arXiv subjects

Uwe Aickelin

Publications and source records attributed to Uwe Aickelin.

At least 91 records · Page 5Linked to original sources

arXiv2014

An Approach for Assessing Clustering of Households by Electricity Usage

How a household varies their regular usage of electricity is useful information for organisations to allow accurate targeting of behaviour modification initiatives with the aim of improving the overall efficiency of the electricity network. The variability of regular activities in a household is one possible indication of that household's willingness to accept incentives to change their behaviour. An approach is presented for identifying a way of representing the variability of a household's behaviour and developing an efficient way of clustering the households, using these measures of variability, into a few, usable groupings. To evaluate the effectiveness of the variability measures, a number of cluster validity indexes are explored with regard to how the indexes vary with the number of clusters, the number of attributes, and the quality of the attributes. The Cluster Dispersion Indicator (CDI) and the Davies-Boulden Indicator (DBI) are selected for future work developing various indicators of household behaviour variability. The approach is tested using data from 180 UK households monitored for over a year at a sampling interval of 5 minutes. Data is taken from the evening peak electricity usage period of 4pm to 8pm.

cs.CE↗

arXiv2014

Comparison of algorithms that detect drug side effects using electronic healthcare databases

The electronic healthcare databases are starting to become more readily available and are thought to have excellent potential for generating adverse drug reaction signals. The Health Improvement Network (THIN) database is an electronic healthcare database containing medical information on over 11 million patients that has excellent potential for detecting ADRs. In this paper we apply four existing electronic healthcare database signal detecting algorithms (MUTARA, HUNT, Temporal Pattern Discovery and modified ROR) on the THIN database for a selection of drugs from six chosen drug families. This is the first comparison of ADR signalling algorithms that includes MUTARA and HUNT and enabled us to set a benchmark for the adverse drug reaction signalling ability of the THIN database. The drugs were selectively chosen to enable a comparison with previous work and for variety. It was found that no algorithm was generally superior and the algorithms' natural thresholds act at variable stringencies. Furthermore, none of the algorithms perform well at detecting rare ADRs.

cs.LG↗

arXiv2014

Signalling Paediatric Side Effects using an Ensemble of Simple Study Designs

Background: Children are frequently prescribed medication off-label, meaning there has not been sufficient testing of the medication to determine its safety or effectiveness. The main reason this safety knowledge is lacking is due to ethical restrictions that prevent children from being included in the majority of clinical trials. Objective: The objective of this paper is to investigate whether an ensemble of simple study designs can be implemented to signal acutely occurring side effects effectively within the paediatric population by using historical longitudinal data. The majority of pharmacovigilance techniques are unsupervised, but this research presents a supervised framework. Methods: Multiple measures of association are calculated for each drug and medical event pair and these are used as features that are fed into a classiffier to determine the likelihood of the drug and medical event pair corresponding to an adverse drug reaction. The classiffier is trained using known adverse drug reactions or known non-adverse drug reaction relationships. Results: The novel ensemble framework obtained a false positive rate of 0:149, a sensitivity of 0:547 and a specificity of 0:851 when implemented on a reference set of drug and medical event pairs. The novel framework consistently outperformed each individual simple study design. Conclusion: This research shows that it is possible to exploit the mechanism of causality and presents a framework for signalling adverse drug reactions effectively.

cs.LG↗

arXiv2014

Feature selection in detection of adverse drug reactions from the Health Improvement Network (THIN) database

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 events, which are collected from day to day clinical practice. In this study we propose a novel concept of feature matrix to detect the ADRs. Feature matrix, which is extracted from big medical data from The Health Improvement Network (THIN) database, is created to characterize the medical events for the patients who take drugs. Feature matrix builds the foundation for the irregular and big medical data. Then feature selection methods are performed on feature matrix to detect the significant features. Finally the ADRs can be located based on the significant features. The experiments are carried out on three drugs: Atorvastatin, Alendronate, and Metoclopramide. Major side effects for each drug are detected and better performance is achieved compared to other computerized methods. The detected ADRs are based on computerized methods, further investigation is needed.

