Clustering Effect Research Articles

NOODLE: Joint Cross-View Discrepancy Discovery and High-Order Correlation Detection for Multi-View Subspace Clustering

Benefiting from the effective exploration of the valuable topological pair-wise relationship of data points across multiple views, multi-view subspace clustering (MVSC) has received increasing attention in recent years. However, we observe that existing MVSC approaches still suffer from two limitations that need to be further improved to enhance the clustering effectiveness. Firstly, previous MVSC approaches mainly prioritize extracting multi-view consistency, often neglecting the cross-view discrepancy that may arise from noise, outliers, and view-inherent properties. Secondly, existing techniques are constrained by their reliance on pair-wise sample correlation and pair-wise view correlation, failing to capture the high-order correlations that are enclosed within multiple views. To address these issues, we propose a novel MVSC framework via joi N t cr O ss-view discrepancy disc O very an D high-order corre L ation d E tection ( NOODLE ), seeking an informative target subspace representation compatible across multiple features to facilitate the downstream clustering task. Specifically, we first exploit the self-representation mechanism to learn multiple view-specific affinity matrices, which are further decomposed into cohesive factors and incongruous factors to fit the multi-view consistency and discrepancy, respectively. Additionally, an explicit cross-view sparse regularization is applied to incoherent parts, ensuring the consistency and discrepancy to be precisely separated from the initial subspace representations. Meanwhile, the multiple cohesive parts are stacked into a three-dimensional tensor associated with a tensor-Singular Value Decomposition (t-SVD) based weighted tensor nuclear norm constraint, enabling effective detection of the high-order correlations implicit in multi-view data. Our proposed method outperforms state-of-the-art methods for multi-view clustering on six benchmark datasets, demonstrating its effectiveness.

Price Prediction and Determination of the Affecting Variables of the Real Estate by Using X-Means Clustering and CART Decision Trees

The use of machine learning in real estate is quite new. When the working area is large, the factors affecting the price may vary according to the geographical regions and socioeconomic factors. It is thought that the price prediction performance of a model that will reflect these differences will be more successful than a general model. Unsupervised learning methods can be used both to increase performance and to show the variation of different factors affecting the price according to regions. With this aim, a hybrid model of X-Means clustering and CART decision trees was established in this study.  This model successfully learned the geographical and physical variables that affect the price. The prediction performance of the model was compared with the direct capitalization method, which is the gold standard in the domain. The hybrid model has a superior performance over direct capitalization in terms of mean square error, root mean square error and adjusted R-Squared metrics. The scores were 72.86, 0.0057 and 0.978, respectively. The effect of clustering was also examined. Clustering increased the prediction performance by 36%. 

Cluster Analysis of MSMES In Suleja, Nigeria: Insights From Fuzzy C-Means Clustering And T-SNE Visualizations

This study employs cluster analysis to segment Micro, Small, and Medium-sized Enterprises (MSMEs) in Suleja, Nigeria into distinct groups based on their financial and operational characteristics. We utilize Fuzzy C-Means Clustering and t-Distributed Stochastic Neighbor Embedding (t-SNE) visualizations to uncover hidden patterns and structures in the data. Our results reveal three distinct clusters, explaining 40.3% of the variance in the data (R² = 0.403). The clusters exhibit reasonable separation (Silhouette coefficient = 0.360) and distinct patterns in their variable means. Cluster 1 comprises high-performing MSMEs with high levels of engagement, participation, and satisfaction. Cluster 2 consists of low-performing MSMEs with low levels of engagement, participation, and satisfaction. Cluster 3 represents moderate-performing MSMEs with balanced levels of engagement, participation, and satisfaction. t-SNE visualizations confirm the clustering structure, revealing three distinct groups with varying densities and separation. The visualizations also highlight the relationships between the clusters, with Cluster 1 and Cluster 3 showing higher similarity than Cluster 2. Model performance metrics indicate a reasonable accuracy (Pearson's γ = 0.440) and a good balance between within-cluster sum of squares and between-cluster sum of squares (Calinski-Harabasz index = 13.087). The findings provide valuable insights for policymakers and practitioners seeking to support MSMEs in Nigeria. The results suggest that targeted interventions and support programs should focus on enhancing engagement, participation, and satisfaction among MSMEs, particularly for those in the low-performing cluster. The study contributes to the literature on MSMEs and cluster analysis, demonstrating the effectiveness of Fuzzy C-Means Clustering and t-SNE visualizations in uncovering meaningful patterns in MSMEs data.

