K-means Research Articles

Characterizing energy-related occupant behavior towards urban residential buildings in China with statistical database establishment

Energy-related occupant behavior has significant impacts on the accuracy of energy consumption predictions. However, existing research on urban residential energy-related occupant behavior in China lacks a comprehensive understanding of its characteristics across different climates. Thus, focusing on energy-related occupant behavior of heating, cooling, cooking, domestic hot water use, lighting, operating other electric appliances, window opening, and shading, this paper proposes an index system and data collection method to reveal its inherent spatial and temporal characteristics. Then, the “Chinese Urban Residential Energy-Related Occupant Behavior Database” was established through large-scale investigations involving 8511 valid questionnaires conducted in the Severe Cold Zone, Cold Zone, Hot Summer and Cold Winter Zone, Hot Summer and Warm Winter Zone, and Mild Zone. Furthermore, typical operational patterns of each behavior were refined using K-Means clustering. Results revealed significant seasonal and regional variability in the characteristics of the investigated behaviors in each zone. The typical operational patterns of heating, cooling, window opening, and shading varied by zone and exhibited “part-time, part-space” characteristics. Cooking and electric appliance operational patterns differ depending on local customs. The index system and data collection method for energy-related occupant behavior could potentially serve as a template for establishing behavioral databases in other countries.

Reconfiguration of PV array for improved performance under different partial shading conditions using Roulette Barrel Shifter approach

This article proposes an innovative reconfiguration technique called Roulette Barrel Shifter (RBS) for Total Cross Tied (TCT) connected PV arrays. Inspired by a spinning roulette wheel and the barrel shifter from digital signal processing, it shifts or rotates input data bits by a number of bits. Unlike other methods, RBS does not require advanced maximum power point tracking devices, sensors, or complex switching mechanisms, making it more cost-effective. Simulation studies on 9 × 9 and 10 × 10 PV arrays under Partial Shading (PS) conditions, as well as experimental validation on a 5 × 5 array, demonstrate that RBS increases power by up to 15.45 % compared to TCT. The algorithm is also tested for scalability and adaptability on a large solar plant (4 MW, 2175 V, 25 × 750 PV array). For the first time, the article introduces a unique wiring loss (WL) performance metric using the k-means algorithm. Based on this metric, RBS is shown to reduce WL by up to 6.98 % compared to other recently published methods. Comparative analysis reveals that RBS reduces mismatch loss (ML) by up to 61.41 % compared to TCT, establishing its superiority over existing dynamic reconfiguration approaches in both performance and efficiency across various scales of solar arrays.

Application of K-means clustering and B-value algorithms for analysis of earthquake-dangerous zones in Java Island

Application of K-means clustering and B-value algorithms for analysis of earthquake-dangerous zones in Java Island

Enhancing digital competence through story-based learning: a massive open online course (MOOC) approach

PurposeThis study investigated a story-based learning MOOC’s effectiveness in enhancing digital competence.Design/methodology/approachA quasi-experimental design with 5,501 participants enrolled in a developed MOOC course was assessed through pretests, formative assessments and posttests. K-means clustering, using the Self-Efficacy in Digital Competence Scale (SDCS), was employed to classify experimental and control groups and analyze differences in perceived competence across age groups (10s–60s).FindingsLearners’ digital competence significantly improved (p < 0.001) after the MOOC, demonstrating knowledge and skill gains across various domains. The highest SDCS domain was communication and collaboration, while the lowest was digital content creation. Additionally, the SDCS data showed higher self-efficacy in the 20–40s age group and lower in the 10, 50 and 60s.Research limitations/implicationsThe findings suggest a gap in learners’ digital content creation competence. Additional content could be incorporated to bridge this gap. This study supports story-based learning MOOCs for promoting digital competence.Originality/valueThis research contributes to the field by developing and evaluating a MOOC with story-based learning to explore learners’ digital competence and its relationship with age.