cs.LG↗

arXiv2014

Data classification using the Dempster-Shafer method

In this paper, the Dempster-Shafer method is employed as the theoretical basis for creating data classification systems. Testing is carried out using three popular (multiple attribute) benchmark datasets that have two, three and four classes. In each case, a subset of the available data is used for training to establish thresholds, limits or likelihoods of class membership for each attribute, and hence create mass functions that establish probability of class membership for each attribute of the test data. Classification of each data item is achieved by combination of these probabilities via Dempster's Rule of Combination. Results for the first two datasets show extremely high classification accuracy that is competitive with other popular methods. The third dataset is non-numerical and difficult to classify, but good results can be achieved provided the system and mass functions are designed carefully and the right attributes are chosen for combination. In all cases the Dempster-Shafer method provides comparable performance to other more popular algorithms, but the overhead of generating accurate mass functions increases the complexity with the addition of new attributes. Overall, the results suggest that the D-S approach provides a suitable framework for the design of classification systems and that automating the mass function design and calculation would increase the viability of the algorithm for complex classification problems.

cs.LG↗

arXiv2014

Ensemble Learning of Colorectal Cancer Survival Rates

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. We build on existing research on clustering and machine learning facets of this data to demonstrate a role for an ensemble approach to highlighting patients with clearer prognosis parameters. Results for survival prediction using 3 different approaches are shown for a subset of the data which is most difficult to model. The performance of each model individually is compared with subsets of the data where some agreement is reached for multiple models. Significant improvements in model accuracy on an unseen test set can be achieved for patients where agreement between models is achieved.

cs.LG↗

arXiv2014

Comparing Stochastic Differential Equations and Agent-Based Modelling and Simulation for Early-stage Cancer

There is great potential to be explored regarding the use of agent-based modelling and simulation as an alternative paradigm to investigate early-stage cancer interactions with the immune system. It does not suffer from some limitations of ordinary differential equation models, such as the lack of stochasticity, representation of individual behaviours rather than aggregates and individual memory. In this paper we investigate the potential contribution of agent-based modelling and simulation when contrasted with stochastic versions of ODE models using early-stage cancer examples. We seek answers to the following questions: (1) Does this new stochastic formulation produce similar results to the agent-based version? (2) Can these methods be used interchangeably? (3) Do agent-based models outcomes reveal any benefit when compared to the Gillespie results? To answer these research questions we investigate three well-established mathematical models describing interactions between tumour cells and immune elements. These case studies were re-conceptualised under an agent-based perspective and also converted to the Gillespie algorithm formulation. Our interest in this work, therefore, is to establish a methodological discussion regarding the usability of different simulation approaches, rather than provide further biological insights into the investigated case studies. Our results show that it is possible to obtain equivalent models that implement the same mechanisms; however, the incapacity of the Gillespie algorithm to retain individual memory of past events affects the similarity of some results. Furthermore, the emergent behaviour of ABMS produces extra patters of behaviour in the system, which was not obtained by the Gillespie algorithm.

cs.MA↗

arXiv2014

A Novel Semi-Supervised Algorithm for Rare Prescription Side Effect Discovery

Drugs are frequently prescribed to patients with the aim of improving each patient's medical state, but an unfortunate consequence of most prescription drugs is the occurrence of undesirable side effects. Side effects that occur in more than one in a thousand patients are likely to be signalled efficiently by current drug surveillance methods, however, these same methods may take decades before generating signals for rarer side effects, risking medical morbidity or mortality in patients prescribed the drug while the rare side effect is undiscovered. In this paper we propose a novel computational meta-analysis framework for signalling rare side effects that integrates existing methods, knowledge from the web, metric learning and semi-supervised clustering. The novel framework was able to signal many known rare and serious side effects for the selection of drugs investigated, such as tendon rupture when prescribed Ciprofloxacin or Levofloxacin, renal failure with Naproxen and depression associated with Rimonabant. Furthermore, for the majority of the drug investigated it generated signals for rare side effects at a more stringent signalling threshold than existing methods and shows the potential to become a fundamental part of post marketing surveillance to detect rare side effects.

