Search

Multiple kernel k‐means clustering (MKKC) can efficiently incorporate multiple base kernels to generate an optimal kernel. Many existing MKKC methods all need two‐step operation: learning clustering indicator matrix and performing clustering on it. However, the optimal clustering results of two steps are not equivalent to those of original problem. To address this issue, in this paper we propose a novel method named one‐step multiple kernel k‐means clustering based on block diagonal representation (OS‐MKKC‐BD). By imposing a block diagonal constraint on the product of indicator matrix and its transpose, this method can encourage the indicator matrix to be block diagonal. Then the indicator matrix can produce explicit clustering indicator, so as to implement one‐step clustering, which avoids the disadvantage of two‐step operation. Furthermore, a simple kernel weighting strategy is used to obtain an optimal kernel, which boosts the quality of optimal kernel. In addition, a three‐step iterative algorithm is designed to solve the corresponding optimization problem, where the Riemann conjugate gradient iterative method is used to solve the optimization problem of the indicator matrix. Finally, by extensive experiments on eleven real data sets and comparison of clustering results with 10 MKC methods, it is concluded that OS‐MKKC‐BD is effective. [ABSTRACT FROM AUTHOR]

The clustering algorithm is an effective method for developing energy efficiency routing protocol for wireless sensor networks (WSNs). In clustered WSNs, cluster heads must handle high traffic, thus consuming more energy. Therefore, forming balanced clusters and selecting optimal cluster heads are significant challenges. The paper proposes a sector clustering algorithm based on K-means called KMSC. KMSC improves efficiency and balances the cluster size by employing symmetric dividing sectors in conjunction with K-means. For the selection of cluster heads (CHs), KMSC uses the residual energy and distance to calculate the weight of the node, then selects the node with the highest weight as CH. A hybrid single-hop and multi-hop communication is utilized to reduce long-distance transmissions. Furthermore, the impact of the number of sectors, the threshold for clustering, and the network size on the performance of KMSC has been explored. The simulation results show that KMSC outperforms EECPK-means, K-means, TSC, LSC, and SEECP in terms of FND, HND, and LND. [ABSTRACT FROM AUTHOR]

We identified groups of mayfly species that share microhabitats in eastern Cuban streams by sampling during rainy and dry seasons in four microhabitats in pools (cobbles, sand, leaf litter and bank vegetation) and one microhabitat (cobbles) in riffles. A total of 20 species and three morphospecies were found. Species similarity in habitat use was analysed using k-means clustering. Overall, the highest number of individuals was collected in cobbles in riffles, followed by cobbles in pools. Five species groups, labelled from I to V, were identified based on their primary microhabitat use. Two groups (I and V) included species with a generalist pattern of habitat use, but differing in seasonality. Species in remaining groups tend to concentrate in specific microhabitats. Species of groups II and IV use mostly cobbles in riffles and in pools, respectively, while species in group III concentrate in sand during the rainy season. Our results allowed to identify the species most vulnerable to alterations of the hydrologic regimen. [ABSTRACT FROM AUTHOR]

Accurate and reliable forecasting of cancellations is important for successful revenue management in the tourism industry. The objective of this study is to develop classification models to predict hotel booking cancellations. The work involves a number of key steps, such as data preprocessing to properly prepare the data; feature engineering to identify relevant attributes to help improve the predictive ability of the models; hyperparameter settings of the models, including choice of optimizers and incorporation of dropout layers to avoid overfitting in the neural networks; potential overfitting is evaluated using K‐fold cross‐validation; and performance is analysed using the confusion matrix and various performance metrics. The algorithms used are Multilayer Perceptron Neural Network, Radial Basis Function Neural Network, Deep Neural Network, Decision Tree Classifier, Random Forest Classifier, Ada Boost Classifier and XgBoost Classifier. Finally, the results of all models are compared, visualizing Deep Neural Network and XgBoost as the most suitable models for predicting hotel reservation cancellations. [ABSTRACT FROM AUTHOR]

Recently, user-friendly internet-based applications are becoming popular in parallel with rapidly developing technology. With the growing information technology, computing power, and wealth of data available, analyzing spatial data has become an important subject for scientists who are interested in earth sciences. Thus, in terms of the software used for spatial data analysis, WEB-based applications have become the essential and increasingly popular for many applications. Here, a WEB-based software developed with R language is introduced. The software named as SoilSpatVis provides spatial data analysis and visualization. SoilSpatVis includes a desktop application that performs internet-based geographic data analysis using the K-means method, one of the machine learning algorithms. In the study, different soil pollution parameters collected from some sample sites in the border town of Kütahya, Turkey were used. These parameters were transferred into RStudio software which supports R language. The data were firstly clustered using the K-means algorithm and a visualization section was created for cluster analysis. The "Visualizations" page has been created which allows composing different graphs according to the desired parameter, and the "About" page provides information about the team that developed the application. Various geographic analysis tools are being added to the application and software codes are shared via GitHub. [ABSTRACT FROM AUTHOR]

Predictive analytics is crucial in precision medicine for personalized patient care. To aid in precision medicine, this study identifies a subset of genetic and clinical variables that can serve as predictors for classifying diseased tissues/disease types. To achieve this, experiments were performed on diseased tissues obtained from the L1000 dataset to assess differences in the functionality and predictive capabilities of genetic and clinical variables. In this study, the k‐means technique was used for clustering the diseased tissue types, and the multinomial logistic regression (MLR) technique was applied for classifying the diseased tissue types. Dimensionality reduction techniques including principal component analysis and Boruta are used extensively to reduce the dimensionality of genetic and clinical variables. The results showed that landmark genes performed slightly better in clustering diseased tissue types compared to any random set of 978 non‐landmark genes, and the difference is statistically significant. Furthermore, it was evident that both clinical and genetic variables were important in predicting the diseased tissue types. The top three clinical predictors for predicting diseased tissue types were identified as morphology, gender, and age of diagnosis. Additionally, this study explored the possibility of using the latent representations of the clusters of landmark and non‐landmark genes as predictors for an MLR classifier. The classification models built using MLR revealed that landmark genes can serve as a subset of genetic variables and/or as a proxy for clinical variables. This study concludes that combining predictive analytics with dimensionality reduction effectively identifies key predictors in precision medicine, enhancing diagnostic accuracy. [ABSTRACT FROM AUTHOR]

When analyzing data combined from multiple sources (e.g., hospitals, studies), the heterogeneity across different sources must be accounted for. In this article, we consider high‐dimensional linear regression models for integrative data analysis. We propose a new adaptive clustering penalty (ACP) method to simultaneously select variables and cluster source‐specific regression coefficients with subhomogeneity. We show that the estimator based on the ACP method enjoys a strong oracle property under certain regularity conditions. We also develop an efficient algorithm based on the alternating direction method of multipliers (ADMM) for parameter estimation. We conduct simulation studies to compare the performance of the proposed method to three existing methods (a fused LASSO with adjacent fusion, a pairwise fused LASSO and a multidirectional shrinkage penalty method). Finally, we apply the proposed method to the multicentre Childhood Adenotonsillectomy Trial to identify subhomogeneity in the treatment effects across different study sites. [ABSTRACT FROM AUTHOR]

