K-means Research Articles

Habitat-based CT radiomics enhances the ability to predict spread through air spaces in stage T1 invasive lung adenocarcinoma.

Spread through air spaces (STAS) represents a novel invasive pattern in lung adenocarcinoma (LUAD) and is a risk factor for poor prognosis in stage T1 LUAD. This study aims to develop and validate a CT habitat imaging analysis model for predicting STAS in stage T1 invasive LUAD. We retrospectively analyzed 217 patients with preoperative stage T1 invasive LUAD (115 STAS-positive and 102 STAS-negative cases, including 151 in the train set and 66 in the test set). Semi-automatic segmentation was performed on the regions of interest (ROIs) in all CT images, with an automatic 3mm expansion around the tumor, considering the intratumoral and peritumoral 3mm area. This area was divided into three sub-regions via K-means clustering, and 1197 radiomic features were extracted from each sub-region and the overall combined region. After dimension reduction through the Mann-Whitney U test, Pearson correlation analysis, and least absolute shrinkage and selection operator(LASSO), the best features for each sub-region and overall were selected. Models were then built using the selected radiomic features through the Adaptive Boosting (AdaBoost) and Multilayer Perceptron (MLP) classifiers. Four different models were established based on different sub-regions and the overall features. The performance of these models was evaluated through receiver operating characteristic curves (AUC) under the DeLong test, calibration curves via the Hosmer-Lemeshow test, and decision curve analysis to assess the performance of these features. In this study, we evaluated the predictive performance of AdaBoost and MLP classifiers on rad feature models across various subregions and the overall dataset. In the test set, the AdaBoost classifier achieved a maximum AUC of 0.871 in Habitat 3, whereas the MLP classifier demonstrated slightly superior performance with an AUC of 0.879. Both classifiers exhibited high efficiency in habitat 3, with the MLP algorithm showing enhanced model performance. CT habitat imaging analysis for the preoperative prediction of STAS in stage T1 invasive LUAD shows satisfactory diagnostic performance, with the habitat3 model exhibiting the highest efficacy, reflecting tumor heterogeneity.

Unsupervised Multi-Scale Hybrid Feature Extraction Network for Semantic Segmentation of High-Resolution Remote Sensing Images

Generating pixel-level annotations for semantic segmentation tasks of high-resolution remote sensing images is both time-consuming and labor-intensive, which has led to increased interest in unsupervised methods. Therefore, in this paper, we propose an unsupervised multi-scale hybrid feature extraction network based on the CNN-Transformer architecture, referred to as MSHFE-Net. The MSHFE-Net consists of three main modules: a Multi-Scale Pixel-Guided CNN Encoder, a Multi-Scale Aggregation Transformer Encoder, and a Parallel Attention Fusion Module. The Multi-Scale Pixel-Guided CNN Encoder is designed for multi-scale, fine-grained feature extraction in unsupervised tasks, efficiently recovering local spatial information in images. Meanwhile, the Multi-Scale Aggregation Transformer Encoder introduces a multi-scale aggregation module, which further enhances the unsupervised acquisition of multi-scale contextual information, obtaining global features with stronger feature representation. The Parallel Attention Fusion Module employs an attention mechanism to fuse global and local features in both channel and spatial dimensions in parallel, enriching the semantic relations extracted during unsupervised training and improving the performance of unsupervised semantic segmentation. K-means clustering is then performed on the fused features to achieve high-precision unsupervised semantic segmentation. Experiments with MSHFE-Net on the Potsdam and Vaihingen datasets demonstrate its effectiveness in significantly improving the accuracy of unsupervised semantic segmentation.

Multi-Layered Unsupervised Learning Driven by Signal-to-Noise Ratio-Based Relaying for Vehicular Ad Hoc Network-Supported Intelligent Transport System in eHealth Monitoring.

