RESUMEN

The complex interactions between groundwater chemical environments and PFAS present challenges for data analysis and factor assessment of the spatial distribution and source attribution of PFAS in groundwater. This study employed spatial response analysis combining self-organizing maps (SOM), K-means clustering, Spearman correlation, positive matrix factorization (PMF) and risk quotient (RQ), to uncover the spatial characteristics, driving factors, sources, and human health risks of groundwater PFAS in the Pearl River Basin. The results indicated that the characteristics of PFAS in groundwater were classified into 16 neurons, which were further divided into 6 clusters (I-VI). This division was due to the contribution of industrial pollution (33.2 %) and domestic pollution (31.5 %) to the composition of PFAS in groundwater. In addition, the hydrochemical indicators such as pH, dissolved organic carbon (DOC), chloride (Cl-), and calcium ions (Ca2+) might also affect the distribution pattern of PFAS. The potential human health risk in the area was minimal, with cluster Ⅱ presenting the highest risk (RQ value 0.25) which is closely related to PFOA emissions from fluoropolymer industry. This study provides a theoretical basis and data support for applying of SOM to the visualization and control of PFAS contamination in groundwater.

RESUMEN

Introduction: Degeneracy in the brain-behavior code refers to the brain's ability to utilize different neural configurations to support similar functions, reflecting its adaptability and robustness. This study aims to explore degeneracy by investigating the non-linear associations between psychometric profiles and resting-state functional connectivity (RSFC). Methods: The study analyzed RSFC data from 500 subjects to uncover the underlying neural configurations associated with various psychometric outcomes. Self-organized maps (SOM), a type of unsupervised machine learning algorithm, were employed to cluster the RSFC data. And identify distinct archetypal connectivity profiles characterized by unique within- and between-network connectivity patterns. Results: The clustering analysis using SOM revealed several distinct archetypal connectivity profiles within the RSFC data. Each archetype exhibited unique connectivity patterns that correlated with various cognitive, physical, and socioemotional outcomes. Notably, the interaction between different SOM dimensions was significantly associated with specific psychometric profiles. Discussion: This study underscores the complexity of brain-behavior interactions and the brain's capacity for degeneracy, where different neural configurations can lead to similar behavioral outcomes. These findings highlight the existence of multiple brain architectures capable of producing similar behavioral outcomes, illustrating the concept of neural degeneracy, and advance our understanding of neural degeneracy and its implications for cognitive and emotional health.

RESUMEN

Papyrus has been used for millennia to record information, for sophisticated works of art as well as mundane notes. The collection, identification, and translation of papyrus fragments therefore opens a gateway into the past. To aid the efforts to access the history recorded in papyri, we investigated the suitability of NIR spectroscopy to perform two tasks: One is to support the authentication of ancient papyri, by differentiation of papyri that were manufactured more recently and subjected to accelerated ageing to resemble the originals. The other is the extensive task to piece together papyrus fragments into readable texts again. In museums around the world, more than 100,000 ancient papyrus fragments still wait for their proper assembly, deciphering and publication. The papyrus writing-ground was analysed by near-infrared (NIR) spectroscopy, and the spectra were evaluated using principal component analysis (PCA), hierarchical cluster analysis (HCA), partial least squares discriminant analysis (PLS-DA), and self-organizing maps (SOM). Cluster analysis and PLS-DA proved to be useful tools for distinguishing modern papyri from ancient papyri which were provided by collections in Vienna and Leipzig. Neither natural nor accelerated ageing affected the classification. A PLS-DA classification model, constructed from NIR spectra of 89 model scores, detected recent Papyri samples with 100 % sensitivity and specificity, even after accelerated ageing. The identification of groups of fragments of ancient papyri based on NIR spectra and chemometry is not straightforward. HCA, which focuses on the differences between samples, only grouped the fragments of 4 out of 20 papyri correctly. SOM, which rather focuses on the similarities, grouped 6 sets of fragments correctly. An automated grouping of fragments remains difficult, since the fragments themselves are heterogeneous while similarities between unrelated ancient papyri can be large.