Investigating the catalytic activity of Mgn (n = 4–8) clusters for the hydrogen evolution reaction using density functional theory

AbstractTo efficiently desorb H2, pure Mgn (n = 4–8) clusters were chosen for the hydrogen evolution reaction with H2O. At the PBE0/def2‐TZVP level and the PBE0‐D3/def2‐TZVP level, the lowest energy structures of Mgn (n = 4–8) clusters and the most stable structures of Mgn@H2O (n = 4–8) complexes were searched in the local region. The transition state was predicted, and then the hydrogen evolution reaction channel was obtained by using the intrinsic reaction coordinate (IRC) to confirm the transition state. To better analyze the hydrogen reaction mechanism, the character of Mgn@H2O (n = 4–8) complexes and MgnO (n = 4–8) clusters, as well as the atomic charge change trend, were investigated using interaction region indicator function analysis (IRI) and natural population analysis (NPA). The reaction effect of Mg4 cluster and H2O is the worst. The energy barrier does, however, progressively lower as the cluster atom count rises, improving the reaction effect.

A new model for bubble cluster dynamics in a viscoelastic media

Bubble cluster dynamics in viscoelastic media is instructive for ultrasound diagnosis and therapy. In this paper, we propose a statistical model for bubble cluster dynamics in viscoelastic media considering the radius distribution of bubble nuclei. By investigating and comparing the response for a bubble in three conditions: single bubble; multi-bubble with the same radius; multi-bubble with different radius, the following rules are found: The promotion or suppression of the bubble cluster on the bubble vibration is not monotonous with the increase of the number of bubbles. The promotion or suppression of the bubble cluster on the bubble vibration varies alternately with the frequency. The effect of bubble cluster on bubble vibration is mostly suppressed when the driving acoustic pressure amplitude pa is high (5000 kPa). Usually, the bubble cluster promotes the vibration of the large bubbles (R0 = 10 μm) more, or suppresses it less.

The Size and Charge Effect of Pt Cluster on the Electrocatalytic Activity Toward the First Step of Dehydrogenation of Methanol

Abstract The O–H/C–H scission of methanol on Pt clusters is a crucial step in direct methanol fuel cells applications. The first dehydrogenation process of methanol on Ptnq clusters (n = 5, 13, 19; q = 0, +1, −1) in various charge states is studied. Our findings indicate that methanol adsorbs more easily on cationic Ptn+ than on neutral Ptn or anionic Ptn−. However, the adsorption capacity of methanol on Ptnq gradually decreases with increasing cluster size, especially for CH3OH on Ptn+, which decreases significantly (from −57.61 kcal/mol to −16.41 kcal/mol). Compared with Ptn and Ptn+, the energy barrier of O–H/C–H bond cleavage is significantly reduced by injecting an electron into Ptn to form Ptn−, and the activity of the catalyst is improved. However, the energy barrier of O–H/C–H cleavage increases gradually with cluster size, leading to a decrease in catalytic activity. The effect of charge weakens as cluster size increases, and small clusters with injected electrons exhibit better catalytic activity.

The clustering effects of current smoking status, overweight/obesity, and physical inactivity with all-cause and cause-specific mortality risks in U.S. adults