Redesigning quick commerce fresh and short food supply chains: circular economy strategies for sustainable last-mile operations

PurposeFresh and short food supply chains in grocery quick commerce (q-grocery FSFSCs), while valued for swift delivery, face challenges in sustainability, resource efficiency and scalability. This study aims to redesign the last mile of q-grocery FSFSCs by identifying and validating a framework of applicable circular economy (CE) practices. Furthermore, the study assesses the impact of these practices across various sustainability dimensions to understand their level of contribution to sustainable livelihoods and supply chain resilience.Design/methodology/approachThe study employs a multi-phase approach. First, an integrative literature review identifies CE practices and strategies. Second, a survey gathers data on the relationship between these practices and strategies and their impact on sustainability. Third, the framework is validated using the partial least squares structural equation modeling (PLS-SEM) method in WarpPLS 8.0. Finally, k-means cluster analysis in Tableau 2019.4 groups CE practices based on their impact across five sustainability dimensions: environmental, economic, social, resource efficiency and scalability.FindingsThe study validates a framework and identifies high-impact CE practices, such as waste reduction, sustainable packaging, sustainable sourcing, route optimization, sustainable processes and customer convenience. Medium-impact practices include energy efficiency, sustainable fleet, resale and redistribution and information flow. Low-impact practices cover composting, reverse logistics and appropriate storage.Research limitations/implicationsThe findings assist q-grocery companies to adopt CE practices and strategies that support sustainable livelihoods and strengthen supply chain resilience while offering policymakers guidance to promote circularity.Originality/valueThis study is unique in the exploration of the intersection of quick commerce, FSFSCs and CE principles, providing actionable insights for sustainability in the q-grocery industry.

Research on Automatic Alignment for Corn Harvesting Based on Euclidean Clustering and K-Means Clustering

Aiming to meet the growing need for automated harvesting, an automatic alignment method based on Euclidean clustering and K-means clustering is proposed to address issues of driver fatigue and inaccurate driving in manually operated corn harvesters. Initially, the corn field environment is scanned using LiDAR to obtain point cloud data, which are then subjected to pass-through filtering and statistical filtering to remove noise and non-corn contour points. Subsequently, Euclidean clustering and K-means clustering methods are applied to the filtered point cloud data. To validate the impact of Euclidean clustering on subsequent clustering, two separate treatments of the obtained point cloud data were conducted during experimental validation: the first used the K-means clustering algorithm directly, while the second involved performing Euclidean clustering followed by K-means clustering. The results demonstrate that the combined method of Euclidean clustering and K-means clustering achieved a success rate of 81.5%, representing a 26.5% improvement over traditional K-means clustering. Additionally, the Rand index increased by 0.575, while accuracy improved by 57% and recall increased by 61%.

Diet Recommendation System Using K-Means Clustering Algorithm of Machine Learning

In today’s world, many people suffer from range of illnesses due to lack of nutrients in their daily diet. It’s not always simple to recommend diet right away. The majority of individuals in the today’s world are fanatically trying to reduce weight, gain weight, or keep their health in check. The study relies on a database that has various amount of nutrients. As a result of the circumstance, we set out to create a program that would help out individuals to become healthy. Only three orts of good are recommended weight loss, weight gain, and staying healthy. The diet recommendation system leverages the user input such as, name, age, height, weight which calculate BMI and provide necessary diet based on the option of vegetarian or non-vegetarian meals from three categories which are weight gain, weight loss, and staying healthy. We’ll discuss about the classification of food based on machine learning in this post. This research includes K-means Clustering algorithm for future diet plan prediction.

The Relationship Between Horizontal Jumping and Sprinting Ability Across Sexes in Young Active Adults

Purpose: The purpose of this research was to investigate the relationship between horizontal jump distance, 10 m time, and 30–40 m time in multi-sport athletes separated by sex and sprint speed. Methods: A total of 1352 athletes (742 males and 610 females) performed 40 m sprints, standing broad jumps (SBJs), and standing triple jumps (STJs). Data were separated by sex and then grouped as fast, average, and slow using the K-Means algorithm in three conditions (acceleration, max speed, and combined). Results: Regression models explained 84.01% of the variance (F(7,757) = 574.5, p < 0.001) for the 10 m times with mass, speed group, and sex as significant predictors and 88.51% of the variance (F = (7,757 = 841.6, p < 0.001) for the 30–40 m times with SBJ, STJ, speed group, sex, and the interaction of sex and group as significant predictors. Conclusions: These results suggest that when examining general athlete physical performance, horizontal jump tests and max speed sprint times can be used equivalently to stratify athletes. However, it is important to group athletes by speed and sex before being able to predict sprint ability from horizontal jump tests. Further, athlete mass is a significant factor in the prediction of acceleration ability but not maximum speed, and horizontal jumps were significant factors in the prediction of max speed but not acceleration.

