http://hdl.handle.net/10197/853 2013-05-23T14:35:30Z 2013-05-23T14:35:30Z Ballatore, Andrea Bertolotto, Michela Wilson, David C. http://hdl.handle.net/10197/3973 2013-01-09T16:17:51Z 2012-10-01T00:00:00Z

Geographic Knowledge Extraction and Semantic Similarity in OpenStreetMap Ballatore, Andrea; Bertolotto, Michela; Wilson, David C. In recent years, a web phenomenon known as Volunteered Geographic Information (VGI) has produced large crowdsourced geographic data sets. OpenStreetMap (OSM), the leading VGI project, aims at building an open-content world map through user contributions. OSM semantics consists of a set of properties (called 'tags') describing geographic classes, whose usage is defined by project contributors on a dedicated Wiki website. Because of its simple and open semantic structure, the OSM approach often results in noisy and ambiguous data, limiting its usability for analysis in information retrieval, recommender systems and data mining. Devising a mechanism for computing the semantic similarity of the OSM geographic classes can help alleviate this semantic gap. The contribution of this paper is twofold. It consists of (1) the development of the OSM Semantic Network by means of a web crawler tailored to the OSM Wiki website; this semantic network can be used to compute semantic similarity through co-citation measures, providing a novel semantic tool for OSM and GIS communities; (2) a study of the cognitive plausibility (i.e. the ability to replicate human judgement) of co-citation algorithms when applied to the computation of semantic similarity of geographic concepts. Empirical evidence supports the usage of co-citation algorithms-SimRank showing the highest plausibility-to compute concept similarity in a crowdsourced semantic network.

2012-10-01T00:00:00Z Balado, Félix http://hdl.handle.net/10197/3971 2013-01-09T16:23:23Z 2012-10-18T00:00:00Z

Capacity of DNA Data Embedding Under Substitution Mutations Balado, Félix A number of methods have been proposed over the last decade for encoding information using deoxyribonucleic acid (DNA), giving rise to the emerging area of DNA data embedding. Since a DNA sequence is conceptually equivalent to a sequence of quaternary symbols (bases), DNA data embedding (diversely called DNA watermarking or DNA steganography) can be seen as a digital communications problem where channel errors are analogous to mutations of DNA bases. Depending on the use of coding or noncoding DNA host sequences, which respectively denote DNA segments that can or cannot be translated into proteins, DNA data embedding is essentially a problem of communications with or without side information at the encoder. In this paper the Shannon capacity of DNA data embedding is obtained for the case in which DNA sequences are subject to substitution mutations modelled using the Kimura model from molecular evolution studies. Inferences are also drawn with respect to the biological implications of some of the results presented.

2012-10-18T00:00:00Z Saad, Mohamed M. http://hdl.handle.net/10197/3969 2012-12-18T16:50:03Z 2012-10-03T00:00:00Z

High accuracy Location Estimation of a Mobile Tag using One-way UWB Signalling Saad, Mohamed M. This paper presents a novel algorithm for determining the 3D location of a Mobile Tag (MT) using wireless Base Stations (BSs) and Ultra Wide Band (UWB) one-way signaling. The algorithm is designed for low power, rapid deployment applications in which the BSs are independent, wireless UWB transceivers located at known positions and the tags are receiveonly or transmit-only UWB mobile units. The algorithm utilizes multi-BS time synchronization and hybrid Time Difference of Arrival-Time of Flight (TDoA-ToF) localization to achieve high accuracy tag localization. The algorithm consists of two concurrent tasks. In task I, the BSs exploit periodic inter-BS transmissions to obtain high accuracy multi-BS time synchronization. In task II, a hybrid TDOA-TOF algorithm is used to determine the location of the MT. The algorithm is based on timestamping, or control, of packet Time of Emission (ToE) and estimation of the packet Time of Arrival (ToA). As such, the method is appropriate for use with, but not limited to, IEEE 802.15.4a UWB. In simulations assuming a typical 2 cm standard deviation in ToA estimation error the proposed algorithm was found to provide a RMS error of 2.1 ps and 4.8 ∗ 10−6 ppm for time offset and crystal clock offset between BSs respectively; and a RMS error in MT location estimation of 2.2 cm; which is 36% better accuracy than the conventional TDoA method. Ubiquitous Positioning Indoor Navigation and Location Based Service (UPINLBS), Helsinki, Finland, October, 2012

2012-10-03T00:00:00Z Saad, Mohamed M. http://hdl.handle.net/10197/3968 2012-12-18T16:49:26Z 2012-06-01T00:00:00Z

High Accuracy Reference-free Ultrasonic Location Estimation Saad, Mohamed M. This paper presents a novel reference-free ultrasonic indoor location system. Unlike most previous proposals, the mobile device (MD) determines its own position based only on ultrasonic signals received at a compact sensor array and sent by a fixed independent beacon. No radio frequency or wired timing reference signal is used. Furthermore, the system is privacy aware and one way in that the receive-only MD determines its own position based on ultrasonic signals received from fixed transmit-only beacons. The MD uses a novel hybrid angle of arrival (AoA)¿time of flight (ToF) with timing lock algorithm to determine its location relative to the beacons with high accuracy. The algorithm utilizes an AoA-based location method to obtain an initial estimate of its own location. Based on this, it estimates the timing offsets (TOs) between the MD clock and the beacon transmissions. The average TO and the known periodicities of the beacon signals are then used to obtain a second more accurate MD location estimate via a ToF method. The system utilizes wideband spread spectrum ultrasonic signaling in order to achieve a high update rate and robustness to noise and reverberation. A prototype system was constructed, and the algorithm was implemented in software. The experimental results show that the method provides 3-D accuracy better than 9.5 cm in 99% of cases, an 80% accuracy improvement over the conventional AoA-only method.

2012-06-01T00:00:00Z Saad, Mohamed M. Bleakley, Chris Dobson, Simon http://hdl.handle.net/10197/3967 2012-12-18T16:49:11Z 2011-10-01T00:00:00Z

Robust High Accuracy Ultrasonic Range Measurement System Saad, Mohamed M.; Bleakley, Chris; Dobson, Simon This paper presents a novel method for ultrasonic range estimation. The method uses a wideband frequency-hop spread spectrum ultrasonic signal to increase robustness to noise and reverberation. The method applies cross-correlation with earliest peak search and a novel minimum variance search technique to correct the error in the cross-correlation time-of-flight estimate to within one wavelength of the carrier before applying a phase-shift technique for subwavelength range refinement. The method can be implemented digitally in software and only requires low-cost hardware for signal transmission and acquisition. Experimental results show an accuracy of better than 0.5 mm in a typical office environment.

