An overview of the use of neural networks for data mining tasks

In the recent years, the area of data mining has been experiencing considerable demand for technologies that extract knowledge from large and complex data sources. There has been substantial commercial interest as well as active research in the area that aim to develop new and improved approaches for extracting information, relationships, and patterns from large datasets. Artificial neural networks (NNs) are popular biologically-inspired intelligent methodologies, whose classification, prediction, and pattern recognition capabilities have been utilized successfully in many areas, including science, engineering, medicine, business, banking, telecommunication, and many other fields. This paper highlights from a data mining perspective the implementation of NN, using supervised and unsupervised learning, for pattern recognition, classification, prediction, and cluster analysis, and focuses the discussion on their usage in bioinformatics and financial data analysis tasks. © 2012 Wiley Periodicals, Inc.

Metabolic phenotype modulation by caloric restriction in a lifelong dog study

Modeling aging and age-related pathologies presents a substantial analytical challenge given the complexity of gene−environment influences and interactions operating on an individual. A top-down systems approach is used to model the effects of lifelong caloric restriction, which is known to extend life span in several animal models. The metabolic phenotypes of caloric-restricted (CR; n = 24) and pair-housed control-fed (CF; n = 24) Labrador Retriever dogs were investigated by use of orthogonal projection to latent structures discriminant analysis (OPLS-DA) to model both generic and age-specific responses to caloric restriction from the 1H NMR blood serum profiles of young and older dogs. Three aging metabolic phenotypes were resolved: (i) an aging metabolic phenotype independent of diet, characterized by high levels of glutamine, creatinine, methylamine, dimethylamine, trimethylamine N-oxide, and glycerophosphocholine and decreasing levels of glycine, aspartate, creatine and citrate indicative of metabolic changes associated largely with muscle mass; (ii) an aging metabolic phenotype specific to CR dogs that consisted of relatively lower levels of glucose, acetate, choline, and tyrosine and relatively higher serum levels of phosphocholine with increased age in the CR population; (iii) an aging metabolic phenotype specific to CF dogs including lower levels of liproprotein fatty acyl groups and allantoin and relatively higher levels of formate with increased age in the CF population. There was no diet metabotype that consistently differentiated the CF and CR dogs irrespective of age. Glucose consistently discriminated between feeding regimes in dogs (≥312 weeks), being relatively lower in the CR group. However, it was observed that creatine and amino acids (valine, leucine, isoleucine, lysine, and phenylalanine) were lower in the CR dogs (<312 weeks), suggestive of differences in energy source utilization. 1H NMR spectroscopic analysis of longitudinal serum profiles enabled an unbiased evaluation of the metabolic markers modulated by a lifetime of caloric restriction and showed differences in the metabolic phenotype of aging due to caloric restriction, which contributes to longevity studies in caloric-restricted animals. Furthermore, OPLS-DA provided a framework such that significant metabolites relating to life extension could be differentiated and integrated with aging processes.

Novel single trial movement classification based on temporal dynamics of EEG

Various complex oscillatory processes are involved in the generation of the motor command. The temporal dynamics of these processes were studied for movement detection from single trial electroencephalogram (EEG). Autocorrelation analysis was performed on the EEG signals to find robust markers of movement detection. The evolution of the autocorrelation function was characterised via the relaxation time of the autocorrelation by exponential curve fitting. It was observed that the decay constant of the exponential curve increased during movement, indicating that the autocorrelation function decays slowly during motor execution. Significant differences were observed between movement and no moment tasks. Additionally, a linear discriminant analysis (LDA) classifier was used to identify movement trials with a peak accuracy of 74%.

