What to do when K-means clustering fails:a simple yet principled alternative algorithm

The K-means algorithm is one of the most popular clustering algorithms in current use as it is relatively fast yet simple to understand and deploy in practice. Nevertheless, its use entails certain restrictive assumptions about the data, the negative consequences of which are not always immediately apparent, as we demonstrate. While more flexible algorithms have been developed, their widespread use has been hindered by their computational and technical complexity. Motivated by these considerations, we present a flexible alternative to K-means that relaxes most of the assumptions, whilst remaining almost as fast and simple. This novel algorithm which we call MAP-DP (maximum a-posteriori Dirichlet process mixtures), is statistically rigorous as it is based on nonparametric Bayesian Dirichlet process mixture modeling. This approach allows us to overcome most of the limitations imposed by K-means. The number of clusters K is estimated from the data instead of being fixed a-priori as in K-means. In addition, while K-means is restricted to continuous data, the MAP-DP framework can be applied to many kinds of data, for example, binary, count or ordinal data. Also, it can efficiently separate outliers from the data. This additional flexibility does not incur a significant computational overhead compared to K-means with MAP-DP convergence typically achieved in the order of seconds for many practical problems. Finally, in contrast to K-means, since the algorithm is based on an underlying statistical model, the MAP-DP framework can deal with missing data and enables model testing such as cross validation in a principled way. We demonstrate the simplicity and effectiveness of this algorithm on the health informatics problem of clinical sub-typing in a cluster of diseases known as parkinsonism.

Neural networks

An overview of neural networks, covering multilayer perceptrons, radial basis functions, constructive algorithms, Kohonen and K-means unupervised algorithms, RAMnets, first and second order training methods, and Bayesian regularisation methods.

MILVA:An interactive tool for the exploration of multidimensional microarray data

Clustering techniques such as k-means and hierarchical clustering are commonly used to analyze DNA microarray derived gene expression data. However, the interactions between processes underlying the cell activity suggest that the complexity of the microarray data structure may not be fully represented with discrete clustering methods.

Exploring ant-based algorithms for gene expression data analysis

Objective: Recently, much research has been proposed using nature inspired algorithms to perform complex machine learning tasks. Ant colony optimization (ACO) is one such algorithm based on swarm intelligence and is derived from a model inspired by the collective foraging behavior of ants. Taking advantage of the ACO in traits such as self-organization and robustness, this paper investigates ant-based algorithms for gene expression data clustering and associative classification. Methods and material: An ant-based clustering (Ant-C) and an ant-based association rule mining (Ant-ARM) algorithms are proposed for gene expression data analysis. The proposed algorithms make use of the natural behavior of ants such as cooperation and adaptation to allow for a flexible robust search for a good candidate solution. Results: Ant-C has been tested on the three datasets selected from the Stanford Genomic Resource Database and achieved relatively high accuracy compared to other classical clustering methods. Ant-ARM has been tested on the acute lymphoblastic leukemia (ALL)/acute myeloid leukemia (AML) dataset and generated about 30 classification rules with high accuracy. Conclusions: Ant-C can generate optimal number of clusters without incorporating any other algorithms such as K-means or agglomerative hierarchical clustering. For associative classification, while a few of the well-known algorithms such as Apriori, FP-growth and Magnum Opus are unable to mine any association rules from the ALL/AML dataset within a reasonable period of time, Ant-ARM is able to extract associative classification rules.

A hybrid generative/discriminative framework to train a semantic parser from an un-annotated corpus

We propose a hybrid generative/discriminative framework for semantic parsing which combines the hidden vector state (HVS) model and the hidden Markov support vector machines (HM-SVMs). The HVS model is an extension of the basic discrete Markov model in which context is encoded as a stack-oriented state vector. The HM-SVMs combine the advantages of the hidden Markov models and the support vector machines. By employing a modified K-means clustering method, a small set of most representative sentences can be automatically selected from an un-annotated corpus. These sentences together with their abstract annotations are used to train an HVS model which could be subsequently applied on the whole corpus to generate semantic parsing results. The most confident semantic parsing results are selected to generate a fully-annotated corpus which is used to train the HM-SVMs. The proposed framework has been tested on the DARPA Communicator Data. Experimental results show that an improvement over the baseline HVS parser has been observed using the hybrid framework. When compared with the HM-SVMs trained from the fully-annotated corpus, the hybrid framework gave a comparable performance with only a small set of lightly annotated sentences. © 2008. Licensed under the Creative Commons.

