Search

This article addresses the challenge of sharing finer scale protected health information (PHI) while maintaining patient privacy by using regionalization to create higher resolution Health Insurance Portability and Accountability Act (HIPAA)-compliant geographical aggregations. We compare four regionalization approaches in terms of their fitness for analysis and display: max-p-regions, regionalization with dynamically constrained agglomerative clustering and partitioning (REDCAP), and self-organizing map (SOM) variants of each. Each method is used to create a configuration of regions that aligns with census boundaries, optimizes intraunit homogeneity, and maximizes the number of spatial units while meeting the minimum population threshold required for sharing PHI under HIPAA guidelines. The relative utility of each configuration was assessed with measures of model fit, compactness, homogeneity, and resolution. Adding the SOM procedure to max-p-regions resulted in statistically significant improvements for nearly all assessment measures, whereas the addition of SOM to REDCAP primarily degraded these measures. These differences can be attributed to the different impacts of SOM on top-down and bottom-up regionalization procedures. Overall, we recommend REDCAP, which outperformed on most measures. The SOM variant of max-p-regions (MSOM) could also be recommended, because it provided the highest resolution while maintaining suitable performance on all other measures. [ABSTRACT FROM AUTHOR]

The identification of new white dwarfs (WDs) polluted with heavy elements is important since they provide a valuable tool for inferring the chemical properties of putative planetary systems accreting material on their surfaces. The Gaia space mission has provided us with an unprecedented amount of astrometric, photometric, and low-resolution (XP) spectroscopic data for millions of newly discovered stellar sources, among them thousands of WDs. In order to find WDs among these data and to identify which ones have metals in their atmospheres, we propose a methodology based on an unsupervised artificial intelligence technique called self-organizing maps. In our approach, a nonlinear high-dimensional data set is projected on a 2D grid map where similar elements fall into the same neuron. By applying this method, we obtained a clean sample of 66,337 WDs. We performed an automatic spectral classification analysis on them, obtaining 143 bona fide polluted WD candidates not previously classified in the literature. The majority of them are cool WDs and we identify in their XP spectra several metallic lines such as Ca, Mg, Na, Li, and K. The fact that we obtain similar precision metrics to those achieved with recent supervised techniques highlights the power of our unsupervised approach to mine the Gaia archives for hidden treasures to follow up spectroscopically with higher resolution.

The current and upcoming large data volume galaxy surveys require the use of machine-learning techniques to maximize their scientific return. This study explores the use of Self-Organizing Maps (SOMs) to estimate galaxy parameters with a focus on handling cases of missing data and providing realistic probability distribution functions for the parameters. We train an SOM with a simulated mass-limited lightcone assuming a ugrizY JHK _s +IRAC data set, mimicking the Hyper Suprime-Cam Deep joint data set. For parameter estimation, we derive SOM likelihood surfaces considering photometric errors to derive total (statistical and systematic) uncertainties. We explore the effects of missing data, including which bands are particularly critical to the accuracy of the derived parameters. We demonstrate that the parameter recovery is significantly better when the missing bands are “filled in” rather than if they are completely omitted. We propose a practical method for such recovery of missing data.

Hypertension and diabetes have become a global health and economic issue, being among the major chronic conditions worldwide, particularly in developed countries. To face this global problem, a better knowledge about these diseases becomes crucial to characterize chronic patients. Our aim is two-fold: (1) to provide an efficient visual tool for identifying clinical patterns in high-dimensional data; and (2) to characterize the patient health-status through a data-driven approach using electronic health records of healthy, hypertensive and diabetic populations. We propose a two-stage methodology that uses diagnosis and drug codes of healthy and chronic patients associated to the University Hospital of Fuenlabrada in Spain. The first stage applies the Self-Organizing Map on the aforementioned data to get a set of prototype patients which are projected onto a grid of nodes. Each node has associated a prototype patient that captures relationships among clinical characteristics. In the second stage, clustering methods are applied on the prototype patients to find groups of patients with a similar health-status. Clusters with distinctive patterns linked to chronic conditions were found, being the most remarkable highlights: a cluster of pregnant women emerged among the hypertensive population, and two clusters of diabetic individuals with significant differences in drug-therapy (insulin and non-insulin dependant). The proposed methodology showed to be effective to explore relationships within clinical data and to find patterns related to diabetes and hypertension in a visual way. Our methodology raises as a suitable alternative for building appropriate clinical groups, becoming a promising approach to be applied to any population due to its data-driven philosophy. A thorough analysis of these groups could spawn new and fruitful findings.

