Optimal Clustering Research Articles

Route Optimization and Optimal Cluster Head Selection for Cluster-Oriented Wireless Sensor Network Utilizing Circle-Inspired Optimization Algorithm

A wireless sensor network (WSN)'s lifespan and optimal orientation are greatly increased by clustering. Clustering selects non-cluster heads (NCHs) and cluster heads (CHs) and integrates sensor nodes via clusters. The purpose of this research is to find the best route and select the best cluster head for the WSN with the help of optimization methodology. The adaptive multi-path routing protocol (AMPRP), which is best chosen utilizing the circle-inspired optimization algorithm (CIOA) algorithm, is proposed in this study as a method for choosing NCHs and CHs. The optimal CHs have been chosen after the probabilities have been calculated, and the findings have been utilized to identify the optimal shortest path employing the same CIOA. To find the best route, the CIOA algorithm employs a fitness function made out of a network. The superiority of the proposed model is demonstrated by validating it with various state-of-the-art methods in terms of distinct analysis. The proposed AMPRP-CIOA for the optimal route and CH selection model in terms of energy consumption is 85.71%, 86.67%, 88.89%, and 77.78% better than EAHPW-TOPSIS, DA-EECHS, GEEC, and EADCR, respectively.

Whole slide image based prognosis prediction in rectal cancer using unsupervised artificial intelligence

BackgroundRectal cancer is a common cancer worldwide and lacks effective prognostic markers. The development of prognostic markers by computational pathology methods has attracted increasing attention. This paper aims to construct a prognostic signature from whole slide images for predicting progression-free survival (PFS) of rectal cancer through an unsupervised artificial intelligence algorithm.MethodsA total of 238 patients with rectal cancer from two datasets were collected for the development and validation of the prognostic signature. A tumor detection model was built by transfer learning. Then, on the basis of the tumor patches recognized by the tumor detection model, a convolutional autoencoder model was built for decoding the tumor patches into deep latent features. Next, on the basis of the deep latent features, the tumor patches were divided into different clusters. The cluster number and other hyperparameters were optimized by a nested cross-validation method. The percentage of each cluster from the patient’s tumor patches, which is hereafter called PCF, was calculated for prognostic signature construction. The prognostic signature was constructed by Cox proportional hazard regression with L2 regularization. Finally, bioinformatic analysis was performed to explore the underlying biological mechanisms of the PCFs.ResultsThe accuracy of the tumor detection model in distinguishing tumor patches from non-tumor patches achieved 99.3%. The optimal cluster number was determined to be 9. Therfore, 9 PCFs were calculated to construct the prognostic signature. The prognostic signature achieved a concordance index of 0.701 in the validation cohort. The Kaplan-Meier survival curves showed the prognostic signature had good risk stratification ability. Through the bioinformatic analysis, several PCF-associated genes were identified. These genes were enriched in various gene ontology terms.ConclusionThe developed prognostic signature can effectively predict PFS in patients with rectal cancer and exploration of the underlying biological mechanisms may help to promote its clinical translation.

Green Optimization with Load balancing in Wireless Sensor Network using Elephant Herding Optimization

Wireless sensor networks (WSNs), which provide sensing capabilities to Internet of Things (IoT) equipment with limited energy resources, are made up of specialized transducers. Since substitution or re-energizing of batteries in sensor hubs is extremely difficult, power utilization becomes one of the pivotalmattersin WSN. Clustering calculation assumes a significant part in power management for the energy-compelled network. Optimal cluster head selection suitably adjusts the load in the sensor network, thereby reduces the energy consumption and elongates the lifetime of assisted sensors. This article centers around to an appropriate load balancing and routing technique by the utilization recently developed of Elephant Herding Optimization (EHO) algorithm that alternates the cluster location amongst nodes with the highest energy. The Scheme considered various parameter residual energy, initial energy and an optimum number of cluster head for the next cluster heads selection. The proposed model increases the lifetime of the network by keeping more nodes active even after the 2700th round. The experiment results of the trials show that the proposed EHO-based CH selection strategy outperforms the cutting-edge CH selection models.