2011-10-01T00:00:00Z Yadav, Nagesh Bleakley, Chris http://hdl.handle.net/10197/3965 2012-12-18T16:48:47Z 2012-09-06T00:00:00Z

Hybrid Bayesian Approach for Fusing Range-based and Sourceless Localization Estimates Under Non-Stationary Observability Yadav, Nagesh; Bleakley, Chris The paper proposes a hybrid Bayesian approach for multi-sensor data fusion for 3D localization. The approach addresses the problem of fusing range-based and sourceless localization estimates under conditions of varying observability in the range-based sub-system. The proposed localization approach uses a mixture of Single-Hypothesis-Tracking (e.g. Kalman filter) and Multi-Hypothesis-Tracking (MHT) (e.g. Particle Filters) Bayesian filtering to improve tracking accuracy under conditions of varying observability. Under conditions of sufficient (or no) range measurements a single hypothesis approach is used. Under the condition of insufficient range measurements (i.e, 1 or 2 ranges), MHT is used, since it more accurately models the distribution of real error in the estimated positions by means of Gaussian mixtures rather that a single Gaussian. The results show up to 10% improvement in 3D position estimation as compared to Single-Constraint-at-a-Time (SCAAT) approach and upto 24% improvement compared to an Extended Kalman Filter approach for intermittent 3 second partial range occlusions when tracking human arm movements. 6th IEEE International Conference on Intelligent Systems IS’12, Sofia, Bulgaria, September 6-8, 2012

2012-09-06T00:00:00Z Ballatore, Andrea Wilson, David C. Bertolotto, Michela http://hdl.handle.net/10197/3936 2012-11-29T14:46:59Z 2012-10-15T00:00:00Z

The Similarity Jury: Combining expert judgements on geographic concepts Ballatore, Andrea; Wilson, David C.; Bertolotto, Michela A cognitively plausible measure of semantic similarity between geographic concepts is valuable across several areas, including geographic information retrieval, data mining, and ontology alignment. Semantic similarity measures are not intrinsically right or wrong, but obtain a certain degree of cognitive plausibility in the context of a given application. A similarity measure can therefore be seen as a domain expert summoned to judge the similarity of a pair of concepts according to her subjective set of beliefs, perceptions, hypotheses, and epistemic biases. Following this analogy, we first define the similarity jury as a panel of experts having to reach a decision on the semantic similarity of a set of geographic concepts. Second, we have conducted an evaluation of 8 WordNet-based semantic similarity measures on a subset of OpenStreetMap geographic concepts. This empirical evidence indicates that a jury tends to perform better than individual experts, but the best expert often outperforms the jury. In some cases, the jury obtains higher cognitive plausibility than its best expert. 6th International Workshop on Semantics and Conceptual Issues in Geographical Information Systems (SeCoGIS 2012) (part of ER 2012), Florence, Italy, October, 2012

2012-10-15T00:00:00Z O'Donnell, Anne Bleakley, Chris Reviriego, P. Maestro, J.A. http://hdl.handle.net/10197/3935 2012-11-28T13:11:54Z 2009-06-01T00:00:00Z

Efficient Concurrent Error Detection and Correction of Soft Errors in NTT-based Convolutions O'Donnell, Anne; Bleakley, Chris; Reviriego, P.; Maestro, J.A. A system for soft error detection and correction is proposed for digital Integrated Circuit (IC) implementation of convolution. The convolution is implemented in a Residue NumberSystem using Fermat Number Theoretic Transforms. The flexibility afforded by the Modified Overlap Technique in allowing transforms of differing lengths in a convolution makes it possible to easily detect and correct soft errors by means of a Single Redundant Channel and pattern matching technique. The proposed system gives area reductions in the majority of cases examined, when compared with Triple Modular Redundancy. In the case of large (e.g. 28 and 32 bit) word lengths, the proposed system provides area reductions of up to 30%. 20th IET Irish Signals and Systems Conference (ISSC), Dublin, Ireland, June, 2009

2009-06-01T00:00:00Z McNally, Kevin O'Mahony, Michael P. Coyle, Maurice Briggs, Peter Smyth, Barry http://hdl.handle.net/10197/3913 2012-11-23T15:42:47Z 2011-10-01T00:00:00Z

A Case Study of Collaboration and Reputation in Social Web Search. McNally, Kevin; O'Mahony, Michael P.; Coyle, Maurice; Briggs, Peter; Smyth, Barry Although collaborative searching is not supported by mainstream search engines, recent research has high- lighted the inherently collaborative nature of many web search tasks. In this paper, we describe HeyStaks (www.heystaks.com), a collaborative web search framework that is designed to complement mainstream search engines. At search time, HeyStaks learns from the search activities of other users and leverages this information to generate recommendations based on results that others have found relevant for similar searches. The key contribution of this paper is to extend the HeyStaks social search model by considering the search expertise, or reputation, of HeyStaks users and using this information to enhance the result recommendation process. In particular, we propose a reputation model for HeyStaks users that utilises the implicit collaboration events that take place between users as recommendations are made and selected. We describe a live-user trial of HeyStaks that demonstrates the relevance of its core recommendations and the ability of the reputation model to further improve recommendation quality. Our findings indicate that incorporating reputation into the recommendation process further improves the relevance of HeyStaks recommendations by up to 40%.

2011-10-01T00:00:00Z Keegan, Stephen O'Hare, G. M. P. (Greg M. P.) O'Grady, Michael J. http://hdl.handle.net/10197/3912 2012-11-23T15:22:04Z 2012-01-01T00:00:00Z

Retail in the Digital City Keegan, Stephen; O'Hare, G. M. P. (Greg M. P.); O'Grady, Michael J. Conventional high street retailers face a multitude of challenges if they are to survive and thrive. Some of these difficulties arise from structural and economic issues; others may be sociological and demographic. However, to thrive, retailers must be perceived as being competitive, and must adopt innovative and invigorating strategies to maximise the potential of their situations while offsetting the limitations. In this paper, it is proposed that a judicious combination of low-cost Information and Communication Technologies (ICTs) could enable small retailers harness the benefits  of  the  information society and provide services congruent with the digital city concept. As an illustration of the issues involved, pertinent results from a systematic end-user evaluation of Easishop are discussed.

2012-01-01T00:00:00Z O'Grady, Michael J. O'Hare, G. M. P. (Greg M. P.) http://hdl.handle.net/10197/3911 2012-11-23T14:53:26Z 2012-01-01T00:00:00Z

The Ambient Digital Library O'Grady, Michael J.; O'Hare, G. M. P. (Greg M. P.) Conventional digital libraries increasingly support remote access from mobile devices. However, the archetypical mobile user differs from the conventional user in a number of aspects; of these the most important is context. Synonymous with mobile computing is the context concept, and factoring the availability of select contextual elements into the design of digital libraries offers significant opportunities for adapting and personalising services for the mobile computing community. This paper proposes the Ambient Digital Library as a construct for integrating digital content, contextual parameters and user models. In this way, a digital library may be made more accessible to a broader category of mobile user.

2012-01-01T00:00:00Z Bourke, Steven Healy, Graham Smeaton, Alan F. Smyth, Barry http://hdl.handle.net/10197/3910 2013-05-22T09:17:46Z 2012-06-21T00:00:00Z

Introducing social networks and brain computer interaction Bourke, Steven; Healy, Graham; Smeaton, Alan F.; Smyth, Barry It is well known that the brain generates electrical patterns of activity in response to visual stimuli such as faces or any- thing that captures attention in a significant way. Signals of this type can be detected using an EEG (Electroencephalograph) system where we attach electrodes to the scalp and we amplify the detected signals and use a computer to capture them in real time. In this paper we examine the role that automatic sensing of brain activity may have on how users interact with interactive applications like Facebook. This offers a new opportunity for implicit feedback into such systems and in our work we focus on social networking applications. We demonstrate some of these implicit responses with experimental data captured while a user searched Facebook for photos of friends while being connected to an EEG. Finally, we discuss the implications that this kind of automatic implicit feedback may have on future design of such systems. iHCI 2012: Irish Human Computer Interaction Conference 2012, Galway, June 20 - 21