Decadal variability in the North Atlantic plays a critical role in modulating regional and global climate. To identify the complex spatiotemporal patterns associated with decadal variability and diagnose mechanisms responsible spatially and over time simultaneously, we debut a novel application of a machine learning method—evolution self‐organizing maps. This time‐evolving framework is applied to a Community Earth System Model pre‐industrial simulation to identify 10‐year consecutive spatiotemporal evolutions of winter sea surface temperature (SST). Here we focus on a single evolution that transitions from SST patterns typically associated with a positive North Atlantic Oscillation (NAO) to a positive Atlantic Multidecadal Variability to a weak negative NAO and find that it can occur over just a 10‐year period. This method facilitates a new examination of buoyancy‐driven and wind‐driven ocean circulations as well as ocean‐atmosphere transient‐eddy feedbacks that confirms the importance of coupled atmosphere‐ocean dynamics in producing this decadal variability. Plain Language Summary: Fluctuations in the North Atlantic Ocean surface temperatures over 10‐year periods impact regional and global climate. This decadal climate variability is often associated with complex interactions between the atmosphere and ocean. These processes vary both spatially and over time making it challenging to characterize this decadal climate variability and diagnose the mechanisms responsible. To address this problem, we debut a novel application of a machine learning method—evolution self‐organizing maps. This framework enables the identification of time evolutions instead of single states, much like characterizing movies as opposed to photos. We apply this framework to a long climate simulation with constant pre‐industrial radiative forcing conditions to identify multiple 10‐year consecutive evolutions of North Atlantic sea surface temperatures. Here we focus on a single evolution pattern with sea surface temperatures that transition between states resembling the North Atlantic Oscillation (the dominant mode of atmospheric variability over the North Atlantic) and the Atlantic Multidecadal Variability (prominent multidecadal variability in the Atlantic Ocean), and show that the entire evolution can occur over just 10 years. Furthermore, with this framework we are able to shed new light on the role of coupled atmosphere‐ocean interactions responsible for this variability. Key Points: The novel evolution self‐organizing map method effectively extracts spatiotemporal evolutions of North Atlantic decadal variabilityEvolutions between North Atlantic Oscillation‐like and Atlantic Multidecadal Variability‐like states can occur over 10 yearsCoupled atmosphere‐ocean interactions are important in generating decadal variability in the North Atlantic [ABSTRACT FROM AUTHOR]

Copyright of Itobiad: Journal of the Human & Social Science Researches / İnsan ve Toplum Bilimleri Araştırmaları Dergisi is the property of Itobiad: Journal of the Human & Social Science Researches and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

• A procedure combined SOM was developed to identify new refrigeration system faults. • Defrosting fault was due to abnormal action of gas-powered suction stop valve. • The diagnostic accuracy for DLL, DML, and DHL were 93.8 %, 91.2 % and 88.6 %, respectively. • Resolution of defrosting issues resulted in up to 18.3 % energy consumption reduction. Refrigeration systems in large cold stores frequently operate suboptimally due to component faults, leading to significant energy wastage and high carbon emissions. This study introduces a novel procedure that leverages data mining to automatically analyze and identify faults, thereby enhancing the intelligence of refrigeration equipment. The research focused on abnormal suction temperatures of compressors during the defrosting of air coolers in a large cold store. Through theoretical analysis and key data acquisition, the root cause of defrosting issues was traced to the abnormal operation of gas-powered suction stop valves, causing leakage of high-pressure hot gas. Clustering methods, Self-Organizing Maps (SOM), were utilized to classify system states and achieved high accuracy rates of 88.6 % to 93.8 % for the three fault modes during the defrosting process, respectively. The resolution of defrosting faults resulted in an energy consumption reduction of up to 18.3 %, aligning with global sustainability initiatives. The study also evaluated the carbon emission reduction, providing a comprehensive approach to improving the efficiency and environmental impact of cold store operations. [ABSTRACT FROM AUTHOR]