Heterogeneity Assessment and Protein Pathway Prediction via Spatial Lipidomic and Proteomic Correlation: Advancing Dry Proteomics concept for Human Glioblastoma Prognosis.

Prediction of proteins and associated biological pathways from lipid analyses via MALDI MSI is a pressing challenge. We introduced "dry proteomics," using MALDI MSI to validate spatial localization of identified optimal clusters in lipid imaging. Consistent cluster appearance across omics images suggests association with specific lipid and protein in distinct biological pathways, forming the basis of dry proteomics. The methodology was refined using rat brain tissue as a model, then applied to human glioblastoma, a highly heterogeneous cancer. Sequential tissue sections underwent omics MALDI MSI and unsupervised clustering. Spatial omics analysis facilitated lipid and protein characterization, leading to a predictive model identifying clusters in any tissue based on unique lipid signatures and predicting associated protein pathways. Application to rat brain slices revealed diverse tissue subpopulations, including successfully predicted cerebellum areas. Similarly, the methodology was applied to a dataset from a cohort of 50 glioblastoma patients, reused from a previous study. However, among the 50 patients, only 13 lipid signatures from MALDI MSI data were available, allowing for the identification of lipid-protein associations that correlated with patient prognosis. For cases lacking lipid imaging data, a classification model based on protein data was developed from dry proteomic results to effectively categorize the remaining cohort.

Comparison of K-Means and FCM Algorithms to Optimize Spatiotemporal Pore Pressure Prediction of Earth Dams

To identify the behavior and health monitoring of dams, it is necessary to correctly interpret the results of instrumentation in different phases of construction, impounding, and operation. Therefore, the approach based on spatiotemporal prediction is presented to improve the interpretation of pore pressure behavior of Eyvashan Earth Dam. In this research, using the results of other existing healthy piezometers, a spatiotemporal distribution model is proposed using panel data, which can be effective for predicting and reconstructing missing data. The optimal spatiotemporal clustering of pore pressure changes monitoring with K-Means and Fuzzy C-means (FCM) algorithms will enable the monitoring of points of the dam where instrumentations are not designed and installed or defective instrumentations. In predicting the pore pressure of dams, the input data is classified based on the pore pressure monitoring data, but with the use of clustering algorithms, the classification after the cluster analysis steps will lead to the proper resolution of the pore pressure clustering. According to the validation results of each of the clustering algorithms, the FCM clustering algorithm has more suitable results than the K-Means algorithm in determining the pore pressure clusters. In general, FCM clustering and K-Means algorithms are suitable and efficient tools in the field of more accurate monitoring of earth dams, and by using the proposed method, the detection of unusual areas of pore pressure and the related safety diagnosis is facilitated.

Multi-view subspace clustering with a consensus tensorized scaled simplex representation

Multi-view clustering has been at the forefront of research focused on identifying an ideal structure for the rational partitioning of sample points. Multi-view clustering faces two main challenges: identifying the optimal structure within each view and fusing these structures into a reliable consensus matrix. To overcome these obstacles, we introduce the Consensus Tensorized Scaled Simplex Representation (CTSSR). First, CTSSR uses the scaled simplex representation to reveal the structure within each view flexibly. Second, we apply a rank constraint strategy to ensure that the learned subspace structure embodies the optimal clustering structure. To fuse multiple views, we propose a normalized view weighting mechanism based on each view's reconstruction error, ensuring reasonable contributions to the consensus matrix. Finally, we employ tensor learning on weighted subspace views to explore high-order correlations and subtle differences between views, refining the exploration of inter-view relationships. CTSSR combines intra-view structure exploration with inter-view relationship analysis, resulting in an ideal consensus matrix. It shows excellent clustering performance on real-life datasets, significantly outperforming state-of-the-art methods in various experimental settings.

