Placeholder image for staff profiles

Dr Colin O'Reilly


Research Fellow

Biography

Biography

I am a Research Fellow at the Institute for Communication Systems (ICS), University of Surrey. My research is in the area of machine learning and data mining. I am involved in the FP7 SocIoTal project.

I received the B.Sc. degree in Mathematics from Queen Mary College, University of London, an M.Eng in Telecommunications Engineering from Dublin City University, and the Ph.D from University of Surrey. My Ph.D thesis focused on anomaly detection.

Research interests

Machine learning; Anomaly detection; Distributed data; Non-stationary data; Univariate and multivariate time-series analysis; Kernel methods; Applications of machine learning in a wide variety of domains

My publications

Publications

O Reilly C, Gluhak A, Imran M (2014) Adaptive Anomaly Detection with Kernel Eigenspace Splitting and Merging, IEEE Transactions on Knowledge and Data Engineering 27 1 pp. 3-16
O Reilly C, Gluhak A, Imran M, Rajasegarar S (2012) Online anomaly rate parameter tracking for anomaly detection in wireless sensor networks, Sensor, Mesh and Ad Hoc Communications and Networks (SECON), 2012 9th Annual IEEE Communications Society Conference on pp. 191 -199-191 -199
OReilly C, Gluhak A, Imran M, Rajasegarar S (2014) Anomaly Detection in Wireless Sensor Networks in a Non-Stationary Environment, IEEE Surveys and Tutorials IEEE
O Reilly C, Gluhak A, Imran M (2013) Online anomaly detection with an incremental centred kernel hypersphere, Machine Learning for Signal Processing (MLSP), 2013 IEEE International Workshop on pp. 1-6
O'Reilly C, Gluhak A, Imran A (2016) Distributed Anomaly Detection using Minimum Volume Elliptical Principal Component Analysis, IEEE Transactions on Knowledge and Data Engineering 28 (9) pp. 2320-2333 IEEE
Principal component analysis and the residual error is an effective anomaly detection technique. In an environment where anomalies are present in the training set, the derived principal components can be skewed by the anomalies. A further aspect of anomaly detection is that data might be distributed across different nodes in a network and their communication to a centralized processing unit is prohibited due to communication cost. Current solutions to distributed anomaly detection rely on a hierarchical network infrastructure to aggregate data or models, however, in this environment links close to the root of the tree become critical and congested. In this paper, an algorithm is proposed that is more robust in its derivation of the principal components of a training set containing anomalies. A distributed form of the algorithm is then derived where each node in a network can iterate towards the centralized solution by exchanging small matrices with neighbouring nodes. Experimental evaluations on both synthetic and real-world data sets demonstrate the superior performance of the proposed approach in comparison to principal component analysis and alternative anomaly detection techniques. In addition, it is shown that in a variety of network infrastructures, the distributed form of the anomaly detection model is able to derive a close approximation of the centralized model.