Every year, about 1.19 million people are killed in traffic accidents; hence, the United Nations has a goal of halving the number of road traffic deaths and injuries by 2030. In line with this objective, technological innovations in telecommunication, particularly brought about by the rise of 5G networks, have contributed to the development of modern Vehicle-to-Everything (V2X) systems for communication. A New Radio V2X (NR-V2X) was introduced in the latest Third Generation Partnership Project (3GPP) releases which allows user devices to exchange information without relying on roadside infrastructures. This, together with Massive Machine Type Communication (mMTC) and Ultra-Reliable Low Latency Communication (URLLC), has led to the significantly increased reliability, coverage, and efficiency of vehicular communication networks. The use of artificial intelligence (AI), especially K-means clustering, has been very promising in terms of supporting efficient data exchange in vehicular ad hoc networks (VANETs). K-means is an unsupervised machine learning (ML) technique that groups vehicles located near each other geographically so that they can communicate with one another directly within these clusters while also allowing for inter-cluster communication via cluster heads. This paper proposes a multi-layered VANET-enabled Intelligent Transportation System (ITS) framework powered by unsupervised learning to optimize communication efficiency, scalability, and reliability. By leveraging AI in VANET solutions, the proposed framework aims to address road safety challenges and contribute to global efforts to meet the United Nations' 2030 target. Additionally, this framework's robust communication and data processing capabilities can be extended to eHealth monitoring systems, enabling real-time health data transmission and processing for continuous patient monitoring and timely medical interventions. This paper's contributions include exploring AI-driven approaches for enhanced data interaction, improved safety in VANET-based ITS environments, and potential applications in eHealth monitoring.

Research on high voltage circuit breaker multi-sensor signal feature selection method based on GA-Kmeans algorithm

Abstract Currently, in the research on fault information of high-voltage circuit breakers (HVCBs) based on multi-sensor data, issues such as shallow feature assessment and unclear feature selection rules exist, leading to a decrease in fault identification accuracy due to redundant characteristics. To address this, this paper proposes a novel feature selection method based on GA-Kmeans. This method encodes the original feature space into binary format and employs the clustering accuracy of the Kmeans model as the fitness function to obtain a high-quality feature subset that maximally represents and distinguishes faults. By combining different feature selection methods with fault diagnosis models, six typical application scenarios are constructed. Results indicate that compared to traditional methods such as Relief-F, KPCA, GA-SVM for feature selection, and SVM for fault diagnosis, the proposed GA-Kmeans method reduces the dimensionality of the original feature space and employs the Kmeans clustering algorithm as the diagnostic model, achieving a final diagnostic accuracy of 95.29%. This method outperforms others, with a 37.24% higher diagnostic accuracy than SVM under the original feature space, and a decrease of 47.90% in standard deviation. This validates the necessity of feature selection and the superiority of the proposed method, providing a reliable and stable diagnostic basis for subsequent mechanical fault diagnosis of HVCBs.

Clustering-based risk stratification of prediabetes populations: Insights from the Taiwan and UK Biobanks.

This study aimed to identify low- and high-risk diabetes groups within prediabetes populations using data from the Taiwan Biobank (TWB) and UK Biobank (UKB) through a clustering-based Unsupervised Learning (UL) approach, to inform targeted type 2 diabetes (T2D) interventions. Data from TWB and UKB, comprising clinical and genetic information, were analyzed. Prediabetes was defined by glucose thresholds, and incident T2D was identified through follow-up data. K-means clustering was performed on prediabetes participants using significant features determined through logistic regression and LASSO. Cluster stability was assessed using mean Jaccard similarity, silhouette score, and the elbow method. We identified two stable clusters representing high- and low-risk diabetes groups in both biobanks. The high-risk clusters showed higher diabetes incidence, with 15.7% in TWB and 13.0% in UKB, compared to 7.3% and 9.1% in the low-risk clusters, respectively. Notably, males were predominant in the high-risk groups, constituting 76.6% in TWB and 52.7% in UKB. In TWB, the high-risk group also exhibited significantly higher BMI, fasting glucose, and triglycerides, while UKB showed marginal significance in BMI and other metabolic indicators. Current smoking was significantly associated with increased diabetes risk in the TWB high-risk group (P < 0.001). Kaplan-Meier curves indicated significant differences in diabetes complication incidences between clusters. UL effectively identified risk-specific groups within prediabetes populations, with high-risk groups strongly associated male gender, higher BMI, smoking, and metabolic markers. Tailored preventive strategies, particularly for young males in Taiwan, are crucial to reducing T2D risk.

Unsupervised Learning for the Automatic Counting of Grains in Nanocrystals and Image Segmentation at the Atomic Resolution.