Smart meter data provide an in-depth perspective on household energy usage. This research leverages on such data to enhance demand response (DR) programs through a novel application of ensemble clustering. Despite its promising capabilities, our literature review identified a notable under-utilization of ensemble clustering in this domain. To address this shortcoming, we applied an advanced ensemble clustering method and compared its performance with traditional algorithms, namely, K-Means++, fuzzy K-Means, Hierarchical Agglomerative Clustering, Spectral Clustering, Gaussian Mixture Models (GMMs), BIRCH, and Self-Organizing Maps (SOMs), across a dataset of 5567 households for a range of cluster counts from three to nine. The performance of these algorithms was assessed using an extensive set of evaluation metrics, including the Silhouette Score, the Davies–Bouldin Score, the Calinski–Harabasz Score, and the Dunn Index. Notably, while ensemble clustering often ranked among the top performers, it did not consistently surpass all individual algorithms, indicating its potential for further optimization. Unlike approaches that seek the algorithmically optimal number of clusters, our method proposes a practical six-cluster solution designed to meet the operational needs of utility providers. For this case, the best performing algorithm according to the evaluation metrics was ensemble clustering. This study is further enhanced by integrating Explainable AI (xAI) techniques, which improve the interpretability and transparency of our clustering results. [ABSTRACT FROM AUTHOR]

Understanding the village characteristics linked to forest networks is essential for the scientific management of forest resources. Forests are complex socio-ecological systems. This study classifies the resources and characteristics of forest networks and neighboring villages using unsupervised learning algorithms: self-organizing maps (SOM) and geographic-self-organizing maps (Geo-SOMs). Considering ecological, economic, and sociocultural indicators, 18 covariates of 379 villages in two forest networks of the Baekdudaegan Mountain Range in South Korea were analyzed. The data visualizing map size was fixed based on changes in quantization and topographic errors of the same grid maps, and the number of clusters was determined by comparing K-means and hierarchical clustering techniques. An optimal map size of 17 × 12 grids and six clusters was used for further classification of the input data for both SOM and Geo-SOM analyses. The common characteristics of villages were identified using SOM classification, whereas geographically bounded characteristics were identified using Geo-SOM. The approach introduced in this study can be applied to socio-ecological classification and the design of sustainable forest management policies that link the remote sensing and geographic information systems.

Modern microseismic monitoring systems can generate extremely large data sets with signals originating from a variety of natural and anthropogenic sources. These data sets may contain multiple signal types that require classification, analysis and interpretation: a considerable task if done manually. Machine learning techniques may be applied to these data sets to expedite and improve such analysis. In this study, we apply an unsupervised technique, the Self-Organizing Map (SOM), to high-volume data recorded by an in-mine microseismic network. This represents a good example of a large seismic data set that contains a wide range of signals, owing to the diversity of source processes occurring within the mine. The signals are quantified by extracting a number of features (temporal and spectral) from the waveforms which are provided as input data for the SOM. We develop and implement a weighted variant of the SOM in which the contributions of various different features to the training of the map are allowed to evolve. The standard and weighted SOMs are applied to the data, and the output maps compared. Both variants are able to separate source types based on the waveform characteristics, allowing for rapid, automatic classification of signals and the ability to find sources with similar waveforms. Fast classification of such signals provides practical benefit by automatically discarding waveforms associated with anthropogenic sources within the mine while seismic signals originating from genuine microseismic events, which constitute a small fraction of all signals, can be prioritized for subsequent processing and analysis. The weighted variant provides an exploratory tool through quantification of the contribution of different features to the clustering process. This helps to optimize the performance of the SOM through the identification of redundant features. Furthermore, those features that are assigned large weights are considered to be more representative of the source generation processes as they contribute more to the cluster separation process. We apply weighted SOMs to data from a mine recorded during two different time periods, corresponding to different stages of the mine development. Changes in feature importance and in the observed distribution of feature values indicate evolving source generation processes and may be used to support investigatory analysis. The weighted SOM therefore represents an effective tool to help manage and investigate large seismic data sets, providing both practical benefit and insight into underlying event mechanisms. [ABSTRACT FROM AUTHOR]