RESUMEN

Cognitive impairments are core features in individuals across the psychosis continuum and predict functional outcomes. Nevertheless, substantial variability in cognitive functioning within diagnostic groups, along with considerable overlap with healthy controls, hampers the translation of research findings into personalized treatment planning. Aligned with precision medicine, we employed a data driven machine learning method, self-organizing maps, to conduct transdiagnostic clustering based on cognitive functions in a sample comprising 228 healthy controls, 200 individuals at ultra-high risk for psychosis, and 98 antipsychotic-naïve patients with first-episode psychosis. The self-organizing maps revealed six clinically distinct cognitive profiles that significantly predicted baseline functional level and changes in functional level after one year. Cognitive flexibility in particular, as well as specific executive functions emerged as cardinal in differentiating the profiles. The application of self-organizing maps appears to be a promising approach to inform clinical decision-making based on individualized cognitive profiles, including patient allocation to different interventions. Moreover, this method has the potential to enable cross-diagnostic stratification in research trials, utilizing data-driven subgrouping informed by categories from underlying dimensions of cognition rather than from clinical diagnoses. Finally, the method enables cross-diagnostic profiling across other data modalities, such as brain networks or metabolic subtypes.

RESUMEN

The river course is a transitional area connecting the source and receiving water bodies. The dissolved organic matter (DOM) in the river course is an important factor affecting the aquatic environment and ecological health. However, there are shortcomings in studying the differences and quantitative contributions of river DOM in different seasons and sources. In this study, ultraviolet-visible (UV-vis) and three-dimensional fluorescence spectra were used to characterize the optical properties, analyze the spatiotemporal changes, and establish the quantitative relationship between environmental factors and DOM in the inflow rivers of Baiyangdian Lake. The results showed that the relative DOM concentrations in summer and autumn were significantly higher than those in the other seasons (P < 0.001) and that the DOM source (SR < 1) was mainly exogenous. The fluorescence abundance of protein-like substances (C1 + C2 + C3) was the highest in spring, whereas that of humus C4 was the highest in autumn. Moreover, the inflow rivers exhibited strong autogenetic characteristics (BIX > 1) throughout the year. Self-organizing maps (SOM) indicated that the main driving factors of water quality were NO3--N in spring, autumn, and winter and DO, pH, and chemical oxygen demand (COD) in summer. Random forest analysis showed that the fluorescent components (C1-C4) were closely related to the migration and transformation of nitrogen, and pH and nitrogen were the main predictors of each component. The Mantel test and structural equation model (SEM) showed that temperature and NO3--N significantly influenced the DOM concentration, components, and molecular properties in different seasons. Moreover, the river source also affected the distribution mechanism of DOM in the water body. Our study comprehensively analyzed the response of DOM in inflow rivers in different seasons and water sources, providing a basis for further understanding the driving mechanisms of water quality.

RESUMEN

Although many studies have discussed the impact of Europe's air quality, very limited research focused on the detailed phenomenology of ambient trace elements (TEs) in PM10 in urban atmosphere. This study compiled long-term (2013-2022) measurements of speciation of ambient urban PM10 from 55 sites of 7 countries (Switzerland, Spain, France, Greece, Italy, Portugal, UK), aiming to elucidate the phenomenology of 20 TEs in PM10 in urban Europe. The monitoring sites comprised urban background (UB, n = 26), traffic (TR, n = 10), industrial (IN, n = 5), suburban background (SUB, n = 7), and rural background (RB, n = 7) types. The sampling campaigns were conducted using standardized protocols to ensure data comparability. In each country, PM10 samples were collected over a fixed period using high-volume air samplers. The analysis encompassed the spatio-temporal distribution of TEs, and relationships between TEs at each site. Results indicated an annual average for the sum of 20 TEs of 90 ± 65 ng/m3, with TR and IN sites exhibiting the highest concentrations (130 ± 66 and 131 ± 80 ng/m3, respectively). Seasonal variability in TEs concentrations, influenced by emission sources and meteorology, revealed significant differences (p < 0.05) across all monitoring sites. Estimation of TE concentrations highlighted distinct ratios between non-carcinogenic and carcinogenic metals, with Zn (40 ± 49 ng/m3), Ti (21 ± 29 ng/m3), and Cu (23 ± 35 ng/m3) dominating non-carcinogenic TEs, while Cr (5 ± 7 ng/m3), and Ni (2 ± 6 ng/m3) were prominent among carcinogenic ones. Correlations between TEs across diverse locations and seasons varied, in agreement with differences in emission sources and meteorological conditions. This study provides valuable insights into TEs in pan-European urban atmosphere, contributing to a comprehensive dataset for future environmental protection policies.