Identifying the grain distribution and grain boundaries of nanoparticles is important for predicting their properties. Experimental methods for identifying the crystallographic distribution, such as precession electron diffraction, are limited by their probe size. In this study, we developed an unsupervised learning method by applying a Gabor filter to HAADF-STEM images at the atomic level for image segmentation and automatic counting of grains in polycrystalline nanoparticles. The methodology comprises a Gabor filter for feature extraction, non-negative matrix factorization for dimension reduction, and K-means clustering. We set the threshold distance and angle between the clusters required for the number of clusters to converge so as to automatically determine the optimal number of grains. This approach can shed new light on the nature of polycrystalline nanoparticles and their structure-property relationships.

Through the eyes of the parents: a transdiagnostic psychiatric perspective for children with differences of sexual development.

Existing literature lacks data on a subgroup exhibiting psychiatric symptoms below the DSM-5 diagnostic threshold within DSD cases. Our study aims to assess parental knowledge, attitudes toward DSD, and parental perceptions of emotional and behavioral states through a transdiagnostic perspective. The study was conducted with a total of 35 parents of children with DSD. Two groups were established via k-means clustering, based on psychiatric symptomatology levels, derived from The Strength and Difficulties Questionnaire- Parent Form and The Revised Children's Anxiety and Depression Scale- Parent Form: with one group exhibiting lower reported psychiatric symptoms (LPS=27) and the other demonstrating higher psychiatric symptoms (HPS=8) by parents. Our study found that many parents were hesitant to disclose DSD diagnoses to their children, believing them to be too young to comprehend the information (42.9 %) and that they were unaware of the available support that could be provided by the medical team in disclosing the diagnosis (25.7 %). Our study found no differences in DSM-5 diagnoses between HPS and LPS groups (p>0.05), with ADHD being the most prevalent diagnosis (21.7 %) and a significant overrepresentation of children with a discrepancy between assigned gender at birth and gender upbringing in the HPS group compared to the LPS group (p<0.001). Our study emphasizes the necessity of a transdiagnostic approach in psychiatry to move beyond binary conceptualizations and better understand the complexities of individuals with DSD.

Unveiling Post-COVID-19 syndrome: incidence, biomarkers, and clinical phenotypes in a Thai population

BackgroundPost-COVID- 19 syndrome (PCS) significantly impacts the quality of life of survivors. There is, however, a lack of a standardized approach to PCS diagnosis and management. Our bidirectional cohort study aimed to estimate PCS incidence, identify risk factors and biomarkers, and classify clinical phenotypes for enhanced management to improve patient outcomes.MethodsA bidirectional prospective cohort study was conducted at five medical sites in Hatyai district in Songkhla Province, Thailand. Participants were randomly selected from among the survivors of COVID-19 aged≥18 years between May 15, 2022, and January 31, 2023. The selected participants underwent a scheduled outpatient visit for symptom and health assessments 12 to 16 weeks after the acute onset of infection, during which PCS was diagnosed and blood samples were collected for hematological, inflammatory, and serological tests. PCS was defined according to the World Health Organization criteria. Univariate and multiple logistic regression analyses were used to identify biomarkers associated with PCS. Moreover, three clustering methods (agglomerative hierarchical, divisive hierarchical, and K-means clustering) were applied, and internal validation metrics were used to determine clustering and similarities in phenotypes.FindingsA total of 300 survivors were enrolled in the study, 47% of whom developed PCS according to the World Health Organization (WHO) definition. In the sampled cohort, 66.3% were females, and 79.4% of them developed PCS (as compared to 54.7% of males, p-value <0.001). Comorbidities were present in 19% (57/300) of all patients, with 11% (18/159) in the group without PCS and 27.7% (39/141) in the group with PCS. The incidence of PCS varied depending on the criteria used and reached 13% when a quality of life indicator was added to the WHO definition. Common PCS symptoms were hair loss (22%) and fatigue (21%), while mental health symptoms were less frequent (insomnia 3%, depression 3%, anxiety 2%). According to our univariate analysis, we found significantly lower hematocrit and IgG levels and greater ALP levels in PCS patients than in patients who did not develop PCS (p-value< 0.05). According to our multivariable analysis, adjusted ALP levels remained a significant predictor of PCS (OR 1.02, p-value= 0.005). Clustering analysis revealed four groups characterized by severe clinical symptoms and mental health concerns (Cluster 1, 4%), moderate physical symptoms with predominant mental health issues (Cluster 2, 9%), moderate mental health issues with predominant physical symptoms (Cluster 3, 14%), and mild to no PCS (Cluster 4, 77%). The quality of life and ALP levels varied across the clusters.InterpretationThis study challenges the prevailing diagnostic criteria for PCS, emphasizing the need for a holistic approach that considers quality of life. The identification of ALP as a biomarker associated with PCS suggests that its monitoring could be used for early detection of the onset of PCS. Cluster analysis revealed four distinct clinical phenotypes characterized by different clinical symptoms and mental health concerns that 'exhibited varying impacts on quality of life. This finding suggested that accounting for the reduced quality of life in the definition of PCS could enhance its diagnosis and management and that moving toward personalized interventions could both improve patient outcomes and help reduce medicalization and optimally target the available resources.FundingThe research publication received funding support from Medical Council of Thailand (Police General Dr. Jongjate Aojanepong Foundation), Hatyai Hospital Charity and Wellcome Trust.

