arXiv subjects

Uwe Aickelin

Publications and source records attributed to Uwe Aickelin.

At least 109 records · Page 6Linked to original sources

arXiv2013

Finding the creatures of habit; Clustering households based on their flexibility in using electricity

Changes in the UK electricity market, particularly with the roll out of smart meters, will provide greatly increased opportunities for initiatives intended to change households' electricity usage patterns for the benefit of the overall system. Users show differences in their regular behaviours and clustering households into similar groupings based on this variability provides for efficient targeting of initiatives. Those people who are stuck into a regular pattern of activity may be the least receptive to an initiative to change behaviour. A sample of 180 households from the UK are clustered into four groups as an initial test of the concept and useful, actionable groupings are found.

cs.LG↗

arXiv2013

Comparing Data-mining Algorithms Developed for Longitudinal Observational Databases

Longitudinal observational databases have become a recent interest in the post marketing drug surveillance community due to their ability of presenting a new perspective for detecting negative side effects. Algorithms mining longitudinal observation databases are not restricted by many of the limitations associated with the more conventional methods that have been developed for spontaneous reporting system databases. In this paper we investigate the robustness of four recently developed algorithms that mine longitudinal observational databases by applying them to The Health Improvement Network (THIN) for six drugs with well document known negative side effects. Our results show that none of the existing algorithms was able to consistently identify known adverse drug reactions above events related to the cause of the drug and no algorithm was superior.

cs.LG↗

arXiv2013

Extending a Microsimulation of the Port of Dover

Modelling and simulating the traffic of heavily used but secure environments such as seaports and airports is of increasing importance. This paper discusses issues and problems that may arise when extending an existing microsimulation strategy. We also discuss how extensions of these simulations can aid planners with optimal physical and operational feedback. Conclusions are drawn about how microsimulations can be moved forward as a robust planning tool for the 21st century.

cs.CE↗

arXiv2013

Biomarker Clustering of Colorectal Cancer Data to Complement Clinical Classification

In this paper, we describe a dataset relating to cellular and physical conditions of patients who are operated upon to remove colorectal tumours. This data provides a unique insight into immunological status at the point of tumour removal, tumour classification and post-operative survival. Attempts are made to cluster this dataset and important subsets of it in an effort to characterize the data and validate existing standards for tumour classification. It is apparent from optimal clustering that existing tumour classification is largely unrelated to immunological factors within a patient and that there may be scope for re-evaluating treatment options and survival estimates based on a combination of tumour physiology and patient histochemistry.

cs.LG↗

arXiv2013

Supervised Learning and Anti-learning of Colorectal Cancer Classes and Survival Rates from Cellular Biology Parameters

In this paper, we describe a dataset relating to cellular and physical conditions of patients who are operated upon to remove colorectal tumours. This data provides a unique insight into immunological status at the point of tumour removal, tumour classification and post-operative survival. Attempts are made to learn relationships between attributes (physical and immunological) and the resulting tumour stage and survival. Results for conventional machine learning approaches can be considered poor, especially for predicting tumour stages for the most important types of cancer. This poor performance is further investigated and compared with a synthetic, dataset based on the logical exclusive-OR function and it is shown that there is a significant level of 'anti-learning' present in all supervised methods used and this can be explained by the highly dimensional, complex and sparsely representative dataset. For predicting the stage of cancer from the immunological attributes, anti-learning approaches outperform a range of popular algorithms.

cs.LG↗

arXiv2013

The Application of a Data Mining Framework to Energy Usage Profiling in Domestic Residences using UK data

This paper describes a method for defining representative load profiles for domestic electricity users in the UK. It considers bottom up and clustering methods and then details the research plans for implementing and improving existing framework approaches based on the overall usage profile. The work focuses on adapting and applying analysis framework approaches to UK energy data in order to determine the effectiveness of creating a few (single figures) archetypical users with the intention of improving on the current methods of determining usage profiles. The work is currently in progress and the paper details initial results using data collected in Milton Keynes around 1990. Various possible enhancements to the work are considered including a split based on temperature to reflect the varying UK weather conditions.

cs.CE↗

arXiv2013

Creating Personalised Energy Plans. From Groups to Individuals using Fuzzy C Means Clustering