Crude oil is an essential energy source that affects international trade, transportation, and manufacturing, highlighting its importance to the economy. Its future price prediction affects consumer prices and the energy markets, and it shapes the development of sustainable energy. It is essential for financial planning, economic stability, and investment decisions. However, reaching a reliable future prediction is an open issue because of its high volatility. Furthermore, many state-of-the-art methods utilize signal decomposition techniques, which can lead to increased prediction time. In this paper, a model called K-means-dense-sparse-dense long short-term memory (K-means-DSD-LSTM) is proposed, which has three main training phrases for crude oil price forecasting. In the first phase, the DSD-LSTM model is trained. Afterwards, the training part of the data is clustered using the K-means algorithm. Finally, a copy of the trained DSD-LSTM model is fine-tuned for each obtained cluster. It helps the models predict that cluster better while they are generalizing the whole dataset quite well, which diminishes overfitting. The proposed model is evaluated on two famous crude oil benchmarks: West Texas Intermediate (WTI) and Brent. Empirical evaluations demonstrated the superiority of the DSD-LSTM model over the K-means-LSTM model. Furthermore, the K-means-DSD-LSTM model exhibited even stronger performance. Notably, the proposed method yielded promising results across diverse datasets, achieving competitive performance in comparison to existing methods, even without employing signal decomposition techniques. [ABSTRACT FROM AUTHOR]

The global increase in wildfires due to climate change highlights the need for accurate wildfire mapping. This study performs a proof of concept on the usefulness of SuperDove imagery for wildfire mapping. To address this topic, we present an automatic methodology that combines the use of various vegetation indices with clustering algorithms (bisecting k-means and k-means) to analyze images before and after fires, with the aim of improving the precision of the burned area and severity assessments. The results demonstrate the potential of using this PlanetScope sensor, showing that the methodology effectively delineates burned areas and classifies them by severity level, in comparison with data from the Copernicus Emergency Management Service (CEMS). Thus, the potential of the SuperDove satellite sensor constellation for fire monitoring is highlighted, despite its limitations regarding radiometric distortion and the absence of Short-Wave Infrared (SWIR) bands, suggesting that the methodology could contribute to better fire management strategies. [ABSTRACT FROM AUTHOR]

Object detection via remote sensing encounters significant challenges due to factors such as small target sizes, uneven target distribution, and complex backgrounds. This paper introduces the K-CBST YOLO algorithm, which is designed to address these challenges. It features a novel architecture that integrates the Convolutional Block Attention Module (CBAM) and Swin-Transformer to enhance global semantic understanding of feature maps and maximize the utilization of contextual information. Such integration significantly improves the accuracy with which small targets are detected against complex backgrounds. Additionally, we propose an improved detection network that combines the improved K-Means algorithm with a smooth Non-Maximum Suppression (NMS) algorithm. This network employs an adaptive dynamic K-Means clustering algorithm to pinpoint target areas of concentration in remote sensing images that feature varied distributions and uses a smooth NMS algorithm to suppress the confidence of overlapping candidate boxes, thereby minimizing their interference with subsequent detection results. The enhanced algorithm substantially bolsters the model's robustness in handling multi-scale target distributions, preserves more potentially valid information, and diminishes the likelihood of missed detections. This study involved experiments performed on the publicly available DIOR remote sensing image dataset and the DOTA aerial image dataset. Our experimental results demonstrate that, compared with other advanced detection algorithms, K-CBST YOLO outperforms all its counterparts in handling both datasets. It achieved a 68.3% mean Average Precision (mAP) on the DIOR dataset and a 78.4% mAP on the DOTA dataset. [ABSTRACT FROM AUTHOR]

Background: Characterizing the condition of patients suffering from knee osteoarthritis is complex due to multiple associations between clinical, functional, and structural parameters. While significant variability exists within this population, especially in candidates for total knee arthroplasty, there is increasing interest in knee kinematics among orthopedic surgeons aiming for more personalized approaches to achieve better outcomes and satisfaction. The primary objective of this study was to identify distinct kinematic phenotypes in total knee arthroplasty candidates and to compare different methods for the identification of these phenotypes. Methods: Three-dimensional kinematic data obtained from a Knee Kinesiography exam during treadmill walking in the clinic were used. Various aspects of the clustering process were evaluated and compared to achieve optimal clustering, including data preparation, transformation, and representation methods. Results: A K-Means clustering algorithm, performed using Euclidean distance, combined with principal component analysis applied on data transformed by standardization, was the optimal approach. Two unique kinematic phenotypes were identified among 80 total knee arthroplasty candidates. The two distinct phenotypes divided patients who significantly differed both in terms of knee kinematic representation and clinical outcomes, including a notable variation in 63.3% of frontal plane features and 81.8% of transverse plane features across 77.33% of the gait cycle, as well as differences in the Pain Catastrophizing Scale, highlighting the impact of these kinematic variations on patient pain and function. Conclusion: Results from this study provide valuable insights for clinicians to develop personalized treatment approaches based on patients' phenotype affiliation, ultimately helping to improve total knee arthroplasty outcomes. [ABSTRACT FROM AUTHOR]

Cultivated land fragmentation is often considered to reduce agricultural productivity, leading to threatening food security. The pattern and drivers of cultivated land fragmentation can be expected to serve as an important prerequisite for scientific management. Taking Jiangsu Province as the study area, this study aims to assess the cultivated land fragmentation at the county level from four dimensions, including PD (patch density), AWMSI (area-weighted mean shape index), SHDI-S (Shannon's diversity index of area), and COHESION (patch cohesion index). A systematic analysis was made on the clustering features of cultivated land fragmentation in different dimensions using the K-means. MGWR (multiscale geography weighted regression) model was applied to explore the driving factors of cultivated land fragmentation in each county from five dimensions: topographic site, soil properties, urbanization, utilization intensity, and protection strength. The results showed that there were north-south differences in the cultivated land, where the PD and AWMSI were higher in the south than those in the north, the SHDI-S was higher in the north than in the south, and the COHESION was higher in the west. The four dimensions of the county-level cropland fineness index showed three types of clustering: Type A and Type B counties were located in the southern part of the province, both of which shared high patch density, irregular shape, and high area diversity. Among them, the Type A counties were higher connectivity of cultivated land than Type B; Type C counties shared lower patch density, regular shape, low area diversity, and high cropland connectivity, which were distributed mainly in the central and northern parts of the province. In addition, spatial heterogeneity was observed in the driving factors of cultivated land fragmentation in different types of regions. Differentiated fragmentation management should be adopted for the different regions. Among them, cultivated land fragmentation in the southern counties and districts (Type A and Type B) was mainly driven by natural factors (elevation, slope, and soil capacity). There were the more complex factors in the central and northern counties (Type C), including cropland allocation and urbanization. Cultivated land in the Type A counties exhibited a high density and irregular shape of patches, but a high degree of connectivity, which was a greater potential for management. Some considerations were given to promote the merging of adjacent cultivated land for large-scale production when the soil properties were similar in the topographic conditions. A low degree of contiguous cultivated land was observed in Type B counties, indicating the more complex driving factors are more difficult to manage. More attention should be paid to protecting the existing cultivated land for future urbanization. Cultivated land in Type C counties shared a low density and regular shape of patches, with the large cultivated land and continuous distribution. Cultivated land in Type C counties was the most affected by the topographic slope and protection. The central and northern regions were mainly plains with flat terrain and arable land, indicating the low potential for management. However, some attention should still be paid to regulating the use of cultivated land. The finding can provide a strong reference to managing the cultivated land fragmentation in Jiangsu Province. The cropland fine fragmentation model can also be optimized to develop the sustainable use of cropland. [ABSTRACT FROM AUTHOR]