Asunto(s)

RESUMEN

BACKGROUND AND OBJECTIVE: This paper proposes a fully automated and unsupervised stochastic segmentation approach using two-level joint Markov-Gibbs Random Field (MGRF) to detect the vascular system from retinal Optical Coherence Tomography Angiography (OCTA) images, which is a critical step in developing Computer-Aided Diagnosis (CAD) systems for detecting retinal diseases. METHODS: Using a new probabilistic model based on a Linear Combination of Discrete Gaussian (LCDG), the first level models the appearance of OCTA images and their spatially smoothed images. The parameters of the LCDG model are estimated using a modified Expectation Maximization (EM) algorithm. The second level models the maps of OCTA images, including the vascular system and other retina tissues, using MGRF with analytically estimated parameters from the input images. The proposed segmentation approach employs modified self-organizing maps as a MAP-based optimizer maximizing the joint likelihood and handles the Joint MGRF model in a new, unsupervised way. This approach deviates from traditional stochastic optimization approaches and leverages non-linear optimization to achieve more accurate segmentation results. RESULTS: The proposed segmentation framework is evaluated quantitatively on a dataset of 204 subjects. Achieving 0.92 ± 0.03 Dice similarity coefficient, 0.69 ± 0.25 95-percentile bidirectional Hausdorff distance, and 0.93 ± 0.03 accuracy, confirms the superior performance of the proposed approach. CONCLUSIONS: The conclusions drawn from the study highlight the superior performance of the proposed unsupervised and fully automated segmentation approach in detecting the vascular system from OCTA images. This approach not only deviates from traditional methods but also achieves more accurate segmentation results, demonstrating its potential in aiding the development of CAD systems for detecting retinal diseases.

Asunto(s)

RESUMEN

Understanding local patterns of rainfall variability is of great concern in East Africa, where agricultural productivity is dominantly rainfall dependent. However, East African rainfall climatology is influenced by numerous drivers operating at multiple scales, and local patterns of variability are not adequately understood. Here, we show evidence of substantial variability of local rainfall patterns between 1981 and 2021 at the national and county level in Kenya, East Africa. Results show anomalous patterns of both wetting and drying in both the long and short rainy seasons, with evidence of increased frequency of extreme wet and dry events through time. Observations also indicate that seasonal and intraseasonal variability increased significantly after 2013, coincident with diminished coherence between ENSO (El Nino Southern Oscillation) and rainfall. Increasing frequency and magnitude of rainfall variability suggests increasing need for local-level climate change adaptation strategies.

RESUMEN

The Minas artisanal cheese from the Serra da Canastra (MAC-CM) microregion is a traditional product due to its production and ripening process. Artisanal chesses manufactured with raw cow's milk and endogenous dairy starters ("also known as pingo") have distinctive flavors and other sensory characteristics because of the unknown microbiota. The aim of this study was to evaluate the microbiota during 30 days of ripening, the physicochemical changes, and their relation in MACs produced in two different microregions located in the Serra da Canastra microregion through culture-dependent and culture-independent methods. The MACs were collected in the cities of Bambuí (MAC-CMB) and Tapiraí (MAC-CMT) in the Canastra microregion (n = 21). Cheeses uniqueness was demonstrated with the multivariate analysis that joined the microbiota and physicochemical characteristics, mainly to the proteolysis process, in which the MAC-CMT showed deeper proteolysis (DI -T0:14.18; T30: 13.95), while the MAC-CMB reached only a primary level (EI -T0:24.23; T30: 31.10). Abiotic factors were responsible for the differences in microbial diversity between the cheese farms. Different microbial groups: the prokaryotes, like Corynebacterium variabile, Lactococcus lactis, and Staphylococcus saprophyticus; and the eukaryotes, like Kluyveromyces lactis and Diutina catenulata dominated ripening over time. The microbial community and proteolysis were responsible for the predominance of volatile groups, with alcohols predominating in MAC-CMB and free fatty acids/acids and esters in MAC-CMT.

