Self-organizing Map Methodology Research Articles

How the global health security index and environment factor influence the spread of COVID-19: A country level analysis

The progress of viral diseases such as the new coronavirus (COVID-19) can be influenced not only by social isolation policies, but also by climatic factors. Understanding how these factors affect the progress of the pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) may be essential to know the risks each country is facing because of the disease. In this study, we verified the existence of a relationship between the basic reproduction number (R0) of SARS-CoV-2 with different climate variables, while also considering the Global Health Security Index (GHS). We collected data from confirmed cases of COVID-19 along with their respective GHS notes and climate data, from December 31, 2019 to April 13, 2020, for 52 countries. The generalized additive model (GAM) was applied to explore the effect of temperature, relative humidity, solar radiation index, and GHS score on the spread rate of COVID-19. The countries that showed similarity to each other were grouped into clusters using the Kohonen self-organizing map methodology to investigate the importance of each variable in the dissemination of the disease. The temperature variable presented a linear relationship (p < 0.001) with the R0, with an explained variation of 36.2%, while the relative humidity variable did not present a significant relationship with the R0. The response curve of the solar radiation variable presented a significant nonlinear relationship (p < 0.001) with an explained variation of 32.3%. The GHS index variable, with a significant nonlinear relationship (p < 0.001), presented the largest explanatory response in the control of COVID-19, with an explained variation of 38.4%; further, it was observed that the countries with the largest GHS index scores were less influenced by climate variables.

Patterns of Water Vapor Transport in the Eastern United States

AbstractThis study presents a climatology of water vapor fluxes for the eastern United States and adjacent Atlantic with particular focus on the Northeast. Pathways of moisture transport comprising this climatology were discerned using a self-organizing map methodology ingesting daily integrated vapor transport data from ECMWF ERA-Interim Reanalysis from 1979 to 2017 at a 2.5° × 2.5° spatial resolution. Sixteen spatially distinct moisture transport patterns capture the variety of water vapor transport in the region. The climatology of water vapor transport is precisely and comprehensively defined via synthesis of spatial and temporal characteristics of the fluxes. Each flux has a distinct seasonality and frequency. The fluxes containing the highest amounts of moisture transport occur less frequently than those with less moisture transport. Because the patterns showing less moisture transport are prevalent, they are major contributors to the manner in which water vapor is moved through the eastern United States. The spatial confinement of fluxes is inversely related to persistence, with strong, narrow bands of enhanced moisture transport most often moving through the region on daily time scales. Many moisture fluxes meet a threshold-based definition of atmospheric rivers, with the diversity in trajectories and moisture sources indicating that a variety of mechanisms develop these enhanced moisture transport conditions. Temporal variability in the monthly frequencies of several of the fluxes in this study aligns with changes in the regional precipitation regime, demonstrating that this water vapor flux climatology provides a precise moisture-delivery framework from which changes in precipitation can be investigated.

Using Self-Organizing Maps to Identify Coherent CONUS Precipitation Regions

Abstract Extreme precipitation events have major societal impacts. These events are rare and can have small spatial scale, making statistical analysis difficult; both factors are mitigated by combining events over a region. A methodology is presented to objectively define “coherent” regions wherein data points have matching annual cycles. Regions are found by training self-organizing maps (SOMs) on the annual cycle of precipitation for each grid point across the contiguous United States (CONUS). Using the annual cycle for our intended application minimizes problems caused by consecutive dry periods and localized extreme events. Multiple criteria are applied to identify useful numbers of regions for our future application. Criteria assess these properties for each region: having many more events than experienced by a single grid point, good connectedness and compactness, and robustness to changing the number of regions. Our methodology is applicable across datasets and is tested here on both reanalysis and gridded observational data. Precipitation regions obtained align with large-scale geographical features and are readily interpretable. Useful numbers of regions balance two conflicting preferences: larger regions contain more events and thereby have more robust statistics, but more compact regions allow weather patterns associated with extreme events to be aggregated with confidence. For 6-h precipitation, 12–15 regions over the CONUS optimize our metrics. The regions obtained are compared against two existing region archetypes. For example, a popular set of regions, based on nine groups of states, has less coherent regions than defining the same number of regions with our SOM methodology.