Information on the genetic diversity of commercial cultivars is of fundamental importance for crop improvement. In addition, information about possible interactions between the maintainers developing these cultivars can help design a breeding program. The objective of this work was to study the genetic diversity of soybean [Glycine max (L.) Merr.] cultivars released in Brazil from 1998 to 2017 and compare the similarity between maintainers of these cultivars based on the phenotypic information disclosed. Data was collected on 1,587 soybean cultivars registered in the National Register of Cultivars of the Ministry of Agriculture, Livestock, and Supply belonging to 59 different maintainers. Among these cultivars, 12 agromorphological traits were evaluated. To perform the grouping and select the main discriminating traits of the cultivars, the Random Forest method was used. Multiple correspondence analysis was performed to obtain the variance explanation percentage of the traits evaluated in each dimension and coordinates among the maintainers. The maintainers were organized through Kohonen self‐organizing map (SOM) through the respective coordinates. There is a wide variety of maintainers of soybean cultivars in Brazil with different objectives for launching new cultivars. Among the maintainers, Soymax presented the most restricted genetic base. The other private companies showed more remarkable similarities and a broader genetic base. The public institution EMBRAPA presented the greatest genetic diversity in its population base. Federal University of Uberlândia and Federal University of Viçosa can be partners to launch soybean cultivars given the proximity between neurons in Kohonen analysis. The high diversity of traits shows that the genetic base of soybean in Brazil is large. Core Ideas: Genetic diversity of soybean cultivars is released in Brazil through computational intelligence approaches.The evolutionary profile of soybean in Brazil from and the genetic diversity among commercial cultivars is shown.This study shows similarity between the maintainers in the development of commercial cultivars. [ABSTRACT FROM AUTHOR]

Social media platforms generate a large amount of content users create, which requires methods for suggesting relevant content. In current empirical research introduces an approach to improving social content recommendations using the Deep Self Organizing Map (DSOM) algorithm and hierarchical clustering. The study uses a database that includes user posts, comments, likes, shared content, and user profiles. The DSOM algorithm analyzes and organizes the data, while hierarchical clustering enhances performance. By utilizing the insights gathered from this social content database, we can significantly improve the accuracy and relevance of recommendations. This improvement will ultimately increase user engagement and satisfaction on social media platforms. The findings of this research have implications for recommendation systems on social media platforms and strategies related to promoting content and analyzing user behavior.

(1) Background: Monitoring effluent in water treatment plants has a key role in identifying potential pollutants that might be released into the environment. A non-target analysis approach can be used for identifying unknown substances and source-specific multipollutant signatures. (2) Methods: Urban and industrial wastewater effluent were analyzed by HPLC-HRMS for non-target analysis. The anomalous infiltration of industrial wastewater into urban wastewater was investigated by analyzing the mass spectra data of “unknown common” compounds using principal component analysis (PCA) and the Self-Organizing Map (SOM) AI tool. The outcomes of the models were compared. (3) Results: The outlier detection was more straightforward in the SOM model than in the PCA one. The differences among the samples could not be completely perceived in the PCA model. Moreover, since PCA involves the calculation of new variables based on the original experimental ones, it is not possible to reconstruct a chromatogram that displays the recurring patterns in the urban WTP samples. This can be achieved using the SOM outcomes. (4) Conclusions: When comparing a large number of samples, the SOM AI tool is highly efficient in terms of calculation, visualization, and identifying outliers. Interpreting PCA visualization and outlier detection becomes challenging when dealing with a large sample size.

