overlap in
their range of applicability. Differentiating between the
applicability of these prepositions is a problematic issue
requiring recourse to both conceptual (Herskovits 1986) and
functional (Coventry and Garrod 2004) information.
However, the topological relations that are present in a given
spatial configuration may also be important in the applicability
of these prepositions.[hide] Mark Dunne, Brian Mac Namee and John Kelleher, "Intelligent Virtual Agent: Creating a Multi-Modal 3D Avatar Interface", In Proceedings of the 9th Annual Information Technology & Telecommunication Conference (IT&T '09). (2009) |pdf| |abstract| Human-computer interactions can be greatly enhanced by the use of 3D avatars, representing both human users and computer systems in 3D virtual spaces. This allows the human user to interface with the computer system in a natural and intuitive human-to-human dialog (human face-to-face conversation). Hence, continuing to blur the boundaries between the real and virtual worlds. This proposed avatar system will go a step further and will use a camera to track the user’s head and eye movements during the dialog. This information will help to build rapport between the user and computer system by registering the user’s emotional state and level of interest. The system will adjust the dialog according to this information paying special attention to the user’s feedback. For example, one obvious benefit for head and eye tracking will be to allow the avatar to make and keep realistic eye contact with the user, but there is lots of room to expand on these techniques in this research.[hide] K. Kennedy, B. Mac Namee & S.J. Delany, "Credit Scoring: Solving the Low Default Portfolio Problem Using One-Class Classification", In Proceedings of the 20th Irish Conference on Artificial Intelligence and Cognitive Science (AICS 2009), pp 168-177. (2009) N. Hanlon, B. Mac Namee & J.D. Kelleher, "Just Say It: An Evaluation of Speech Interfaces for Augmented Reality Design Applications", In Proceedings of the 20th Irish Conference on Artificial and Cognitive Science (AICS 2009), pp 128 - 137. (2009) Kenneth Kennedy, Brian Mac Namee & Sarah-Jane Delany, "Low-Default Portfolio/One-Class Classi cation: A Literature Review", School of Computing Technical Report: SOC-AIG-001-09. (2009) |pdf| |abstract| Consider a bank which wishes to decide whether a credit applicant will obtain credit or not. The bank has to assess if the applicant will be able to redeem the credit. This is done by estimating the probability that the applicant will default prior to the maturity of the credit. To estimate this probability of default it is first necessary to identify criteria which separate the \good" from the \bad" creditors, such as loan amount and age or factors concerning the income of the applicant. The question then arises of how a bank identi es a sucient number of selective criteria that posses the necessary discriminatory power. As a solution, many traditional binary classi cation methods have been proposed with varying degrees of success. However, a particular problem with credit scoring is that defaults are only observed for a small subsample of applicants. An imbalance exists between the ratio of non-defaulters to defaulters. This has an adverse e ffect on the aforementioned binary classi cation methods. Recently one-class classifi cation approaches have been proposed to address the imbal-
ance problem. The purpose of this literature review is threefold: (i) Present the reader with an overview of credit scoring; (ii) Review existing binary classifi cation approaches; and (iii) introduce and examine one-class classifi cation approaches.[hide] Brian Mac Namee and Mark Dunne, "Widening the Evaluation Net", In Proceedings of the 9th International Conference on Intelligent Virtual Agents (IVA '09). (2009) |abstract| Intelligent Virtual Agent (IVA) systems are notoriously diffi cult to evaluate, particularly due to the subjectivity involved. From the various e fforts to develop standard evaluation schemes for IVA systems the scheme proposed by Isbister & Doyle, which evaluates systems across fi ve 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 fi ve 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 for computer game characters across the breadth of the fi ve categories is described.[hide] Brian Mac Namee and John D Kelleher, "Stepping Off the Stage", In Proceedings of the 22nd Annual Conference on Computer Animation and Social Agents (CASA '09). (2009) |abstract| 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 O the Stage system in which mixed-reality agents are allowed to step o the robot stage and move to other parts of the environment, o ering compelling new interaction possibilities.