Viral Fitness Landscapes Based on Self-organizing Maps.

The creation of fitness maps from viral populations especially in the case of RNA viruses, with high mutation rates producing quasispecies, is complex since the mutant spectrum is in a very high-dimensional space. In this work, a new approach is presented using a class of neural networks, Self-Organized Maps (SOM), to represent realistic fitness landscapes in two RNA viruses: Human Immunodeficiency Virus type 1 (HIV-1) and Hepatitis C Virus (HCV). This methodology has proven to be very effective in the classification of viral quasispecies, using as criterium the mutant sequences in the population. With HIV-1, the fitness landscapes are constructed by representing the experimentally determined fitness on the sequence map. This approach permitted the depiction of the evolutionary paths of the variants subjected to processes of fitness loss and gain in cell culture. In the case of HCV, the efficiency was measured as a function of the frequency of each haplotype in the population by ultra-deep sequencing. The fitness landscapes obtained provided information on the efficiency of each variant in the quasispecies environment, that is, in relation to the entire spectrum of mutants. With the SOM maps, it is possible to determine the evolutionary dynamics of the different haplotypes.

PM10-bound trace elements in pan-European urban atmosphere.

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.

Self-organizing maps on "what-where" codes towards fully unsupervised classification.

Interest in unsupervised learning architectures has been rising. Besides being biologically unnatural, it is costly to depend on large labeled data sets to get a well-performing classification system. Therefore, both the deep learning community and the more biologically-inspired models community have focused on proposing unsupervised techniques that can produce adequate hidden representations which can then be fed to a simpler supervised classifier. Despite great success with this approach, an ultimate dependence on a supervised model remains, which forces the number of classes to be known beforehand, and makes the system depend on labels to extract concepts. To overcome this limitation, recent work has been proposed that shows how a self-organizing map (SOM) can be used as a completely unsupervised classifier. However, to achieve success it required deep learning techniques to generate high quality embeddings. The purpose of this work is to show that we can use our previously proposed What-Where encoder in tandem with the SOM to get an end-to-end unsupervised system that is Hebbian. Such system, requires no labels to train nor does it require knowledge of which classes exist beforehand. It can be trained online and adapt to new classes that may emerge. As in the original work, we use the MNIST data set to run an experimental analysis and verify that the system achieves similar accuracies to the best ones reported thus far. Furthermore, we extend the analysis to the more difficult Fashion-MNIST problem and conclude that the system still performs.

Spatiotemporal evolution of COVID-19 in Portugal's Mainland with self-organizing maps.

BACKGROUND: Self-Organizing Maps (SOM) are an unsupervised learning clustering and dimensionality reduction algorithm capable of mapping an initial complex high-dimensional data set into a low-dimensional domain, such as a two-dimensional grid of neurons. In the reduced space, the original complex patterns and their interactions can be better visualized, interpreted and understood. METHODS: We use SOM to simultaneously couple the spatial and temporal domains of the COVID-19 evolution in the 278 municipalities of mainland Portugal during the first year of the pandemic. Temporal 14-days cumulative incidence time series along with socio-economic and demographic indicators per municipality were analyzed with SOM to identify regions of the country with similar behavior and infer the possible common origins of the incidence evolution. RESULTS: The results show how neighbor municipalities tend to share a similar behavior of the disease, revealing the strong spatiotemporal relationship of the COVID-19 spreading beyond the administrative borders of each municipality. Additionally, we demonstrate how local socio-economic and demographic characteristics evolved as determinants of COVID-19 transmission, during the 1st wave school density per municipality was more relevant, where during 2nd wave jobs in the secondary sector and the deprivation score were more relevant. CONCLUSIONS: The results show that SOM can be an effective tool to analysing the spatiotemporal behavior of COVID-19 and synthetize the history of the disease in mainland Portugal during the period in analysis. While SOM have been applied to diverse scientific fields, the application of SOM to study the spatiotemporal evolution of COVID-19 is still limited. This work illustrates how SOM can be used to describe the spatiotemporal behavior of epidemic events. While the example shown herein uses 14-days cumulative incidence curves, the same analysis can be performed using other relevant data such as mortality data, vaccination rates or even infection rates of other disease of infectious nature.