2012-06-21T00:00:00Z Mooney, Catherine Haslam, Niall J. Pollastri, Gianluca Shields, Denis C. http://hdl.handle.net/10197/3891 2012-11-07T15:27:40Z 2012-10-01T00:00:00Z

Towards the Improved Discovery and Design of Functional Peptides: Common Features of Diverse Classes Permit Generalized Prediction of Bioactivity Mooney, Catherine; Haslam, Niall J.; Pollastri, Gianluca; Shields, Denis C. The conventional wisdom is that certain classes of bioactive peptides have specific structural features that endow their particular functions. Accordingly, predictions of bioactivity have focused on particular subgroups, such as antimicrobial peptides. We hypothesized that bioactive peptides may share more general features, and assessed this by contrasting the predictive power of existing antimicrobial predictors as well as a novel general predictor, PeptideRanker, across different classes of peptides.We observed that existing antimicrobial predictors had reasonable predictive power to identify peptides of certain other classes i.e. toxin and venom peptides. We trained two general predictors of peptide bioactivity, one focused on short peptides (4-20 amino acids) and one focused on long peptides (>20 amino acids). These general predictors had performance that was typically as good as, or better than, that of specific predictors. We noted some striking differences in the features of short peptide and long peptide predictions, in particular, high scoring short peptides favour phenylalanine. This is consistent with the hypothesis that short and long peptides have different functional constraints, perhaps reflecting the difficulty for typical short peptides in supporting independent tertiary structure.We conclude that there are general shared features of bioactive peptides across different functional classes, indicating that computational prediction may accelerate the discovery of novel bioactive peptides and aid in the improved design of existing peptides, across many functional classes. An implementation of the predictive method, PeptideRanker, may be used to identify among a set of peptides those that may be more likely to be bioactive.

2012-10-01T00:00:00Z O'Grady, Michael J. O'Hare, G. M. P. (Greg M. P.) http://hdl.handle.net/10197/3881 2012-11-02T15:44:07Z 2012-03-30T00:00:00Z

How Smart Is Your City? O'Grady, Michael J.; O'Hare, G. M. P. (Greg M. P.) The idea of ambient intelligence implies an intrinsic link between individuals and their environment, enabling individuals to access and interact with computing artifacts in ways that are intuitive and do not disrupt everyday activities. Given the many different environments encountered as part of everyday life—within the home (1) as well as beyond it—enabling such interaction is a formidable technological challenge. The reward may be an environment that is safer, uses less energy, and responds to the needs of all individuals (see the figure). Recent advances in embedded systems, robotics, and sensor technology suggest that ambient intelligence may indeed be realized, particularly if crucial privacy and security concerns are addressed.

2012-03-30T00:00:00Z Kelly, Daniel Coughlan, Garrett Green, Brian Caulfield, Brian http://hdl.handle.net/10197/3874 2012-10-16T15:31:52Z 2012-05-17T00:00:00Z

Automatic Detection of Tackles in Elite Level Rugby Union Kelly, Daniel; Coughlan, Garrett; Green, Brian; Caulfield, Brian Elite rugby union teams currently employ technology in order to monitor and evaluate the physical demands of training and games on their players. Tackling has been shown to be the most common cause of injury in rugby union (Fuller et al. (2007a), Garraway et al. (1999)). However, current player monitoring technology does not effectively evaluate player tackling measurements. Sensing devices, currently being used by elite rugby union teams, contain a GPS receiver and a 3-axis accelerometer. GPS has been utilized to measure player speed and distance. Accelerometers, on the other hand, have an under-utilized potential to analyse body impact and collisions. Presented at the IRFU Sports Medicine Conference: Injury Prevention in Rugby Union, May 17th-19th, 2012 in the AVIVA Stadium, Dublin

2012-05-17T00:00:00Z Yadav, Nagesh Bleakley, Chris http://hdl.handle.net/10197/3862 2012-10-11T17:07:57Z 2011-10-28T00:00:00Z

Two Stage Kalman Filtering for Position Estimation Using Dual Inertial Measurement Units Yadav, Nagesh; Bleakley, Chris Herein a two stage Kalman filter based algorithm is proposed for processing of Inertial Measurement Unit (IMU) data to obtain accurate position estimation over a short period of time. The proposed algorithm uses a novel sensor placement strategy on rigid body. An Extended Kalman filter algorithm incorporates these placement constraints to achieve accurate position estimation. The results show 30% improvement in position estimation as compared to a conventional Dead Reckoning (DR) approach. To the best of the authors' knowledge, the proposed technique is the first which employs spatially separated dual IMUs on a single rigid body for position estimation. IEEE Sensors 2011, Limerick, Ireland, 28-31 October, 2011

2011-10-28T00:00:00Z Yadav, Nagesh Bleakley, Chris Lennon, Olive http://hdl.handle.net/10197/3861 2012-10-11T16:38:37Z 2010-09-02T00:00:00Z

Wearable Absolute 6 DOF Exercise Training System for Post Stroke Rehabilitation Yadav, Nagesh; Bleakley, Chris; Lennon, Olive This paper introduces a multidisciplinary research effort to design an interactive, real time system to assist rehabilitation of stroke patients. The proposed system aims to help stroke survivors with limited mobility to relearn lost skills and regain maximal functional independence. The system assesses the quality of exercise being performed and provides advisory feedback to the patient in order to enable task specific training and correct motor relearning. The system uses a novel, ambulatory and wearable 6 Degree of Freedom (DOF) motion capture system composed of miniature ultrasonic and inertial sensors. The system captures the 3D kinematic parameters of the subject¿s movement while performing exercise, enabling tele-medicine applications or subsequent review by clinical experts. The paper presents the architecture of the aforementioned system and results from early stages of the research. 4th Irish Human Computer Interaction Conference (iHCI), Dublin, Ireland, 2-3 September, 2010

2010-09-02T00:00:00Z Reviriego, P. Bleakley, Chris Maestro, J.A. http://hdl.handle.net/10197/3860 2012-10-11T16:22:27Z 2012-06-01T00:00:00Z

A Novel Concurrent Error Detection Technique for the Fast Fourier Transform Reviriego, P.; Bleakley, Chris; Maestro, J.A. A novel Concurrent Error Detection technique for the Fast Fourier Transform (FFT) is proposed in this paper. The technique is similar to the conventional Sum of Squares (SOS) approach but is of lower computational complexity. Complexity reduction is achieved by checking the FFTs of two data blocks in a single calculation. The technique is based on checking the equivalence of the results of time and frequency domain calculations of the first sample of the circular convolution of the two blocks. In the case of error, the FFTs of both blocks must be recomputed. Assuming that errors are rare, this additional cost has negligible impact on the average number of operations per block. 23nd IET Irish Signals and Systems Conference, 28th - 29th June 2012, Maynooth

2012-06-01T00:00:00Z Phelan, Cormac Bleakley, Chris Cummins, Fred http://hdl.handle.net/10197/3859 2012-10-11T15:38:12Z 2009-06-10T00:00:00Z

Adapting and Parameterising Auditory Icons for use in a Synthetic Musical Instrument Phelan, Cormac; Bleakley, Chris; Cummins, Fred In this paper we describe the adaptation and parameterization of environmental auditory event structures for use in a real-time musical synthesizer. In doing so, we have developed a new software musical instrument based on the parametric representation of ecological sound structures, and which facilitates the application of typically non-musical auditory events in a musical context. Since this approach is to be realised within a low-latency, performance oriented synthesizer, our aim is not the development of computationally expensive physical models, but rather to effectively convey complex auditory events using arrays of simple sinusoidal components, while still retaining the key perceptual features of those events. By offering a performer ecologically-derived parameter control, we aim to encourage an Everyday Listening approach to electronic music performance, while also allowing the user to combine and develop typically unrelated elements of environmental auditory events. 20th IET Irish Signals and Systems Conference (ISSC), Dublin, Ireland, June, 2009