Rapid and Robust Identification of Sepsis Using SeptiCyte RAPID in a Heterogeneous Patient Population.

Background/Objective: SeptiCyte RAPID is a transcriptional host response assay that discriminates between sepsis and non-infectious systemic inflammation (SIRS) with a one-hour turnaround time. The overall performance of this test in a cohort of 419 patients has recently been described [Balk et al., J Clin Med 2024, 13, 1194]. In this study, we present the results from a detailed stratification analysis in which SeptiCyte RAPID performance was evaluated in the same cohort across patient groups and subgroups encompassing different demographics, comorbidities and disease, sources and types of pathogens, interventional treatments, and clinically defined phenotypes. The aims were to identify variables that might affect the ability of SeptiCyte RAPID to discriminate between sepsis and SIRS and to determine if any patient subgroups appeared to present a diagnostic challenge for the test. Methods: (1) Subgroup analysis, with subgroups defined by individual demographic or clinical variables, using conventional statistical comparison tests. (2) Principal component analysis and k-means clustering analysis to investigate phenotypic subgroups defined by unique combinations of demographic and clinical variables. Results: No significant differences in SeptiCyte RAPID performance were observed between most groups and subgroups. One notable exception involved an enhanced SeptiCyte RAPID performance for a phenotypic subgroup defined by a combination of clinical variables suggesting a septic shock response. Conclusions: We conclude that for this patient cohort, SeptiCyte RAPID performance was largely unaffected by key variables associated with heterogeneity in patients suspected of sepsis.

Forecasting Non-stationary Time Series Using Deep Learning in a Fuzzy Time Series Framework and its Application to Stock Markets

Non-stationary time series prediction is challenging due to its dynamic and complex nature. Fuzzy time series models offer a promising solution for forecasting such data, but a key challenge lies in partitioning the universe of discourse, which significantly impacts forecasting accuracy. Traditional fuzzy time series models often use equal-length interval partitioning, which is more suited for stationary data and limits their adaptability to non-stationary time series. This paper introduces a novel variable-length interval partitioning method designed specifically for non-stationary time series. The developed method combines a Long Short-Term Memory (LSTM) Autoencoder with K-means clustering, enabling dynamic, data-driven partitioning that adapts to the changing characteristics of the data. The LSTM Autoencoder encodes the time series, which is clustered using K-means, and intervals are defined based on cluster centers. Furthermore, the Variable Length Interval Partitioning-based Fuzzy Time Series model (VLIFTS) is developed by incorporating this partitioning method and the concepts of Markov chain and transition probability matrix. In this model, fuzzy sets are viewed as states of a Markov chain, and transition probabilities are used in the forecasting phase. The model is validated on stock market indices Nifty 50, NASDAQ, S&amp;P 500, and Dow Jones. Stationarity and heteroscedasticity are tested using Augmented Dickey-Fuller (ADF) and Levene's tests respectively. Statistical forecast accuracy metrics Root Mean Squared Error (RMSE) and Mean Absolute Percent Error (MAPE) show that VLIFTS significantly improves forecasting accuracy over traditional models. This hybrid approach enhances fuzzy time series modelling and can be applied to various non-stationary time series forecasting problems.