Characterization of movement patterns using unsupervised learning neural networks: Exploring a novel approach for monitoring athletes during sidestepping.

The monitoring of athletes is crucial to preventing injuries, identifying fatigue or supporting return-to-play decisions. The purpose of this study was to explore the ability of Kohonen neural network self-organizing maps (SOM) to objectively characterize movement patterns during sidestepping and their association with injury risk. Further, the network's sensitivity to detect limb dominance was assessed. The data of 67 athletes with a total of 613 trials were included in this study. The 3D trajectories of 28 lower-body passive markers collected during sidestepping were used to train a SOM. The network consisted of 1247 neurons distributed over a 43 × 29 rectangular map with a hexagonal neighbourhood topology. Out of 61,913 input vectors, the SOM identified 1247 unique body postures. Visualizing the movement trajectories and adding several hidden variables allows for the investigation of different movement patterns and their association with joint loading. The used approach identified athletes that show significantly different movement strategies when sidestepping with their dominant or non-dominant leg, where one strategy was clearly associated with ACL-injury-relevant risk factors. The results highlight the ability of unsupervised machine learning to monitor an individual athlete's status without the necessity to reduce the complexity of the data describing the movement.

Comparative Analysis of the Clustering Quality in Self-Organizing Maps for Human Posture Classification.

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.

TCDD-Induced Allosteric Perturbation of the AhR:ARNT Binding to DNA.

The aryl hydrocarbon receptor (AhR) is a ligand-activated transcription factor that mediates the biological and toxicological effects of structurally diverse chemicals, including halogenated aromatic hydrocarbons. In this work, we investigate the effects of the binding of the AhR prototypical ligand, TCDD, on the stability of the AhR:ARNT complex, as well as the mechanisms by which ligand-induced perturbations propagate to the DNA recognition site responsible for gene transcription. To this aim, a reliable structural model of the overall quaternary structure of the AhR:ARNT:DRE complex is proposed, based on homology modelling. The model shows very good agreement with a previous one and is supported by experimental evidence. Moreover, molecular dynamics simulations are performed to compare the dynamic behaviour of the AhR:ARNT heterodimer in the presence or absence of the TCDD. Analysis of the simulations, performed by an unsupervised machine learning method, shows that TCDD binding to the AhR PASB domain influences the stability of several inter-domain interactions, in particular at the PASA-PASB interface. The inter-domain communication network suggests a mechanism by which TCDD binding allosterically stabilizes the interactions at the DNA recognition site. These findings may have implications for the comprehension of the different toxic outcomes of AhR ligands and drug design.

Spatio-temporal variation of groundwater pollution in urban wetlands and management strategies for zoning.

Groundwater is an important resource to maintain the sustainable development of urban wetlands. The Jixi National Wetland Park (JNWP) was studied to realize the refined prevention and control of groundwater. The self-organizing map-K-means algorithm (SOM-KM), improved water quality index (IWQI), health risk assessment model and forward model were used comprehensively to evaluate the groundwater status and solute sources in different periods. The results showed that the groundwater chemical type in most areas was the HCO3-Ca type. Groundwater chemistry data from different periods were clustered into five groups. Groups 1 and 5 are affected by agricultural and industrial activities, respectively. The IWQI value in the normal period was higher in most areas due to the influence of spring ploughing. The east side of the JNWP was disturbed by human activities, and the quality of drinking water continued to deteriorate from the wet period to the dry period. 64.29% of the monitoring points showed good irrigation suitability. The health risk assessment model showed that the health risk was the largest in the dry period and the smallest in the wet period. The main factors causing health risks in the wet period and other periods were NO3- and F-, respectively. The overall cancer risk was within acceptable limits. The forward model and ion ratio analysis showed that the weathering of carbonate rocks was the main factor affecting the evolution of groundwater chemistry, accounting for 67.16%. The high-risk areas of pollution were mainly concentrated in the east of the JNWP. K+ and Cl- were the key monitoring ions in the risk-free zone and potential risk zone, respectively. The research can be used to help decision-makers carry out fine zoning control of groundwater.