2009-06-10T00:00:00Z Ballal, Tarig Saad, Mohamed M. Bleakley, Chris http://hdl.handle.net/10197/3858 2012-10-11T15:30:36Z 2011-06-22T00:00:00Z

Design and Implementation of an Indoor Ultrasonic Communication System Ballal, Tarig; Saad, Mohamed M.; Bleakley, Chris In this paper, an indoor communication system using ultrasonic signals is described. The system uses differential binary phase-shift keying (DBPSK) for transmitting binary data as a part of an indoor positioning system. A synchronization and decoding approach is proposed that exploits the correlation properties of the DBPSK waveforms. All of the detection and decoding/demodulation processes are performed digitally - no analogue circuits are involved. Experiments that were carried out using off-the-shelf components confirmed the feasibility of the proposed system. 22nd IET Irish Signals and Systems Conference (ISSC), Dublin, Ireland, June 23-24, 2011

2011-06-22T00:00:00Z Reviriego, P. Sanchez-Macian, A. Maestro, J.A. Bleakley, Chris http://hdl.handle.net/10197/3857 2012-10-11T14:27:38Z 2010-06-23T00:00:00Z

Increasing the MTU size for Energy Efficiency in Ethernet Reviriego, P.; Sanchez-Macian, A.; Maestro, J.A.; Bleakley, Chris The commonly used Maximum Transfer Unit (MTU) on the Internet has remained unchanged for many years at around 1500 bytes due mainly to backward compatibility issues. This is in contrast with link data rate, which has increased by several orders of magnitude. In this paper, a new advantage of using larger MTUs is introduced, namely Energy Efficiency. In wire-line environments, the link power consumption is generally roughly independent of the number of frames that are transmitted resulting in a poor energy efficiency. This will change with the development of standards like IEEE 802.3az, Energy Efficient Ethernet. This new standard allows a link to enter a low power mode when there are no frames to transmit therefore making power consumption almost proportional to the link load. In this context the use of larger MTUs minimizes the number of transitions between the active and low power modes thereby improving energy efficiency. The benefits of using larger MTUs in terms of energy efficiency are analyzed in this paper. 21st IET Irish Signals and Systems Conference (ISSC), Cork, Ireland, 23rd-24th June, 2010

2010-06-23T00:00:00Z Russell, Sean E. Jordan, Howell O'Hare, G. M. P. (Greg M. P.) Collier, Rem http://hdl.handle.net/10197/3854 2012-10-11T14:02:19Z 2011-10-06T00:00:00Z

Agent Factory: A Framework for Prototyping Heterogeneous AOP Languages Russell, Sean E.; Jordan, Howell; O'Hare, G. M. P. (Greg M. P.); Collier, Rem Recent years have seen the emergence of a number of AOP languages. While these can mostly be characterized as logic-oriented languages that map situations to courses of action, they are based on a variety of concepts, resulting in obvious differences in syntax and semantics. Less obviously, the development tools and infrastructure - such as environment integration, reuse mechanisms, debugging, and IDE integration - surrounding these languages also vary widely. Two drawbacks of this diversity are: a perceived lack of transferability of knowledge and expertise between languages; and a potential obscuring of the fundamental conceptual differences between languages. These drawbacks can impact on both the languages' uptake and comparability. In this paper, we present a Common Language Framework that has emerged out of ongoing work on AOP languages that have been deployed through Agent Factory. This framework consists of a set of pre-written components for building agent interpreters, together with a set of tools that can be easily adapted to different AOP languages. Through this framework we have been able to rapidly prototype a range of different AOP languages, one of which is presented as a case study in this paper. Multiagent System Technologies, MATES 2011, 9th German Conference on Multi-Agent System Technologies, October 6-7, 2011

2011-10-06T00:00:00Z Saaya, Zurina Smyth, Barry Coyle, Maurice Briggs, Peter http://hdl.handle.net/10197/3853 2012-10-11T13:51:33Z 2011-06-28T00:00:00Z

Recognising and Recommending Context in Social Web Search Saaya, Zurina; Smyth, Barry; Coyle, Maurice; Briggs, Peter  In this paper we focus on an approach to social search, HeyStaks that is designed to integrate with mainstream search engines such as Google, Yahoo and Bing. HeyStaks is motivated by the idea that Web search is an inherently social or collaborative activity. Heystaks users search as normal but benefit from collaboration features, allowing searchers to better organise and share their search experiences. Users can create and share repositories of search knowledge (so-called search staks) in order to benefit from the searches of friends and colleagues. As such search staks are community-based information resources. A key challenge for HeyStaks is predicting which search stak is most relevant to the users current search context and in this paper we focus on this so-called stak recommendation issue by looking at a number of different approaches to profling and recommending community-search knowledge.  International Conference on User Modeling, Adaptation and Personalization (UMAP-11), Girona, Spain, July 11-15, 2011

2011-06-28T00:00:00Z Dong, Ruihai McCarthy, Kevin O'Mahony, Michael P. Schaal, Markus Smyth, Barry http://hdl.handle.net/10197/3836 2012-10-04T16:02:12Z 2012-02-14T00:00:00Z

Towards an intelligent reviewer's assistant: recommending topics to help users to write better product reviews Dong, Ruihai; McCarthy, Kevin; O'Mahony, Michael P.; Schaal, Markus; Smyth, Barry User opinions and reviews are an important part of the modern web and all major e-commerce sites typically provide their users with the ability to provide and access customer reviews across their product catalog. Indeed this has become a vital part of the service provided by sites like Amazon and TripAdvisor, so much so that many of us will routinely check appropriate product reviews before making a purchase decision, regardless of whether we intend to purchase online or not. The importance of reviews has highlighted the need to help users to produce better reviews and in this paper we describe the development and evaluation of a Reviewer's Assistant for this purpose. We describe a browser plugin that is designed to work with major sites like Amazon and to provide users with suggestions as they write their reviews. These suggestions take the form of topics (e.g. product features) that a reviewer may wish to write about and the suggestions automatically adapt as the user writes their review. We describe and evaluate a number of different algorithms to identify useful topics to recommend to the user and go on to describe the results of a preliminary live-user trial. ACM international conference on Intelligent User Interfaces (IUI '12), Lisbon, Portugal, February 14 - 17, 2012

2012-02-14T00:00:00Z Balado, Félix Haughton, David http://hdl.handle.net/10197/3835 2012-10-04T15:39:15Z 2012-06-28T00:00:00Z

Gene Tagging and the Data Hiding Rate Balado, Félix; Haughton, David We analyze the maximum number of ways in which one can intrinsically tag a very particular kind of digital asset: a gene, which is just a DNA sequence that encodes a protein. We consider gene tagging under the most relevant biological constraints: protein encoding preservation with and without codon count preservation. We show that our finite and deterministic combinatorial results are asymptotically—as the length of the gene increases— particular cases of the stochastic Gel’fand and Pinsker capacity formula for communications with side information at the encoder, which lies at the foundations of data hiding theory. This is because gene tagging is a particular case of DNA watermarking. 23nd IET Irish Signals and Systems Conference, Maynooth, Ireland, 28-29th June, 2012