Elucidating the role of PPARG inhibition in enhancing MERS virus immune response: A network pharmacology and computational drug discovery

BackgroundMiddle East Respiratory Syndrome (MERS) has become a severe zoonotic disease, posing significant public health concerns due to the lack of specific medications. This urgently demands the development of novel therapeutic molecules. Understanding MERS's genetic underpinnings and potential therapeutic targets is crucial for developing effective treatments. MethodsTwo gene expression datasets (GSE81909 and GSE100504) were analyzed to identify differentially expressed genes (DEGs) using GEO2R. Furthermore, gene ontology (GO), pathway enrichment analysis, and protein-protein interaction (PPI) network were performed to understand the gene’s functions. A possible drug target was identified, and an FDA-approved drug library was screened against the selected target using molecular docking and validated the findings through molecular dynamics simulation, principal component analysis, free energy landscape, and MM/GBSA calculations. ResultsThe study on GSE81909 and GSE100504 datasets with icMERS and MOCK samples at 24 and 48 h revealed an upregulation in 73 and 267 DEGs, respectively. In the network pharmacology, STAT1, MX1, DDX58, EIF2AK2, ISG15, IFIT1, IFIH1, OAS1, IRF9, and OASL were identified as the top 10 hub genes. STAT1 was identified as the most connected hub gene among these top 10 hub genes, which plays a crucial role in the immune response to the MERS virus. Further study on STAT1 showed that PPARG helps reduce STAT1, which could modulate the immune response. Therefore, by inhibiting PPARG, the immunological response can be successfully enhanced. The known inhibitor of PPARG, 570 (Farglitazar), was used as a control. Further, screening using Tanimoto and K-mean clustering was performed, from which three compounds were identified: 2267, 3478, and 40326. Compound 3478 showed characteristics similar to the control, indicating robust binding to PPARG. 3478 showed the highest negative binding free energy with −41.20 kcal/mol, indicating strong binding with PPARG. ConclusionsThese findings suggest that 3478 promises to be a potential inhibitor of PPARG, and further experimental investigations can explore its potential as a MERS inhibitor.

Three-point bending damage detection of SiC coated C/C composites based on acoustic emission

In this study, the three-point bending process of needled C/C composites, pack cementation SiC coated-C/C composites (PC-SiC-C/C) and chemical vapor deposition SiC coated-C/C composites (CVD-SiC-C/C) were monitored by the acoustic emission (AE) technology. To study the bending damage evolution process of three kinds of composite materials, the K-means algorithm was used to analyze the AE characteristic parameters. The damage type was analyzed by combining the electron microscope image of the sample fracture. The findings revealed that C/C composites and CVD-SiC-C/C composites contain three distinct types of damage: matrix cracking, carbon fiber-pyrolytic carbon interface debonding, and fiber fracture under three-point bending loading. PC-SiC-C/C composites has two additional damage: coating cracking and pyrolytic carbon-SiC interface debonding. The various damages could be identified by different AE signals: matrix cracking (175.781–421.875 KHz), carbon fiber-pyrolytic carbon interface debonding (70.312–164.062 KHz), fiber fracture (2.929–46.875 KHz), coating cracking (375–585.937 KHz), pyrolytic carbon-SiC interface debonding (169.921–257.812 KHz). The cumulative AE energy shows that the order of damage types of the three composites during the three-point bending loading is different.

Basketball self-evaluation matrix: discrepancy between self-confidence and decision-making performance on psychological profiling of players.

In basketball training, self-evaluation plays a crucial role in the decision-making and execution of movements of players. The self-evaluation of players is influenced by their perception of own basketball ability and self-confidence state. This study aimed to explore potential discrepancies between self-confidence levels of players and their decision-making performance, while also characterizing different types of players. Data was collected from 20 youth basketball players who participated in a decision-making video task and a self-confidence assessment. Based on data from their self-confidence and decision-making awareness assessment, the K-means cluster analysis was used to categorize the players into different groups. Then, ANOVA and post hoc Scheffe test were conducted to compare these clusters. The cluster analysis identified four distinct profiles of players and the results of the ANOVA and post hoc Scheffe tests revealed significant differences between the four clusters. The "High Self-confidence & Low Decision-making Awareness" players might display an overconfident mindset, while the "High Self-confidence & High Decision-making Awareness" players potentially demonstrated the better performance and maintained a consistent and confident attitude. The "Low Self-confidence & High Decision-making Awareness" players appeared to lack confidence and needed to foster greater faith in their abilities. Finally, the "Low Self-confidence & Low Decision-making Awareness" players required a long-term and comprehensive training program to improve their skills. These preliminary findings informed the development of a self-evaluation matrix, designed to help coaches better understand player profiles and design tailored interventions. Moreover, this study contributes on sport calibration and enhances understanding of the behavioral and psychological states of players.