Efficient Data Recognition and Classification in IoT Ecosystem using Optimized K-Means Algorithm and Hybrid Deep Learning Model

Efficient Data Recognition and Classification in IoT Ecosystem using Optimized K-Means Algorithm and Hybrid Deep Learning Model

AI-Powered Geotechnics: Enhancing Rock Mass Classification for Safer Engineering Practices

AbstractRock mass classification is fundamental for evaluating rock mass quality, essential for stability analysis and geotechnical design. Traditional classification methods are limited by joint observation technology, which typically gathers joint information from one-dimensional or two-dimensional perspectives, failing to comprehensively capture three-dimensional joint occurrences. This often necessitates empirical formulas for joint distribution, resulting in less precise joint parameter calculations. This paper reviews 44 seminal articles on rock engineering classification in construction and subterranean projects, tracing the evolution from foundational methods like Rock Quality Designation, Rock Mass Rating, Q-system, Basic Quality, and Hydropower Classification to contemporary techniques. It highlights the transformative impact of data science, particularly artificial intelligence, on rock engineering. The analysis reveals 73 distinct algorithms used 162 times in literature, with Support Vector Machines Support, Vector Regression, K-means clustering, K-Nearest Neighbors, Artificial Neural Networks and Random Forest being the most successful. This paper examines each method's advantage and limitations, discussing the challenges of algorithm deployment in the scientific community. The findings underscore the integration of machine learning and meta-heuristic optimization methods in rock engineering classification, offering valuable insights for future research and applications.

Change-oriented Leadership in the Context of Transitioning to Strategic Autonomy

Growing geopolitical tensions have transformed the business landscape , driving domestic firms toward an era of strategic independence (Yale School of Management, 2024). This research examines a well-known Eastern European consulting firm that, after transitioning to an independent entity, was confronted with a new personnel assessment system. This shift necessitates a comprehensive understanding of employee readiness and resistance — fundamental concepts in change management literature (Armenakis et al., 1993). Our study incorporated quantitative methods to divide employees according to their readiness for the new system (k-means clustering, factor analysis, and discriminant analysis). At the same time, it employed qualitative research methods to explore motives and attitudes behind employee resistance or readiness (Choi & Ruona, 2011). Based on their adaptability to the new system, we identified three distinct clusters of employees: “Active Supporters,” “Cautious Appraisers,” and “Conservative Skeptics,” allowing us to pinpoint specific non-readiness factors and formulate tailored strategies to address them. The findings suggest that emotional involvement, openness to change, and previous experiences with similar practices significantly influence employee readiness. To mitigate these issues, the paper proposes a strategy rooted in psychological safety and differentiated error management, as advocated by Edmondson (2023), to enhance the organization's learning capability and adaptability. Our results align with previous research indicating that stronger attitudes, often based on personal experience, significantly predict behavior (Eagly & Chaiken, 1993). We found that the initial uncertainty of organizational changes served as a major stressor, underscoring the importance of understanding and conceptualizing changes (Kramer, 2015). Unlike Schwartz (1994), the value orientation of “Tradition” did not exert significant influence, but values of “Autonomy,” “Stimulation,” “Achievement” (consistent with Sortheix & Lönnqvist, 2014), “Hedonism,” and “Power” positively impacted employee openness to changes. The implications of this study extend to other Eastern European companies undergoing similar transitions, providing guidance on how change can be managed effectively in the context of transitioning to strategic autonomy.