Pyrolysis Atmospheres and Temperatures Co-Mediated Spectral Variations of Biochar-Derived Dissolved Organic Carbon: Quantitative Prediction and Self-Organizing Maps Analysis.

Biochar-derived dissolved organic carbon (BDOC), as a highly activated carbonaceous fraction of biochar, significantly affects the environmental effect of biochar. This study systematically investigated the differences in the properties of BDOC produced at 300-750 °C in three atmosphere types (including N2 and CO2 flows and air limitation) as well as their quantitative relationship with biochar properties. The results showed that BDOC in biochar pyrolyzed in air limitation (0.19-2.88 mg/g) was more than that pyrolyzed in N2 (0.06-1.63 mg/g) and CO2 flows (0.07-1.74 mg/g) at 450-750 °C. The aliphaticity, humification, molecular weight, and polarity of BDOC strongly depended on the atmosphere types as well as the pyrolysis temperatures. BDOC produced in air limitation contained more humic-like substances (0.65-0.89) and less fulvic-like substances (0.11-0.35) than that produced in N2 and CO2 flows. The multiple linear regression of the exponential form of biochar properties (H and O contents, H/C and (O+N)/C) could be used to quantitatively predict the bulk content and organic component contents of BDOC. Additionally, self-organizing maps could effectively visualize the categories of fluorescence intensity and components of BDOC from different pyrolysis atmospheres and temperatures. This study highlights that pyrolysis atmosphere types are a crucial factor controlling the BDOC properties, and some characteristics of BDOC can be quantitatively evaluated based on the properties of biochar.

Determinants of the European Sovereign Debt Crisis: Application of Logit, Panel Markov Regime Switching Model and Self Organizing Maps.

The study aims to empirically identify the determinants of the debt crisis that occurred within the framework of 15 core EU member countries (EU-15). Contrary to previous empirical studies that tend to use event-based crisis indicators, our study develops a continuous fiscal stress index to identify the debt crises in the EU-15 and employs three different estimation techniques, namely self-organizing map, multivariate logit and panel Markov regime switching models. Our estimation results show first that the study correctly identifies the time and the length of the debt crisis in each EU-15-member country. Empirical results then indicate, via three different models, that the debt crisis in the EU-15 is the consequence of deterioration of both financial and macroeconomic variables such as nonperforming loans over total loans, GDP growth, unemployment rates, primary balance over GDP, and cyclically adjusted balance over GDP. Furthermore, variables measuring governance quality, such as voice and accountability, regulatory quality, and government effectiveness, also play a significant role in the emergence and the duration of the debt crisis in the EU-15.

Analysis of the uncharted, druglike property space by self-organizing maps.

Physicochemical properties are fundamental to predict the pharmacokinetic and pharmacodynamic behavior of drug candidates. Easily calculated descriptors such as molecular weight and logP have been found to correlate with the success rate of clinical trials. These properties have been previously shown to highlight a sweet-spot in the chemical space associated with favorable pharmacokinetics, which is superior against other regions during hit identification and optimization. In this study, we applied self-organizing maps (SOMs) trained on sixteen calculated properties of a subset of known drugs for the analysis of commercially available compound databases, as well as public biological and chemical databases frequently used for drug discovery. Interestingly, several regions of the property space have been identified that are highly overrepresented by commercially available chemical libraries, while we found almost completely unoccupied regions of the maps (commercially neglected chemical space resembling the properties of known drugs). Moreover, these underrepresented portions of the chemical space are compatible with most rigorous property filters applied by the pharma industry in medicinal chemistry optimization programs. Our results suggest that SOMs may be directly utilized in the strategy of library design for drug discovery to sample previously unexplored parts of the chemical space to aim at yet-undruggable targets.

Damage Classification Using Supervised Self-Organizing Maps in Structural Health Monitoring.