Measuring internalized health-related stigma across health conditions: development and validation of the I-HEARTS Scale.

Health-related stigma and its internalization among individuals with chronic health conditions contribute to impaired mental and physical health and quality of life. Research on health-related stigma has been siloed, with disease-specific measures that may not capture the experiences of individuals with multiple health conditions and that prevent comparisons across health conditions. The current study aimed to develop and test a transdiagnostic measure of internalized health-related stigma for use among adults with different physical health conditions. An existing measure of internalized mental health stigma was adapted to assess stigma due to chronic physical health conditions following COSMIN procedures, with input from advisory boards of community members living with a range of stigmatized health conditions (obesity, type 1 and type 2 diabetes, skin diseases, HIV, chronic pain, and cancers) and of health professionals who specialized in these conditions. The new Internalized Health-Related Stigma (I-HEARTS) Scale was tested in an online sample of 300 adults with these health conditions, recruited from ResearchMatch. Additional psychosocial measures of mental health and quality of life were administered, and participants provided information about their health conditions and demographic characteristics. Exploratory factor analysis and tests of reliability and validity were conducted to determine the psychometric properties of the I-HEARTS Scale, and k-means clustering and receiver of characteristic curve analysis were used to determine a clinically meaningful cutoff score indicating high levels of internalized stigma. Factor analysis results yielded a 25-item scale with a 3-factor solution, with subscales of Perceived and Anticipated Stigma, Stereotype Application and Self-Devaluation, and Stigma Resistance. Psychometric properties for internal consistency, inter-item and item-total correlations, and test-retest reliability were strong. Certain demographics (e.g., younger age) and characteristics related to health conditions (e.g., greater symptom severity) were associated with higher levels of internalized stigma. I-HEARTS Scale scores correlated moderately to strongly with related but distinct psychosocial measures, and a cutoff score of 3.40 or higher on the 1-7 rating scale was determined to indicate clinically meaningful levels of internalized stigma. The I-HEARTS Scale is a reliable and valid measure for the assessment of internalized health-related stigma among adults with varied stigmatized chronic health conditions. STUDY PRE-REGISTRATION: https://osf.io/84c5d/?view_only=87238512f6d6475c87f8f64280a8a15f .

A proposed model to measure the maturity level for social, organizational and technological determinant factors of social entrepreneurships

Purpose The primary aim of this study is to create a comprehensive model quantifying the maturity levels of key determinants crucial for the sustained success of public sector entrepreneurship (PSE) [social entrepreneurship (SE)]. By integrating social, organizational and technological elements with Max-Neef's human needs, the model offers a holistic perspective for SE measurement. Notably, it emphasizes Max-Neef's existential needs (being, having, doing, interacting) to analyze variables crucial for sustainability, from diverse perspectives within SE. Design/methodology/approach This study presents a quantitative approach to develop a maturity model for assessing SE based on Max-Neef's human needs. The model integrates social, organizational and technological dimensions, using K-means algorithm for data processing. A panel of experts assigns weights to variables, and the maturity levels are adapted from the Capability Maturity Model. Data from 47 SEs in Ecuador's Zone 6 inform model construction, validated with two textile sector SEs. The methodology comprises three stages: variable selection, model construction and nonprobabilistic sample validation in Zone 6. Findings The research yields a maturity model enabling the quantification of PSE entrepreneurship maturity over time. It incorporates social, organizational and technological variables with Max-Neef's human needs, providing a broader perspective for SE evaluation. The model allows assessing the maturity level of each determinant, performance per variable in a Likert Scale, and facilitates comparisons between individual entrepreneurship and the overall population or sample. Visualization is enhanced through a color scale based on the Capability Maturity Model. Research limitations/implications Limitations may stem from the nonprobabilistic convenience sample used for validation, potentially affecting the generalizability of findings. The model's application is specific to Zone 6 of Ecuador and may require adjustments for broader contexts. Although the K-means algorithm aids data processing, its limitations should be considered. Future research could explore the model's applicability in diverse geographical and sectoral settings for a more comprehensive understanding. Practical implications This research has led to the development of a model that quantifies the maturity level of key determinants crucial for the long-term sustainability of PSE. This model integrates elements from social, organizational and technological dimensions, offering a comprehensive framework for assessing SE. Social implications This model offers valuable insights for the development and sustainability of social entrepreneurship by providing a structured approach to measure and enhance key social, organizational and technological determinants. By integrating Max-Neef's framework of human needs, the model helps social enterprises better align their efforts with fundamental human needs, ensuring that initiatives not only address societal challenges effectively but also contribute to long-term social well-being. This approach encourages the development of more resilient and impactful social enterprises that are capable of adapting to diverse socioeconomic contexts. Originality/value The model's uniqueness lies in its integration of social, organizational and technological variables with Max-Neef's human needs, offering a nuanced assessment of PSE entrepreneurship determinant factors from a human perspective. By applying existential needs (being, having, doing, interacting) as analysis levels, the model provides a distinctive and insightful approach to evaluating the impact of key variables. Its value lies in identifying strengths and weaknesses in each entrepreneurship, guiding support strategies and informing discussions for constructing effective public policies.