[hide] Rong Hu, Sarah Jane Delany, Brian Mac Namee, "Sampling with Confidence: Using k-NN Confidence Measures in Active Learning", In: Proceedings of the UKDS Workshop at 8th International Conference on Case-based Reasoning (ICCBR 09) p.181-192. (2009) |pdf| John Kelleher, Colm Sloan and Brian Mac Namee, "An Investigation into the Semantics of English Topological Prepositions", In Proceedings of the 4th International Conference on Spatial Cognition. Rome, September 14-18. (2009) |Full text| P Rooney, K O'Rourke, B Mac Namee, G Burke, C Igbrude, "Cross-disciplinary approaches for developing serious games in Higher Education", In Proceedings of the First International IEEE Conference in Serious Games and Virtual Worlds (VS-Games '09). (2009) |pdf| |abstract| While some educators have adopted commercial off-the-shelf games for use in the classroom, such games may not always meet the individual requirements of lecturers whose courses are tied to specific learning outcomes. An alternative is to capitalise on in-house expertise in Higher Education and create serious games through cross-disciplinary team projects. This paper outlines such a project within one Higher Education institution. It describes synergies created across disciplines as a result of the collaboration on game design and implementation. It looks at tensions generated between the pedagogical requirements (of lecturers), entertainment objectives (of games designers) and technical excellence (sought by developers). Additionally, this paper looks at two serious games designed within this framework. Through reflections on the process and the product, this paper examines whether the collaborative process adopted within a Higher Education context can generate a product good enough to sit beside professionally designed games.[hide] Brian Mac Namee, "Agent Based Modeling in Computer Graphics and Games", In the Encyclopedia of Complexity and Systems Science, (Ed: Robert A . Meyers), Springer. (2009) |Full text| |abstract| A review of the state of the art of agent based modelling in computr graphics and games.[hide]
2008
John D. Kelleher & Brian Mac Namee, "A Review of Negation in Clinical Texts", Dublin Institute of Technology School of Computing Technical Report, SOC-AIG-001-08. (2008) |pdf| |abstract| A review of common approaches to negation detection in medical texts.[hide] Brian Mac Namee, John D. Kelleher and Sarah Jane Delany, "Medical Language Processing for Patient Diagnosis Using Text Classification and Negation Labelling", In Proceedings of the Second i2b2 Shared-Task Workshop
on Challenges in Natural Language Processing for Clinical Data, American Medical Informatics Association Annual conference (AMIA '08). (2008) |pdf| |abstract| 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.[hide] Qian Zhang, Rong Hu, Brian Mac Namee & Sarah Jane Delany, "Back to the Future: Knowledge Light Case Base Cookery", In: Proceedings of the Workshop on the Computer Cooking Contest, 9th European Conference on Case-based Reasoning, M Schaaf (ed.) p239-248. (2008) |pdf| Patrick Lindstrom, Sarah Jane Delany, & Brian Mac Namee, "AUTOPILOT: Simulating Changing Concepts in Real Data", In Proceedings of the THE 19th Irish Conference on Artificial Intelligence and Cognitive Science. (2008) |pdf| |abstract| An increasingly important area in supervised incremental
learning is learning in the presence of changing concepts. Research into
concept drift is hampered by the lack of availability of controllable `real
life' datasets. In this paper we propose an approach for generating real
life data over which we have control of the concept and can generate
data exhibiting di erent types of concept drift. The approach uses a 3-D
driving game to produce a data stream of instances describing how to
drive around a track. The classi cation problem is learning the driving
technique of the driver, which can be a ected by changes in the driving
environment causing changes to the concept. The paper gives illustra-
tions of di erent types of concept drift and how standard concept drift
handling techniques can adapt to the concept drift.[hide] Rong Hu, Brian Mac Namee, and Sarah Jane Delany, "Sweetening the Dataset: Using Active Learning to Label Unlabelled Datasets", In Proceedings of the the 19TH Irish Conference on Artificial Intelligence and Cognitive Science (AICS '08). (2008) |pdf| |abstract| Supervised machine learning approaches assume the exis-
tence of a large collection of manually labelled examples of the problem
under consideration. However, in many cases such a collection does not
exist and creating one is time consuming and expensive. This can be a