A mileage correction method of pipeline inertial measurement for dam internal deformation monitoring

Internal deformation monitoring is of great significance to the safe operation and maintenance of dams. Some scholars have carried out dam internal deformation monitoring by pipeline inertial measurement with a pipeline measurement robot, which has improved the monitoring accuracy and efficiency considerably, compared with the traditional monitoring methods. However, there are still shortcomings in this method. Because the odometer on the pipeline measurement robot will slip or slide, resulting in errors in the mileage of the multiple measurement routes, which hinders the development of the accuracy of pipeline inertial measurement. This paper proposes a mileage correction method based on junction detection to improve the accuracy of pipeline inertial measurement for better dam internal deformation monitoring. The mileage correction method establishes a reference model of pipeline junction location, detects the locations of pipeline junction welds on the measurement routes using two k-mean clustering, and corrects the odometer data based on the difference between the detected and reference locations. We evaluate the enhancement of this mileage correction method on the internal accuracy and deviation values compared with other method for pipeline inertial measurement. The proposed method is validated using measured data from the internal pipeline of Tianchi Dam. The results show that compared with the results directly fused without detection–correction, the method proposed in this paper reduces the root-mean-square error of the results by an average of 30.30% and improves the deviation compared with the reference deformation by an average of 2.3 mm. Therefore, the method has good results and practical applications.

Kinematic signature of high risk labored breathing revealed by novel signal analysis.

Breathing patterns (respiratory kinematics) contain vital prognostic information. This dimension of physiology is not captured by conventional vital signs. We sought to determine the feasibility and utility of quantifying respiratory kinematics. Using inertial sensors, we analyzed upper rib, lower rib, and abdominal motion of 108 patients with respiratory symptoms during a hospital encounter (582 two-minute recordings). We extracted 34 features based on an explainable correspondence with well-established breathing patterns. K-means clustering revealed that respiratory kinematics had three dimensions apart from the respiratory rate. We represented these dimensions using respiratory rate variability, respiratory alternans (rib-predominant breaths alternating with abdomen-predominant ones), and recruitment of accessory muscles (increased upper rib excursion). Latent profile analysis of the kinematic measures revealed two profiles consistent with the established clinical constructs of labored and unlabored breathing. In logistic regression, the labored breathing profile improved model discrimination for critical illness beyond the Sequential Organ Failure Assessment (SOFA) score (AUROC 0.77 v/s 0.72; p = 0.02). These findings quantitatively confirm the prior understanding that the respiratory rate alone does not adequately represent the complexity of respiratory kinematics; they demonstrate that high-dimensional signatures of labored breathing can be quantified in routine practice settings, and they can improve predictions of clinical deterioration.

Profiling feedback antecedents in higher education students: a person-oriented perspective

The ability to give, receive and process feedback is essential for higher education students not only during their studies, but also for their future work life. Despite the extensive amount of research on feedback in education, there is limited research on feedback skills as collaborative skills and on what might influence these skills. Through surveying a large sample of 2,907 university students who worked in self-managed project teams, this study explores how individual characteristics as antecedents relate to students’ perceived feedback skills. We use a person-oriented approach to examine how these antecedents relate within students and how these profiles relate to perceived feedback skills. In addition to reliability, confirmatory factor analysis provided evidence for the structural validity of a newly developed feedback skills instrument. Five scales were used from existing feedback instruments as antecedents of feedback skills, and these were also found to be valid and reliable. Through a person-oriented approach, we applied a hierarchical and a k-means cluster analysis to create student profiles or groups based on feedback antecedents. We identified five distinct groups of students with common feedback antecedents. The results indicate that the five groups also had different levels of perceived feedback skills. The study contributes to the limited research on the dynamics of giving and receiving feedback from the perspective of students in the context of collaborative learning. It has implications for researchers and practitioners to better understand individual differences and to consider these differences when designing collaborative learning activities and facilitating student teams.

A data-driven approach to traditional village colors: K-Means clustering of online images

ABSTRACT This study aims to quantify the color characteristics of traditional villages, explore the key aspects of color that attract tourist attention, and propose solutions to enhance the readability and legibility of these villages. The findings are intended to provide practical guidance for the restoration and use of village colors. The research focuses on how tourists perceive the color characteristics of traditional villages. The objective is to conduct color clustering analysis to identify the composition and characteristics of village colors, and further analyze the underlying causes to offer suggestions for optimization and enhancement. It employs a methodology based on urban imagery theory, using clustering and secondary extraction of color data from online images. The results reveal distinct contrasts and harmonies in the colors of the five elements providing a basis for improving spatial readability and visual guidance. These findings not only offer practical design references for optimizing traditional village colors but also provide valuable insights for the protection and restoration of other traditional sites. In particular, the contrast between the colors of boundaries and landmarks can enhance visual recognition, while the complementary color designs of paths and boundaries can improve spatial readability, contributing to the sustainable development of traditional villages.