Asunto(s)

RESUMEN

Background and objective: Systemic autoinflammatory diseases (SAIDs) are characterized by widespread inflammation, but for most of them there is a lack of specific biomarkers for accurate diagnosis. Although a number of machine learning algorithms have been used to analyze SAID datasets, aiding in the discovery of novel biomarkers, there is a growing recognition of the importance of SAID timeseries clustering, as it can capture the temporal dynamics of gene expression patterns. Methodology: This paper proposes a novel clustering methodology to efficiently associate three-dimensional data. The algorithm utilizes competitive learning to create a self-organizing neural network and adjust neuron positions in time-dependent and high dimensional feature space in order to assign them as clustering centers. The quantitative evaluation of the clustering was based on well-known clustering indices. Furthermore, a differential expression analysis and classification pipeline was employed to assess the capability of the proposed methodology to extract more accurate pathway-specific genes from its clusters. For that, a comparative analysis was also conducted against a heuristic timeseries clustering method. Results: The proposed methodology achieved better overall clustering indices scores and classification metrics using genes derived from its clusters. Notable cases include a threefold increase in the Calinski-Harabasz clustering index, a twofold improvement in the Davies-Bouldin clustering index and a ∼60% increase in the classification specificity score. Conclusion: A novel clustering methodology was developed and applied on several gene expression timeseries datasets from systemic autoinflammatory diseases, and its ability to efficiently produce well separated clusters compared to existing heuristic methods was demonstrated.

RESUMEN

CONTEXT: Ubiquitin-like with PHD and RING finger domain containing protein 1 (UHRF1) is responsible for preserving the stability of genomic methylation through the recruitment of DNA methyltransferase 1 (DNMT1). However, the interaction between Developmental pluripotency associated 3 (DPPA3) and the pre-PHD-PHD (PPHD) domain of UHRF1 hinders the nuclear localization of UHRF1. This disruption has implications for potential cancer treatment strategies. Drugs that mimic the binding pattern between DPPA3 and PPHD could offer a promising approach to cancer treatment. Our study reveals that DPPA3 undergoes dissociation from the C-terminal through three different modes of helix unfolding. Furthermore, we have identified key residue pairs involved in this dissociation process and potential drug-targeting residues. These findings offer valuable insights into the dissociation mechanism of DPPA3 from PPHD and have the potential to inform the design of novel drugs targeting UHRF1 for cancer therapy. METHODS: To comprehend the dissociation process and binding patterns of PPHD-DPPA3, we employed enhanced sampling techniques, including steered molecular dynamics (SMD) and conventional molecular dynamics (cMD). Additionally, we utilized self-organizing maps (SOM) and time-resolved force distribution analysis (TRFDA) methodologies. The Gromacs software was used for performing molecular dynamics simulations, and the AMBER FF14SB force field was applied to the protein.

Asunto(s)

RESUMEN

There is demand for scalable algorithms capable of clustering and analyzing large time series data. The Kohonen self-organizing map (SOM) is an unsupervised artificial neural network for clustering, visualizing, and reducing the dimensionality of complex data. Like all clustering methods, it requires a measure of similarity between input data (in this work time series). Dynamic time warping (DTW) is one such measure, and a top performer that accommodates distortions when aligning time series. Despite its popularity in clustering, DTW is limited in practice because the runtime complexity is quadratic with the length of the time series. To address this, we present a new a self-organizing map for clustering TIME Series, called SOMTimeS, which uses DTW as the distance measure. The method has similar accuracy compared with other DTW-based clustering algorithms, yet scales better and runs faster. The computational performance stems from the pruning of unnecessary DTW computations during the SOM's training phase. For comparison, we implement a similar pruning strategy for K-means, and call the latter K-TimeS. SOMTimeS and K-TimeS pruned 43% and 50% of the total DTW computations, respectively. Pruning effectiveness, accuracy, execution time and scalability are evaluated using 112 benchmark time series datasets from the UC Riverside classification archive, and show that for similar accuracy, a 1.8× speed-up on average for SOMTimeS and K-TimeS, respectively with that rates vary between 1× and 18× depending on the dataset. We also apply SOMTimeS to a healthcare study of patient-clinician serious illness conversations to demonstrate the algorithm's utility with complex, temporally sequenced natural language. Supplementary Information: The online version contains supplementary material available at 10.1007/s10618-023-00979-9.