On the Internet, online microblogging and social networks have experienced tremendous growth. Millions of individuals share opinions on social networking platforms including Twitter, Facebook, YouTube, and Microblogging sites. Millions of individuals express their thoughts on social platforms namely Twitter, Facebook, YouTube, and microblogging sites. As user‐generated content is growing to a huge extent on the internet, the analysis, extraction identification and classification of opinion and sentiment polarity of different aspects has now become a challenging issue in sentiment analysis. In sentiment analysis, aspect level opinion mining, opinion spam review detection, extraction and representation of most relevant accessed data from the user‐generated data is a difficult process. The word vector representation using existing deep learning techniques affects the performance in aspect level opinion mining. Spammers propagate false opinion for payment exchange, which leads to degradation of the financial growth, business, and fame of the organization. To overcome the limitations aspect level opinion mining is used to recognize sentiment and polarity of aspects in the specified text. This work presents various input feature vectors of deep learning approaches aiming to improve performance in aspect level opinion mining. Next, three meta‐heuristic algorithms with k‐means clustering approach for classification of opinion spam reviews on social media transit tweets is presented. The proposed approaches are evaluated and compared with other existing approaches as well as other benchmark datasets namely Restaurant and Amazon reviews. [ABSTRACT FROM AUTHOR]

With the increasingly widespread application of large-scale energy storage battery systems, the demand for battery safety is rising. Research on how to detect battery anomalies early and reduce the occurrence of thermal runaway (TR) accidents has become particularly important. Existing research on battery TR warning algorithms can be mainly divided into two categories: model-driven and data-driven methods. However, the common model-driven methods are often of high complexity, with poor versatility and low early warning capability; and the common data-driven methods are mostly based on neural networks, requiring substantial training costs, with better early warning capabilities but higher false alarm probabilities. To address the limitations of existing works, this paper proposes a combined data-driven and model-based algorithm for accurate battery TR warnings. Specifically, the K-Means algorithm serves as the data-driven module, capturing outliers in battery data, and the Bernardi equation serves as the model-driven module used to evaluate battery temperature. Ultimately, the outputs of the weighted model-driven module and data-driven module are combined to comprehensively assess whether the battery is abnormal. The proposed algorithm combines the advantages of model-driven and data-driven approaches, achieving a 25 min advance warning for thermal runaway, with a significantly reduced probability of false alarms. [ABSTRACT FROM AUTHOR]

Background: Novel diabetes phenotypes were proposed by the Europeans through cluster analysis, but Chinese community diabetes populations might exhibit different characteristics. This study aims to explore the clinical characteristics of novel diabetes subgroups under data‐driven analysis in Chinese community diabetes populations. Methods: We used K‐means cluster analysis in 6369 newly diagnosed diabetic patients from eight centers of the REACTION (Risk Evaluation of cAncers in Chinese diabeTic Individuals) study. The cluster analysis was performed based on age, body mass index, glycosylated hemoglobin, homeostatic modeled insulin resistance index, and homeostatic modeled pancreatic β‐cell functionality index. The clinical features were evaluated with the analysis of variance (ANOVA) and chi‐square test. Logistic regression analysis was done to compare chronic kidney disease and cardiovascular disease risks between subgroups. Results: Overall, 2063 (32.39%), 658 (10.33%), 1769 (27.78%), and 1879 (29.50%) populations were assigned to severe obesity‐related and insulin‐resistant diabetes (SOIRD), severe insulin‐deficient diabetes (SIDD), mild age‐associated diabetes mellitus (MARD), and mild insulin‐deficient diabetes (MIDD) subgroups, respectively. Individuals in the MIDD subgroup had a low risk burden equivalent to prediabetes, but with reduced insulin secretion. Individuals in the SOIRD subgroup were obese, had insulin resistance, and a high prevalence of fatty liver, tumors, family history of diabetes, and tumors. Individuals in the SIDD subgroup had severe insulin deficiency, the poorest glycemic control, and the highest prevalence of dyslipidemia and diabetic nephropathy. Individuals in MARD subgroup were the oldest, had moderate metabolic dysregulation and the highest risk of cardiovascular disease. Conclusion: The data‐driven approach to differentiating the status of new‐onset diabetes in the Chinese community was feasible. Patients in different clusters presented different characteristics and risks of complications. [ABSTRACT FROM AUTHOR]

The School Bus Routing Problem (SBRP) is a challenging optimization problem that has received increasing attention in recent years. The problem is composed of three sub-problems: facility location selection, assignment problem, and vehicle routing problem, which can be solved in a single stage or across multiple stages. In this study, we propose a novel two-stage approach to solve the SBRP that combines Fuzzy C Means (FCM) and K-means clustering algorithms with a Genetic Algorithm (GA). In the first stage, we used FCM and K-means to identify the optimal bus stop locations and assigned students to the nearest stop based on the distance metric. This two-stage approach reduces the search space and improves the efficiency of the GA in the second stage. In the second stage, we employed the GA to generate the optimal vehicle route that minimizes the total distance traveled by all vehicles. We compared our results with those in the literature and found that the K Means-GA approach outperformed the previous results. However, the FCM-GA approach yielded significantly inferior results, indicating that the choice of clustering algorithm plays a crucial role in the performance of the overall system. Our study provides insights into the importance of selecting appropriate clustering algorithms for solving the SBRP and proposes a two-stage solution that can be easily implemented in real-world scenarios. Our approach reduces the computational time and provides an effective solution for reducing the total distance traveled by school buses. [ABSTRACT FROM AUTHOR]

With the increasing need for rare-earth elements (REEs) to reach the goals of the ongoing green energy transition, new and innovative methods are needed to identify new primary resources of these critical metals. This study explores the potential to use a non-biased, uniform till dataset to generate evidentiary layers that describe these critical factors and geochemical anomalies to aid mineral potential mapping (MPM) for REEs using machine-assisted methods. The till samples used in this study were collected from the "REE Line", a sub-region within the Bergslagen lithotectonic province, Sweden, where numerous REE mineralizations occur. Multiple approaches were used in this study to isolate geochemical anomalies using multivariate methods, namely principal component analysis (PCA) and K-means clustering. Additional factors for classifying till samples were also tested, including alteration indices. Using known REE occurrences in Bergslagen as validation points, the results demonstrated the usefulness of multivariate methods applied to till geochemistry for predictive bedrock mapping, and to identify potential areas of REE mineralization within the REE line. The results of the alteration indices showed that the till geochemistry demonstrated similar levels of alteration when compared to the underlying bedrock, allowing for a regional alteration map to be generated. These results show that regional-scale till sampling can provide low-cost data for mineral exploration at the regional scale and generate usable evidentiary layers for GIS-based MPM. [ABSTRACT FROM AUTHOR]