Comparative Cluster/Double Star observations of the high and low latitude dayside magnetopause

The launch of the Double Star mission has provided the opportunity to monitor events at distinct locations on the dayside magnetopause, in coordination with the quartet of Cluster spacecraft. We present results of two such coordinated studies. In the first, 6 April 2004, both Cluster and the Double Star TC-1 spacecraft were on outbound transits through the dawn-side magnetosphere. Cluster observed northward moving FTEs with +/- polarity, whereas TC-1 saw -/+ polarity FTEs. The strength, motion and occurrence of the FTE signatures changes somewhat according to changes in IMF clock angle. These observations are consistent with ongoing reconnection on the dayside magnetopause, resulting in a series of flux transfer events (FTEs) seen both at Cluster and TC-1. The observed polarity and motion of each FTE signature advocates the existence of an active reconnection region consistently located between the positions of Cluster and TC-1, lying north and south of the reconnection line, respectively. This scenario is supported by the application of a model, designed to track flux tube motion, to conditions appropriate for the prevailing interplanetary conditions. The results from the model confirm the observational evidence that the low-latitude FTE dynamics is sensitive to changes in convected upstream conditions. In particular, changing the interplanetary magnetic field (IMF) clock angle in the model predicts that TC-1 should miss the resulting FTEs more often than Cluster, as is observed. For the second conjunction, on the 4 Jan 2005, the Cluster and TC-1 spacecraft all exited the dusk-side magnetosphere almost simultaneously, with TC-1 lying almost equatorial and Cluster at northern latitudes at about 4 RE from TC-1. The spacecraft traverse the magnetopause during a strong reversal in the IMF from northward to southward and a number of magnetosheath FTE signatures are subsequently observed. One coordinated FTE, studied in detail by Pu et al, [this issue], carries and inflowing energetic electron population and shows a motion and orientation which is similar at all spacecraft and consistent with the predictions of the model for the flux tube dynamics, given a near sub-solar reconnection line. This event can be interpreted either as the passage of two parallel flux tubes arising from adjacent x-line positions, or as a crossing of a single flux tube at different positions.

Opportunities for magnetospheric research with coordinated cluster and ground-based observations

ESA’s first multi-satellite mission Cluster is unique in its concept of 4 satellites orbiting in controlled formations. This will give an unprecedented opportunity to study structure and dynamics of the magnetosphere. In this paper we discuss ways in which ground-based remote-sensing observations of the ionosphere can be used to support the multipoint in-situ satellite measurements. There are a very large number of potentially useful configurations between the satellites and any one ground-based observatory; however, the number of ideal occurrences for any one configuration is low. Many of the ground-based instruments cannot operate continuously and Cluster will take data only for a part of each orbit, depending on how much high-resolution (‘burst-mode’) data are acquired. In addition, there are a great many instrument modes and the formation, size and shape of the cluster of the four satellites to consider. These circumstances create a clear and pressing need for careful planning to ensure that the scientific return from Cluster is maximised by additional coordinated ground-based observations. For this reason, ESA established a working group to coordinate the observations on the ground with Cluster. We will give a number of examples how the combined spacecraft and ground-based observations can address outstanding questions in magnetospheric physics. An online computer tool has been prepared to allow for the planning of conjunctions and advantageous constellations between the Cluster spacecraft and individual or combined ground-based systems. During the mission a ground-based database containing index and summary data will help to identify interesting datasets and allow to select intervals for coordinated studies. We illustrate the philosophy of our approach, using a few important examples of the many possible configurations between the satellite and the ground-based instruments.

The housing pathways of young people in the UK

The authors examine the housing pathways of young people in the UK in the years 1999 to 2008, and consider the changing nature of these pathways in the run up to 2020. They employ a highly innovative methodology, which begins with the identification and description of key drivers likely to affect young people’s housing circumstances in the future. The empirical identification and analysis of housing pathways is then achieved using multiple-sequence analysis and cluster analysis of the British Household Panel Survey, contextualised by qualitative interviews with a large sample of young people. The authors describe how the interactions between the meanings, perceptions, and aspirations of young people, and the opportunities and constraints imposed by the drivers, are having a major impact on young people’s housing pathways, resulting in considerable housing policy challenges, particularly in relation to the private rented sector

Typification of farming systems for constructing representative farm models: two illustrations of the application of multi-variate analyses in Chile and Pakistan