ObjectiveTo estimate the associations of smoking, weight status and physical inactivity with all-cause and cause-specific deaths, and the advanced rate period (RAP) to determine how early death was advanced among United States (U.S.) adults aged 18 years or older. MethodsWe used data from the third National Health and Nutrition Examination Survey (NHANES III) and the 2019 Linked Mortality File (LMF) with a follow-up period of 21.6 years (n = 16,612, including 7,278 deaths). Smoking, weight status, and physical inactivity were obtained from NHANES III and mortality outcomes from the 2019 LMF. Cox regression was used to estimate hazard ratios, RAPs and their corresponding confidence intervals. ResultsFor adults who currently smoke, were obese and physically inactive, the rate of dying from all-cause, CVD, and cancer was at least 231 % greater than for those who never smoked, were normal weight and physically active. The RAPs associated with the clustering of these risk factors for all cause, CVD- and cancer-specific cause of deaths were 13.0, 12.1 and 18.9 years older, respectively. ConclusionsOur findings underscore the need to focus on modifiable risk factors for illness prevention and health promotion and call attention to the increasing clustering of unhealthy risk factors in the U.S. population.

Resolvent analysis of turbulent flow laden with low-inertia particles

We extend the resolvent framework to two-phase flows with low-inertia particles. The particle velocities are modelled using the equilibrium Eulerian model. We analyse the turbulent flow in a vertical pipe with Reynolds number of $5300$ (based on diameter and bulk velocity), for Stokes numbers $St^+=0-1$ , Froude numbers $Fr_z=-4,-0.4,0.4,4$ and $1/Fr_z = 0$ (gravity omitted). The governing equations are written in input–output form and a singular value decomposition is performed on the resolvent operator. As for single-phase flows, the operator is low rank around the critical layer, and the true response can be approximated using one singular vector. Even with a crude forcing model, the formulation can predict physical phenomena observed in Lagrangian simulations, such as particle clustering and gravitational effects. Increasing the Stokes number shifts the predicted concentration spectra to lower wavelengths; this shift also appears in the direct numerical simulation spectra and is due to particle clustering. When gravity is present, there are two critical layers, one for the concentration field, and one for the velocity field. For upward flow, the peak of concentration fluctuations shifts closer to the wall, in agreement with the literature. We explain this with the aid of the different locations of the two critical layers. Finally, the model correctly predicts the interaction of near-wall vortices with particle clusters. Overall, the resolvent operator provides a useful framework to explain and interpret many features observed in Lagrangian simulations. The application of the resolvent framework to higher $St^+$ flows in combination with Lagrangian simulations is also discussed.

Single-cell RNA sequencing reveals that an imbalance in monocyte subsets rather than changes in gene expression patterns is a feature of postmenopausal osteoporosis.

The role of monocytes in postmenopausal osteoporosis is widely recognized; however, the mechanisms underlying monocyte reprogramming remain unknown. In this study, single-cell RNA sequencing (scRNA-seq) was conducted on CD14+ bone marrow monocytes obtained from 3 postmenopausal women with normal BMD and 3 women with postmenopausal osteoporosis (PMOP). Monocle2 was used to classify the monocytes into 7 distinct clusters. The proportion of cluster 1 significantly decreased in PMOP patients, while the proportion of cluster 7 increased. Further analysis via GSEA, transcription factor activity analysis, and sc-metabolic analysis revealed significant differences between clusters 1 and 7. Cluster 7 exhibited upregulated pathways associated with inflammation, immunity, and osteoclast differentiation, whereas cluster 1 demonstrated the opposite results. Monocle2, TSCAN, VECTOR, and scVelo data indicated that cluster 1 represented the initial subset and that cluster 7 represents one of the terminal subsets. BayesPrism and ssGSEA were employed to analyze the bulk transcriptome data obtained from the GEO database. The observed alterations in the proportions of 1 and 7 were validated and found to have diagnostic significance. CD16 serves as the marker gene for cluster 7, thus leading to an increased proportion of CD16+ monocytes in women with PMOP. Flow cytometry was used to assess the consistency of outcomes with those of the bioinformatic analysis. Subsequently, an additional scRNA-seq analysis was conducted on bone marrow mononuclear cells obtained from 3 patients with PMOP and 3 postmenopausal women with normal BMD. The differential proportions of cluster 1 and cluster 7 were once again confirmed, with the pathological effect of cluster 7 may attribute to cell-cell communication. The scRNA-seq findings suggest that an imbalance in monocyte subsets is a characteristic feature of PMOP. These findings elucidate the limitations of utilizing bulk transcriptome data for detecting alterations in monocytes, which may influence novel research inquiries.