Load estimation for microgrid planning based on a self-organizing map methodology

This study presents a novel load estimation method for isolated communities that do not receive energy or only receive it for a limited time each day. These profiles have been used to determine the installed capacity of generating units for microgrid electrification projects. The social characteristics and lifestyles of isolated communities differ from those in urban areas; therefore, the load profiles of microgrids are sensitive to minor variations in generation and/or consumption. The proposed methodology for obtaining the residential profiles is based on clustering algorithms such as k-means, a self-organizing map (SOM) or others. In this work, SOM clustering is considered because it allows a better interpretation of results that can be contrasted with social aspects. The proposed methodology includes the following components. First, the inputs are processed based on surveys of residents that live in each socio-economic level of housing and the community. Second, family types are clustered using an SOM, from which relevant information is derived that distinguishes one family from another. Third, the load profiles of each cluster are selected from a database. Additionally, social aspects and relevant energy supply information from communities with similar characteristics are used to generate the required database. The SOM for the clustering of families of the community with available energy measurements is used as an initial guess for the clustering of the families in the community with unknown energy measurements.The methodology is applied and tested in the community of El Romeral, Chile, where a microgrid will be installed. The SOM technique compares favorably with a benchmark method that uses the average load profile of a community; furthermore, the SOM clustering algorithm for the methodology is favorably compared with the k-means algorithm because the results obtained by SOM are consistent with the social aspects.

A Classification of Multidimensional Open Data for Urban Morphology

Identifying socio-spatial pa erns through geodemographic classification has provenutility over a range of disciplines. While most of these spatial classification systems include a plethora of socioeconomic attributes, there is arguably little to no input regarding attributes of the built environment or physical space, and their relationship to socioeconomic profiles within this context has not been evaluated in any systematic way. This research explores the generation of neighbourhood characteristics and other attributes using a geographic data science approach, taking advantage of the increasing availability of such spatial data from open data sources. We adopt a SOM (Self-Organizing Maps) methodology to create a classification of Multidimensional Open Data Urban Morphology (MODUM) and test the extent to which this output systematically follows conventional socioeconomic profiles. Such an analysis can also provide a simplified structure of the physical properties of geographic space that can be further used as input to more complex socioeconomic models.

HOW DO DIFFERENT TIME SPANS AFFECT THE PREDICTION ACCURACY OF BUSINESS FAILURE?