2012-06-28T00:00:00Z Xu, Lina O'Hare, G. M. P. (Greg M. P.) Collier, Rem Murdoch, Olga http://hdl.handle.net/10197/3790 2012-09-05T15:46:56Z 2012-04-16T00:00:00Z

A Self-adaptive Unifying Mechanism For Autonomous Energy Management In Wireless Sensor Networks Xu, Lina; O'Hare, G. M. P. (Greg M. P.); Collier, Rem; Murdoch, Olga 4th Workshop on Adaptive and Reconfigurable Embedded Systems APRES 2012. Beijing, China, April 16 2012

2012-04-16T00:00:00Z Wan, Jie O'Grady, Michael J. O'Hare, G. M. P. (Greg M. P.) http://hdl.handle.net/10197/3788 2012-09-05T15:28:17Z 2012-06-18T00:00:00Z

Towards Holistic Activity Modeling and Behavioral Analyses Wan, Jie; O'Grady, Michael J.; O'Hare, G. M. P. (Greg M. P.) As the age profile of many societies continues to increase, supporting health, both mental and physical, is of increasing importance if independent living is to be maintained. Sensing and, ultimately, recognizing activities of daily living has been perceived as a prerequisite for detecting tasks that people avoid or find increasingly difficult to perform, as well as being indicators of certain illnesses. To date, extensive research efforts have been made on activity monitoring, recognition and assistance in indoor scenarios, frequently through smart home initiatives. However, the scenarios outside of the home have not received a similar degree of attention from the research community. This paper advocates a need for platforms that enable activity recognition in a range of environments, thus enabling the construction of more complex yet realistic activity models and behavior patterns. The design of a prototype supporting an integrated approach to sensor data capture and activity model construction is proposed. The application domain is that of dementia. 6th International workshop on Ubiquitous health and wellness (UbiHealth 2012), in the Pervasive 2012 Conference, Newcastle UK

2012-06-18T00:00:00Z O'Hare, G. M. P. (Greg M. P.) Muldoon, Conor O'Grady, Michael J. Collier, Rem Murdoch, Olga Carr, Dominic http://hdl.handle.net/10197/3763 2012-08-24T15:06:17Z 2012-04-01T00:00:00Z

Sensor Web Interaction O'Hare, G. M. P. (Greg M. P.); Muldoon, Conor; O'Grady, Michael J.; Collier, Rem; Murdoch, Olga; Carr, Dominic Ubiquitous sensing fuses the concepts of intelligent systems with ubiquitous computing in the development of novel sensor web applications, whereby the interaction of multiple disparate autonomous artefacts is a key requirement. In this paper, we present SIXTH, which is a middleware infrastructure for Ubiquitous Sensing that facilitates, and supports, the development and deployment of Sensor Web applications. SIXTH has been designed to be extensible, with provisions for user definable data retention policies, custom sensor data representations, and custom sensor node representations, whilst still providing a rich set of default behaviours. Within SIXTH, support is provided for the development and interaction of applications that incorporate both physical and cyber (virtual server side) sensors. With a view to supporting intelligent, in network, interaction policies, whereby sensor nodes must negotiate and coordinate their behaviour, the system has been designed to operate in conjunction with Agent Factory Micro Edition (AFME). AFME is a minimised footprint intelligent agent platform designed for resource constrained devices. It is based on the standard Agent Factory platform, which was developed for desktop machines, and is representative of a class of agent systems, which are referred to as Agent Oriented Programming frameworks. The paper discusses a ubiquitous mapping application that was developed using the middleware.

2012-04-01T00:00:00Z O'Hare, G. M. P. (Greg M. P.) Collier, Rem Dragone, Mauro O'Grady, Michael J. Muldoon, Conor De J. Montoya, Alcides http://hdl.handle.net/10197/3760 2012-08-20T16:39:39Z 2012-01-01T00:00:00Z

Embedding Agents within Ambient Intelligent Applications O'Hare, G. M. P. (Greg M. P.); Collier, Rem; Dragone, Mauro; O'Grady, Michael J.; Muldoon, Conor; De J. Montoya, Alcides This chapter reflects upon the challenges that confront the deployment of Ambient Intelligence (AmI) applications. Ambient Intelligence demands that everyday artefacts be imbued with intelligent reasoning capabilities together with the capacity for collaborative intelligent behaviour. Traditional ambient devices do not provide the requisite computational platform to support such requirements. With the ongoing developments of ubiquitous devices, however, the situation is changing. This chapter discusses a software stack, which supports the needs of ambient applications that incorporate embedded intelligence.

2012-01-01T00:00:00Z Salamó, Maria McCarthy, Kevin Smyth, Barry http://hdl.handle.net/10197/3759 2012-08-20T16:29:20Z 2012-06-17T00:00:00Z

Generating recommendations for consensus negotiation in group personalization services Salamó, Maria; McCarthy, Kevin; Smyth, Barry There are increasingly many personalization services in ubiquitous computing environments that involve a group of users rather than individuals. Ubiquitous commerce is one example of these environments. Ubiquitous commerce research is highly related to recommender systems that have the ability to provide even the most tentative shoppers with compelling and timely item suggestions. When the recommendations are made for a group of users, new challenges and issues arise to provide compelling item suggestions. One of the challenges a group recommender system must cope with is the potentially conflicting preferences of multiple users when selecting items for recommendation. In this paper we focus on how individual user models can be aggregated to reach a consensus on recommendations. We describe and evaluate nine different consensus strategies and analyze them to highlight the benefits of group recommendation using live-user preference data. Moreover, we show that the performance is significantly different among strategies.

2012-06-17T00:00:00Z Kelly, Daniel Coughlan, Garrett Green, Brian Caulfield, Brian http://hdl.handle.net/10197/3758 2012-10-16T15:25:06Z 2012-01-01T00:00:00Z

Automatic detection of collisions in elite level rugby union using a wearable sensing device Kelly, Daniel; Coughlan, Garrett; Green, Brian; Caulfield, Brian Elite rugby union teams currently employ the latest technology to monitor and evaluate the physical demands of training and games on their players. Tackling has been shown to be the most common cause of injury in rugby union, yet current player monitoring technology does not effectively evaluate player tackling measurements. Currently, to evaluate measurements specific to player tackles, a time-consuming manual analysis of player sensor data and video footage is required. The purpose of this work is to investigate tackle modeling techniques which can be utilised to automatically detect player tackles and collisions using sensing technology already being used by elite international and club level rugby union teams. This paper discusses issues relevant to automatic tackle analysis, describes a technique to detect tackles using sensing data and validates the technique by comparing automatically detected collisions to manually labeled collisions using data from elite club and international level players. The results of the validation show that the system is able to consistently identify collisions with very few false posi- tives and false negatives, achieving a recall and precision rating of 0.933 and 0.958, respectively. The aim is that the automatically detected tackles can provide coaching, medical and strength and conditioning staff with objective tackle-specific measurements, in real time, which can be used in injury prevention and rehabilitation strategies.