The surging demand for electricity, propelled by the widespread adoption of intelligent grids and heightened consumer interaction with electricity demand and pricing, underscores the imperative for precise prognostication of optimal power plant utilization. To confront this challenge, a dataset centered on issue-centric power plans is meticulously crafted. This dataset encapsulates pivotal facets indispensable for attaining sustainable power generation, including meager gas emissions, installation cost, low maintenance cost, elevated power generation, and copious resource availability. The selection of an optimal power plant entails a multifaceted decision-making process, demanding a systematic approach. Our research advocates the amalgamation of multiple-criteria decision-making (MCDM) models with self-organizing maps to gauge the efficacy of diverse sustainable energy systems. The examination discerns solar energy as the preeminent MCDM criterion, securing the apex position with a score of 83.4%, attributable to its ample resource availability, considerable energy generation, nil greenhouse gas emissions, and commendable efficiency. Wind and hydroelectric power closely trail, registering scores of 75.3% and 74.5%, respectively, along with other energy sources. The analysis underscores the supremacy of the renewable energy sources, particularly solar and wind, in fulfilling sustainability objectives and scrutinizing factors such as cost, resource availability, and the environmental impact. The proposed methodology empowers stakeholders to make judicious decisions, accentuating facets that are required for more sustainable and resilient power infrastructure. [ABSTRACT FROM AUTHOR]

This work applies emergent self-organizing map (ESOM) techniques, a form of machine learning, in the multidimensional interpretation and prediction of rare earth element (REE) abundance in produced and geothermal waters in the United States. Visualization of the variables in the ESOM trained using the input data shows that each REE, with the exception of Eu, follows the same distribution patterns and that no single parameter appears to control their distribution. Cross-validation, using a random subsample of the starting data and only using major ions, shows that predictions are generally accurate to within an order of magnitude. Using the same approach, an abridged version of the U.S. Geological Survey Produced Waters Database, Version 2.3 (which includes both data from produced and geothermal waters) was mapped to the ESOM and predicted values were generated for samples that contained enough variables to be effectively mapped. Results show that in general, produced and geothermal waters are predicted to be enriched in REEs by an order of magnitude or more relative to seawater, with maximum predicted enrichments in excess of 1000-fold. Cartographic mapping of the resulting predictions indicates that maximum REE concentrations exceed values in seawater across the majority of geologic basins investigated and that REEs are typically spatially co-associated. The factors causing this co-association were not determined from ESOM analysis, but based on the information currently available, REE content in produced and geothermal waters is not directly controlled by lithology, reservoir temperature, or salinity. [ABSTRACT FROM AUTHOR]

Reducing uncertainty in 3D carbonate rock type distribution is a critical factor that profoundly impacts field development for hydrocarbon or carbon capture and storage (CCS) projects. Miocene carbonate reservoirs in the Central Luconia offshore region are economically important global gas reservoirs. The nature of these carbonate rocks can be visually distinct in the core and the multiscale reservoir heterogeneity might vary in scale from the 100-m scale to the sub-millimeter scale. This work presents a series of steps workflow to obtain spatial information about the organization scheme of carbonate rock types, and capture the most important petrophysical and sedimentary controls on rock property distribution in the E11 field, a carbonate buildup, located in Central Luconia Province, offshore Malaysia. The spatial data were generated from a supervised neural Kohonen algorithm. The rock types predicted with this workflow were propagated using IPSOM probabilized self-organizing maps SOM. This tool is used for classifying multivariate data samples according to “patterns” or multivariate responses. The workflow includes several steps: A Step 1—Core data description, B Step 2—Thin section description, C Step 3—Well log interpretation, and D Step 4—IPSOM probabilized self-organizing maps for facies prediction SOM. The depth plots of the predicted rock type showed close correspondence to the core-based rock types in terms of the stratigraphic organization of tight and reservoir layers, proportions, and juxtaposition. This result is sufficient to merit the application of the rock type logs into a future porosity model of the E11 field, and to understand the lateral and vertical distribution of tight and reservoir rock types of distribution. The results can be used to build a future realistic digital twin of the subsurface, and in digital geological modeling.