A Web-Based and Mobile Intervention Program Using a Spaced Education Approach for Workplace Mental Health Literacy: Cluster Randomized Controlled Trial.

Workplace mental health is an important global health concern. This unblinded, phase-III, wait-listed cluster randomized controlled trial aimed to examine the effectiveness of a mobile health (mHealth) psychoeducation program using a spaced education approach on mental health literacy (MHL) in the workplace. The main interest of this paper was the immediate and 3-month medium-term effect of the program on the MHL of workers. The purposely built mHealth platform was also evaluated as a health-related app. The mHealth platform was designed using the principle of spaced education as a psychoeducation intervention program, with various modules of web-based and mobile materials presented to the participant in a progressive manner. Short quizzes at the end of each module ensured adequate learning, and successful completion qualified the learner to progress to the next level. The trial recruited 456 employees of specific industries with high levels of work-related stress. Participants who were nested in different offices or units were allocated into the intervention and wait-listed control groups using a block randomization process, with the office or unit as the cluster. A separate sample of 70 individual raters were used for the evaluation of the mHealth platform. The Australian National MHL and Stigma Survey and the Mobile Apps Rating Scale were completed through a web-based self-reported survey to assess MHL and evaluate the app. The trial and follow-up data were analyzed by a generalized linear latent and mixed model with adjustments for the clustering effect of work sites and repeated measures. Of the 456 participants in the trial, 236 (51.8%) responded to the follow-up survey. Most MHL outcomes obtained significant results immediately after the intervention and across time. After adjusting for the clustering effect, the postintervention weighted mean scores were significantly higher in the intervention group than the control group for correct recognition of a mental health problem, help seeking, and stigmatization by 0.2 (SE 0.1; P=.003), 0.9 (SE 0.2; P<.001), and 1.8 (SE 0.4; P<.001), respectively. After adjusting for the clustering effect, significant differences across time were found in help-seeking intention (P=.01), stigmatization (P<.001), and social distancing (P<.001). The evaluation of the mHealth program resulted in average scores of the 4 major domains ranging from 3.8 to 4.2, with engagement having the lowest score. The mHealth psychoeducation intervention program using this platform had immediate and 3-month medium-term effects of retaining and improving MHL. The platform was evaluated to have satisfactory performance in terms of functionality, aesthetics, information content, and utility in enhancing MHL. It is anticipated that ongoing development in digital health will provide great benefits in improving the mental health of the global population.

Mapping fear in financial markets: Insights from dynamic networks and centrality measures

Investor sentiment, particularly fear sentiment, significantly influences financial markets by increasing uncertainty and triggering extreme judgments during volatile periods. This study delves into the impact of fear sentiment on market dynamics and interdependencies between various financial assets, focusing on implied volatility indices for stocks, oil, gold, foreign currency, and bonds. The COVID-19 pandemic created an unprecedented economic shock in 2020, necessitating an examination of how fear sentiments propagated across these assets during times of crisis. By analyzing network dependencies and centralities, this research provides novel insights into financial market fear spillovers. It distinguishes itself by employing implied volatilities instead of historical volatilities and investigating these dynamics during the pandemic. The fear indices, specifically stock and Eurocurrency (stock and gold), exhibited the highest dependency effects during COVID-19 (Russia-Ukraine war), with clustering effects among these indices. We notice also that stock and Eurocurrency (Stock and gold) played a central role in connecting various fear indices, during extreme market conditions. The study also uncovers time-varying dependencies among the fear indices of the considered variables in this study, offering a comprehensive understanding of how extreme events like the pandemic impact financial market fear. This research contributes to the literature on financial market interdependencies during periods of fear, helping investors and policymakers make informed decisions about asset allocation, policy development, and risk assessment in times of financial distress.