An autoencoder-based arithmetic optimization clustering algorithm to enhance principal component analysis to study the relations between industrial market stock indices in real estate

An autoencoder-based arithmetic optimization clustering algorithm to enhance principal component analysis to study the relations between industrial market stock indices in real estate

Improving subsurface structural interpretation in complex geological settings through geophysical imaging and machine learning

This study employs seismic refraction tomography (SRT) and electrical resistivity tomography (ERT) to assess subsurface geological conditions along the proposed Porsgrunn Highway in Norway. The primary objective is to analyze SRT and ERT tomograms to identify subsurface geological structures. However, interpreting tomograms is often limited by smoothed boundaries and reduced resolution. To address these challenges, we apply k-means clustering, a machine learning technique that groups data based on similarities in physical properties, to post-process the geophysical tomograms. This study pioneers the use of k-means clustering to interpret tomograms from SRT and ERT data in complex geological settings. We first evaluate the effectiveness of clustering techniques using numerical modeling for two geological scenarios: a horizontally layered case and a layered case with undulation and a fault structure. Utilizing automated methods (Elbow and Silhouette), we objectively determine the optimal number of clusters for each geophysical tomogram. Subsequently, we compare the performance of the k-means clustering algorithm with subjective expert interpretations and the Laplacian edge detection method. Borehole data validate the clustering results and confirm the effectiveness of optimal cluster selection techniques. The findings of this study demonstrate that k-means clustering significantly enhances the detection of geological structures by establishing clearer boundaries and minimizing noise interference, enabling more accurate fault zone delineation. Compared to traditional edge detection and subjective interpretation methods, k-means clustering offers a systematic and objective approach that improves consistency and reliability across diverse geological settings. Moreover, its automated classification of geophysical data into meaningful clusters enables efficient analysis of large datasets. This study underscores the value of integrating machine learning techniques with geophysical methods such as SRT and ERT to improve interpretability and accurately identify subsurface geological structures, particularly in fault zone identification.

A new approach for assessing the contribution of Ground Motions Frequency Content and Soil-Structure Interaction to the Seismic Response of Reinforced Concrete Moment Frames

One of the key steps in the seismic resilience assessment of buildings is gaining insight into their seismic response. The frequency content of ground motions and the dynamic characteristics of the building contribute mutually to the seismic response of the entire system (soil + structure). This study aims to present a new approach to assess the effects of the soil structure interaction (SSI) and of the frequency content of the ground motion. A case study of reinforced concrete moment frames (RCMFs) is herein presented by applying 280 ground motion time history records, which were registered on site classes A and B (based on ASCE 7–16). To this end, initially the characteristics of the input motions (e.g. amplitude and frequency content) were calculated, and then the time histories were partitioned into three clusters based on two optimal clustering features, namely Peak Ground Acceleration to Peak Ground Velocity ratio (PGA/PGV) and F5 (representing the frequency associated with 5% of total power in cumulative power spectral density, PSD). The clustering were done by implementing an unsupervised machine learning (ML) algorithm (i.e. K-means clustering), also the number of clusters was achieved using a well-known method in ML literature. Several time histories from each of the clusters were randomly selected to perform incremental dynamic analysis (IDA) on a 6- and a 10-story RCMF. Two different base conditions were considered: fixed-based (SSI neglected) and flexible-base (considering SSI effects). The findings demonstrate the contribution of frequency content and SSI to the seismic response of RCMFs, and also present an approach for considering frequency content in seismic analysis.

Stress shadow effects in multistage horizontal hydrofracturing of tight reservoirs: a numerical analysis considering perforation cluster spacings and fracturing sequences

AbstractMultistage horizontal fracturing technology of reservoirs has been widely used to enhance tight hydrocarbon resource recovery. Determining the proper perforation cluster spacing is crucial to developing a complex fracture network that connects natural rock fractures and facilitates gas flow in reservoirs. The stress shadow effect that occurs between multiple clusters has a significant effect on the development of the fracture network in reservoirs. The quantification of the stress shadow effect and its influences on the development of fracture networks has not been resolved satisfactorily due to experimental and numerical difficulties with detecting and identifying crack propagation and intersection in deep reservoirs. In this study, we used an adaptive finite element-discrete element method to analyze crack propagation and intersection in tight shale reservoirs by altering perforation spacings and fracture sequences. The effects of five perforation cluster spacings using sequential, simultaneous and parallel fracturing techniques were compared. The non-linear properties of shales, hydromechanical coupling and fluid leak-off effects, proppant transport, dual-rupture criteria of strength and energy, and intersection of hydraulic fractures were taken into account in the simulation. The areas affected by the stress shadow and the optimum perforation cluster spacing in terms of hydraulic fracture propagation lengths, volumes, and microseismic magnitudes were evaluated when adopting different fracturing methods. This study extends the understanding of the impact of the different independent factors that contribute to the stress shadow effect and, therefore, provides new information to help guide wellbore completion design in horizontal fracturing wells.