RESUMEN

The Italian garlic ecotype "Vessalico" possesses distinct characteristics compared to its French parent cultivars Messidor and Messidrôme, used for sowing, as well as other ecotypes in neighboring regions. However, due to the lack of a standardized seed supply method and cultivation protocol among farmers in the Vessalico area, a need to identify garlic products that align with the Vessalico ecotype arises. In this study, an NMR-based approach followed by multivariate analysis to analyze the chemical composition of Vessalico garlic sourced from 17 different farms, along with its two French parent cultivars, was employed. Self-organizing maps allowed to identify a homogeneous subset of representative samples of the Vessalico ecotype. Through the OPLS-DA model, the most discriminant metabolites based on values of VIP (Variable Influence on Projections) were selected. Among them, S-allylcysteine emerged as a potential marker for distinguishing the Vessalico garlic from the French parent cultivars by NMR screening. Additionally, to promote sustainable agricultural practices, the potential of Vessalico garlic extracts and its main components as agrochemicals against Xanthomonas campestris pv. campestris, responsible for black rot disease, was explored. The crude extract exhibited a MIC of 125 µg/mL, and allicin demonstrated the highest activity among the tested compounds (MIC value of 31.25 µg/mL).

RESUMEN

The Adriatic Sea plays a crucial role as both a significant fishing ground and a thriving trading market for small pelagic edible fish. Recognized for their nutritional value, these fish are esteemed for their high protein content and abundance of polyunsaturated omega-3 and omega-6 fatty acids, making them a sought-after and healthful food choice. Nevertheless, pelagic species can also serve as a reservoir for lipophilic organochlorine pollutants, posing potential risks to human health. In this study, we compared traditional classification methods traditional principal component analysis (PCA) and Ward's clustering with an advanced self-organizing map (SOM) algorithm in determining distribution patterns of 24 organochlorines and 19 fatty acids in sardine and anchovy samples taken from the eastern Adriatic. The outcomes reveal the strengths and weaknesses of the three approaches (PCA, Ward's clustering, and SOM). However, it is evident that SOM has proven to be the most effective in offering detailed information and data visualization. Although sardines and anchovies exhibit similar distribution patterns for p,p'-DDE, PCB-28, PCB-138, PCB-153, PCB-118, and PCB-170, they differ in the concentrations of fatty acids such as stearic, palmitic, myristic, oleic, docosapentaenoic, and docosahexaenoic acid. Our findings supply valuable insights for environmental authorities and fish consumers concerning the potential risks associated with organochlorines in these two types of fish.

Asunto(s)

RESUMEN

We propose a new nature- and neuro-science-inspired algorithm for spatiotemporal learning and prediction based on sequential recall and vector symbolic architecture. A key novelty is the learning of spatial and temporal patterns as decoupled concepts where the temporal pattern sequences are constructed using the learned spatial patterns as an alphabet of elements. The decoupling, motivated by cognitive neuroscience research, provides the flexibility for fast and adaptive learning with dynamic changes to data and concept drift and as such is better suited for real-time learning and prediction. The algorithm further addresses several key computational requirements for predicting the next occurrences based on real-life spatiotemporal data, which have been found to be challenging with current state-of-the-art algorithms. Firstly, spatial and temporal patterns are detected using unsupervised learning from unlabeled data streams in changing environments; secondly, vector symbolic architecture (VSA) is used to manage variable-length sequences; and thirdly, hyper dimensional (HD) computing-based associative memory is used to facilitate the continuous prediction of the next occurrences in sequential patterns. The algorithm has been empirically evaluated using two benchmark and three time-series datasets to demonstrate its advantages compared to the state-of-the-art in spatiotemporal unsupervised sequence learning where the proposed ST-SOM algorithm is able to achieve 45% error reduction compared to HTM algorithm.

RESUMEN

The Toce River (Northern Italy) is characterized by legacy contamination of dichloro-diphenyl-trichloroethane (DDT), mercury, and arsenic deriving from an industrial plant active between ca. 1915 and 1996. Chironomidae taxa assemblages and sediments were collected in 2014 and 2019 upstream and downstream of the industrial area to analyze species responses to toxic substances in a river stretch with relatively uniform natural (i.e., hydro-morphological) characteristics. A total of 32 chironomid taxa were identified. Sediment concentrations reached levels potentially toxic for benthic invertebrates: 15.7 µg kg-1 1% organic carbon for DDT, 197 µg kg-1 dry weight (d.w.) for Hg, and 55.7 mg kg-1 d.w. for As. Canonical Correspondence Analysis (CCA) revealed a predominant seasonal gradient, followed by an upstream-downstream gradient. Partial CCA indicated that 5.2% of the total variation was associated with sediment contamination. Self-Organizing Maps (SOMs) were used to represent species responses to toxicants. Most species appeared to be tolerant, e.g., Chironomus riparius, Micropsectra atrofasciata, Conchapelopia pallidula, and Polypedilum spp. Sensitivity to contaminants was observed in only a few species: Diamesa spp., Sympotthastia spinifera, and Prodiamesa olivacea to DDT; Potthastia longimanus to Hg; Odontomesa fulva and Microtendipes pedellus to As. The chironomid community was characterized in presence of contamination levels commonly observed in freshwater ecosystems.