If the fundamental precepts of Farming Systems Research were to be taken literally then it would imply that for each farm 'unique' solutions should be sought. This is an unrealistic expectation, but it has led to the idea of a recommendation domain, implying creating a taxonomy of farms, in order to increase the general applicability of recommendations. Mathematical programming models are an established means of generating recommended solutions, but for such models to be effective they have to be constructed for 'truly' typical or representative situations. The multi-variate statistical techniques provide a means of creating the required typologies, particularly when an exhaustive database is available. This paper illustrates the application of this methodology in two different studies that shared the common purpose of identifying types of farming systems in their respective study areas. The issues related with the use of factor and cluster analyses for farm typification prior to building representative mathematical programming models for Chile and Pakistan are highlighted. (C) 2003 Elsevier Science Ltd. All rights reserved.

Bio-inspired ant colony optimization based clustering algorithm with mobile sinks for applications in consumer home automation networks

With the fast development of wireless communications, ZigBee and semiconductor devices, home automation networks have recently become very popular. Since typical consumer products deployed in home automation networks are often powered by tiny and limited batteries, one of the most challenging research issues is concerning energy reduction and the balancing of energy consumption across the network in order to prolong the home network lifetime for consumer devices. The introduction of clustering and sink mobility techniques into home automation networks have been shown to be an efficient way to improve the network performance and have received significant research attention. Taking inspiration from nature, this paper proposes an Ant Colony Optimization (ACO) based clustering algorithm specifically with mobile sink support for home automation networks. In this work, the network is divided into several clusters and cluster heads are selected within each cluster. Then, a mobile sink communicates with each cluster head to collect data directly through short range communications. The ACO algorithm has been utilized in this work in order to find the optimal mobility trajectory for the mobile sink. Extensive simulation results from this research show that the proposed algorithm significantly improves home network performance when using mobile sinks in terms of energy consumption and network lifetime as compared to other routing algorithms currently deployed for home automation networks.

A pharmacist-led information technology intervention for medication errors (PINCER): a multicentre, cluster randomised, controlled trial and cost-effectiveness analysis

Background: Medication errors are common in primary care and are associated with considerable risk of patient harm. We tested whether a pharmacist-led, information technology-based intervention was more effective than simple feedback in reducing the number of patients at risk of measures related to hazardous prescribing and inadequate blood-test monitoring of medicines 6 months after the intervention. Methods: In this pragmatic, cluster randomised trial general practices in the UK were stratified by research site and list size, and randomly assigned by a web-based randomisation service in block sizes of two or four to one of two groups. The practices were allocated to either computer-generated simple feedback for at-risk patients (control) or a pharmacist-led information technology intervention (PINCER), composed of feedback, educational outreach, and dedicated support. The allocation was masked to general practices, patients, pharmacists, researchers, and statisticians. Primary outcomes were the proportions of patients at 6 months after the intervention who had had any of three clinically important errors: non-selective non-steroidal anti-inflammatory drugs (NSAIDs) prescribed to those with a history of peptic ulcer without co-prescription of a proton-pump inhibitor; β blockers prescribed to those with a history of asthma; long-term prescription of angiotensin converting enzyme (ACE) inhibitor or loop diuretics to those 75 years or older without assessment of urea and electrolytes in the preceding 15 months. The cost per error avoided was estimated by incremental cost-eff ectiveness analysis. This study is registered with Controlled-Trials.com, number ISRCTN21785299. Findings: 72 general practices with a combined list size of 480 942 patients were randomised. At 6 months’ follow-up, patients in the PINCER group were significantly less likely to have been prescribed a non-selective NSAID if they had a history of peptic ulcer without gastroprotection (OR 0∙58, 95% CI 0∙38–0∙89); a β blocker if they had asthma (0∙73, 0∙58–0∙91); or an ACE inhibitor or loop diuretic without appropriate monitoring (0∙51, 0∙34–0∙78). PINCER has a 95% probability of being cost eff ective if the decision-maker’s ceiling willingness to pay reaches £75 per error avoided at 6 months. Interpretation: The PINCER intervention is an effective method for reducing a range of medication errors in general practices with computerised clinical records. Funding: Patient Safety Research Portfolio, Department of Health, England.