barrier to the use of supervised learning in certain situations, particu-
larly when the doubt as to whether the system will work or not makes
the cost of creating a dataset unjusti¯able. Active learning is a machine
learning technique that has been used widely to create classi¯cation sys-
tems in the absence of large numbers of labelled examples, but that can
also be used to create such collections. This paper will describe a system
that uses active learning to label large collections of unlabelled data. We
will show that the system can create an accurately labelled dataset ap-
proximately 10 times the size of the set of examples manually labelled
by an expert. The experiments described are based on recipe data from
the 1st Computer Cooking Contest to be held at ECCBR'08 and focus
on identifying those recipes in the set that are desserts.[hide] Qingqing Dong, Zhongyi Sun & Brian Mac Namee, "Physics-Based Table-Top Mixed Reality Games", In Proceedings of the 39th Conference of the International Simulation & Gaming Association (ISAGA 2008). (2008) |pdf| John D. Kelleher and Brian Mac Namee, "Referring Expression Generation Challenge 2008 DIT System Descriptions (DIT-FBI, DIT-TVAS, DIT-CBSR, DIT-RBR, DIT-FBI-CBSR, DIT-TVAS-RBR)", In Proceedings of the 5th International Natural Language Generation Conference (INLG-08). (2008) |pdf| |abstract| This paper describes systems developed at DIT for the REG 2008 challenge.[hide]
2007
Pauline Rooney & Brian Mac Namee, "Using Serious Games for Learning - "False Dawn" or Untapped Resource?", CAL '07 Development, Disruption & Debate - D3, Trinity College Dublin, 26th-28th March 2007. (2007) Pauline Rooney & Brian Mac Namee, "Students@Play: Serious Games for Learning in Higher Education", INTED2007 International Technology, Education and Development. (2007) |pdf| |abstract| The rise of digital games over recent years has been exponential. While many are used for entertainment, digital games have also begun to permeate education — which has lead to the coining of the term “serious games”.
Proponents of serious games argue that they hold enormous potential for learning [2], by embodying a range of pedagogical strategies. While some have adopted commercial games for use in the classroom, others have designed games specifically for educational purposes. However, designing complex and realistic serious games with limited budgets and resources is difficult. In addition, achieving a successful balance between the competing goals of teaching and entertaining is extremely
challenging.
This paper describes a project undertaken at the Dublin Institute of Technology, which involved designing a serious game to teach food safety principles to undergraduates. The design strategy and process will be outlined, paying particular attention to the theoretical underpinnings of pedagogical design and game design. Results of initial pilots will be outlined.
The paper concludes by reflecting on lessons learned during the course of this project and by suggesting implications for the development and implementation of serious games in the wider Higher Education sector. Plans for future research in the area will also be detailed.[hide] Hao Guo & Brian Mac Namee, "Using Computer Vision to Create a 3D Representation of a Snooker Table for Televised Competition Broadcasting", In Proceedings of the 18th Irish Conference on Artifical Intelligence & Cognitive Science, pp 220-229. (2007) |pdf| |abstract| 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 the table.[hide]
2006
M. Wang & B. Mac Namee, "Bluetooth Assassin: A Location-Based Game For Mobile Devices", In Proceedings of the 9th International Conference on Computer Games: AI, Animation, Mobile, Educational & Serious Games CGAMES06. (2006) |pdf| |abstract| This short paper will describe Bluetooth Assassin, a location-based game developed for mobile devices.[hide] Rooney P, Mac Namee B, "Using Serious Games To Teach Food Safety: the Serious Gordon Case Study", Innovations in Learning Technology: New Frontiers Irish Learning Technology Association eLearning Symposium Trinity College Dublin. (2006) J. Gilligan, B. Mac Namee & P. Smith, "Interface Design Requirements For Playing Pong With A Single Switch Device", In Proceedings of the 9th International Conference on Computer Games: AI, Animation, Mobile, Educational & Serious Games CGAMES06. (2006) |pdf| |abstract| Motivated by a desire for increased accessibility in digital games, in this paper we consider the design requirements for an interface to a variation of the game Pong for single-switch users. We consider the issues in the design of accessible interfaces for games and propose a set of interface configurations for playing Pong, using this as a proof of concept for more elaborate games.