Effect of asymptomatic intervertebral flexion patterns on lumbar disc pressure: A finite element analysis study.

Movement patterns may be a factor for manipulating the lumbar load, although little information is yet available in the literature about the relationship between this variable and intervertebral disc pressure (IDP). A finite element model of the lumbar spine (49-year-old asymptomatic female) was used to simulate intervertebral movements (L2-L5) of 127 asymptomatic participants. The data from participants that at least completed a simulation of lumbar vertebral movement during the first 53% of a movement cycle (flexion phase) were used for further analyses. Then, for each vertebral angular motion curve with constant spatial peaks, different temporal patterns were simulated in two stages: (1) in lumbar pattern exchange (LPE), each vertebral angle was simulated by the corresponding vertebrae of other participants data; (2) in vertebral pattern exchange (VPE), vertebral angles were simulated by each other. The k-mean algorithm was used to cluster two groups of variables; peak and cumulative IDP, in both stages of simulations (i.e., LPE and VPE). In the second stage of the simulation (VPE), Kendall's tau was utilized to consider the relationship between different temporal patterns and IDPs for each individual lumbar level. Cluster analyses showed that the temporal movement pattern did not exhibit any effect on the peak IDP while the cumulative IDP changed significantly for some patterns. Earlier involvement in lumbar motion at any level led to higher IDP in the majority of simulations. There is therefore a possibility of manipulating lumbar IDP by changing the temporal pattern with the same ROM, in which optimal distribution of the loads among lumbar levels may be applied as preventive or treatment interventions. Evaluating load benefits, such as load, on biomechanically relevant lumbar levels, dynamically measured by quantitative fluoroscopy, may help inform interventional exercises.

Exploring the Configurational Relationships between Urban Heat Island Patterns and the Built Environment: A Case Study of Beijing

The spatial heterogeneity of land surface temperature (LST) within cities is profoundly influenced by the built environment. Although significant progress has been made in the study of the urban thermal environment, there is still a lack of research on how the pattern and structural layout of the built environment affects the thermal environment. In this study, we take the Fifth Ring Road of Beijing as an example, invert the urban LST on the basis of multisource spatial data, characterize the built environment, and use k-means cluster analysis to investigate the main influencing factors of the LST in different functional areas and building patterns within the city, as well as the spatial relationship between the built environment and the urban LST. The results show the following: (1) The urban heat island (UHI) effect occurs to varying degrees over a large part of the study area, and these UHI areas are mainly concentrated in the southwestern part of the city, forming a large contiguous area between the second and fifth ring roads. (2) Class 1 is dominated by transport blocks, Class 3 is dominated by commercial blocks, and Class 5 is dominated by green space blocks, with a clustering index of 0.38. (3) The high-density, high-height class (HH-Class 2) has a greater number of blocks distributed in a ring shape around the periphery of the second ring road. The high-density, low-height class (HL-Class 2) has a relatively small number of blocks but a relatively large area, and the largest blocks are located in the western part of the study area. (4) In the HH and HL building patterns, extreme heat scenarios often occur; from the perspective of functional areas, the probability of extreme heat in the transport block is much higher than that of other functional areas, and except for the HH scenario, the green space functional area plays a very important role in reducing the temperature. This study explores the characteristics of the built environment that influence the urban LST from the perspective of different urban functional zones in cities to provide decision support for quantitative territorial spatial planning, optimization, and management.