Improvements in computing capacity have allowed computers today to execute increasingly complex tasks. One of the main benefits of these improvements is the possibility of developing machine learning algorithms, of which the fields of application are extensive and varied. However, an area in which this type of algorithms acquires an increasing relevance is structural health monitoring (SHM), where inspection strategies and guided wave-based approaches make the evaluation of the structural conditions of an aircraft, vessel or building among others possible, by detecting and classifying existing damages. The use of sensors, data acquisition systems (DAQ) and computation has also allowed these damage detection and classification tasks to be carried out automatically. Despite today's advances, it is still necessary to continue with the development of more robust, reliable, and low-cost structural health monitoring systems. For this reason, this work contemplates three key points: (i) the configuration of a data acquisition system for signal gathering from an an active piezoelectric (PZT) sensor network; (ii) the development of a damage classification methodology based on signal processing techniques (normalization and PCA), from which the models that describe the structural conditions of the plate are built; and (iii) the use of machine learning algorithms, more specifically, three variants of the self-organizing maps called CPANN (counterpropagation artificial neural network), SKN (supervised Kohonen) and XYF (X-Y fused Kohonen). The data obtained allowed one to carry out an experimental validation of the damage classification methodology, to determine the presence of damages in two aluminum plates of different sizes, where masses were added to change the vibrational responses captured by the sensor network and a composite (CFRP) plate with real damages, such as delamination and cracks. This classification methodology allowed one to obtain excellent results by validating the usefulness of the SKN and XYF networks in damage classification tasks, showing overall accuracies of 73.75% and 72.5%, respectively, according to the cross-validation process. These percentages are higher than those obtained in comparison with other neural networks such as: kNN, discriminant analysis, classification trees, partial least square discriminant analysis, and backpropagation neural networks, when the cross-validation process was applied.

Usefulness of Vaccine Adverse Event Reporting System for Machine-Learning Based Vaccine Research: A Case Study for COVID-19 Vaccines.

Usefulness of Vaccine-Adverse Event-Reporting System (VAERS) data and protocols required for statistical analyses were pinpointed with a set of recommendations for the application of machine learning modeling or exploratory analyses on VAERS data with a case study of COVID-19 vaccines (Pfizer-BioNTech, Moderna, Janssen). A total of 262,454 duplicate reports (29%) from 905,976 reports were identified, which were merged into a total of 643,522 distinct reports. A customized online survey was also conducted providing 211 reports. A total of 20 highest reported adverse events were first identified. Differences in results after applying various machine learning algorithms (association rule mining, self-organizing maps, hierarchical clustering, bipartite graphs) on VAERS data were noticed. Moderna reports showed injection-site-related AEs of higher frequencies by 15.2%, consistent with the online survey (12% higher reporting rate for pain in the muscle for Moderna compared to Pfizer-BioNTech). AEs {headache, pyrexia, fatigue, chills, pain, dizziness} constituted >50% of the total reports. Chest pain in male children reports was 295% higher than in female children reports. Penicillin and sulfa were of the highest frequencies (22%, and 19%, respectively). Analysis of uncleaned VAERS data demonstrated major differences from the above (7% variations). Spelling/grammatical mistakes in allergies were discovered (e.g., ~14% reports with incorrect spellings for penicillin).

Unsupervised Learning in Drug Design from Self-Organization to Deep Chemistry.

The availability of computers has brought novel prospects in drug design. Neural networks (NN) were an early tool that cheminformatics tested for converting data into drugs. However, the initial interest faded for almost two decades. The recent success of Deep Learning (DL) has inspired a renaissance of neural networks for their potential application in deep chemistry. DL targets direct data analysis without any human intervention. Although back-propagation NN is the main algorithm in the DL that is currently being used, unsupervised learning can be even more efficient. We review self-organizing maps (SOM) in mapping molecular representations from the 1990s to the current deep chemistry. We discovered the enormous efficiency of SOM not only for features that could be expected by humans, but also for those that are not trivial to human chemists. We reviewed the DL projects in the current literature, especially unsupervised architectures. DL appears to be efficient in pattern recognition (Deep Face) or chess (Deep Blue). However, an efficient deep chemistry is still a matter for the future. This is because the availability of measured property data in chemistry is still limited.

Self-organizing maps with variable neighborhoods facilitate learning of chromatin accessibility signal shapes associated with regulatory elements.