With the continuous development of information and communication network technology and data mining technology, an ICT routing algorithm based on improved k-means clustering algorithm and gray wolf optimization is proposed to improve the energy efficiency and extend the life cycle of wireless communication networks. Firstly, we model the atmospheric channel, design the topology of the tolerant network and optimize the routing algorithm to achieve the interoperability between multiple networks and break through the traditional network requirements for time and space constraints. Then we implement an IPv6-based soft router supporting Anycast routing protocol under Linux environment and propose a new Anycast routing implementation scheme. Finally, an ICT routing algorithm (KGRA algorithm) based on improved k-means clustering and gray wolf optimization is designed, which first clusters the sensor nodes in the monitoring area using the improved k-means clustering algorithm. The clusters formed by the improved k-means clustering algorithm are optimized, and then the grey wolf optimization algorithm with improved convergence factor is used to select the cluster heads in the optimized cluster area. Finally, the nodes in the monitoring area will send data to the aggregation nodes using single-hop intra-cluster and multi-hop inter-cluster transmission, thus increasing the survival period of the network and greatly reducing energy consumption while balancing the energy consumption of the network. [ABSTRACT FROM AUTHOR]

This study investigates the impact of Free-to-Publish (F2P) versus Pay-to-Publish (P2P) models in dermatology journals, focusing on their differences in terms of journal metrics, Article Processing Charges (APCs), and Open Access (OA) status. Utilizing k-means clustering, the research evaluates dermatology journals based on SCImago Journal Rankings (SJR), H-Index, and Impact Factor (IF), and examines the correlation between these metrics, APCs, and OA status (Full or Hybrid). Data from the SCImago Journal Rank and Journal Citation Report databases were used, and metrics from 106 journals were normalized and grouped into three tiers. The study reveals a higher proportion of F2P journals, especially in higher-tier journals, indicating a preference for quality-driven research acceptance. Conversely, a rising proportion of P2P journals in lower tiers suggests potential bias towards the ability to pay. This disparity poses challenges for researchers from less-funded institutions or those early in their careers. The study also finds significant differences in APCs between F2P and P2P journals, with hybrid OA being more common in F2P. Conclusively, the study highlights the disparities in dermatology journals between F2P and P2P models and underscores the need for further research into authorship demographics and institutional affiliations in these journals. It also establishes the effectiveness of k-means clustering as a standardized method for assessing journal quality, which can reduce reliance on potentially biased individual metrics. [ABSTRACT FROM AUTHOR]

Relying on existing literature to identify suitable techniques for characterizing individual differences presents practical and methodological challenges. These challenges include the frequent absence of detailed descriptions of raw data, which hinders the assessment of analysis appropriateness, as well as the exclusion of data points deemed outliers, or the reliance on comparing only extreme groups by categorizing continuous variables into upper and lower quartiles. Despite the availability of algorithmic modeling in standard statistical software, investigations into individual differences predominantly focus on factor analysis and parametric tests. To address these limitations, this application-oriented study proposes a comprehensive approach that leverages behavioral responses through the use of signal detection theory and clustering techniques. Unlike conventional methods, signal detection theory considers both sensitivity and bias, offering insights into the intricate interplay between perceptual ability and decision-making processes. On the other hand, clustering techniques enable the identification and classification of distinct patterns within the dataset, allowing for the detection of singular behaviors that form the foundation of individual differences. In a broader framework, these combined approaches prove particularly advantageous when analyzing large and heterogeneous datasets provided by data archive platforms. By applying these techniques more widely, our understanding of the cognitive and behavioral processes underlying learning can be expedited and enhanced. [ABSTRACT FROM AUTHOR]

Accurate forecasting is crucial for successfully integrating photovoltaic (PV) power plants into electrical grids and microgrids. Accordingly, this work presents a hybrid methodology for day-ahead PV power forecasting (PPF). It begins by examining three deep learning (DL) techniques, long short-term memory (LSTM), gated recurrent unit (GRU), and multilayer perceptron (MLP), as potential forecasting models. To find a robust forecasting model, feature selection is employed to select the most relevant input features, and additionally, hyperparameter optimization is performed using the Chu–Beasley genetic algorithm to automatically set the hyperparameters for each technique. An initial day-ahead PPF is computed recursively after selecting the optimal forecasting model. Subsequently, this initial forecast is refined using a long-short-term memory autoencoder (LSTM-AE) that corrects the initial PPF. To further enhance the interpretability of the final forecast, the k-means algorithm, incorporating a soft-dynamic time warping (DTW) metric, is utilized. The efficacy of the methodology is validated using real data from a solar farm at the State University of Campinas (UNICAMP) in Brazil. Empirical results demonstrate that the proposed methodology improves the forecast accuracy by more than 3.5% when LSTM-AE is applied for correction compared to state-of-the-art models. [ABSTRACT FROM AUTHOR]

The rapid development of the metaverse has sparked extensive discussion on how to estimate its development maturity using quantifiable indicators, which can offer an assessment framework for governing the metaverse. Currently, the measurable methods for assessing the maturity of the metaverse are still in the early stages. Data-driven approaches, which depend on the collection, analysis, and interpretation of large volumes of data to guide decisions and actions, are becoming more important. This paper proposes a data-driven approach to assess the maturity of the metaverse based on K-means-AdaBoost. This method automatically updates the indicator weights based on the knowledge acquired from the model, thereby significantly enhancing the accuracy of model predictions. Our approach assesses the maturity of metaverse systems through a thorough analysis of metaverse data and provides strategic guidance for their development. [ABSTRACT FROM AUTHOR]

Hypospadias phenotype assessment determines if the anatomy is favorable for reconstruction. Glans-Urethral Meatus-Shaft (GMS) has been adopted in an effort to standardize hypospadias classification. While extremely subjective, GMS has been widely used to classify the severity of the phenotype to predict surgical outcomes. The use of digital image analysis has proven to be feasible and prior efforts by our team have demonstrated that machine learning algorithms can emulate an expert's assessment of the phenotype. Nonetheless, the creation of these image recognition algorithms is highly subjective. In order to reduce a subjective input in the evaluation of the phenotype, we propose a novel approach to analyze the anatomy using digital image pixel analysis and to compare the results using the GMS score. Our hypothesis is that pixel cluster segmentation can discriminate between favorable and unfavorable anatomy. To evaluate whether image segmentation and digital pixel analysis are able to analyze favorable vs unfavorable hypospadias anatomy in a less subjective manner than GMS score. A total of 148 patients with different types of hypospadias were classified by 1 of 5 independent experts following the GMS score into "favorable" (GG), "moderately favorable" (GM) and "unfavorable" (GP) glans. From there, 592 images were generated using digital image segmentation. 584 were included for final analysis due to certain images being excluded for poor image quality or inadequate capture of target anatomy. For each image, the region of interest was segmented separately by two evaluators into "glans," "urethral plate," "foreskin" and "periurethral plate". The values obtained for each segmented region using machine-learning statistical pixel k-means cluster analysis were analyzed and compared to the GMS score given to that image using an ANOVA analysis. Analysis of image segmentation demonstrated that k-means pixel cluster analysis discriminated "favorable" vs "unfavorable" urethral plates. There was a significant difference between scores when comparing the GG and GM groups (p = 0.03) and GG and GP groups (p = 0.05). Pixel cluster analysis could not discriminate between "moderately favorable" and "unfavorable" urethral plates. Through our analysis, we found significant pairwise difference for different tissue qualities. Digital image segmentation and statistical k-means cluster analysis can discriminate anatomical features in a similar way to the GMS score. Future research can target discerning between different tissue qualities in an effort to predict surgical outcomes for hypospadias repair. [Display omitted] [ABSTRACT FROM AUTHOR]