Optimization of thermal environment and airflow distribution in data center with row-based cooling using the Taguchi/TOPSIS method

The short air supply distance of the row-based cooling system improved the cooling efficiency. However, the row-based coolers are closer to the racks, resulting in high-speed airflow and airflow mixing problem in the aisles. The internal structure of a row-cooled cluster is closely related to the cooling effect, and existing studies neglect the synergistic effect of multiple factors on the thermal performance of the row-based cooling system, which is still controversial about the optimal form of a row-based cooling cluster. This study analyzes and presents row-based cooling system airflow problems through large-scale field experiments and simulation. All rows' supply heat index (SHI) exceeds 0.2, and the return temperature index (RTI) exceeds 100 %, indicating a poor thermal environment in the DC. Taguchi and TOPSIS methods were used to analyze the coupling effect on the number of racks, power density, hot and cold aisle width, cooler's location, server's location, and blanking panels of the cluster's thermal environment. The optimal row-based cooling cluster structure form for different rack numbers and power density was determined. In order to optimize the air supply path of the cooler to reduce the air supply stream's collision, the effects of deflectors with different structures installed at the cooler supply and return air vents on the thermal environment were analyzed based on the optimal cluster structure. In practice, it is recommended to install deflectors of 45° with 50 mm, 75° with 30 mm, or 70 mm in the air supply vent of the cooler to create a better thermal environment. After cluster and deflector optimization, temperature uniformity, vortex airflow, and hot spots in the cluster are improved. SHI, RTI, and standard deviation of each cluster's average inlet air temperature are all closer to the ideal values.

K-means Optimized Network Security Management in the Internet Context

The rapid development of the Internet has had a broad and profound impact on humanity, making information acquisition and dissemination more convenient. It has also brought significant opportunities and benefits to business and the economy. However, there are some issues, such as personal factors and data security concerns. In order to solve the above problems, the K-means algorithm is optimized from the perspectives of K-value validity index, feature weighting and three-branch decision making. First, the optimal clustering results are determined according to K-value validity index, and the influence of different dimensional features on clustering is considered for feature weighting, and the uncertain objects in the three-branch decision deadlock class are divided into the boundary domain. The delay decision of the boundary domain data is carried out, and the K-means clustering optimization algorithm is improved by combining the above three aspects, and the intelligent network security management system is developed on this basis. The results showed that the K-means optimization algorithm achieved the highest average accuracy rate, adjusted Morandi index, and adjusted mutual information across various datasets, with values of 96.01%, 0.866, and 0.869, respectively. In practical network attack scenarios, the K-means optimization algorithm attained an attack threat recognition accuracy of 94.38%. Under unknown network attack types, its detection rate and false alarm rate were 94.63% and 1.32%, respectively. Surveys conducted post-implementation of the intelligent network security management system indicated that over 90% of users were satisfied with their experience of the system. In summary, the proposed method accurately identifies potential network threats in network data, fulfilling performance requirements for network security management systems and ensuring the security of network resources.

Comprehensive vitality evaluation and spatio-temporal characteristics of nighttime tourism in Shenzhen: an empirical analysis based on multi-source data integration

ABSTRACT Nighttime tourism is emerging as a significant growth driver in the global tourism industry with substantial potential for development. A typical example of this trend is the Chinese city of Shenzhen, a globally leading hub for innovation, whose rapid development in this sector is both representative and pioneering. This study applies sentiment analysis, optimal clustering and other methodologies to evaluate the vitality and spatio-temporal characteristics of nighttime tourism in Shenzhen from diverse dimensions. Data were collected through various sources, including travel reviews, cellular signalling data, etc. Based on systems theory, the research explores the mechanisms behind Shenzhen’s nighttime tourism, looking at land use, spatio-temporal patterns, and accessibility. It further identifies several replicable development models. The findings not only offer innovative recommendations for Shenzhen’s nighttime tourism development but also provide valuable insights and practical guidance for similar port cities in China and even around the world.