Beyond the Hip: Clinical Phenotypes of Hip Osteoarthritis Across the Biopsychosocial Spectrum

Background/Objectives: To identify clinical phenotypes of hip osteoarthritis (OA) within a biopsychosocial framework. Methods: A cross-sectional analysis of 143 individuals with hip OA awaiting total hip arthroplasty (THA) was performed. Phenotyping features included sociodemographic and biomedical information, pain-related cognitions and emotions, mental disorders, traumatic experiences, self-efficacy, social support, perceived stress, and somatosensory function. Outcome measures included the hip disability and osteoarthritis outcome score and the numeric pain-rating scale. Decision tree learning was used to select the most important phenotyping features. K-means clustering analyses were performed to identify clinical phenotypes and a decision tree algorithm was trained to classify individuals in the identified clinical phenotypes. Results: Selected phenotyping features associated with pain and disability included a combination of biomedical, psychological, and social variables. Two distinct clinical phenotypes were identified. Individuals within the maladaptive phenotype (34%) reported more comorbidities, less self-efficacy and higher levels of anxiety, depression, pain-related fear-avoidance, and feelings of injustice. No differences were found regarding social support and somatosensory function. Regarding the outcome measures, individuals within the maladaptive phenotype reported higher levels of pain and disability. Finally, based on the Fear-Avoidance Components Scale (FACS) and the anxiety subscale of the Hospital Anxiety and Depression Scale (HADS-A), individuals could be classified into the clinical phenotypes with 87.8% accuracy. Conclusions: Two clinical phenotypes, an adaptive and a maladaptive phenotype, can be identified in individuals with hip OA using the FACS and HADS-A. The identification of these clinical phenotypes represents a crucial step toward precision medicine, enabling the development of targeted treatment pathways tailored to the distinct biomedical and psychological features of each phenotype.

A Multi-Robot Task Allocation Method Based on the Synergy of the K-Means++ Algorithm and the Particle Swarm Algorithm

Addressing challenges in the traditional K-means algorithm, such as the challenge of selecting initial clustering center points and the lack of a maximum limit on the number of clusters, and where the set of tasks in the clusters is not reasonably sorted after the task assignment, which makes the cooperative operation of multiple robots inefficient, this paper puts forward a multi-robot task assignment method based on the synergy of the K-means++ algorithm and the particle swarm optimization (PSO) algorithm. According to the processing capability of the robots, the K-means++ algorithm that limits the maximum number of clusters is used to cluster the target points of the task. The clustering results are assigned to the multi-robot system using the PSO algorithm based on the distances between the robots and the centers of the clusters, which divides the multi-robot task assignment problem into a multiple traveling salesmen problem. Then, the PSO algorithm is used to optimize the ordering of the task sets in each cluster for the multiple traveling salesmen problem. An experimental verification platform is established by building a simulation and physical experiment platform utilizing the Robot Operating System (ROS). The findings indicate that the proposed algorithm outperforms both the clustering-based market auction algorithm and the non-clustering particle swarm algorithm, enhancing the efficiency of collaborative operations among multiple robots.

Insights into Target Gas-Oxygen Interactions in Highly Sensitive Gas Sensors Using Data-Driven Methods.