cs.LG↗

arXiv2013

Detect adverse drug reactions for drug Atorvastatin

Adverse drug reactions (ADRs) are big concern for public health. ADRs are one of most common causes to withdraw some drugs from markets. Now two major methods for detecting ADRs are spontaneous reporting system (SRS), and prescription event monitoring (PEM). The World Health Organization (WHO) defines a signal in pharmacovigilance as "any reported information on a possible causal relationship between an adverse event and a drug, the relationship being unknown or incompletely documented previously". For spontaneous reporting systems, many machine learning methods are used to detect ADRs, such as Bayesian confidence propagation neural network (BCPNN), decision support methods, genetic algorithms, knowledge based approaches, etc. One limitation is the reporting mechanism to submit ADR reports, which has serious underreporting and is not able to accurately quantify the corresponding risk. Another limitation is hard to detect ADRs with small number of occurrences of each drug-event association in the database. In this paper we propose feature selection approach to detect ADRs from The Health Improvement Network (THIN) database. First a feature matrix, which represents the medical events for the patients before and after taking drugs, is created by linking patients' prescriptions and corresponding medical events together. Then significant features are selected based on feature selection methods, comparing the feature matrix before patients take drugs with one after patients take drugs. Finally the significant ADRs can be detected from thousands of medical events based on corresponding features. Experiments are carried out on the drug Atorvastatin. Good performance is achieved.

cs.CE↗

arXiv2013

Measuring the Directional Distance Between Fuzzy Sets

The measure of distance between two fuzzy sets is a fundamental tool within fuzzy set theory. However, current distance measures within the literature do not account for the direction of change between fuzzy sets; a useful concept in a variety of applications, such as Computing With Words. In this paper, we highlight this utility and introduce a distance measure which takes the direction between sets into account. We provide details of its application for normal and non-normal, as well as convex and non-convex fuzzy sets. We demonstrate the new distance measure using real data from the MovieLens dataset and establish the benefits of measuring the direction between fuzzy sets.

cs.AI↗

arXiv2013

Artificial Immune Systems (INTROS 2)

The biological immune system is a robust, complex, adaptive system that defends the body from foreign pathogens. It is able to categorize all cells (or molecules) within the body as self or non-self substances. It does this with the help of a distributed task force that has the intelligence to take action from a local and also a global perspective using its network of chemical messengers for communication. There are two major branches of the immune system. The innate immune system is an unchanging mechanism that detects and destroys certain invading organisms, whilst the adaptive immune system responds to previously unknown foreign cells and builds a response to them that can remain in the body over a long period of time. This remarkable information processing biological system has caught the attention of computer science in recent years. A novel computational intelligence technique, inspired by immunology, has emerged, called Artificial Immune Systems. Several concepts from the immune system have been extracted and applied for solution to real world science and engineering problems. In this tutorial, we briefly describe the immune system metaphors that are relevant to existing Artificial Immune Systems methods. We will then show illustrative real-world problems suitable for Artificial Immune Systems and give a step-by-step algorithm walkthrough for one such problem. A comparison of the Artificial Immune Systems to other well-known algorithms, areas for future work, tips & tricks and a list of resources will round this tutorial off. It should be noted that as Artificial Immune Systems is still a young and evolving field, there is not yet a fixed algorithm template and hence actual implementations might differ somewhat from time to time and from those examples given here.

cs.NE↗

arXiv2013

Extending Similarity Measures of Interval Type-2 Fuzzy Sets to General Type-2 Fuzzy Sets

Similarity measures provide one of the core tools that enable reasoning about fuzzy sets. While many types of similarity measures exist for type-1 and interval type-2 fuzzy sets, there are very few similarity measures that enable the comparison of general type-2 fuzzy sets. In this paper, we introduce a general method for extending existing interval type-2 similarity measures to similarity measures for general type-2 fuzzy sets. Specifically, we show how similarity measures for interval type-2 fuzzy sets can be employed in conjunction with the zSlices based general type-2 representation for fuzzy sets to provide measures of similarity which preserve all the common properties (i.e. reflexivity, symmetry, transitivity and overlapping) of the original interval type-2 similarity measure. We demonstrate examples of such extended fuzzy measures and provide comparisons between (different types of) interval and general type-2 fuzzy measures.