A COMPARATIVE EVALUATING NUMERICAL MEASURE VARIATIONS IN K-MEDOIDS CLUSTERING FOR EFFECTIVE DATA GROUPING

The K-Medoids Clustering algorithm is a frequently employed technique among researchers for data categorization. The primary difficulty addressed in this investigation pertains to the extent of optimality achieved when varying distance computation methodologies are applied within the framework of K-Medoids Clustering. This study is primarily concerned with the application of K-Medoids Clustering, employing a multitude of distance calculation methods, specifically those involving numerical metrics. The aim is to undertake a comparative analysis of Davies-Bouldin Index (DBI) values in order to ascertain the most productive distance calculation technique. In this research, the distance calculation methodologies include Manhattan Distance, Jaccard Similarity, Dynamic Time Warping Distance, Cosine Similarity, Chebyshev Distance, Canberra Distance and Euclidean Distance. The dataset consists of sales data from Devi Cosmetics, covering the period between January and April 2022 and comprising 56 distinct sales items. The research provides an exhaustive evaluation of numerical metrics concerning the K-Medoids Clustering algorithm. The findings indicate that the optimal clustering is achieved using the Chebyshev distance, resulting in 9 clusters with a DBI value of 166.632. The study's contribution is that it can improve more optimal data grouping to help make decisions correctly.

Adaptive gravitational clustering algorithm integrated with noise detection

Clustering analysis is frequently used in data mining, image processing, artificial intelligence, and so on. Traditional approaches heavily rely on manually configured parameters, of which the initial selection exerts a profound influence on the clustering outcomes. In addition, they usually only consider the relationship between two individual samples when calculating distances, neglecting the overall structure of the dataset, which can negatively affect clustering performance. At the same time, many contemporary algorithms are tailored to specific datasets, posing challenges in achieving optimal clustering performance for intricate, noisy datasets. To address these limitations, we propose an Adaptive Gravitational Clustering Algorithm Integrated with Noise Detection called GCIND. Inspired by the law of gravitation, GCIND takes into account the natural neighborhood structure of the entire dataset, adaptively computing the gravitation between data points by leveraging shared neighbors and Euclidean distance relationships. Our algorithm initially identifies and eliminates outliers or edge points in the dataset. It subsequently uses gravitation to autonomously cluster the remaining core data. Finally, the removed data are reallocated to their respective clusters. GCIND has four notable advantages: (1) it uses gravitation to build the neighborhood graph, reflecting the overall dataset structure; (2) it demonstrates stronger robustness in handling noisy datasets; (3) it uses adaptive gravitational neighborhood graph clustering, removing manual parameter tuning; (4) it adapts to complex manifold-structured datasets, offering broad applicability. Experiments have shown that GCIND, without requiring any parameter settings, demonstrates slightly better performance than the algorithms compared in the study, especially when dealing with complex manifold datasets.

Energy efficient mobile sink driven data collection in wireless sensor network with nonuniform data

In wireless sensor network, mobile sink is used to collect data from sensor nodes by periodically traversing the network to prevent hotspot problem. However, when sensor nodes generate data non-uniformly, the efficiency of data collection is constrained by rendezvous points and network topology. It becomes more challenging under network energy consumption constraint. Thus, this paper investigates non-uniform data generation in wireless sensor network and proposes an innovative approach: Optimal Clustering and Network Topology for Mobile Sink-Driven Data Collection, called OCNTMS. It focuses on determining optimal rendezvous points and their associated clusters. Through innovative methods such as weight-balanced clustering, cost function optimization, load-balanced link construction, and node forwarding selection, the OCNTMS can efficiently construct link sets within clusters and accurately plan the mobile sink’s traversal of rendezvous points. Simulation results show that the OCNTMS reduces energy consumption by 18% and increases network lifetime by 40% compared with existing approaches under the constraint of non-uniform data generation. This greatly improves the network energy efficiency and data transmission efficiency.