Extreme wind storms over Europe in present and future climate: a cluster analysis approach

Boreal winter wind storm situations over Central Europe are investigated by means of an objective cluster analysis. Surface data from the NCEP-Reanalysis and ECHAM4/OPYC3-climate change GHG simulation (IS92a) are considered. To achieve an optimum separation of clusters of extreme storm conditions, 55 clusters of weather patterns are differentiated. To reduce the computational effort, a PCA is initially performed, leading to a data reduction of about 98 %. The clustering itself was computed on 3-day periods constructed with the first six PCs using "k-means" clustering algorithm. The applied method enables an evaluation of the time evolution of the synoptic developments. The climate change signal is constructed by a projection of the GCM simulation on the EOFs attained from the NCEP-Reanalysis. Consequently, the same clusters are obtained and frequency distributions can be compared. For Central Europe, four primary storm clusters are identified. These clusters feature almost 72 % of the historical extreme storms events and add only to 5 % of the total relative frequency. Moreover, they show a statistically significant signature in the associated wind fields over Europe. An increased frequency of Central European storm clusters is detected with enhanced GHG conditions, associated with an enhancement of the pressure gradient over Central Europe. Consequently, more intense wind events over Central Europe are expected. The presented algorithm will be highly valuable for the analysis of huge data amounts as is required for e.g. multi-model ensemble analysis, particularly because of the enormous data reduction.

Cluster analysis of downscaled and explicitly simulated North Atlantic tropical cyclone tracks

A realistic representation of the North Atlantic tropical cyclone tracks is crucial as it allows, for example, explaining potential changes in US landfalling systems. Here we present a tentative study, which examines the ability of recent climate models to represent North Atlantic tropical cyclone tracks. Tracks from two types of climate models are evaluated: explicit tracks are obtained from tropical cyclones simulated in regional or global climate models with moderate to high horizontal resolution (1° to 0.25°), and downscaled tracks are obtained using a downscaling technique with large-scale environmental fields from a subset of these models. For both configurations, tracks are objectively separated into four groups using a cluster technique, leading to a zonal and a meridional separation of the tracks. The meridional separation largely captures the separation between deep tropical and sub-tropical, hybrid or baroclinic cyclones, while the zonal separation segregates Gulf of Mexico and Cape Verde storms. The properties of the tracks’ seasonality, intensity and power dissipation index in each cluster are documented for both configurations. Our results show that except for the seasonality, the downscaled tracks better capture the observed characteristics of the clusters. We also use three different idealized scenarios to examine the possible future changes of tropical cyclone tracks under 1) warming sea surface temperature, 2) increasing carbon dioxide, and 3) a combination of the two. The response to each scenario is highly variable depending on the simulation considered. Finally, we examine the role of each cluster in these future changes and find no preponderant contribution of any single cluster over the others.

Method for exploratory cluster analysis and visualisation of single-trial ERP ensembles

Background: The validity of ensemble averaging on event-related potential (ERP) data has been questioned, due to its assumption that the ERP is identical across trials. Thus, there is a need for preliminary testing for cluster structure in the data. New method: We propose a complete pipeline for the cluster analysis of ERP data. To increase the signalto-noise (SNR) ratio of the raw single-trials, we used a denoising method based on Empirical Mode Decomposition (EMD). Next, we used a bootstrap-based method to determine the number of clusters, through a measure called the Stability Index (SI). We then used a clustering algorithm based on a Genetic Algorithm (GA)to define initial cluster centroids for subsequent k-means clustering. Finally, we visualised the clustering results through a scheme based on Principal Component Analysis (PCA). Results: After validating the pipeline on simulated data, we tested it on data from two experiments – a P300 speller paradigm on a single subject and a language processing study on 25 subjects. Results revealed evidence for the existence of 6 clusters in one experimental condition from the language processing study. Further, a two-way chi-square test revealed an influence of subject on cluster membership.