Changes in the UK electricity market mean that domestic users will be required to modify their usage behaviour in order that supplies can be maintained. Clustering allows usage profiles collected at the household level to be clustered into groups and assigned a stereotypical profile which can be used to target marketing campaigns. Fuzzy C Means clustering extends this by allowing each household to be a member of many groups and hence provides the opportunity to make personalised offers to the household dependent on their degree of membership of each group. In addition, feedback can be provided on how user's changing behaviour is moving them towards more "green" or cost effective stereotypical usage.

cs.CE↗

arXiv2013

Examining the Classification Accuracy of TSVMs with ?Feature Selection in Comparison with the GLAD Algorithm

Gene expression data sets are used to classify and predict patient diagnostic categories. As we know, it is extremely difficult and expensive to obtain gene expression labelled examples. Moreover, conventional supervised approaches cannot function properly when labelled data (training examples) are insufficient using Support Vector Machines (SVM) algorithms. Therefore, in this paper, we suggest Transductive Support Vector Machines (TSVMs) as semi-supervised learning algorithms, learning with both labelled samples data and unlabelled samples to perform the classification of microarray data. To prune the superfluous genes and samples we used a feature selection method called Recursive Feature Elimination (RFE), which is supposed to enhance the output of classification and avoid the local optimization problem. We examined the classification prediction accuracy of the TSVM-RFE algorithm in comparison with the Genetic Learning Across Datasets (GLAD) algorithm, as both are semi-supervised learning methods. Comparing these two methods, we found that the TSVM-RFE surpassed both a SVM using RFE and GLAD.

cs.LG↗

arXiv2013

Systems Dynamics or Agent-Based Modelling for Immune Simulation?

In immune system simulation there are two competing simulation approaches: System Dynamics Simulation (SDS) and Agent-Based Simulation (ABS). In the literature there is little guidance on how to choose the best approach for a specific immune problem. Our overall research aim is to develop a framework that helps researchers with this choice. In this paper we investigate if it is possible to easily convert simulation models between approaches. With no explicit guidelines available from the literature we develop and test our own set of guidelines for converting SDS models into ABS models in a non-spacial scenario. We also define guidelines to convert ABS into SDS considering a non-spatial and a spatial scenario. After running some experiments with the developed models we found that in all cases there are significant differences between the results produced by the different simulation methods.

cs.CE↗

arXiv2013

Quiet in Class: Classification, Noise and the Dendritic Cell Algorithm

Theoretical analyses of the Dendritic Cell Algorithm (DCA) have yielded several criticisms about its underlying structure and operation. As a result, several alterations and fixes have been suggested in the literature to correct for these findings. A contribution of this work is to investigate the effects of replacing the classification stage of the DCA (which is known to be flawed) with a traditional machine learning technique. This work goes on to question the merits of those unique properties of the DCA that are yet to be thoroughly analysed. If none of these properties can be found to have a benefit over traditional approaches, then "fixing" the DCA is arguably less efficient than simply creating a new algorithm. This work examines the dynamic filtering property of the DCA and questions the utility of this unique feature for the anomaly detection problem. It is found that this feature, while advantageous for noisy, time-ordered classification, is not as useful as a traditional static filter for processing a synthetic dataset. It is concluded that there are still unique features of the DCA left to investigate. Areas that may be of benefit to the Artificial Immune Systems community are suggested.

cs.LG↗

arXiv2013

Detect adverse drug reactions for drug Alendronate

Adverse drug reaction (ADR) is widely concerned for public health issue. In this study we propose an original approach to detect the ADRs using feature matrix and feature selection. The experiments are carried out on the drug Simvastatin. Major side effects for the drug are detected and better performance is achieved compared to other computerized methods. The detected ADRs are based on the computerized method, further investigation is needed.

cs.CE↗

arXiv2013

Discovering Sequential Patterns in a UK General Practice Database

The wealth of computerised medical information becoming readily available presents the opportunity to examine patterns of illnesses, therapies and responses. These patterns may be able to predict illnesses that a patient is likely to develop, allowing the implementation of preventative actions. In this paper sequential rule mining is applied to a General Practice database to find rules involving a patients age, gender and medical history. By incorporating these rules into current health-care a patient can be highlighted as susceptible to a future illness based on past or current illnesses, gender and year of birth. This knowledge has the ability to greatly improve health-care and reduce health-care costs.