RESUMEN

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.

RESUMEN

Collected evidence has shown that contaminants of emerging concern (CECs) in conjunction with more conventional tracers (major ions, nutrients, isotopes etc.) can be used to trace pollution origin in aquatic systems. However, in highly mixed aquifer systems signals obtained from conventional tracers overlap diminishing their potential to be used as tracers. In this study, we present an approach that incorporates multivariate statistical analysis (principal component analysis (PCA) and Kohonen's Self-Organizing Map method (SOM)) and mixing modelling to identify the most suitable CECs to be employed as anthropogenic tracers. The study area is located in the Besòs River Delta (Barcelona, NE Spain) and represents the highly mixed aquifer system. A one-year monthly based monitoring campaign was performed to collect the information about the concentrations of 105 CECs as well as major and minor ions in the river and along the groundwater flow. The dimensionality of the obtained dataset was reduced to 25 CECs, based on their estimated health risk effects, for multivariate data analysis. The obtained results showed the overlap of conventional tracers' signals obtained from PCA. In case of CECs, PCA revealed differences in their distributions allowing the differentiation of the roles of natural attenuation processes, local and regional flows on their occurrence in different parts of the aquifer. This was not possible to do using solely CECs' distribution profiles. SOMs provided the lacking information about the modality of the distribution of each CECs, revealing their ability to represent factors controlling the groundwater hydrochemistry, which assist in defining their tracer potential. Based on the obtained results four identified persistent CECs, two with unimodal (lamotrigine and 5-Desamino-5-oxo-lamotrigine) and two with bimodal (carbamazepine and diazepam (higher modality was not revealed)) distributions, were selected to run a mixing model to compare their tracer performance.

Asunto(s)

RESUMEN

Introduction: The escalating challenge of climate change has underscored the critical need to understand cold defense mechanisms in cultivated grapevine Vitis vinifera. Temperature variations can affect the growth and overall health of vine. Methods: We used Self Organizing Maps machine learning method to analyze gene expression data from leaves of five Vitis vinifera cultivars each treated by four different temperature conditions. The algorithm generated sample-specific "portraits" of the normalized gene expression data, revealing distinct patterns related to the temperature conditions applied. Results: Our analysis unveiled a connection with vitamin B1 (thiamine) biosynthesis, suggesting a link between temperature regulation and thiamine metabolism, in agreement with thiamine related stress response established in Arabidopsis before. Furthermore, we found that epigenetic mechanisms play a crucial role in regulating the expression of stress-responsive genes at low temperatures in grapevines. Discussion: Application of Self Organizing Maps portrayal to vine transcriptomics identified modules of coregulated genes triggered under cold stress. Our machine learning approach provides a promising option for transcriptomics studies in plants.

RESUMEN

The objective of this article is to develop a methodology for selecting the appropriate number of clusters to group and identify human postures using neural networks with unsupervised self-organizing maps. Although unsupervised clustering algorithms have proven effective in recognizing human postures, many works are limited to testing which data are correctly or incorrectly recognized. They often neglect the task of selecting the appropriate number of groups (where the number of clusters corresponds to the number of output neurons, i.e., the number of postures) using clustering quality assessments. The use of quality scores to determine the number of clusters frees the expert to make subjective decisions about the number of postures, enabling the use of unsupervised learning. Due to high dimensionality and data variability, expert decisions (referred to as data labeling) can be difficult and time-consuming. In our case, there is no manual labeling step. We introduce a new clustering quality score: the discriminant score (DS). We describe the process of selecting the most suitable number of postures using human activity records captured by RGB-D cameras. Comparative studies on the usefulness of popular clustering quality scores-such as the silhouette coefficient, Dunn index, Calinski-Harabasz index, Davies-Bouldin index, and DS-for posture classification tasks are presented, along with graphical illustrations of the results produced by DS. The findings show that DS offers good quality in posture recognition, effectively following postural transitions and similarities.