Multi-level visualisation using Gaussian process latent variable models

Projection of a high-dimensional dataset onto a two-dimensional space is a useful tool to visualise structures and relationships in the dataset. However, a single two-dimensional visualisation may not display all the intrinsic structure. Therefore, hierarchical/multi-level visualisation methods have been used to extract more detailed understanding of the data. Here we propose a multi-level Gaussian process latent variable model (MLGPLVM). MLGPLVM works by segmenting data (with e.g. K-means, Gaussian mixture model or interactive clustering) in the visualisation space and then fitting a visualisation model to each subset. To measure the quality of multi-level visualisation (with respect to parent and child models), metrics such as trustworthiness, continuity, mean relative rank errors, visualisation distance distortion and the negative log-likelihood per point are used. We evaluate the MLGPLVM approach on the ‘Oil Flow’ dataset and a dataset of protein electrostatic potentials for the ‘Major Histocompatibility Complex (MHC) class I’ of humans. In both cases, visual observation and the quantitative quality measures have shown better visualisation at lower levels.

One-stop health centres:What co-location means for pharmacy

This paper examines the potential for the development of patient services that could arise from the co-location of pharmacies with medical practices in the new "one-stop" centres. A review of the pharmacy-specific literature shows limited understanding of influence of location upon service development and highlights a tension between the professional and commercial drives. The aim of the survey of health centre pharmacists was to describe the current patterns of integration in the primary health care team. The study demonstrates that co-location offers opportunities but that there are barriers linked to the loss of traditional commercial activity. © 2003 Elsevier Science Ltd. All rights reserved.

A highly emissive inorganic hexamolybdenum cluster complex as a handy precursor for the preparation of new luminescent materials

The synthesis and characterisation of a new, highly luminescent inorganic cluster complex, (Bu4N)2[Mo6I 8(NO3)6], are described. The complex possesses labile nitrato ligands and is therefore a useful precursor for the design of new luminescent materials. To exemplify this, functionalised polystyrene beads have been utilised as "polymeric ligands" to immobilise the molybdenum cluster complex. This journal is © the Partner Organisations 2014.

Influence of birth cohort on age of onset cluster analysis in bipolar I disorder

PURPOSE: Two common approaches to identify subgroups of patients with bipolar disorder are clustering methodology (mixture analysis) based on the age of onset, and a birth cohort analysis. This study investigates if a birth cohort effect will influence the results of clustering on the age of onset, using a large, international database. METHODS: The database includes 4037 patients with a diagnosis of bipolar I disorder, previously collected at 36 collection sites in 23 countries. Generalized estimating equations (GEE) were used to adjust the data for country median age, and in some models, birth cohort. Model-based clustering (mixture analysis) was then performed on the age of onset data using the residuals. Clinical variables in subgroups were compared. RESULTS: There was a strong birth cohort effect. Without adjusting for the birth cohort, three subgroups were found by clustering. After adjusting for the birth cohort or when considering only those born after 1959, two subgroups were found. With results of either two or three subgroups, the youngest subgroup was more likely to have a family history of mood disorders and a first episode with depressed polarity. However, without adjusting for birth cohort (three subgroups), family history and polarity of the first episode could not be distinguished between the middle and oldest subgroups. CONCLUSION: These results using international data confirm prior findings using single country data, that there are subgroups of bipolar I disorder based on the age of onset, and that there is a birth cohort effect. Including the birth cohort adjustment altered the number and characteristics of subgroups detected when clustering by age of onset. Further investigation is needed to determine if combining both approaches will identify subgroups that are more useful for research.

Polymerisable octahedral rhenium cluster complexes as precursors for photo/electroluminescent polymers

New polymerisable photoluminescent octahedral rhenium cluster complexes trans-[{Re6Q8}(TBP)4(VB)2] (Q = S or Se; TBP-p-tert-butylpyridine; VB-vinyl benzoate) have been synthesised, characterised and used to construct rhenium cluster-organic polymer hybrid materials. These novel polymer systems are solution-processable and the rhenium clusters retain their photoluminescent properties within the polymer environment. Notably, when the rhenium cluster complexes are incorporated into the matrix of the electroluminescent polymer poly(N-vinylcarbazole), the resultant cluster polymer hybrid combined properties of both components and was used successfully in the construction of a polymer light emitting diode (PLED). These prototype devices are the first PLEDs to incorporate octahedral rhenium clusters and provide the first direct evidence of the electroluminescent properties of rhenium clusters and indeed, to the best of our knowledge, of any member of the family of 24-electron hexanuclear cluster complexes of molybdenum, tungsten or rhenium.