Self Organizing Maps (SOM) are unsupervised neural networks suited for visualisation purposes and clustering analysis. This study uses SOM to solve a software engineering problem: detecting the most important (key) classes from software projects. Key classes are meant to link the most valuable concepts of a software system and in general these are found in the solution documentation. UML models created in the design phase become deprecated in time and tend to be a source of confusion for large legacy software. Therefore, developers try to reconstruct class diagrams from the source code using reverse engineering. However, the resulting diagram is often very cluttered and difficult to understand. There is an interest for automatic tools for building concise class diagrams, but the machine learning possibilities are not fully explored at the moment. This paper proposes two possible algorithms to transform SOM in a classification algorithm to solve this task, which involves separating the important classes - that should be on the diagrams - from the others, less important ones. Moreover, SOM is a reliable visualization tool which able to provide an insight about the structure of the analysed projects. Received by the editors: 24 May 2021. 2010 Mathematics Subject Classification. 68T05, 68T20. 1998 CR Categories and Descriptors. I.2.6 [Artificial Intelligence]: Learning - Connectionism and neural nets; D.2.2 [Software Engineering]: Design Tools and Techniques - Computer-aided software engineering (CASE).

The current richness of sequence data needs efficient methodologies to display and analyze the complexity of the information in a compact and readable manner. Traditionally, phylogenetic trees and sequence similarity networks have been used to display and analyze sequences of protein families. These methods aim to shed light on key computational biology problems such as sequence classification and functional inference. Here, we present a new methodology, AlignScape, based on self-organizing maps. AlignScape is applied to three large families of proteins: the kinases and GPCRs from human, and bacterial T6SS proteins. AlignScape provides a map of the similarity landscape and a tree representation of multiple sequence alignments These representations are useful to display, cluster, and classify sequences as well as identify functional trends. The efficient GPU implementation of AlignScape allows the analysis of large MSAs in a few minutes. Furthermore, we show how the AlignScape analysis of proteins belonging to the T6SS complex can be used to predict coevolving partners., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Filella-Merce, Mallet, Durand, Nilges, Bouvier and Pellarin.)

We propose to use Self-Organizing Maps (SOM) to map the impact of physical models onto observables. Using this approach, we are able to determine how theories relate to each other given their signatures. In cosmology this will be particularly useful to determine cosmological models (such as dark energy, modified gravity or inflationary models) that should be tested by the new generation of experiments. As a first example, we apply this approach to the representation of a subset of the space of modified gravity theories probed by cosmic shear. We therefore train a SOM on shear correlation functions in the f(R), dilaton and symmetron models. The results indicate these three theories have similar signatures on shear for small values of their parameters but the dilaton has different signature for higher values. We also show that modified gravity (especially the dilaton model) has a different impact on cosmic shear compared to a dynamical dark energy so both need to be tested by galaxy surveys.

This article proposes a kernel‐based regularization least squares algorithm for nonlinear time‐delayed systems with unknown structure. Since the structure and the time‐delay of the model are unknown, a model pool constituted of several Volterra series is constructed with the aim of approximating the nonlinear model which has different time‐delays. Then, a self‐organizing maps method and a kernel‐based regularization method are interactively used to update the time‐delay and parameters. Compared with the traditional algorithms, the proposed algorithm has no limitation on the nonlinear model, and can describe the dynamics of the nonlinear model with a simple structure. Finally, simulation examples are given to show the effectiveness of the algorithm. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) is a complex degenerative brain disease that affects nerve cells in the brain responsible for body movement. Machine learning is widely used to track the progression of PD in its early stages by predicting unified Parkinson's disease rating scale (UPDRS) scores. In this paper, we aim to develop a new method for PD diagnosis with the aid of supervised and unsupervised learning techniques. Our method is developed using the Laplacian score, Gaussian process regression (GPR) and self-organizing maps (SOM). SOM is used to segment the data to handle large PD datasets. The models are then constructed using GPR for the prediction of the UPDRS scores. To select the important features in the PD dataset, we use the Laplacian score in the method. We evaluate the developed approach on a PD dataset including a set of speech signals. The method was evaluated through root-mean-square error (RMSE) and adjusted R-squared (adjusted R²). Our findings reveal that the proposed method is efficient in the prediction of UPDRS scores through a set of speech signals (dysphonia measures). The method evaluation showed that SOM combined with the Laplacian score and Gaussian process regression with the exponential kernel provides the best results for R-squared (Motor-UPDRS = 0.9489; Total-UPDRS = 0.9516) and RMSE (Motor-UPDRS = 0.5144; Total-UPDRS = 0.5105) in predicting UPDRS compared with the other kernels in Gaussian process regression. [ABSTRACT FROM AUTHOR]