Analysis of the sulfate-reducing bacterial and methanogenic archaeal populations in contrasting Antarctic sediments

The distribution and activity of communities of sulfate-reducing bacteria (SRB) and methanogenic archaea in two contrasting Antarctic sediments were investigated. Methanogenesis dominated in freshwater Lake Heywood, while sulfate reduction dominated in marine Shallow Bay. Slurry experiments indicated that 90% of the methanogenesis in Lake Heywood was acetoclastic. This finding was supported by the limited diversity of clones detected in a Lake Heywood archaeal clone library, in which most clones were closely related to the obligate acetate-utilizing Methanosaeta concilii. The Shallow Bay archaeal clone library contained clones related to the C-1-utilizing Methanolobus and Methanococcoides and the H-2-utilizing Methanogenium. Oligonucleotide probing of RNA extracted directly from sediment indicated that archaea represented 34% of the total prokaryotic signal in Lake Heywood and that Methanosaeta was a major component (13.2%) of this signal. Archaea represented only 0.2% of the total prokaryotic signal in RNA extracted from Shallow Bay sediments. In the Shallow Bay bacterial clone library, 10.3% of the clones were SRB-like, related to Desulfotalea/Desulforhopalus, Desulfofaba, Desulfosarcina, and Desulfobacter as well as to the sulfur and metal oxidizers comprising the Desulfuromonas cluster. Oligonucleotide probes for specific SRB clusters indicated that SRB represented 14.7% of the total prokaryotic signal, with Desulfotalea/Desulforhopalus being the dominant SRB group (10.7% of the total prokaryotic signal) in the Shallow Bay sediments; these results support previous results obtained for Arctic sediments. Methanosaeta and Desulfotalea/Desulforhopalus appear to be important in Lake Heywood and Shallow Bay, respectively, and may be globally important in permanently low-temperature sediments.

Potential energy surface and MULTIMODE vibrational analysis of C2H3+

A full dimensional, ab initio-based semiglobal potential energy surface for C2H3+ is reported. The ab initio electronic energies for this molecule are calculated using the spin-restricted, coupled cluster method restricted to single and double excitations with triples corrections [RCCSD(T)]. The RCCSD(T) method is used with the correlation-consistent polarized valence triple-zeta basis augmented with diffuse functions (aug-cc-pVTZ). The ab initio potential energy surface is represented by a many-body (cluster) expansion, each term of which uses functions that are fully invariant under permutations of like nuclei. The fitted potential energy surface is validated by comparing normal mode frequencies at the global minimum and secondary minimum with previous and new direct ab initio frequencies. The potential surface is used in vibrational analysis using the "single-reference" and "reaction-path" versions of the code MULTIMODE. (c) 2006 American Institute of Physics.

The use of trajectory cluster analysis to interpret trace gas measurements at Mace Head, Ireland

A first step in interpreting the wide variation in trace gas concentrations measured over time at a given site is to classify the data according to the prevailing weather conditions. In order to classify measurements made during two intensive field campaigns at Mace Head, on the west coast of Ireland, an objective method of assigning data to different weather types has been developed. Air-mass back trajectories calculated using winds from ECMWF analyses, arriving at the site in 1995–1997, were allocated to clusters based on a statistical analysis of the latitude, longitude and pressure of the trajectory at 12 h intervals over 5 days. The robustness of the analysis was assessed by using an ensemble of back trajectories calculated for four points around Mace Head. Separate analyses were made for each of the 3 years, and for four 3-month periods. The use of these clusters in classifying ground-based ozone measurements at Mace Head is described, including the need to exclude data which have been influenced by local perturbations to the regional flow pattern, for example, by sea breezes. Even with a limited data set, based on 2 months of intensive field measurements in 1996 and 1997, there are statistically significant differences in ozone concentrations in air from the different clusters. The limitations of this type of analysis for classification and interpretation of ground-based chemistry measurements are discussed.