In the gas-sensing mechanism of a metal-oxide-semiconductor (n-type) gas sensor, oxygen adsorption or desorption on the oxide surface leads to an increase or decrease in the resistance of the gas sensor system. Additionally, oxygen can be adsorbed again at the location where initially adsorbed oxygen reacted with the target gas. Thus, the adsorption-desorption equilibrium of the reducing gas on the oxide surface is a significant factor in determining the sensitivity and reaction rate. In particular, for ultralow-concentration gas measurements, the relative concentration of oxygen was very high. To design an ultrasensitive gas sensor, not only the reaction of the target gas but also the competing reaction between the target gas and oxygen must be considered. Although qualitative investigations of these complex relationships have been performed according to the gas concentration and flow rate, reliable quantitative results are limited. In this study, a quantitative approach was used to understand the correlation between oxygen and a target gas by applying data analysis methods. We investigated the behavior of oxygen and the target molecules depending on the gas concentration and flow rate using the parts per billion level of the acetone gas sensor. Initial response data according to various detection conditions were processed using principal component analysis and K-means clustering; as a result, four types of reaction behaviors were inferred for 15 types of reaction conditions. Furthermore, the response time, depending on the detection conditions, can be distinguished using the suggested categorization. Our investigation suggests a possibility beyond simple optimization through the data analysis of the gas-sensing results.

Abstract 4125691: A machine learning approach to examining the associations of minority stressors and physical activity among sexual and gender minority adults

Introduction: Physical activity (PA) is an important modifiable factor for cardiovascular disease (CVD). Sexual and gender minority (SGM; e.g., lesbian/gay, bisexual, transgender) adults face higher risks of inadequate PA and CVD due to increased exposure to minority stressors, such as experienced and anticipated discrimination, which may influence SGM adults’ willingness to engage in PA. To our knowledge, researchers have not investigated the impact of minority stressors on objectively-measured PA among SGM adults. Goal: Using k-means clustering, we sought to identify whether clusters characterized by greater exposure to minority stressors were associated with lower moderate and vigorous PA (MVPA) and higher sedentary behavior among SGM adults. Methods: This daily diary study included an online sample of SGM adults living in the United States. Participants completed daily surveys about personally experienced discrimination and anticipated discrimination (i.e., expectation of experiencing discrimination) and wore wrist accelerometers for 28 days to objectively measure PA. We used k-means clustering to identify clusters based on reports of experienced and anticipated discrimination. We first determined the optimal number of clusters using established partition criteria. Next, we ran linear regression models (adjusted for demographic factors) to examine the associations of minority stress clusters with MVPA and sedentary time per week. Results: Among 42 SGM adults (mean age 27.0±7.7 years) with 1133 person-days of accelerometry data (~3% missing data), we identified four minority stress clusters: low anticipated/low experienced (LALE; reference group); low anticipated/high experienced (LAHE); high anticipated/low experienced (HALE); and high anticipated/high experienced discrimination (HAHE). Participants in the HALE cluster (n=12) engaged in 202 fewer minutes of MVPA than those in the LALE cluster (n=7). Participants in the LAHE cluster (n=10) had 123 fewer minutes of vigorous PA than those in the LALE cluster. No differences were identified for sedentary time. Conclusions: This is the first study to examine the association of minority stressors with objective PA among SGM adults. Participants in the HALE and LAHE clusters engaged in significantly lower PA than those with low levels of both experienced and anticipated discrimination. Findings underscore the importance of assessing minority stressors and the need for interventions to improve PA among SGM adults.

Distinct causes underlie double-peaked trilobite morphological disparity in cephalic shape.

Trilobite cephalic shape disparity varied through geological time and was integral to their ecological niche diversity, and so is widely used for taxonomic assignments. To fully appreciate trilobite cephalic evolution, we must understand how this disparity varies and the factors responsible. We explore trilobite cephalic disparity using a dataset of 983 cephalon outlines of c. 520 species, analysing the associations between cephalic morphometry and taxonomic assignment and geological Period. Elliptical Fourier transformation visualised as a Principal Components Analysis suggests significant differences in morphospace occupation and in disparity measures between the groups. Cephalic shape disparity peaks in the Ordovician and Devonian. The Cambrian-Ordovician expansion of morphospace occupation reflects radiations to new niches, with all trilobite orders established by the late Ordovician. In comparison, the Silurian-Devonian expansion seems solely a result of within-niche diversification. Linear Discriminant Analyses cross-validation, average cephalon shapes, and centroid distances demonstrate that, except for Harpida and the Cambrian and Ordovician Periods, order and geological Period cannot be robustly predicted for an unknown trilobite. Further, k-means clustering analyses suggest the total dataset naturally subdivides into only seven groups that do not correspond with taxonomy, though k-means clusters do decrease in number through the Palaeozoic, aligning with findings of decreasing disparity.