(ProQuest: ... denotes formulae omitted.)1. INTRODUCTIONThe global financial crisis that started in 2007 in the United States of America, and the consequent increase of bankruptcy firms since then in many countries, has revived the interest in predicting companies' failure.Even though business failure has been widely tackled in financial literature, most authors focused on applying new methodologies and selecting the most suitable financial ratios and other macro-economic variables to improve prediction.However, there is much less attention on study the time dimension in business failure prediction. This can be approached through two perspectives: (1) in terms of number of years taken as inputs for prediction; and (2) with regard to the bankruptcy time horizon, i.e. the number of years between the end of the analyzed period and the bankruptcy.In relation to the first approach, most studies use data from 1 to 4 years previous to the bankruptcy time horizon (Bellovary et al., 2007) but other authors (Blum, 1974) demonstrated that using financial data of 8 years improves the prediction accuracy.On the other hand, as du Jardin (2015) has pointed out, it is possible to obtain positive prediction results using a bankruptcy time horizon of only one year, but these results are getting significantly worse when a medium term prediction is used. Therefore, a bankruptcy horizon of 1 year is the common approach (Bellovary et al., 2007). Nonetheless, other authors as Dwyer (1992) built methods with high success percentage using a 3-year bankruptcy horizon. In a similar way, du Jardin and Severin (2011) also have proved that Self-Organizing Maps (SOM) can increase the period of bankruptcy prediction up to 3-years without losing predictive accuracy in business failure.This study focuses on analyzing the first approach: the impact of the input data timeframe on the prediction accuracy of business failure when SOM models are applied in classifying healthy and bankrupt companies.The paper is aimed to compare the error rate in identifying healthy and bankrupt companies from the Spanish chemical industry, through SOM methodology, using 3 years previous to the bankruptcy time horizon (2005-2007), by using 6 years (2002-2007) and 9 years (1999-2007). That will enable us to analyze the consequences of longer or shorter timeframe data sample, and to observe if the inclusion of former information provides added value or distorts the obtained results.The remainder of this paper is organized as follows: Section 2 briefly reviews prior studies on business failure. In Section 3 we describe the data and methodology used. In Section 4 the empirical results are discussed. In the final section, we present the conclusions of the study.2. LITERATURE REVIEWCreditors, owners or managers of a company have always been concerned about business failure prediction. Back in the early part of the 20th century, some researchers tried to respond this problem by individual ratio analysis and subsequent comparison between bankrupt and healthy companies (FitzPatrick, 1932; Merwin, 1942; Smith and Winakor, 1935).Nevertheless, was in the mid 1960's when the studies of Beaver (1966) by applying univariate techniques and Altman (1968) by using multi variant discriminant analysis awake the interest on this topic. Altman formulated two scenarios, taking data both from 1 and 2 years previously to bankruptcy.In the 1970's and 1980's a large number of works were made applying different statistic techniques: Libby (1975) combined the principal components analysis (PCA) with discriminant analysis; Ohlson (1980) proposed a logit model to predict business failure; Zmijewski (1984) was pioneer on using a probit model by applying profitability related ratios only; or West (1985) that combined factorial analysis with a logit model. Most of papers in this period were designed using data that are measured over a period t to achieve a prediction over a periodt+1. …

Fast Emulation of Self-organizing Maps for Large Datasets

The self-organizing map (SOM) methodology does vector quantization and clustering on the dataset, and then projects the obtained clusters to a lower dimensional space, such as a 2D map, by positioning similar clusters in locations that are spatially closer in the lower dimension space. This makes the SOM methodology an effective tool for data visualization. However, in a world where mined information from big data have to be available immediately, SOM becomes an unattractive tool because of its time complexity. In this paper, we propose an alternative visualization methodology for large datasets that emulates SOM methodology without the speed constraints inherent to SOM. To demonstrate the efficiency and the potential of the proposed scheme as a fast visualization tool, the methodology is used to cluster and project the 3,823 image samples of handwritten digits of the Optical Recognition of Handwritten Digits dataset. Although the dataset is not, by any means large, it is sufficient to demonstrate the speed-up that can be achieved by using this proposed SOM emulation procedure.

Parameter variation and data mining of oil-film bearings: a stochastic study on the Reynolds’s equation of lubrication

The modeling and simulation process of oil-film bearing dynamics constitutes a rather essential task integrated in the workflow of various mechanical products. Specifically, in the turbo charger industry, the correct capture and understanding of the associated nonlinear rotating dynamics is of utmost importance, since the system’s efficiency and lifetime span depends on it. The root cause of the nonlinear rotordynamic effects is the oil-film concentrated in the rotor’s journal bearings. Its behavior is highly coupled with both the system’s geometric and dynamic configuration. The dynamics of the oil-film are described by the well-known Navier–Stokes equation, which under a series of assumptions and simplifications results to the, so-called, Reynolds equation. In this paper, the Reynolds equation is numerically solved based on a finite difference scheme and several parameter variation studies are conducted in an effort to pinpoint the most influential parameters—journal bearing geometric dimensions, oil-film properties and rotor-velocity-driven inputs—with respect to designated responses—friction, oil-film pressure force, minimum oil-film thickness and boundary oil-flow—all of which are regarded as important in terms of the aforementioned system’s efficiency and lifetime span. Based on multivariate analysis algorithms, correlation outcomes and global sensitivity results are presented. In an effort to capture possible nonlinear phenomena, which might not be possible via linear data mining tools, the Spearman rank-order coefficient and self-organizing maps methodology are applied.