Enhancing Clustering Performance of Failed Test Cases during HIL Simulation: A Study on Deep Auto-Encoder Structures and Hyperparameter Tuning

Over the last decade, hardware-in-the-loop (HIL) simulation has been established as a safe, efficient, reliable, and flexible method for performing real-time simulation. Furthermore, in the automotive sector, the HIL system has been recommended in the ISO 26262 standard as a powerful platform for performing realistic simulation during system integration testing. As a result of performing HIL black-box tests, the results of executing test cases (TCs) are reported as pass/fail without determining the nature and root causes of the underlying failures. The conventional analysis process of the failed TCs relies on expert knowledge. The higher the number of failed TCs, the higher the cost of manual analysis in terms of time and effort. In light of the shortcomings of existing methodologies, this study presents a novel intelligent framework capable of analyzing failed TCs without the need for expert knowledge or code access. To this end, a convolutional auto-encoder-based deep-learning approach is proposed to extract representative features from the textual description of the failed TCs. Furthermore, k-means-based clustering is used to categorize the extracted features according to their respective failure classes. To illustrate the effectiveness and validate the performance of the proposed method, a virtual test drive with real-time HIL simulation is presented as a case study. The proposed model exhibits superior clustering performance compared to other standalone k-means algorithms, as demonstrated by the David Bouldin Index (DBI) and accuracy values of 0.5184 and 94.33%, respectively. Furthermore, the proposed model shows a significant advantage in terms of feature extraction and clustering performance compared to the current state-of-the-art fault-analysis method. The proposed approach not only supports the validation process and improves the safety and reliability of the systems but also reduces the costs of manual analysis in terms of time and effort.

The extent of overtourism in some European locations using multi-criteria decision-making methods between 2014 and 2023

Purpose Overtourism has been identified as a significant global problem with numbers of negative externalities. The purpose of this paper is to contribute to the establishment of a standard that objectively measures the extent of tourism to produce a dynamic ranking of selected European settlements, as there is a lack of studies using sophisticated statistical methods to analyse secondary data on overtourism. Design/methodology/approach The 28 selected sites, studied according to their involvement in overtourism, were ranked using multi-criteria decision-Mmaking Methods between 2014 and 2023. Rankings were calculated by VIKOR, TOPSIS and MMOORA, and an aggregate ranking was created by using the cross-entropy optimization. Additionally, the annual changes in the rankings were presented graphically using principal component analysis on a two-dimensional space, referred to as the “sites' space.” Finally, the sites were clustered into three distinct groups based on their level of overtourism: less, medium and more. This was achieved through the use of the K-means algorithm. Findings Following the onset of the pandemic in 2020, there was a notable decline in overtourism. However, following the year 2021, the numbers began to rise once more, and by 2022, they had returned to their pre-pandemic levels. Among the methods, MMOORA demonstrated the most effective performance in comparison to the optimal ranking. Originality/value The applied methods with novel rank aggregation could also shed light on the most relevant indicators to overtourism. These included the number of nights spent in paid accommodation per population, the number of overnight visits per population and the number of air passengers.

Organizational Workforce Management in the Digital Age: The Role of Technocultural Interventions in Mitigating the Negative Impacts of AI-Driven Technological Change

This study explores the impact of AI-driven technological change on workforce management, focusing on job displacement, employee satisfaction, and productivity. A mixed-method approach was employed, including logistic regression, K-means clustering, and multivariate regression analysis, to evaluate the effectiveness of technocultural interventions (upskilling programs, ethical AI frameworks, and innovation culture). Data was sourced from the U.S. Bureau of Labor Statistics (BLS) and survey questionnaires. Logistic regression revealed that routine AI adoption showed a weak positive relationship with job displacement (B = 0.013, p = 0.111), but the overall model was not statistically significant. The K-means clustering identified three distinct organizational patterns in adopting technocultural interventions. Multivariate regression highlighted the substantial role of leadership commitment in increasing employee satisfaction (B = -0.067, p = 0.039) but found limited direct effects of upskilling programs and AI frameworks on productivity. Based on the findings, the study highlights the importance of customized, sector-specific interventions and recommends that organizations integrate leadership and ethical considerations to manage AI-driven changes effectively.