2012-01-01T00:00:00Z Wan, Jie O'Grady, Michael J. O'Hare, G. M. P. (Greg M. P.) http://hdl.handle.net/10197/3757 2012-08-20T15:53:37Z 2012-03-19T00:00:00Z

Sensing the sensor web Wan, Jie; O'Grady, Michael J.; O'Hare, G. M. P. (Greg M. P.) The maturity of pervasive computing and Wireless Sensor Networks (WSNs) enables the development of smart environments in many scenarios, including surveillance and environmental monitoring. Extensive research efforts are being undertaken in sensor perception, data capture, management and interpretation. Such developments are a prerequisite for paradigms such as pervasive sensing and crowd-sourcing services. For mobile users, the issues of dynamic sensor discovery, data interpretation and visualization must be addressed if such services are to be realized in practice. This paper explores the genesis of a generic framework for heterogeneous sensor access and data visualization in remote contexts. Paper presented at Pervasive Computing and Communications Workshops (PERCOM Workshops) 2012, 19th March, Lugano, Switzerland

2012-03-19T00:00:00Z O'Grady, Michael J. Angove, Philip Magnin, W O'Hare, G. M. P. (Greg M. P.) O'Flynn, Brendan Barton, John O'Mathuna, Cian http://hdl.handle.net/10197/3756 2012-08-20T15:45:23Z 2012-03-08T00:00:00Z

Enabling Intelligence on a Wireless Sensor Network Platform O'Grady, Michael J.; Angove, Philip; Magnin, W; O'Hare, G. M. P. (Greg M. P.); O'Flynn, Brendan; Barton, John; O'Mathuna, Cian Conventional Wireless Sensor Networks (WSNs) usually adopt a centralised approach to data processing and interpretation primarily due to the limited computation and energy resources available on sensor nodes. These constraints limits the potential of intelligent techniques to data analy- sis and such activities on the centralised host. In contrast, Intelligent WSNs (iWSNs) will be significantly more powerful thus enabling the harnessing of intelligent techniques for diverse purposes. One such purpose is the practical realisation of smart environments, and facilitating mobility and interaction with the inhabitants of such environments. As a step in this direction, this paper presents the design of an iWSN sensor node platform that enables the hosting of lightweight Artificial Intelligence (AI) frameworks whilst enabling the ubiquitous energy constraints be quantified, mitigated and managed. Paper presented at Practical Applications of Agents and Multi-Agent Systems 10th International Conference on Practical Applications of Agents and Multi-Agent Systems 28th of March, Salamanca, Spain

2012-03-08T00:00:00Z Wan, Jie O'Grady, Michael J. O'Hare, G. M. P. (Greg M. P.) Colakov, Todor http://hdl.handle.net/10197/3755 2012-08-20T15:36:00Z 2012-02-24T00:00:00Z

Browsing the Sensor Web : Pervasive Access for Wide-area Wireless Sensor Networks Wan, Jie; O'Grady, Michael J.; O'Hare, G. M. P. (Greg M. P.); Colakov, Todor Wireless Sensor Networks (WSNs) are almost exclusively regarded as data gathering entities. Various sensed data elements are captured and routed back to a central server for processing, visualization and interpretation. However, it can be realistically conjectured that scenarios will increasingly emerge that demand a facility for ad-hoc interaction with individual sensor nodes. Moreover, such interaction will occur in the physical environment in close proximity to where the sensor node is physically located. In this paper, the need for in-situ ad-hoc interaction is motivated. A methodology for facilitating such interaction is presented, and the implementation of a sensor browser is described. Paper presented at Sensornets 2012, 1st International Conference on Sensor Networks, 24-26 February, 2012, Rome, Italy

2012-02-24T00:00:00Z Salter-Townshend, Michael White, Arthur Gollini, Isabella Murphy, Thomas Brendan http://hdl.handle.net/10197/3753 2012-08-17T16:25:41Z 2012-08-01T00:00:00Z

Review of Statistical Network Analysis: Models, Algorithms, and Software Salter-Townshend, Michael; White, Arthur; Gollini, Isabella; Murphy, Thomas Brendan The analysis of network data is an area that is rapidly growing, both within and outside of the discipline of statistics. This review provides a concise summary of methods and models used in the statistical analysis of network data, including the Erdos–Renyi model, the exponential family class of network models, and recently developed latent variable models. Many of the methods and models are illustrated by application to the well-known Zachary karate dataset. Software routines available for implementing methods are emphasized throughout. The aim of this paper is to provide a review with enough detail about many common classes of network models to whet the appetite and to point the way to further reading.

2012-08-01T00:00:00Z Garcia Esparza, Sandra O'Mahony, Michael P. Smyth, Barry http://hdl.handle.net/10197/3746 2012-08-17T14:26:34Z 2012-05-01T00:00:00Z

Mining the Real-Time Web: A Novel Approach to Product Recommendation Garcia Esparza, Sandra; O'Mahony, Michael P.; Smyth, Barry Real-time web (RTW) services such as Twitter allow users to express their opinions and interests, often expressed in the form of short text messages providing abbreviated and highly personalized commentary in real-time. Although this RTW data is far from the structured data (movie ratings, product features, etc.) that is familiar to recommender systems research, it can contain useful consumer reviews on products, services and brands. This paper describes how Twitter-like short-form messages can be leveraged as a source of indexing and retrieval information for product recommendation. In particular, we describe how users and products can be represented from the terms used in their associated reviews. An evaluation performed on four different product datasets from the Blippr service shows the potential of this type of recommendation knowledge, and the experiments show that our proposed approach outperforms a more traditional collaborative-filtering based approach.

2012-05-01T00:00:00Z Ballatore, Andrea Wilson, David C. Bertolotto, Michela http://hdl.handle.net/10197/3740 2012-08-10T15:24:53Z 2012-04-01T00:00:00Z

A holistic semantic similarity measure for viewports in interactive maps Ballatore, Andrea; Wilson, David C.; Bertolotto, Michela In recent years, geographic information has entered the mainstream, deeply altering the pre-existing patterns of its production, distribution, and consumption. Through web mapping, millions of online users utilise spatial data in interactive digital maps. The typical unit of visualisation of geo-data is a viewport, defined as a bi-dimensional image of a map, fixed at a given scale, in a rectangular frame. In a viewport, the user performs analytical tasks, observing individual map features, or drawing high-level judgements about the objects in the viewport as a whole. Current geographic information retrieval (GIR) systems aim at facilitating analytical tasks, and little emphasis is put on the retrieval and indexing of visualised units, i.e. viewports. In this paper we outline a holistic, viewport-based GIR system, offering an alternative approach to feature-based GIR. Such a system indexes viewports, rather than individual map features, extracting descriptors of their high-level, overall semantics in a vector space model. This approach allows for efficient comparison, classification, clustering, and indexing of viewports. A case study describes in detail how our GIR system models viewports representing geographical locations in Ireland. The results indicate advantages and limitations of the viewport-based approach, which allows for a novel exploration of geographic data, using holistic semantics. Web and Wireless Geographical Information Systems International Symposium (W2GIS 2012). April 12-13, 2012, Naples, Italy

2012-04-01T00:00:00Z Campbell, Abraham G. Collier, Rem Dragone, Mauro Gorgu, Levent Holz, Thomas O'Grady, Michael J. O'Hare, G. M. P. (Greg M. P.) Sassu, Antonella Stafford, John W. http://hdl.handle.net/10197/3662 2013-02-26T10:02:22Z 2012-01-19T00:00:00Z

Facilitating ubiquitous interaction using intelligent agents Campbell, Abraham G.; Collier, Rem; Dragone, Mauro; Gorgu, Levent; Holz, Thomas; O'Grady, Michael J.; O'Hare, G. M. P. (Greg M. P.); Sassu, Antonella; Stafford, John W. Facilitating intuitive interaction is a prerequisite for the ubiquitous computing paradigm in all its manifestations. How to achieve such interaction in practice remains an open question. Such interfaces must be perceived as being intuitive across a variety of contexts, including those of the hosting devices. Indeed, the heterogeneity of the device population raises significant challenges. While individual devices and the interaction modalities supported by, each satisfy the requirements of individual domains, integrating diverse devices such that the user experiences is perceived as consistent and intuitive is problematic. This chapter discusses and illustrates how intelligent agents may be harnessed for integrating a range of diverse interface and interaction modalities such that the ubiquitous user interface concept may be validated.