Study on cluster centers optimization of max-min distance k-means clustering algorithm based on inter-cluster separation measure

Clustering is an essential unsupervised technique when category information is not available. Although K-means and Max-min distance K-means clustering algorithms are widely used, they have some disadvantages such as dependence on the initial centers, sensitivity to outliers caused by using only distance as the clustering criterion. To overcome the problems, this paper proposes SMM-K-means algorithm which overcomes the dependence on the initial cluster centers and the initial number of clusters and the sensitivity to the outliers. First, the initial value K of the optimal cluster number is determined by the elbow method, and K-means is used for initial clustering. A new inter-cluster separation measure is then constructed based on the idea of q-nearest neighbors, which is constructed by comprehensive considering the separation between clusters and the distribution compactness of clusters themselves. Finally, the two sample points with highest degree of separation are brought into Max-min distance K-means algorithm as new initial centers for clustering. The definite determining method of cluster centers eliminates the complicated iterative calculation, and the construction of inter-cluster separation measure overcomes the sensitivity of clustering results to noise points and isolated points, and has good applicability and generalization. In addition, this algorithm is not limited by the shape and size of the clusters and has better flexibility. The experimental results show that the SMM-K-means algorithm has higher CH values, resulting in a better clustering effect and stability.

A participatory and comprehensive intervention to improve violence prevention in two high-risk occupations: effect and process evaluation of a stepped wedge cluster randomised trial

BackgroundWork-related violence committed by clients, patients, and customers represents a major occupational health risk for employees that needs to be reduced.MethodsWe tested a comprehensive violence prevention intervention involving active participation of both employees and managers in the Prison and Probation Service (PPS) and on psychiatric wards in Denmark. We used a stepped wedge cluster randomised controlled trial design. We measured the degree of implementation of the intervention by registration of fidelity, reach, and dose and used a mixed-effects regression analysis to estimate the effects of the intervention.ResultsWe recruited 16 work units for the intervention, but three work units dropped out. The average implementation rate was 73%. In the psychiatric wards, the intervention led to statistically significant improvements in the primary outcome (an increase in the degree to which managers and employees continuously work on violence prevention practices based on their registration and experiences), but none statistically significant improvements in any of the secondary outcomes. In the PPS units, the intervention did not lead to a statistically significant improvement in the primary outcome, but to statistically significant improvements in three secondary outcomes.ConclusionMost work units were able to carry out the intervention as planned. The intervention showed mixed results regarding the primary outcome. Nevertheless, the results indicate improvements also in the sector where a change in the primary outcome was not achieved. The results point at that a participatory and comprehensive approach could be a viable way of working with violence prevention in high-risk workplaces.Trial registrationISRCTN86993466: 20/12/2017

Clustering of lifestyle risk factors in relation to suicidal thoughts and behaviors in young adolescents: a cross-national study of 45 low- and middle-income countries

BackgroundPrior research has reaffirmed lifestyle risk behaviors to cluster among adolescents. However, the lifestyle cluster effect on suicidal thoughts and behaviors (STBs) was unclear among adolescents in low- and middle-income countries (LMICs). No comparison of such associations was conducted across nations.MethodsData from 45 LMICs were obtained from the Global School-based Student Health Survey (GSHS) between 2009 and 2019. Lifestyle behavior factors were collected through a structured questionnaire. Suicidal ideation, plan, and attempt were ascertained by three single-item questions. Lifestyle risk scores were calculated via a sufficient dimension reduction technique, and lifestyle risk clusters were constructed using a latent class analysis. Generalized linear mixed models with odds ratio (OR) and 95% confidence interval (CI) were used to estimate the lifestyle-STB associations.ResultsA total of 229,041 adolescents were included in the final analysis. The weighted prevalence of suicidal ideation, plan, and attempt was 7.37%, 5.81%, and 4.59%, respectively. Compared with the favorable lifestyle group, the unfavorable group had 1.48-, 1.53-, and 3.11-fold greater odds of suicidal ideation (OR = 1.48, 95%CI: 1.30–1.69), plan (OR = 1.53, 95%CI 1.34–1.75), and attempt (OR = 3.11, 95%CI 2.64–3.65). Four clusters of lifestyle risk behaviors were identified, namely healthy lifestyles (H–L), insufficient intake of vegetables and fruit (V-F), frequent consumption of soft drinks and fast food (D-F), and tobacco smoking and alcohol drinking (S-A) clusters. Compared with H–L cluster, V-F cluster was associated with 43% and 42% higher odds of suicidal ideation and plan, followed by S-A cluster (26% for ideation and 20% for plan), but not significant in D-F cluster (P > 0.05). D-F cluster was associated with 2.85-fold increased odds of suicidal attempt, followed by V-F cluster (2.43-fold) and S-A cluster (1.18-fold).ConclusionsClustering of lifestyle risk behaviors is informative for risk stratification of STBs in resource-poor settings. Lifestyle-oriented suicide prevention efforts should be initiated among school-attending adolescents in LMICs.