In the process of the K-means clustering algorithm, one of the issues that arises is the high number of iterations. This study aims to optimize the cluster evaluation results in K-means by reducing iterations through the application of the Weight Product Model (WPM). The evaluation method used in this research is the Davies-Bouldin Index (DBI). Three datasets were analyzed: the QSAR Dataset consisting of 908 data points, 7 attributes; the Whoscale Customer dataset consisting of 440 data points, 8 attributes from the UCI Machine Learning Repository, as well as direct observational data from captured fisheries obtained from the North Aceh District Office of Marine and Fisheries, Indonesia consisting of 75 data points, 8 attributes. The results of 10 testing iterations on three different datasets show that for the QSAR Dataset, the average cluster evaluation using DBI with K-means is 0.852. However, when applying WPM+K-means, the average DBI value increases to 0.727, with the average number of K-means iterations reduced from 23 to 8 iterations. For the Whoscale Customer dataset, the average cluster evaluation using DBI with K-means is 0.921. In contrast, when employing WPM+K-means, the average DBI value slightly improves to 0.910, accompanied by a reduction in the average number of K-means iterations from 23 to 10 iterations. In the case of the captured fisheries dataset, the average cluster evaluation using DBI with K-means yields a value of 1.222. However, implementing WPM+K-means results in an improved average DBI of 1.052. Furthermore, the average number of K-means iterations is reduced to 9 iterations, whereas for WPM+K-means, this number is reduced to 4 iterations. The results of this study demonstrate an improvement in DBI values, where lower DBI values indicate better performance of the K-means algorithm. These also findings demonstrate that WPM is effective in optimizing cluster evaluation values in Kmeans clustering. With the reduction in the number of K-means iterations, computational time is expected to be faster. [ABSTRACT FROM AUTHOR]

Batteries are a fundamental storage component due to its various applications in mobility, renewable energies and consumer electronics among others. Regardless of the battery typology, one key variable from a user's perspective is the remaining energy in the battery. It is usually presented as the percentage of remaining energy compared to the total energy that can be stored and is labeled State Of Charge (SOC). This work addresses the development of a hybrid model based on a Lithium Iron Phosphate (LiFePO4) power cell, due to its broad implementation. The proposed model calculates the SOC, by means of voltage and electric current as inputs and the latter as the output. Therefore, four models based on k-Means, Agglomerative Clustering, Gaussian Mixture and Spectral Clustering techniques have been tested in order to obtain an optimal solution. [ABSTRACT FROM AUTHOR]

Business continuity is greatly influenced by the menu, especially in the culinary industry. Micro, Small, and Medium Enterprises (MSMEs) account for 64.1 million units or around 99% of all businesses in Indonesia. For many years, MSME has been using menu analyses to keep its menu optimized. However, this is not enough since 50% of MSMEs are failing in their first 5 years due to poor decisionmaking as a result of a lack of knowledge. Based on that problem, there is a necessity for menu analysis and tools to assist in decision-making, also called Business Intelligence. The method used consists of three stages: data collection, business intelligence design, as well as analysis and results. The BI design focuses on menu engineering using the KMeans algorithm to divide menu items into four unique clusters according to Kasavana-Smith's menu engineering concept. After validating its findings with the Davies-Boudlin Index evaluation, it concludes that a four-cluster solution is most optimal among other value-cluster. This study aims to assist business owners in making better decisions, and it may be used as a reference for business owners by providing suggestions based on the menu review analysis. [ABSTRACT FROM AUTHOR]

Chronic exposure to the hypobaric hypoxia environment of plateau could influence human cognitive behaviours which are supported by dynamic brain connectivity states. Until now, how functional connectivity (FC) of the brain network changes with altitudes is still unclear. In this article, we used EEG data of the Go/NoGo paradigm from Weinan (347 m) and Nyingchi (2950 m). A combination of dynamic FC (dFC) and the K-means cluster was employed to extract dynamic FC states which were later distinguished by graph metrics. Besides, temporal properties of networks such as fractional windows (FW), transition numbers (TN) and mean dwell time (MDT) were calculated. Finally, we successfully extracted two different states from dFC matrices where State 1 was verified to have higher functional integration and segregation. The dFC states dynamically switched during the Go/NoGo tasks and the FW of State 1 showed a rise in the high-altitude participants. Also, in the regional analysis, we found higher state deviation in the fronto-parietal cortices and enhanced FC strength in the occipital lobe. These results demonstrated that long-term exposure to the high-altitude environment could lead brain networks to reorganize as networks with higher inter- and intra-networks information transfer efficiency, which could be attributed to a compensatory mechanism to the compromised brain function due to the plateau environment. This study provides a new perspective in considering how the plateau impacted cognitive impairment. [ABSTRACT FROM AUTHOR]

Monthly precipitation data from 58 synoptic stations throughout Botswana, spanning 1981–2016, were used in this study. The data were examined using multivariate analysis to determine regions exhibiting distinct precipitation variability patterns and regimes. To accomplish this, the T-mode of principal component analysis was applied to the correlation matrix of the data. Based on the maximum loading values of the rotational principal component scores, the T-mode indicated three separate subregions with varying precipitation patterns over time. Four clusters with distinct rainfall patterns were identified when cluster analysis was performed on the principal component scores. An assessment of the homogeneity of the clusters was performed using L-moment's heterogeneity measure (H). Statistical analysis was employed to model annual rainfall data using five commonly used rainfall analysis probability distribution functions: normal, lognormal, gamma, Weibull, and Gumbel. The probability distributions with the greatest fit were determined based on the maximum overall score, which was calculated by adding the individual point scores of three chosen goodness-of-fit tests. Each cluster exhibited distinct probability distribution functions, with the gamma, Gumbel, lognormal, and Weibull distributions providing the most accurate descriptions. [ABSTRACT FROM AUTHOR]

Nowadays, the demand for risk response is increasing in countries worldwide, leading to the development of emergency-related industries as strategic emerging sectors. However, the emergency logistics industry is facing increasingly critical distribution issues. This study applies K-means clustering analysis to convert multiple distribution centers into multiple single distribution center problems. It then compares and analyzes the vehicle routing model with time windows for emergency logistics delivery in multiple distribution centers using guided local search (GLS), taboo search (TS), and simulated annealing (SA) algorithm. The results demonstrate that the GLS algorithm outperformed both the SA and TS algorithm in optimizing emergency logistics delivery paths for multiple distribution centers. The GLS algorithm proved to be more effective in solving this problem. This study confirms the contemporary value of emergency logistics distribution problems and offers practical insights into optimizing emergency logistics distribution paths in multiple distribution centers. [ABSTRACT FROM AUTHOR]

Climate classification plays a fundamental role in understanding climatic patterns, particularly in the context of a changing climate. This study utilized hourly meteorological data from 36 major cities in China from 2011 to 2021, including 2 m temperature (T2), relative humidity (RH), and precipitation (PRE). Both original hourly sequences and daily value sequences were used as inputs, applying two non-hierarchical clustering methods (k-means and k-medoids) and four hierarchical clustering methods (ward, complete, average, and single) for clustering. The classification results were compared using two clustering evaluation indices: the silhouette coefficient and the Calinski–Harabasz index. Additionally, the clustering was compared with the Köppen–Geiger climate classification based on the maximum difference in intra-cluster variables. The results showed that the clustering method outperformed the Köppen–Geiger climate classification, with the k-medoids method achieving the best results. Our research also compared the effectiveness of climate classification using two variables (T2 and PRE) versus three variables, including the addition of hourly RH. Cluster evaluation confirmed that incorporating the original sequence of hourly T2, PRE, and RH yielded the best performance in climate classification. This suggests that considering more meteorological variables and using hourly observation data can significantly improve the accuracy and reliability of climate classification. In addition, by setting the class numbers to two, the clustering methods effectively identified climate boundaries between northern and southern China, aligning with China's traditional geographical division along the Qinling–Huaihe River line. [ABSTRACT FROM AUTHOR]

