Seminar by Dr Richard G. Clegg "Analysing time varying graphs"

Dr Richard G. Clegg is Senior Research Fellow in Electronic Engineering at UCL. Dr Clegg and a renowned expert in the statistical nature of network traffic, complex network analysis and overlay networks.

Abstract: Models which construct graphs have attracted a great deal of research interest.  Erdos-Reyni (random graphs), Watts-Strogatz (small worlds) and Barabasi-Albert (preferential attachment) all propose tractable mathematical models which produce graphs with different properties. It has been found that many real-life graphs have properties which are also properties of some of these models. For example, scale free behaviour is produced by the preferential attachment model and observed in social networks, computer networks, authorship networks and many others.  However, the exact statistical nature of these networks differs and there is a need to distinguish which model best fits a given "target" graph.

This talk describes the Framework for Evolving Topology Analysis (FETA) which uses combined models to produce an exact likelihood measure of whether a particular target graph has evolved using a hypothesised model.  The framework is shown to recover known parameters from artificial models and also to be able to predict goodness-of-fit of models on real data.  Example networks are drawn from the Internet, authorship networks and online social networks

Seminar by Mr Mr Abbas R. Ali:"In God We Trust, All Others Bring Data"

Our speaker is Mr Abbas R. Ali; an experienced Data Scientist at IBM Business Analytics and Optimization Centre of Competence and Bournemouth University.

Mr Ali received his B.S. degree in Computer Science and Mathematics in 2004, M.S. degree in Artificial Intelligence and Natural Language Processing in 2009 and is currently undertaking his PhD at BU. He is author of 6 very interesting papers in machine learning, statistics and predictive analytics domains. His current research interests include predictive and prescriptive, big data, and social network analytics.


This talk will be focus on applied side of Artificial Intelligence, Statistics and Mathematics:

a.    Introduction of Advanced Analytics

b.    Social Network Analytics(demonstration of telecommunication churn prediction and customer segmentation for marketing purpose)

c.    Entity Resolution Analytics(demonstration of Banking loan fraud detection)

d.    Text Analytics(demonstration of quality insights)

e.    Big Data Analytics(internet scale and run in-motion streams)


Location: PG 144, Poole House, BU (please mind that PG144 is in Thomas Hardy Suite building).

Seminar by Dr Damien Fay: "GlasDasha: predicting arrival times from crowd sourced Smartphone data without localisation or route maps"

Our speaker is Dr Damien Fay, Lecturer at BU, former mathematics Lecturer at the National University of Ireland and senior research associate in Cambridge and Cork.

Dr Fay has a very good track record in areas such as time series prediction using a wide range of approaches, Gaussian processes and applied graph theory to cite a few.

Abstract: Accurately predicting the arrival of occupants to a building would enable more efficient HVAC control and improved occupant comfort. We present an approach to arrival prediction through the use of Smartphones and WiFi access points. The techniques use the concept of a field, representing expected travel times from access points to an anchor location for different models of travel. The field is constructed from crowd-sourced data. Users maintain privacy by not revealing location information, but instead using offline reporting of access point IDs. The system is light on battery use, handles multiple travel modes, provides tailored predictions for individuals, and identifies deviations from normal behaviour.
We demonstrate the effectiveness of the approach by a live field study using data collected over a period of five months. There is also a large data analysis section to this talk which includes extracting modes from distributions using Gaussian Mixture Models, smoothing and in addition outlier detection.

Seminar by Dr Dariusz Krol “On Understanding Error Propagation Phenomenon”

Dr Dariusz Krol is senior IEEE member, Assistant Professor of Wrocław University of Technology and Marie Curie Senior Research Fellow at BU. Dr Krol has published a large number of influential papers in the area of knowledge propagation.

New INFER team members recruited

Two new INFER team members have been recruited:

1. Lecturer In Computational Intelligence, Dr Damien Fay, who joined in April 2013,

2. Lecturer in Computational Intelligence and Predictive Analytics, Dr Jianbing Ma, who joined in April 2013.

New PhD students recruited

Two new PhD students have been recruited:

1. Ms Bassma Al-Jubouri, who joined in January 2013,

2. Mr Abbas Raza Ali, who joined in April 2013.

Seminar by Mr Mateusz Wojciechowski "Communication Networks in Automotive Industry"

The seminar will take place at PG 142, Bournemouth University. Mr Wojciechowski will introduce and discuss several communication networks used in automobile industry like CAN, LIN, FlexRay and MOST.

Seminar by Dr Mavrovounioutis, "Ant Colony Optimization for Dynamic Optimization Problems"

The title of the talk is: “Ant Colony Optimization for Dynamic Optimization Problems”; Dr Mavrovouniotis will discuss very recent advances in nature-inspired metaheuristics in optimization problems with a special foucs on Ant Colony Optimization problems.

Venue: Wednesday, December the 5th, 16:00 at P302 (Poole House).

Special Session in INCONIP012 in Doha, Quatar: “Non-stationary Time Series Processing in Computational Neuroscience”

Event Date: 
12 Nov 2012 (All day) - 15 Nov 2012 (All day)

The 19th International Conference on Neural Information Processing

Special Session Organized by the INFER team: Non-stationary Time Series Processing in Computational Neuroscience

Doha, 12-15 November 2012

One of the most fundamental and yet unsolved problems in neuroscience is the understanding of the dynamics underlying the immediate and effortless perceptual processes. For instance, the reliable identification of speaker’s age, sex, identity or musical instruments in a noisy environment requires the on-line disentanglement of sophisticated temporal patterns of sounds, characterized by hundreds of variables (frequencies) which are separated by only 1/10 of a millisecond.

In other words, the enormous complexity of the human cognitive landscape requires the existence of an exceptionally fast and accurate dynamical code within the peripheral machinery and the cortex; which simultaneously adapts to continuous changes of external inputs and evaluates the flux of top-down information from higher cognitive areas. Performing such almost instantaneous robust pattern recognition is a very challenging task, not only for neurocompuational models but also for the state-of-the-art time series prediction algorithms. The nature of this incredibly precise machinery is still poorly understood. However, efforts in time series analyses of non-stationary neural recordings during the last decade could provide relevant insights for designing a new class of highly adaptive predictive models for rapidly varying underlying probability distributions.

Therefore, modeling the subtle trade-off between integration of complex information and exquisite temporal resolution in the human brain may enable us to build algorithms which perform with high precision and generalization capability in real-life, non-stationary environments. In this special session we propose the contribution of works which are focused in temporal pattern recognition on particularly challenging environments; which aim to go beyond out-of-sample performance measures on relatively stationary test datasets.

Seminar by Mr Renihard Dudda, "Data Mining at EVONIK and Impact on INFER"

Seminar by Mr Renihard Dudda, Evonik Industries AG, Germany, entitled "Data Mining at EVONIK and Impact on INFER"

Location: P302, Poole House, Bournemouth University.

Syndicate content