Classification of circulation types over Eastern mediterranean using a self-organizing map approach

In this study an Artificial Neural Network called Self-Organizing Map (SOM) is used in order to classify the synoptic circulation over Europe and especially Eastern Mediterranean. The classification of circulation types is an effective way of summarizing and describing the atmospheric circulation and it is useful in climatology because it provides a better understanding of the climatic variability over an area. Here, the SOM methodology is applied on winter daily geopotential height anomalies of the 500 hPa level, for the period 1971–2000. Twelve unique circulation patterns are identified. Eight of these types are characterized as cyclonic, representing 61% of the total days examined and four types are characterized as anticyclonic, representing 39% of the study period. The results of this classification are comparable to other objective classifications applied on the same study region and present a similar image. Therefore, the SOM methodology is found to be applicable and useful in the classification of circulation types.

Financial Efficiency and Social Impact of Microfinance Institutions Using Self-Organizing Maps

This paper contributes to the literature by investigating whether the increased focus on financial self-sustainability of microfinance institutions has been disadvantageous to the target audience. We investigate the association between social efficiency and financial performance using a comprehensive data set that includes 650 microfinance institutions. A self-organizing map methodology is used to fully capture the existing heterogeneity among institutions. The results show that we cannot support the hypothesis that there exists a trade-off. On the contrary, we find evidence of a significant, positive relationship between social efficiency and financial performance.

Assessment of the water quality of a river catchment by chemometric expertise

AbstractThe present paper deals with the successive application of self‐organizing map (SOM) classification and Hasse diagram technique (HDT) as chemometric tool for assessment of river water quality. The study is carried out by using long‐term water quality monitoring data from the Struma River catchment, Bulgaria. The advantages of the SOM algorithm for advanced visualization and classification of large data sets are used for proper selection of chemical parameters being most effective in quality assessment. The proper variable selection combined with some state directives for surface water quality parameters was then used for performing a new data classification separating the objects of interest (sampling sites) into specific patterns. The simultaneous application of the SOM methodology and partial order theory allows to visualize the spatial and temporal evolution of water quality parameters. Thus, it can be seen that the nitrate loads are decreasing with time and the high specificity of a certain sampling station with respect to its water quality data pattern is changing. Copyright © 2010 John Wiley &amp; Sons, Ltd.

Patterning ecological risk of pesticide contamination at the river basin scale

Ecological risk assessment was conducted to determine the risk posed by pesticide mixtures to the Adour–Garonne river basin (south-western France). The objectives of this study were to assess the general state of this basin with regard to pesticide contamination using a risk assessment procedure and to detect patterns in toxic mixture assemblages through a self-organizing map (SOM) methodology in order to identify the locations at risk. Exposure assessment, risk assessment with species sensitivity distribution, and mixture toxicity rules were used to compute six relative risk predictors for different toxic modes of action: the multi-substance potentially affected fraction of species depending on the toxic mode of action of compounds found in the mixture (msPAF CA TMoA values). Those predictors computed for the 131 sampling sites assessed in this study were then patterned through the SOM learning process. Four clusters of sampling sites exhibiting similar toxic assemblages were identified. In the first cluster, which comprised 83% of the sampling sites, the risk caused by pesticide mixture toward aquatic species was weak (mean msPAF value for those sites < 0.0036%), while in another cluster the risk was significant (mean msPAF < 1.09%). GIS mapping allowed an interesting spatial pattern of the distribution of sampling sites for each cluster to be highlighted with a significant and highly localized risk in the French department called “Lot et Garonne”. The combined use of the SOM methodology, mixture toxicity modelling and a clear geo-referenced representation of results not only revealed the general state of the Adour–Garonne basin with regard to contamination by pesticides but also enabled to analyze the spatial pattern of toxic mixture assemblage in order to prioritize the locations at risk and to detect the group of compounds causing the greatest risk at the basin scale.