2012-01-19T00:00:00Z McArdle, Gavin Ballatore, Andrea Tahir, Ali Bertolotto, Michela http://hdl.handle.net/10197/3661 2012-06-14T15:40:01Z 2010-01-01T00:00:00Z

An open-source web architecture for adaptive location-based services McArdle, Gavin; Ballatore, Andrea; Tahir, Ali; Bertolotto, Michela As the volume of information available online continues to grow, there is an increasing problem with information overload. This issue is also escalating in the spatial domain as the amount of geo-tagged information expands. With such an abundance of geo-information, it is difficult for map users to find content that is relevant to them. The problem is intensified when considering Location-Based Services. These services, which are dependent upon a user’s geographic location, generally operate on portable devices. These devices have a reduced screen size coupled with a limited processing power and so the need to provide personalised content is of paramount importance. Our previous work has focused on examining techniques to determine user interests in order to provide adapted and personalised map content which is suitable to display on portable devices. In this paper, in order to reduce the processing load on the user’s device, a novel client server architecture is employed. The framework is designed using open-source, web-based technologies which monitor user locations and interactions with map content overtime to produce a user profile. This profile is then used to render personalised maps. By utilising the power of web-based technologies in an innovative manner, any operational issues between different mobile devices is alleviated, as the device only requires a web-browser to receive map content. This article describes the techniques, architecture and technologies used to achieve this. 14th International Symposium on Spatial Data Handling (SDH), at the Joint International Conference on Theory, Data Handling and Modelling in GeoSpatial Information Science Hong Kong, 26-28 May, 2010

2010-01-01T00:00:00Z Tuite, Clíodhna Agapitos, Alexandros O'Neill, Michael Brabazon, Anthony http://hdl.handle.net/10197/3655 2012-06-14T15:21:50Z 2011-04-27T00:00:00Z

A preliminary investigation of overfitting in evolutionary driven model induction : implications for financial modelling Tuite, Clíodhna; Agapitos, Alexandros; O'Neill, Michael; Brabazon, Anthony This paper investigates the effects of early stopping as a method to counteract overfitting in evolutionary data modelling using Genetic Programming. Early stopping has been proposed as a method to avoid model overtraining, which has been shown to lead to a significant degradation of out-of-sample performance. If we assume some sort of performance metric maximisation, the most widely used early training stopping criterion is the moment within the learning process that an unbiased estimate of the performance of the model begins to decrease after a strictly monotonic increase through the earlier learning iterations. We are conducting an initial investigation on the effects of early stopping in the performance of Genetic Programming in symbolic regression and financial modelling. Empirical results suggest that early stopping using the above criterion increases the extrapolation abilities of symbolic regression models, but is by no means the optimal training-stopping criterion in the case of a real-world financial dataset. EvoFIN 2011, 5th European Event on Evolutionary and Natural Computation in Finance and Economics in EvoApplications, Torino, Italy, 27-29 April 2011

2011-04-27T00:00:00Z Swafford, John Mark Hemberg, Erik O'Neill, Michael Nicolau, Miguel Brabazon, Anthony http://hdl.handle.net/10197/3612 2012-05-15T15:40:44Z 2011-07-12T00:00:00Z

A non-destructive grammar modification approach to modularity in grammatical evolution Swafford, John Mark; Hemberg, Erik; O'Neill, Michael; Nicolau, Miguel; Brabazon, Anthony Modularity has proven to be an important aspect of evolutionary computation. This work is concerned with discovering and using modules in one form of grammar-based genetic programming, grammatical evolution (GE). Previous work has shown that simply adding modules to GE’s grammar has the potential to disrupt fit individuals developed by evolution up to that point. This paper presents a solution to prevent the disturbance in fitness that can come with modifying GE’s grammar with previously discovered modules. The results show an increase in performance from a previously examined grammar modification approach and also an increase in performance when compared to standard GE. Presented at GECCO '11, the 13th annual conference companion on Genetic and evolutionary computation, Dublin, Ireland, 12-16, July 2011

2011-07-12T00:00:00Z Schoofs, Anthony Delaney, Declan T. O'Hare, G. M. P. (Greg M. P.) Ruzzelli, Antonio G. http://hdl.handle.net/10197/3611 2012-05-15T15:02:54Z 2011-11-01T00:00:00Z

COPOLAN : non-invasive occupancy profiling for preliminary assessment of HVAC fixed timing strategies Schoofs, Anthony; Delaney, Declan T.; O'Hare, G. M. P. (Greg M. P.); Ruzzelli, Antonio G. Nowadays, control of heating, cooling and ventilation equipment operation is mainly achieved via timers with fixed setback schedules, configured using experience and standard models of space occupancy. Applying generic timing strategies is however rarely optimal. Sensor-based systems offer a solution for dynamic control of equipment operation using real-time space occupancy input, but both deployment time and cost constraints hinder their integration if savings and return on investment are uncertain. This work introduces COPOLAN, a tool that correlates power consumption pat- terns and computers’ VLAN activity. Utilising computers’ VLAN activity auditing is key to obtain the power state of employees’ computer equipment over time, a prime indicator of employees’ presence within a building. At low cost and non-invasively, COPOLAN uncovers misalignment and pro- duces ground for (1) determining opportunities of improv- ing HVAC timing strategies and (2) helping decision making prior to integrating new equipment such as sensor-based systems. COPOLAN has been experimented on within a University department, where misalignment between power consumption and space occupancy patterns have highlighted 10 % energy saving opportunities. BuildSys 2011, 3rd ACM Workshop On Embedded Sensing Systems For Energy-Efficiency In Buildings, Seattle, USA, 1 November 2011

2011-11-01T00:00:00Z Fagan, David http://hdl.handle.net/10197/3602 2012-08-14T13:34:05Z 2011-07-12T00:00:00Z

Genotype-phenotype mapping in dynamic environments with grammatical evolution Fagan, David The application of a genotype-phenotype mapping in Evolutionary Computation is not a new idea, however, how this mapping process is interpreted, and implemented varies wildly. In the majority of cases a very simple abstraction of the biological genotype-phenotype mapping is used, but as our understanding of this process increases, the deficiencies in current approaches become more evident. In this paper, an outline of what approaches have been taken in the investigation of the genotype-phenotype map in Grammatical Evolution are presented and an outline of proposed future work is introduced. GECCO 2011, ACM Genetic and Evolutionary Computation Conference, Graduate Student Workshop, Dublin, Ireland, 12-16th July, 2011

2011-07-12T00:00:00Z Salter-Townshend, Michael Murphy, Thomas Brendan http://hdl.handle.net/10197/3574 2012-12-18T15:39:22Z 2012-01-01T00:00:00Z