This paper introduces a novel formulation of the clustering problem, namely, the minimum sum-of-squares clustering of infinitely tall data (MSSC-ITD), and presents HPClust, an innovative set of hybrid parallel approaches for its effective solution. By utilizing modern high-performance computing techniques, HPClust enhances key clustering metrics: effectiveness, computational efficiency, and scalability. In contrast to vanilla data parallelism, which only accelerates processing time through the MapReduce framework, our approach unlocks superior performance by leveraging the multi-strategy competitive–cooperative parallelism and intricate properties of the objective function landscape. Unlike other available algorithms that struggle to scale, our algorithm is inherently parallel in nature, improving solution quality through increased scalability and parallelism and outperforming even advanced algorithms designed for small- and medium-sized datasets. Our evaluation of HPClust, featuring four parallel strategies, demonstrates its superiority over traditional and cutting-edge methods by offering better performance in the key metrics. These results also show that parallel processing not only enhances the clustering efficiency, but the accuracy as well. Additionally, we explore the balance between computational efficiency and clustering quality, providing insights into optimal parallel strategies based on dataset specifics and resource availability. This research advances our understanding of parallelism in clustering algorithms, demonstrating that a judicious hybridization of advanced parallel approaches yields optimal results for MSSC-ITD. Experiments on the synthetic data further confirm HPClust's exceptional scalability and robustness to noise. [ABSTRACT FROM AUTHOR]

In Internet of Things (IoT), WSNs are crucial components because they sense, acquire data and communicate with the base station. Because IoT connects devices with scarce resources, the energy needed for communication is viewed as one of the most challenging issues facing WSN assisted IoT. Clustering techniques have the potential to conserve energy and keep network nodes running for longer periods of time. Traditional hierarchical routing protocols are based on a random probability equation for cluster head (CH) selection. Moreover, there is scope to enhance the network lifespan by improving the CH selection approach. To address this, we present the hybrid K-means ant Lion optimization approach for Energy-efficient clustering based Routing (K-LionER) scheme for WSN supported by the IoT. The proposed K-LionER focuses on prolonging the network lifespan and improving energy efficiency. The clusters in WSN under investigation are created using K-means and each CH is chosen using ant lion optimization. CHs acquire the data from cluster members and transmit the agglomerated data to the base station. K-LionER selects the CH based on routing metrics, Remnant Energy (RE), distance between the CHs and Base station (CBD) and Intra-cluster Communication Cost (ICC). A comprehensive simulation is carried out on MATLAB 2017a. K-LionER's accomplishment is contrasted with LEACH, ECFU and GADA-LEACH. The simulation's outcome reveals gains in performance in various aspects, such as alive nodes, stability period, dead nodes and network lifetime metrics. In comparison to the aforementioned routing protocols, the proposed K-LionER protocol improves the network's lifetime by 10% to 48%. [ABSTRACT FROM AUTHOR]

The Consillium Academica initiative, spearheaded by the academic vicedeanship of the Faculty of Sciences at Universidad Nacional de Colombia in Bogotá, is based on a comprehensive clustering analysis of undergraduate students. This study leverages data spanning from the 2012-1S to 2022-2S academic terms to semi-automatically identify a group of students consistently exhibiting academic underperformance each semester with a potential high risk of academic dropout. The methodology employed in this initiative serves as a proactive measure to identify and support students at risk, to improve the effectiveness of the intervention strategies of the tutor-teacher program, facilitating direct contact between mentors and identified students to provide personalized guidance and academic advisement. This article presents the methodology, key findings, and implications of the Consillium Academica initiative, shedding light on its potential to fortify academic support systems and contribute to the overall success and retention of undergraduate students. [ABSTRACT FROM AUTHOR]

This article explains the idea of pattern systems that develop gradually. These systems involve symbolic communication that includes symbols, syntax, and layout rules. Some pattern systems change over time, like historical scripts. The scientific study of pattern systems is called pattern evolution research, and scriptinformatics is concerned with the modelling of the evolution of scripts. The symbol series consists of symbols from a pattern system, while the graph sequence is a symbol sequence applied with a specific technology. This article describes a method for examining tested pattern systems to confirm their classification, which focuses on more ancient features. The method's effectiveness was tested on Rovash scripts and graph sequences. Multivariate analysis was carried out by using PAST4 software, employing principal coordinates analysis ordination and k -means clustering algorithms. [ABSTRACT FROM AUTHOR]

The collection of SuperDARN ionospheric echo data to make ionospheric convection maps is of great significance for Space Weather research. The ionospheric echoes for SuperDARN are generally mixed with scatter from the ground or sea surface, thus the clustering analysis of SuperDARN backscatter echoes is important. In this paper, the first implementation of deep clustering based on the graph automatic encoder network is efficiently realized for classifying the SuperDARN data. In addition, the model is compared with the traditional algorithm and machine learning clustering algorithms. Application of the model to sample data reveals that the deep clustering algorithm can capture the structural characteristics of the echoes and improve the accuracy of echo clustering and classifying. [ABSTRACT FROM AUTHOR]

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

Restaurant reviews play a pivotal role in shaping consumer decisions and perceptions. Analyzing these reviews through sentiment analysis provides valuable insights into customer sentiments towards various aspects of dining experiences, such as food quality, service, ambiance, and pricing. By leveraging sentiment analysis techniques, businesses can better understand customer preferences, identify areas for improvement, and enhance overall customer satisfaction. This research focuses on utilizing aspect-based sentiment analysis to predict restaurant survival, leveraging customer-generated content from online reviews. The proposed methodology encompasses data acquisition, pre-processing, feature extraction, and unsupervised approaches-based classification. Data pre-processing involves tokenization, stop word removal, lemmatization, punctuation removal, and filtering short and long words to standardize the format. Feature extraction includes lexicon-based and word encoding methods, leveraging Term Frequency-Inverse Document Frequency (TF-IDF) vectors, Ngram, Bag of Words, and Word Embedding. Unsupervised approachesbased classification entails Fuzzy C-Means (FCM), K-Means, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Hierarchical Method, Hybrid Binary Particle Swarm-Optimized FCM, and HBPSO-Optimized Kmeans. Evaluation parameters are defined to assess the performance of each approach. The results showcase the effectiveness of aspect-based sentiment analysis in predicting restaurant survival, with HBPSO-Optimized FCM demonstrating the highest accuracy at 89.50%. These findings underscore the significance of leveraging customergenerated content for informed decision-making in the restaurant industry. [ABSTRACT FROM AUTHOR]