Using a self-organizing map to predict invasive species: sensitivity to data errors and a comparison with expert opinion

Summary 1. Predicting which species are more likely to invade a region presents significant difficulties to researchers and government agencies. Methods for estimating the risk of establishment are often qualitative and rely on consultation with experts and stakeholders. The inherent subjectivity of this process can lead to ambiguities in any estimate of a species’ risk of establishment. 2. Using global presence ⁄ absence data of insect crop pests employed a self-organizing map (SOM) to categorize regions based on similarities in species assemblages. This technique enabled them to generate a list of species and rank them based on an index of the risk of establishment. However, the sensitivity of this risk list to errors in the presence ⁄ absence data has never been tested. 3. We evaluated the sensitivity of the SOM method by altering the original presence ⁄ absence data by increasing amounts and compared estimates of risk with those generated by a national coordinating body (Plant Health Australia) utilizing expert stakeholder opinion. 4. The risk list was unaffected by alterations of up to 20% of data over all regions. The error rate we detected in the data was within these limits. 5. Comparison with the expert stakeholder methodology revealed significant differences in the estimates of establishment risk. Further analysis of the Australian data revealed that a number of regions with strong trade links to Australia supported species assemblages similar to those in Australia, suggesting they are possible sources of pest species with high probability of establishment. 6. Synthesis and applications. This analysis confirms that the SOM methodology is a robust tool in the quantification of risk of establishment. In addition, SOMs can deliver a level of objectivity, which can complement current consultative processes employed by many biosecurity agencies around the world, providing a better overall assessment of invasion risk. This assessment can inform research and development funding decisions and incursion management plans for both government and host industries. While SOMs are utilized in this work for the prioritization of pest insects they can potentially be applied to any taxa (pest or native) or at any scale in which the data are available.

Neural networks and cluster analysis for unsupervised classification of cultivated species ofTilia(Malvaceae)

A case study of the classification of 19 species of the genus Tilia (Malvaceae) using morphological data is presented. The value of a self-organizing map (SOM) neural network when applied to this problem is compared with that of a standard cluster analysis method. An interpretation of the results and a discussion of traditional classification systems are provided in order to evaluate the practical usefulness of the SOM methodology. The SOM technique is shown to provide an easily understandable two-dimensional topological map which enables simple linear separation of taxonomic groups. Good separation of traditional infrageneric groups in Tilia is achieved and suggestions about changes to the existing classification are provided. It is concluded that the SOM and cluster analysis methods, whilst both producing results similar to existing classifications, are most effective at different hierarchical levels. © 2009 The Linnean Society of London, Botanical Journal of the Linnean Society, 2009, 159, 300–314.

Molecular modeling of mono- and bis-quaternary ammonium salts as ligands at the α4β2 nicotinic acetylcholine receptor subtype using nonlinear techniques

The neuronal nicotinic acetylcholine receptor (nAChR) has been a target for drug development studies for over a decade. A series of mono- and bis-quaternary ammonium salts, known to be antagonists at nAChRs, were separated into 3 structural classes and evaluated using both self-organizing map (SOM) and genetic functional approximation (GFA) algorithm models. Descriptors from these compounds were used to create several nonlinear quantitative structure-activity relationships (QSARs). The SOM methodology was effective in appropriately grouping these compounds with diverse structures and activities. The GFA models were also able to predict the activities of these molecules. Charge distribution and the hydrophobic free energies were found to be important indicators of bioactivity for this particular class of molecules. These QSAR approaches may be a useful to screen and select in silico new drug candidates from larger compound libraries to be further evaluated in in vitro biological assays.