Sentiment analysis of online media Salter-Townshend, Michael; Murphy, Thomas Brendan A joint model for annotation bias and document classification is presented in the context of media sentiment analysis. We consider an Irish online media data set comprising online news articles with user annotations of negative, positive or irrelevant impact on the Irish economy. The joint model combines a statistical model for user annotation bias and a Naive Bayes model for the document terms. An EM algorithm is used to estimate the annotation bias model, the unobserved biases in the user annotations, the classifier parameters and the sentiment of the articles. The joint modeling of both the user biases and the classifier is demonstrated to be superior to estimation of the bias followed by the estimation of the classifier parameters. Paper presented at the DAGM-GfKl/IFCS 2011, Joint Conference of the German Classification Society (GfKl) and the German Association for Pattern Recognition (DAGM), August 31 to September 2, 2011 and at the IFCS 2011 Symposium of the International Federation of Classification Societies (IFCS), August 30, 2011, Frankfurt am Main, Germany

2012-01-01T00:00:00Z Agapitos, Alexandros O'Neill, Michael Brabazon, Anthony Theodoridis, Theodoros http://hdl.handle.net/10197/3573 2013-02-26T09:42:46Z 2011-08-31T00:00:00Z

Learning environment models in car racing using stateful genetic programming Agapitos, Alexandros; O'Neill, Michael; Brabazon, Anthony; Theodoridis, Theodoros For computational intelligence to be useful in creating game agent AI we need to focus on methods that allow the creation and maintenance of models for the environment, which the artificial agents inhabit. Maintaining a model allows an agent to plan its actions more effectively by combining immediate sensory information along with a memories that have been acquired while operating in that environment. To this end, we propose a way to build environment models for non-player characters in car racing games using stateful Genetic Programming. A method is presented, where general purpose 2-dimensional data-structures are used to build a model of the racing track. Results demonstrate that model-building behaviour can be cooperatively coevolved with car controlling behaviour in modular programs that make use of these models in order to navigate successfully around a racing track. Paper presented at the 2011 IEEE Conference on Computational Intelligence and Games (CIG’11), Seoul, South Korea, Aug.31-Sept.3, 2011

2011-08-31T00:00:00Z O'Grady, Michael J. O'Hare, G. M. P. (Greg M. P.) Collier, Rem http://hdl.handle.net/10197/3572 2012-04-17T13:48:05Z 2010-01-01T00:00:00Z

Mobile multimedia : reflecting on dynamic service provision O'Grady, Michael J.; O'Hare, G. M. P. (Greg M. P.); Collier, Rem Delivering multimedia services to roaming subscribers raises significant challenges for content providers. There are a number of reasons for this; however,the principal difficulties arise from the inherent differences between the nature of mobile computing usage, and that of its static counterpart. The harnessing of appropriate contextual elements pertaining to a mobile subscriber at any given time offers significant opportunities for enhancing and customising service delivery. Dynamic content provision is a case in point. The versatile nature of the mobile subscriber offers opportunities for the delivery of content that is most appropriate to the subscriber's prevailing context, and hence is most likely to be welcomed. To succeed in this endeavour requires an innate understanding of the technologies, the mobile usage paradigm and the application domain in question, such that conflicting demands may be reconciled to the subscriber's benefit. In this paper, multimedia-augmented service provision for mobile subscribers is considered in light of the availability of contextual information. In particular, context-aware pre-caching is advocated as a means of maximising the possibilities for delivering context-aware services to mobile subscribers in scenarios of dynamic contexts.

2010-01-01T00:00:00Z O'Neill, Michael Nicolau, Miguel Brabazon, Anthony http://hdl.handle.net/10197/3571 2012-04-17T13:40:36Z 2011-01-01T00:00:00Z

Dynamic environments can speed up evolution with genetic programming O'Neill, Michael; Nicolau, Miguel; Brabazon, Anthony We present a study of dynamic environments with genetic programming to ascertain if a dynamic environment can speed up evolution when compared to an equivalent static environment. We present an analysis of the types of dynamic variation which can occur with a variable-length representation such as adopted in genetic programming identifying modular varying, structural varying and incremental varying goals. An empirical investigation comparing these three types of varying goals on dynamic symbolic regression benchmarks reveals an advantage for goals which vary in terms of increasing structural complexity. This provides evidence to support the added difficulty variable length representations incur due to their requirement to search structural and parametric space concurrently, and how directing search through varying structural goals with increasing complexity can speed up search with genetic programming.

2011-01-01T00:00:00Z Fagan, David Nicolau, Miguel Hemberg, Erik O'Neill, Michael Brabazon, Anthony http://hdl.handle.net/10197/3570 2012-04-17T13:25:14Z 2011-04-14T00:00:00Z

Dynamic ant : introducing a new benchmark for genetic programming in dynamic environments Fagan, David; Nicolau, Miguel; Hemberg, Erik; O'Neill, Michael; Brabazon, Anthony In this paper we present a new variant of the ant problem in the dynamic problem domain. This approach presents a functional dynamism to the problem landscape, where by the behaviour of the ant is driven by its ability to explore the search space being constrained. This restriction is designed in such a way as to ensure that no generalised solution to the problem is possible, thus providing a functional change in behaviour.

2011-04-14T00:00:00Z Swafford, John Mark O'Neill, Michael Nicolau, Miguel Brabazon, Anthony http://hdl.handle.net/10197/3554 2012-08-08T11:42:35Z 2011-04-27T00:00:00Z

Exploring grammatical modification with modules in grammatical evolution Swafford, John Mark; O'Neill, Michael; Nicolau, Miguel; Brabazon, Anthony There have been many approaches to modularity in the field of evolutionary computation, each tailored to function with a particular representation. This research examines one approach to modularity and grammar modification with a grammar-based approach to genetic programming, grammatical evolution (GE). Here, GE’s grammar was modified over the course of an evolutionary run with modules in order to facilitate their appearance in the population. This is the first step in what will be a series of analysis on methods of modifying GE’s grammar to enhance evolutionary performance. The results show that identifying modules and using them to modify GE’s grammar can have a negative effect on search performance when done improperly. But, if undertaken thoughtfully, there are possible benefits to dynamically enhancing the grammar with modules identified during evolution. Presented at Genetic Programming - 14th European Conference, EuroGP 2011, Torino, Italy, April 27-29, 2011

2011-04-27T00:00:00Z Schoofs, Anthony Ruzzelli, Antonio G. O'Hare, G. M. P. (Greg M. P.) http://hdl.handle.net/10197/3547 2012-03-29T16:15:17Z 2011-03-24T00:00:00Z

Debugging low-power and lossy wireless networks : a survey Schoofs, Anthony; Ruzzelli, Antonio G.; O'Hare, G. M. P. (Greg M. P.) Recent economic and technical advances in wireless communication have allowed the deployment of low-power and lossy wireless networks—LowPANs, potentially comprised of a large number of nodes to serve new types of applications. However, the resource-constrained nature of microsensor platforms together with the unreliability and low-bandwidth of low-power and lossy wireless links have increased the risk and occurrence of network failures. Unlike with traditional wireless networks and controlled pre-deployment simulations and laboratory setups, likely events such as node crashes, inefficient networking and environmental interferences can potentially freeze a network post deployment. A survey of existing tools and related work in debugging LowPANs is presented, to provide a comprehensive state of the art of debugging tools and techniques. We divide debugging tools in two categories, pre-deployment tools and post-deployment tools, and evaluate their performance and limitations. From this study, we discuss the challenges in debugging LowPANs, providing the main issues and requirements that LowPANs’ specific constraints impose on debugging tools, to help developers choose the appropriate tool for specific needs.

2011-03-24T00:00:00Z