Dynamics between energy intensity and carbon emissions: What does the clustering effect of labor and capital play?

Energy depletion and environmental degradation have emerged as pressing concerns in the era of China's high-quality green economic development. We present an integrated framework that incorporate energy consumption intensity, industrial clustering, and carbon emissions into the STIRPAT framework. Our study examines 30 Chinese provinces from 2006 to 2017. Unlike previous analyses, our study measures industrial clustering from two dimensions: labor and capital clustering. Specifically, the benchmark results confirm that a 1% increase in energy consumption intensity will, on average, raise regional carbon emission intensity by 0.03389%. Moderating analysis shows that labor and capital clustering significantly lower carbon emission intensity by reducing energy consumption. These findings have been consolidated after performing a panel vector autoregressive model. Interestingly, the promoting effect of energy consumption intensity on carbon emission intensity tends to be tightened when labor clustering surpasses a threshold. In contrast, the corresponding effects substantially weaken after capital clustering exceeds a threshold. In all, these findings provide new evidence to understand the energy-emission nexus from an industrial clustering perspective.

A Practical Guide to Power Analyses of Moderation Effects in Multisite Individual and Cluster Randomized Trials

Multisite trials that randomize individuals (e.g., students) within sites (e.g., schools) or clusters (e.g., teachers/classrooms) within sites (e.g., schools) are commonly used for program evaluation because they provide opportunities to learn about treatment effects as well as their heterogeneity across sites and subgroups (defined by moderating variables). Despite the rich opportunities they present, a critical step in ensuring those opportunities is identifying the sample size that provides sufficient power to detect the desired effects if they exist. Although a strong literature base for conducting power analyses for the moderator effects in multisite trials already exists, software for power analysis of moderator effects is not readily available in an accessible platform. The purpose of this tutorial paper is to provide practical guidance on implementing power analyses of moderator effects in multisite individual and cluster randomized trials. We conceptually motivate, describe, and demonstrate the calculation of statistical power and minimum detectable effect size difference (MDESD) using highly accessible software. We conclude by outlining guidelines on power analysis of moderator effects in multisite individual randomized trials (MIRTs) and multisite cluster randomized trials (MCRTs).

Spatial variations and determinants of timely completion of vaccination in Ethiopia using further analysis of EDHS 2019 data: Spatial and multilevel analysis.