Mental health is indispensable for effective daily functioning and stress management. Facial expressions may provide vital clues about the mental state of a person as they are universally consistent across cultures. This study intends to detect the emotional variances through facial micro-expressions using facial action units (AUs) to identify probable mental health issues. In addition, convolutional neural networks (CNN) were used to detect and classify the micro-expressions. Further, combinations of AUs were identified for the segmentation of micro-expressions classes using K-means square. Two benchmarked datasets CASME II and SAMM were employed for the training and evaluation of the model. The model achieved an accuracy of 95.62% on CASME II and 93.21% on the SAMM dataset, respectively. Subsequently, a case analysis was done to identify depressive patients using the proposed framework and it attained an accuracy of 92.99%. This experiment revealed the fact that emotions like disgust, sadness, anger, and surprise are the prominent emotions experienced by depressive patients during communication. The findings suggest that leveraging facial action units for micro-expression detection offers a promising approach to mental health diagnostics. [ABSTRACT FROM AUTHOR]

In the last decades, technological advances have led to a considerable increase in computing power constraints to simulate complex phenomena in various application fields, among which are climate, physics, genomics and medical diagnosis. Often, accurate results in real time, or quasi real time, are needed, especially if related to a process requiring rapid interventions. To deal with such demands, more sophisticated approaches have been designed, including GPUs, multicore processors and hardware accelerators. Supercomputers manage high amounts of data at a very high speed; however, despite their considerable performance, their limitations are due to maintenance costs, rapid obsolescence and notable energy consumption. New processing architectures and GPUs in the medical field can provide diagnostic and therapeutic support whenever the patient is subject to risk. In this context, image processing as an aid to diagnosis, in particular pulmonary ultrasound to detect COVID-19, represents a promising diagnostic tool with the ability to discriminate between different degrees of disease. This technique has several advantages, such as no radiation exposure, low costs, the availability of follow-up tests and the ease of use even with limited resources. This work aims to identify the best approach to optimize and parallelize the selection of the most significant frames of a video which is given as the input to the classification network that will differentiate between healthy and COVID patients. Three approaches have been evaluated: histogram, entropy and ResNet-50, followed by a K-means clustering. Results highlight the third approach as the most accurate, simultaneously showing GPUs significantly lowering all processing times. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Marmara University Social Sciences Institute / Öneri is the property of Marmara University, Institute of Social Sciences and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Due to technological progress and changes in people's aesthetic standards, traditional design models need to be constantly broken through, seeking more efficient and accurate design methods. Seeking effective design models to improve design efficiency and prediction accuracy is an important task. Therefore, this study proposes an indoor scene coloring design model that combines improved K-means clustering and simulated annealing algorithm for this important task. Based on the analysis of indoor scene coloring, particle swarm optimization algorithm is used to optimize K-means clustering to achieve color classification. Combined with simulated annealing algorithm, adaptive adjustment of lighting conditions is achieved to enhance the naturalness and realism of coloring. These results confirmed that the proposed method had the highest average F-value, with an average F-value of 92.524 and 143.601 on both datasets, respectively. The average ARI values were 0.361 and 0.897, respectively. The designed algorithm performed the best and converged faster than other three. Therefore, the proposed method can effectively ensure the consistency between the distribution of data objects after clustering and the actual situation. For indoor scene coloring design, it has important practical significance and provides new possible paths for improving design efficiency and prediction accuracy. [ABSTRACT FROM AUTHOR]

Every work environment contains different types of risks and interactions between risks. Therefore, the method to be used when making a risk assessment is very important. When determining which risk assessment method (RAM) to use, there are many factors such as the types of risks in the work environment, the interactions of these risks with each other, and their distance from the employees. Although there are many RAMs available, there is no RAM that will suit all workplaces and which method to choose is the biggest question. There is no internationally accepted scale or trend on this subject. In the study, 26 sectors, 10 different RAMs and 10 criteria were determined. A hybrid approach has been designed to determine the most suitable RAMs for sectors by using k-means clustering and support vector machine (SVM) classification algorithms, which are machine learning (ML) algorithms. First, the data set was divided into subsets with the k-means algorithm. Then, the SVM algorithm was run on all subsets with different characteristics. Finally, the results of all subsets were combined to obtain the result of the entire dataset. Thus, instead of the threshold value determined for a single and large cluster affecting the entire cluster and being made mandatory for all of them, a flexible structure was created by determining separate threshold values for each sub-cluster according to their characteristics. In this way, machine support was provided by selecting the most suitable RAMs for the sectors and eliminating the administrative and software problems in the selection phase from the manpower. The first comparison result of the proposed method was found to be the hybrid method: 96.63%, k-means: 90.63 and SVM: 94.68%. In the second comparison made with five different ML algorithms, the results of the artificial neural networks (ANN): 87.44%, naive bayes (NB): 91.29%, decision trees (DT): 89.25%, random forest (RF): 81.23% and k-nearest neighbours (KNN): 85.43% were found. [ABSTRACT FROM AUTHOR]

In this paper, we address the difficulty of solving large-scale multi-dimensional knapsack instances (MKP), presenting a novel deep reinforcement learning (DRL) framework. In this DRL framework, we train different agents compatible with a discrete action space for sequential decision-making while still satisfying any resource constraint of the MKP. This novel framework incorporates the decision variable values in the 2D DRL where the agent is responsible for assigning a value of 1 or 0 to each of the variables. To the best of our knowledge, this is the first DRL model of its kind in which a 2D environment is formulated, and an element of the DRL solution matrix represents an item of the MKP. Our framework is configured to solve MKP instances of different dimensions and distributions. We propose a K-means approach to obtain an initial feasible solution that is used to train the DRL agent. We train four different agents in our framework and present the results comparing each of them with the CPLEX commercial solver. The results show that our agents can learn and generalize over instances with different sizes and distributions. Our DRL framework shows that it can solve medium-sized instances at least 45 times faster in CPU solution time and at least 10 times faster for large instances, with a maximum solution gap of 0.28% compared to the performance of CPLEX. Furthermore, at least 95% of the items are predicted in line with the CPLEX solution. Computations with DRL also provide a better optimality gap with respect to state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Abstract The clustering algorithm is an effective method for developing energy efficiency routing protocol for wireless sensor networks (WSNs). In clustered WSNs, cluster heads must handle high traffic, thus consuming more energy. Therefore, forming balanced clusters and selecting optimal cluster heads are significant challenges. The paper proposes a sector clustering algorithm based on K-means called KMSC. KMSC improves efficiency and balances the cluster size by employing symmetric dividing sectors in conjunction with K-means. For the selection of cluster heads (CHs), KMSC uses the residual energy and distance to calculate the weight of the node, then selects the node with the highest weight as CH. A hybrid single-hop and multi-hop communication is utilized to reduce long-distance transmissions. Furthermore, the impact of the number of sectors, the threshold for clustering, and the network size on the performance of KMSC has been explored. The simulation results show that KMSC outperforms EECPK-means, K-means, TSC, LSC, and SEECP in terms of FND, HND, and LND.

Abstract In the process of penicillin fermentation, there is a strong nonlinear relationship between the input eigenvector and multiple output vectors, which makes the prediction accuracy of the existing model difficult to meet the requirements of chemical production. Therefore, a local selective ensemble learning multi-objective soft sensing modeling strategy is proposed in this study. Firstly, a localization method based on transfer entropy and k-means is proposed to reconstruct the sample set. Then, based on the reconstructed local samples, the local soft sensing model is established by the multi-objective support vector regression method, and the selective ensemble of sub-models and the adaptive calculation of prediction weights are realized. At the same time, to reduce the adverse effects caused by improper selection of model parameters, the sparrow search algorithm is used to realize the tuning of the mentioned model parameters. Finally, the proposed modeling strategy is simulated. The results show that, compared with other methods, the proposed local selective ensemble learning multi-objective soft sensing modeling strategy has better prediction performance.