cs.LG↗

arXiv2013

Detect adverse drug reactions for the drug Pravastatin

Adverse drug reaction (ADR) is widely concerned for public health issue. ADRs are one of most common causes to withdraw some drugs from market. Prescription event monitoring (PEM) is an important approach to detect the adverse drug reactions. The main problem to deal with this method is how to automatically extract the medical events or side effects from high-throughput medical data, which are collected from day to day clinical practice. In this study we propose an original approach to detect the ADRs using feature matrix and feature selection. The experiments are carried out on the drug Pravastatin. Major side effects for the drug are detected. The detected ADRs are based on computerized method, further investigation is needed.

cs.CE↗

arXiv2013

Modelling the Effects of User Learning on Forced Innovation Diffusion

Technology adoption theories assume that users' acceptance of an innovative technology is on a voluntary basis. However, sometimes users are force to accept an innovation. In this case users have to learn what it is useful for and how to use it. This learning process will enable users to transit from zero knowledge about the innovation to making the best use of it. So far the effects of user learning on technology adoption have received little research attention. In this paper - for the first time - we investigate the effects of user learning on forced innovation adoption by using an agent-based simulation approach using the case of forced smart metering deployments in the city of Leeds

cs.CY↗

arXiv2013

Modelling Reactive and Proactive Behaviour in Simulation: A Case Study in a University Organisation

Simulation is a well established what-if scenario analysis tool in Operational Research (OR). While traditionally Discrete Event Simulation (DES) and System Dynamics Simulation (SDS) are the predominant simulation techniques in OR, a new simulation technique, namely Agent-Based Simulation (ABS), has emerged and is gaining more attention. In our research we focus on discrete simulation methods (i.e. DES and ABS). The contribution made by this paper is the comparison of DES and combined DES/ABS for modelling human reactive and different level of detail of human proactive behaviour in service systems. The results of our experiments show that the level of proactiveness considered in the model has a big impact on the simulation output. However, there is not a big difference between the results from the DES and the combined DES/ABS simulation models. Therefore, for service systems of the type we investigated we would suggest to use DES as the preferred analysis tool.

cs.CE↗

arXiv2013

Investigating the Detection of Adverse Drug Events in a UK General Practice Electronic Health-Care Database

Data-mining techniques have frequently been developed for Spontaneous reporting databases. These techniques aim to find adverse drug events accurately and efficiently. Spontaneous reporting databases are prone to missing information, under reporting and incorrect entries. This often results in a detection lag or prevents the detection of some adverse drug events. These limitations do not occur in electronic health-care databases. In this paper, existing methods developed for spontaneous reporting databases are implemented on both a spontaneous reporting database and a general practice electronic health-care database and compared. The results suggests that the application of existing methods to the general practice database may help find signals that have gone undetected when using the spontaneous reporting system database. In addition the general practice database provides far more supplementary information, that if incorporated in analysis could provide a wealth of information for identifying adverse events more accurately.

cs.CE↗

arXiv2013

Application of a clustering framework to UK domestic electricity data

This paper takes an approach to clustering domestic electricity load profiles that has been successfully used with data from Portugal and applies it to UK data. Clustering techniques are applied and it is found that the preferred technique in the Portuguese work (a two stage process combining Self Organised Maps and Kmeans) is not appropriate for the UK data. The work shows that up to nine clusters of households can be identified with the differences in usage profiles being visually striking. This demonstrates the appropriateness of breaking the electricity usage patterns down to more detail than the two load profiles currently published by the electricity industry. The paper details initial results using data collected in Milton Keynes around 1990. Further work is described and will concentrate on building accurate and meaningful clusters of similar electricity users in order to better direct demand side management initiatives to the most relevant target customers.

cs.CE↗

arXiv2013

A Comparison of Non-stationary, Type-2 and Dual Surface Fuzzy Control

Type-1 fuzzy logic has frequently been used in control systems. However this method is sometimes shown to be too restrictive and unable to adapt in the presence of uncertainty. In this paper we compare type-1 fuzzy control with several other fuzzy approaches under a range of uncertain conditions. Interval type-2 and non-stationary fuzzy controllers are compared, along with 'dual surface' type-2 control, named due to utilising both the lower and upper values produced from standard interval type-2 systems. We tune a type-1 controller, then derive the membership functions and footprints of uncertainty from the type-1 system and evaluate them using a simulated autonomous sailing problem with varying amounts of environmental uncertainty. We show that while these more sophisticated controllers can produce better performance than the type-1 controller, this is not guaranteed and that selection of Footprint of Uncertainty (FOU) size has a large effect on this relative performance.

cs.AI↗