Timely vaccination is the practice of administering the vaccine within the first birthday of the child. Not vaccinating the child at the appropriate age is the cause of improper protection of diseases and can be a possible factor in death. The problem of not completing the vaccine in the scheduled period is a globally distributed problem, but especially in sub-Saharan African countries, it is a bottleneck to child health. Even if timely vaccination is crucial for reducing the impact of VPDs, there are no current national-level studies to generate conclusive and tangible evidence in Ethiopia. To assess spatial variations and determinants of timely completion of vaccination in Ethiopia using further analysis of EDHS 2019 data. The secondary data analysis of a community-based cross-sectional study design was employed among 3094 participants. Stata-14 software was used for data cleaning, recording, and analysis. Arc GIS version 10.3 and Kuldorff SAT scan version 9.6 software are used for spatial and SAT scan statistics. A multilevel mixed-effect binary logistic regression analysis was used to identify the predictors of timely vaccination. The clustering effect was also evaluated by Moran's I statistics and intra class correlation. The timely completion of vaccination among Ethiopian women who had a child aged 12-35 months was 19.5% (95%CI: 18.2-20.8), and the spatial distribution of timely completion of vaccinations in Ethiopia was non-randomly distributed. A statistically significant high proportion of timely completion areas were clustered in the eastern part of Amhara, the south part of Afar, Addis Ababa, and Oromia. The primary cluster was located at a 13.11 km radius in Diredawa, which was 3.68 times higher than outside the window (RR = 3.68, LLR = 68.76, p-value < 0.001). History of antenatal care follow-up (AOR = 1.63, 95% CI: 1.3-2.04), giving birth at health facilities (AOR = 1.63, 95% CI: 1.25-2.13), age ≥ 35 years (AOR = 186, 95% CI: 1.35-2.63), age 25-34 years (AOR = 1.72, 95% CI: 1.33-2.21), and being richest (AOR = 2.71, 95% CI: 1.86-3.94) were the factors contributing to the timely completion of vaccination. The prevalence of timely completion of vaccination was low in Ethiopia, and the spatial distribution of timely completion of vaccination in Ethiopia was non-randomly distributed across the regions. The factors associated with the timely completion of vaccinations were ANC follow-up, place of delivery, age of the participant, and wealth index. We recommend expanding facility delivery, antenatal care services, and empowering women to scale up timely vaccination in Ethiopia.

Effectiveness of digital marketing and its value in new ventures

This paper analyzes the effect of digital marketing and cluster membership on the entrepreneurship and performance of dental clinics in Colombia. The use of different digital marketing tools in dental clinics is evaluated, and the effect of these tools on the creation of new markets, and clinics’ services and general performance, are analyzed. In addition, the cluster effect on the learning and implementation of digital tools in individual clinics is studied. The results show the most effective digital tools to create new markets, as well as the tools that improve clinics’ performance through the Internet image and online visibility. The combined use of corporate Facebook and Instagram, a robust website with wide online visibility and YouTube develops the image of companies on the Internet in the most effective way. In addition, the importance of belonging to a cluster in the learning and implementation of digital tools in individual clinics was verified.

Clustering Analysis of Hotel Network Reviews Based on Text Mining Method

With the development of information technology, users use online platforms to post real-time online comments to express their preferences and opinions on goods or services. Online review information expresses users' behavioral habits and special preferences. In depth, analysis of hotel online reviews can improve the adaptability of hotel services to user needs. Effective mining of the vast user review data will provide value for the development of the tourism industry. Using text mining methods to process hotel review data, multiple clustering methods were compared and analyzed for positive and negative feature words from the perspective of user experience. It was found that the k-means++ algorithm had a better clustering effect on user network reviews and achieved better clustering and segmentation of user evaluation information. Unsupervised clustering analysis can be used to further classify online comment information into categories based on positive and negative reviews, providing intellectual support for improving the precision and personalized service quality of hotels.

Data science integrated with computational fluid dynamics for particle collision modeling in fluidized bed

Fluidized beds are critical in numerous industrial applications, including chemical processing and energy production. Accurate modeling of solid particles and fluids within these beds is essential for process optimization and improved efficiency. In this study, we developed a machine learning model to predict the coefficient of restitution (COR) of solid particles in fluidized beds. Four variables—collision velocity, effective temperature, effective mass, and effective elastic modulus—were used in the model. Our dataset comprised 2446 data points from previous literature. We employed self-organizing map (SOM) and artificial neural network (ANN) approaches for data analysis. The initial ANN model, which did not incorporate data clustering, exhibited an impressive coefficient of determination (R-squared) of 0.989, indicating its high accuracy. To enhance the model further, we clustered the data into four groups using SOM and developed separate ANN models for each group. All four models achieved R-squared greater than 0.99, illustrating the effectiveness of data clustering. The resulting model can be integrated into simulation software, such as MFIX, to provide a more precise representation of fluidized bed behavior across various industrial settings. The findings emphasize the potential of machine learning models to enhance fluidized bed simulations, leading to increased efficiency and cost-effectiveness in industrial processes. Future studies should explore the inclusion of additional variables and extend the model's application to different industrial processes. Additionally, incorporating recommendations for optimizing fluidized bed behavior based on the model's predictions would provide valuable insights for process engineers.