The research is motivated by issues encountered in the process of distributing products such as shifts in consumption patterns post the Covid-19 pandemic, and potential losses arising from the process of delivering food to customers. The objective of this study is to identify customer segmentation in order to enhance the efficiency of the distribution process and to identify the most efficient route for the distribution process. During the segmentation process, it is critical to identify the suitable attributes. Moreover, once the attributes have been identified, the segmentation process will be implemented using the K-Means method. Subsequently, the optimization process will be executed using the Traveling Salesman Problem. The result showed the segmentation process enable to find the optimal number of cluster, this is shown by reducing the number of clusters from 14 clusters to 9 clusters. Furthermore, the research outcomes regarding the optimization process demonstrate that the model is indeed optimal. The results indicate a 15.16% reduction in the overall travel distance, resulting in a decrease from 3,386.5 kilometers to 2,940.8 kilometers.

Pasar swalayan menghasilkan transaksi penjualan dengan pelanggan dengan laju pertumbuhan data tinggi. Data transaksi sejumlah barang memiliki pola berbeda, ada yang tinggi dan ada yang rendah. Perbedaan ini mengakibatkan pola penjualan antar satu produk dengan produk lainnya berbeda. Pola ini juga mengakibatkan pengelolaan stok dan promosi juga berbeda. Maka, untuk memudahkan pengelolaan barang, perlu dilakukan pengelompokan trend penjualan otomatis menggunakan K-Means. Namun, metode perhitungan jarak (dissimilarity) standar tidak tepat digunakan pada data periodik. Penelitian ini bereksperimen mengelompokkan data periodic trend penjualan produk menggunakan metode K-Means dan DTW (Dynamic Time Warping) untuk perhitungan jarak. DTW melakukan perhitungan jarak dengan memperhatikan data histori periode sebelum dan setelah data yang sedang dihitung. Pelibatan data disekitarnya akan membentuk jarak sesuai dengan pola data periodik. Hasil pengelompokan data tahun 2021, Cluster 1 dengan 417 data memiliki pola naik dari awal tahun kemudian menurun, selanjutnya perlahan naik kembali di pertengahan hingga akhir tahun. Cluster 2 dengan 2403 data memiliki pola stabil di awal tahun, ketika di pertengahan tahun mulai naik, kemudian di akhir tahun turun namun kembali naik. Cluster 3 dengan 289 data memiliki pola menurun saat awal tahun, namun terlihat stabil hingga akhir tahun. Hasil ekeperimen pengelompokan trend penjualan menggunakan metode K-Means dengan jarak DTW menunjukkan hasil yang baik dan memiliki pola data dalam kelompok yang sesuai karakteristik alami. Hal ini didukung oleh validitas Davies-Bouldin index -1.215 dimana nilai yang semakin kecil mendekati nol menunjukkan kualitas cluster yang dicapai baik.

Abstract Crude oil is an essential energy source that affects international trade, transportation, and manufacturing, highlighting its importance to the economy. Its future price prediction affects consumer prices and the energy markets, and it shapes the development of sustainable energy. It is essential for financial planning, economic stability, and investment decisions. However, reaching a reliable future prediction is an open issue because of its high volatility. Furthermore, many state-of-the-art methods utilize signal decomposition techniques, which can lead to increased prediction time. In this paper, a model called K-means-dense-sparse-dense long short-term memory (K-means-DSD-LSTM) is proposed, which has three main training phrases for crude oil price forecasting. In the first phase, the DSD-LSTM model is trained. Afterwards, the training part of the data is clustered using the K-means algorithm. Finally, a copy of the trained DSD-LSTM model is fine-tuned for each obtained cluster. It helps the models predict that cluster better while they are generalizing the whole dataset quite well, which diminishes overfitting. The proposed model is evaluated on two famous crude oil benchmarks: West Texas Intermediate (WTI) and Brent. Empirical evaluations demonstrated the superiority of the DSD-LSTM model over the K-means-LSTM model. Furthermore, the K-means-DSD-LSTM model exhibited even stronger performance. Notably, the proposed method yielded promising results across diverse datasets, achieving competitive performance in comparison to existing methods, even without employing signal decomposition techniques.

Abstract Background: Characterizing the condition of patients suffering from knee osteoarthritis is complex due to multiple associations between clinical, functional, and structural parameters. While significant variability exists within this population, especially in candidates for total knee arthroplasty, there is increasing interest in knee kinematics among orthopedic surgeons aiming for more personalized approaches to achieve better outcomes and satisfaction. The primary objective of this study was to identify distinct kinematic phenotypes in total knee arthroplasty candidates and to compare different methods for the identification of these phenotypes. Methods: Three-dimensional kinematic data obtained from a Knee Kinesiography exam during treadmill walking in the clinic were used. Various aspects of the clustering process were evaluated and compared to achieve optimal clustering, including data preparation, transformation, and representation methods. Results: A K-Means clustering algorithm, performed using Euclidean distance, combined with principal component analysis applied on data transformed by standardization, was the optimal approach. Two unique kinematic phenotypes were identified among 80 total knee arthroplasty candidates. The two distinct phenotypes divided patients who significantly differed both in terms of knee kinematic representation and clinical outcomes, including a notable variation in 63.3% of frontal plane features and 81.8% of transverse plane features across 77.33% of the gait cycle, as well as differences in the Pain Catastrophizing Scale, highlighting the impact of these kinematic variations on patient pain and function. Conclusion: Results from this study provide valuable insights for clinicians to develop personalized treatment approaches based on patients’ phenotype affiliation, ultimately helping to improve total knee arthroplasty outcomes.

Abstract Mudstones and shales serve as natural barrier rocks in various geoenergy applications. Although many studies have investigated their mechanical properties, characterizing these parameters at the microscale remains challenging due to their fine-grained nature and susceptibility to microstructural damage introduced during sample preparation. This study aims to investigate the micromechanical properties of clay matrix composite in mudstones by combining high-speed nanoindentation mapping and machine learning data analysis. The nanoindentation approach effectively captured the heterogeneity in high-resolution mechanical property maps. Utilizing machine learning-based k-means clustering, the mechanical characteristics of matrix clay, brittle minerals, as well as measurements on grain boundaries and structural discontinuities (e.g., cracks) were successfully distinguished. The classification results were validated through correlation with broad ion beam-scanning electron microscopy images. The resulting average reduced elastic modulus (E r ) and hardness (H) values for the clay matrix were determined to be 16.2 ± 6.2 and 0.5 ± 0.5 GPa, respectively, showing consistency across different test settings and indenter tips. Furthermore, the sensitivity of indentation measurements to various factors was investigated, revealing limited sensitivity to indentation depth and tip geometry (when comparing Cube corner and Berkovich tip in a small range of indentation depth variations), but decreased stability at lower loading rates. Box counting and bootstrapping methods were applied to assess the representativeness of parameters determined for the clay matrix. A relatively small dataset (indentation number = 60) is needed to achieve representativeness, while the main challenges is to cover a representative mapping area for clay matrix characterization. Overall, this study demonstrates the feasibility of high-speed nanoindentation mapping combined with data analysis for micromechanical characterization of the clay matrix in mudstones, paving the way for efficient analysis of similar fine-grained sedimentary rocks.