BACKGROUND: Assigning chromatin states genome-wide (e.g. promoters, enhancers, etc.) is commonly performed to improve functional interpretation of these states. However, computational methods to assign chromatin state suffer from the following drawbacks: they typically require data from multiple assays, which may not be practically feasible to obtain, and they depend on peak calling algorithms, which require careful parameterization and often exclude the majority of the genome. To address these drawbacks, we propose a novel learning technique built upon the Self-Organizing Map (SOM), Self-Organizing Map with Variable Neighborhoods (SOM-VN), to learn a set of representative shapes from a single, genome-wide, chromatin accessibility dataset to associate with a chromatin state assignment in which a particular RE is prevalent. These shapes can then be used to assign chromatin state using our workflow. RESULTS: We validate the performance of the SOM-VN workflow on 14 different samples of varying quality, namely one assay each of A549 and GM12878 cell lines and two each of H1 and HeLa cell lines, primary B-cells, and brain, heart, and stomach tissue. We show that SOM-VN learns shapes that are (1) non-random, (2) associated with known chromatin states, (3) generalizable across sets of chromosomes, and (4) associated with magnitude and multimodality. We compare the accuracy of SOM-VN chromatin states against the Clustering Aggregation Tool (CAGT), an unsupervised method that learns chromatin accessibility signal shapes but does not associate these shapes with REs, and we show that overall precision and recall is increased when learning shapes using SOM-VN as compared to CAGT. We further compare enhancer state assignments from SOM-VN in signals above a set threshold to enhancer state assignments from Predicting Enhancers from ATAC-seq Data (PEAS), a deep learning method that assigns enhancer chromatin states to peaks. We show that the precision-recall area under the curve for the assignment of enhancer states is comparable to PEAS. CONCLUSIONS: Our work shows that the SOM-VN workflow can learn relationships between REs and chromatin accessibility signal shape, which is an important step toward the goal of assigning and comparing enhancer state across multiple experiments and phenotypic states.

Machine learning for holistic visualization of STEMI registry data.

BACKGROUND: Widespread adoption of evidence-based guidelines and treatment pathways in ST-Elevation Myocardial Infarction (STEMI) patients has considerably improved cardiac survival and decreased the risk of recurrent myocardial infarction. However, survival outcomes appear to have plateaued over the last decade. The hope underpinning the current study is to engage data visualization to develop a more holistic understanding of the patient space, supported by principles and techniques borrowed from traditionally disparate disciplines, like cartography and machine learning. METHODS AND RESULTS: The Minnesota Heart Institute Foundation (MHIF) STEMI database is a large prospective regional STEMI registry consisting of 180 variables of heterogeneous data types on more than 5000 patients spanning 15 years. Initial assessment and preprocessing of the registry database was undertaken, followed by a first proof-of-concept implementation of an analytical workflow that involved machine learning, dimensionality reduction, and data visualization. 38 pre-admission variables were analyzed in an all-encompassing representation of pre-index STEMI event data. We aim to generate a holistic visual representation - a map of the multivariate patient space - by training a high-resolution self-organizing neural network consisting of several thousand neurons. The resulting 2-D lattice arrangement of n-dimensional neuron vectors allowed patients to be represented as point locations in a 2-D display space. Patient attributes were then visually examined and contextualized in the same display space, from demographics to pre-existing conditions, event-specific procedures, and STEMI outcomes. Data visualizations implemented in this study include a small-multiple display of neural component planes, composite visualization of the multivariate patient space, and overlay visualization of non-training attributes. CONCLUSION: Our study represents the first known marriage of cartography and machine learning techniques to obtain visualizations of the multivariate space of a regional STEMI registry. Combining cartographic mapping techniques and artificial neural networks permitted the transformation of the STEMI database into novel, two-dimensional visualizations of patient characteristics and outcomes. Notably, these visualizations also drive the discovery of anomalies in the data set, informing corrections applied to detected outliers, thereby further refining the registry for integrity and accuracy. Building on these advances, future efforts will focus on supporting further understanding of risk factors and predictors of outcomes in STEMI patients. More broadly, the thorough visual exploration of display spaces generated through a conjunction of dimensionality reduction with the mature technology base of geographic information systems appears a promising direction for biomedical research.