cs.AI↗

arXiv2013

Detect adverse drug reactions for drug Pioglitazone

In this study we propose a novel method to successfully detect the ADRs using feature matrix and feature selection. A feature matrix, which characterizes the medical events before patients take drugs or after patients take drugs, is created from THIN database. The feature selection method of Student's t-test is used to detect the significant features from thousands of medical events. The significant ADRs, which are corresponding to significant features, are detected. Experiments are performed on the drug Pioglitazone. Compared to other computerized methods, our proposed method achieves good performance.

cs.CE↗

arXiv2013

Performance Measurement Under Increasing Environmental Uncertainty In The Context of Interval Type-2 Fuzzy Logic Based Robotic Sailing

Performance measurement of robotic controllers based on fuzzy logic, operating under uncertainty, is a subject area which has been somewhat ignored in the current literature. In this paper standard measures such as RMSE are shown to be inappropriate for use under conditions where the environmental uncertainty changes significantly between experiments. An overview of current methods which have been applied by other authors is presented, followed by a design of a more sophisticated method of comparison. This method is then applied to a robotic control problem to observe its outcome compared with a single measure. Results show that the technique described provides a more robust method of performance comparison than less complex methods allowing better comparisons to be drawn.

cs.RO↗

arXiv2013

An investigation into the relationship between type-2 FOU size and environmental uncertainty in robotic control

It has been suggested that, when faced with large amounts of uncertainty in situations of automated control, type-2 fuzzy logic based controllers will out-perform the simpler type-1 varieties due to the latter lacking the flexibility to adapt accordingly. This paper aims to investigate this problem in detail in order to analyse when a type-2 controller will improve upon type-1 performance. A robotic sailing boat is subjected to several experiments in which the uncertainty and difficulty of the sailing problem is increased in order to observe the effects on measured performance. Improved performance is observed but not in every case. The size of the FOU is shown to be have a large effect on performance with potentially severe performance penalties for incorrectly sized footprints.

cs.RO↗

arXiv2013

A Beginners Guide to Systems Simulation in Immunology

Some common systems modelling and simulation approaches for immune problems are Monte Carlo simulations, system dynamics, discrete-event simulation and agent-based simulation. These methods, however, are still not widely adopted in immunology research. In addition, to our knowledge, there is few research on the processes for the development of simulation models for the immune system. Hence, for this work, we have two contributions to knowledge. The first one is to show the importance of systems simulation to help immunological research and to draw the attention of simulation developers to this research field. The second contribution is the introduction of a quick guide containing the main steps for modelling and simulation in immunology, together with challenges that occur during the model development. Further, this paper introduces an example of a simulation problem, where we test our guidelines.

cs.CE↗

arXiv2013

Using Clustering to extract Personality Information from socio economic data

It has become apparent that models that have been applied widely in economics, including Machine Learning techniques and Data Mining methods, should take into consideration principles that derive from the theories of Personality Psychology in order to discover more comprehensive knowledge regarding complicated economic behaviours. In this work, we present a method to extract Behavioural Groups by using simple clustering techniques that can potentially reveal aspects of the Personalities for their members. We believe that this is very important because the psychological information regarding the Personalities of individuals is limited in real world applications and because it can become a useful tool in improving the traditional models of Knowledge Economy.

cs.LG↗

arXiv2013

Variance in System Dynamics and Agent Based Modelling Using the SIR Model of Infectious Disease

Classical deterministic simulations of epidemiological processes, such as those based on System Dynamics, produce a single result based on a fixed set of input parameters with no variance between simulations. Input parameters are subsequently modified on these simulations using Monte-Carlo methods, to understand how changes in the input parameters affect the spread of results for the simulation. Agent Based simulations are able to produce different output results on each run based on knowledge of the local interactions of the underlying agents and without making any changes to the input parameters. In this paper we compare the influence and effect of variation within these two distinct simulation paradigms and show that the Agent Based simulation of the epidemiological SIR (Susceptible, Infectious, and Recovered) model is more effective at capturing the natural variation within SIR compared to an equivalent model using System Dynamics with Monte-Carlo simulation. To demonstrate this effect, the SIR model is implemented using both System Dynamics (with Monte-Carlo simulation) and Agent Based Modelling based on previously published empirical data.

cs.CE↗