[hide] B Mac Namee, P Rooney, P Lindstrom, A Ritchie, F Boylan & G Burke, "Serious Gordon: Using Serious Games to Teach Food Safety in the Kitchen", In Proceedings of the 9th International Conference on Computer Games: AI, Animation, Mobile, Educational & Serious Games CGAMES06. (2006) |pdf| |abstract| This paper will describe the development of Serious Gordon, an interactive digital game developed to tech the basics of kitchen food safety to workers in industries dealing with food. The motivations driving the development of the game will be described as will the development process itself. An initial evaluation of the game, from both a technical and pedagogical point of view, will be presented as will conclusions on the viability of using a commercial game engine for the purpose of developing educational games.[hide]
2004
B Mac Namee, "Proactive Persistent Agents: Using Situational Intelligence to Create Support characters in Character-Centric Computer Games", PhD Thesis, Trinity College Dublin. (2004) |pdf|
2003
C Peters, S Dobbyn, B Mac Namee & C O'Sullivan, "Smart Objects for Attentive Agents", In Proceedings of the International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision. (2003) |pdf| |abstract| We present an extended framework for modelling agent-object interactions in virtual environments. Our
framework is based on the concept of Smart Objects and provides agents with pre-programmed interaction
information for the automatic generation of animations. The ability to generate such animations without human
intervention is vital when constructing plausible, real-time agents. Unlike previous approaches, our model also
contains information for directing the attention of agents when interacting with objects. Such information is
useful for driving gaze behaviours, for example when grasping objects. Our framework supports both bottom-up
(attention capture) and top-down, task driven, simulation of behavioural animation on a per-object basis. It also
provides support for the management of the interactions of multiple agents with a single object. We show how
objects are designed and provide a concrete example of using the modelling approach with a gaze controller in an
animation system.[hide] B Mac Namee & P Cunningham, "Enhancing Non Player Characters in Computer Games using Psychological Models", ERCIM News No. 53 Cognitive Systems Sepcial. (2003) |Full text| B Mac Namee, S Dobbyn, P Cunningham & C O'Sullivan, "Simulating Virtual Humans Across Diverse Situations", In Proceedings of Intelligent Virtual Agents ’03, pp 159-63. (2003) |pdf| |abstract| Perhaps due to its existentiality, the fact that simulated virtual humans give no impression of having an existence beyond their interactions with human users is often ignored in intelligent agent systems for virtual human control. This paper will describe the Proactive Persistent Agent architecture, which is designed for the control of intelligent agents in character-centric computer games. The architecture allows agents give the impression of living beyond interactions with players. Along with details of the architecture a sample simulation will be described and some steps towards evaluation will be outlined.[hide] B Mac Namee & P Cunningham, "Creating Socially Interactive Non Player Characters: The µ-SIC System", International Journal of Intelligent Games & Simulations, Vol.2 No.1. (2003) |pdf|
2002
C O'Sullivan, J Cassell, H Vilhjalmsson, J Dingliana, S Dobbyn, B Mac Namee, C Peters & T Giang, "Levels of Detail for Crowds and Groups", Computer Graphics Forum, 21(4). (2002) |pdf| B Mac Namee, P Cunningham, S Byrne & O Corrigan, "The Problem of Bias in Training Data in Regression Problems in Medical Decision Support", Artificial Intelligence in Medicine, Volume 24, Issue 1, pp 51-70. (2002) |pdf| B Mac Namee, S Dobbyn, P Cunningham & C O'Sullivan, "Men Behaving Appropriately: Applying the Role Passing Technique to the ALOHA System", In Proceedings of Artificial Intelligence and the Simulation of Behaviour '02. (2002) |pdf| B Mac Namee & P Cunningham, "The µ-SIC System; A Connectionist Driven Simulation of Socially Interactive Agents", GAME-ON 2002. (2002) |pdf|
2001
C. Fairclough, M. Fagan, B. Mac Namee & P. Cunningham, "Research Directions for AI in Computer Games", In Proceedings of the 12th Irish Conference on AI and Cognitive Science. (2001) |pdf| B Mac Namee & P Cunningham, "Proposal for an Agent Architecture for Proactive Persistent Non Player Characters", In Proceedings of the 12th Irish Conference on Artificial Intelligence and Cognitive Science, pp. 221 - 232. (2001) |pdf|
|