Framework for Behavioral Analysis of Mobile Networks.

The arrival of the Fifth Generation (5G) entails a significant evolution in the context of mobile communication networks. This new technology will bring heterogeneous scenarios with new types of services and an increasingly high number of users and nodes. The efficient management of such complex networks has become an important challenge. To address this problem, automatic and efficient algorithms must be developed to facilitate operators' management and optimization of their networks. These algorithms must be able to cope with a very high number of heterogeneous data and different types of scenarios. In this paper, a novel framework for a cellular network behavioral analysis and monitoring is presented. This framework is based on a combination of unsupervised and supervised machine learning techniques. The proposed system can analyze the behavior of cells and monitor them, searching for behavior changes over time. The information extracted by the framework can be used to improve subsequent management and optimization functions.

Detecting Phase-Synchrony Connectivity Anomalies in EEG Signals. Application to Dyslexia Diagnosis.

Objective Dyslexia diagnosis is a challenging task, since traditional diagnosis methods are not based on biological markers but on behavioural tests. Although dyslexia diagnosis has been addressed by these tests in clinical practice, it is difficult to extract information about the brain processes involved in the different tasks and, then, to go deeper into its biological basis. Thus, the use of biomarkers can contribute not only to the diagnosis but also to a better understanding of specific learning disorders such as dyslexia. In this work, we use Electroencephalography (EEG) signals to discover differences among controls and dyslexic subjects using signal processing and artificial intelligence techniques. Specifically, we measure phase synchronization among channels, to reveal the functional brain network activated during auditory processing. On the other hand, to explore synchronicity patterns risen by low-level auditory processing, we used specific stimuli consisting in band-limited white noise, modulated in amplitude at different frequencies. The differential information contained in the functional (i.e., synchronization) network has been processed by an anomaly detection system that addresses the problem of subjects variability by an outlier-detection method based on vector quantization. The results, obtained for 7 years-old children, show that the proposed method constitutes an useful tool for clinical use, with the area under ROC curve (AUC) values up to 0.95 in differential diagnosis tasks.

Fault Prediction and Early-Detection in Large PV Power Plants Based on Self-Organizing Maps.

In this paper, a novel and flexible solution for fault prediction based on data collected from Supervisory Control and Data Acquisition (SCADA) system is presented. Generic fault/status prediction is offered by means of a data driven approach based on a self-organizing map (SOM) and the definition of an original Key Performance Indicator (KPI). The model has been assessed on a park of three photovoltaic (PV) plants with installed capacity up to 10 MW, and on more than sixty inverter modules of three different technology brands. The results indicate that the proposed method is effective in predicting incipient generic faults in average up to 7 days in advance with true positives rate up to 95%. The model is easily deployable for on-line monitoring of anomalies on new PV plants and technologies, requiring only the availability of historical SCADA data, fault taxonomy and inverter electrical datasheet.

Estimation of Organizational Competitiveness by a Hybrid of One-Dimensional Convolutional Neural Networks and Self-Organizing Maps Using Physiological Signals for Emotional Analysis of Employees.

The theory of modern organizations considers emotional intelligence to be the metric for tools that enable organizations to create a competitive vision. It also helps corporate leaders enthusiastically adhere to the vision and energize organizational stakeholders to accomplish the vision. In this study, the one-dimensional convolutional neural network classification model is initially employed to interpret and evaluate shifts in emotion over a period by categorizing emotional states that occur at particular moments during mutual interaction using physiological signals. The self-organizing map technique is implemented to cluster overall organizational emotions to represent organizational competitiveness. The analysis of variance test results indicates no significant difference in age and body mass index for participants exhibiting different emotions. However, a significant mean difference was observed for the blood volume pulse, galvanic skin response, skin temperature, valence, and arousal values, indicating the effectiveness of the chosen physiological sensors and their measures to analyze emotions for organizational competitiveness. We achieved 99.8% classification accuracy for emotions using the proposed technique. The study precisely identifies the emotions and locates a connection between emotional intelligence and organizational competitiveness (i.e., a positive relationship with employees augments organizational competitiveness).