A Raster-Based Multi-Objective Spatial Optimization Framework for Offshore Wind Farm Site-Prospecting

Siting an offshore wind project is considered a complex planning problem with multiple interrelated objectives and constraints. Hence, compactness and contiguity are indispensable properties in spatial modeling for Renewable Energy Sources (RES) planning processes. The proposed methodology demonstrates the development of a raster-based spatial optimization model for future Offshore Wind Farm (OWF) multi-objective site-prospecting in terms of the simulated Annual Energy Production (AEP), Wind Power Variability (WPV) and the Depth Profile (DP) towards an integer mathematical programming approach. Geographic Information Systems (GIS), statistical modeling, and spatial optimization techniques are fused as a unified framework that allows exploring rigorously and systematically multiple alternatives for OWF planning. The stochastic generation scheme uses a Generalized Hurst-Kolmogorov (GHK) process embedded in a Symmetric-Moving-Average (SMA) model, which is used for the simulation of a wind process, as extracted from the UERRA (MESCAN-SURFEX) reanalysis data. The generated AEP and WPV, along with the bathymetry raster surfaces, are then transferred into the multi-objective spatial optimization algorithm via the Gurobi optimizer. Using a weighted spatial optimization approach, considering and guaranteeing compactness and continuity of the optimal solutions, the final optimal areas (clusters) are extracted for the North and Central Aegean Sea. The optimal OWF clusters, show increased AEP and minimum WPV, particularly across offshore areas from the North-East Aegean (around Lemnos Island) to the Central Aegean Sea (Cyclades Islands). All areas have a Hurst parameter in the range of 0.55–0.63, indicating greater long-term positive autocorrelation in specific areas of the North Aegean Sea.

Cluster Validity for Optimizing Classification Model: Davies Bouldin Index – Random Forest Algorithm

Several factors impact pregnant women’s health and mortality rates. The symptoms of disease in pregnant women are often similar. This makes it difficult to evaluate which factors contribute to a low, medium, or high risk of mortality among pregnant women. The purpose of this research is to generate classification rules for maternal health risk using optimal clusters. The optimal cluster is obtained from the process carried out by the validity cluster. The methods used are K-Means clustering, Davies Bouldin Index (DBI), and the Random Forest algorithm. These methods build optimum clusters from a set of k-tests to produce the best classification. Optimal clusters comprising cluster members withstrong similarities are high-dimensional data. Therefore, the Principal Component Analysis (PCA) technique is required to evaluate attribute value. The result of the research is that the best classification rule was obtained from k-tests = 22 on the 20th cluster, which has an accuracy of 97% to low, mid, and high risk. The novelty lies in using DBI for data that the Random Forest will classify. According to the research findings, the classification rules created through optimal clusters are 9.7% better than without the clustering process. This demonstrates that optimizing the data group has implications for enhancing the classification algorithm’s performance.

Energy‐Aware Routing in WSN Utilizing Self‐Attention–Based Cycle‐Consistent Generative Adversarial Network With Honey Badger Algorithm

ABSTRACTEnergy efficiency and secure data transmission are considered as the main design targets of wireless sensor network (WSN). Previous energy‐aware cluster head (CH) selection approaches could not provide secured data transmission. To address this problem, a self‐attention–based cycle‐consistent generative adversarial network (SaCyCsGAN) with honey badger algorithm (HyBA)–adopted energy‐aware routing (EgAR) in WSN is proposed. Initially, the proposed system uses a CH to carry out the routing practice. Accordingly, SaCyCsGAN classifier is exploited for CH selection under firm fitness function: delay, distance, energy, cluster density, and traffic rate. Afterward CH selection, a spiteful node may enter the cluster and acts as a CH. Hence, best path selection is needed. For that, HyBA is utilized, it selects the best path depending upon triplet parameter: trust, connectivity, and service degree. Finally, data are conveying into base station (BS) and vice versa under best path. Finally, the proposed EgAR‐WSN‐SaCyCsGAN‐HyBA method attains 24.13%, 28.57%, 5.88%, and 20.37% higher throughput and 18.50%, 21.67%, 13.33%, and 22.22% lesser energy consumption evaluated to the existing methods such as multiple‐objective CH utilizing self‐attention basis progressive generative adversarial network for safe data aggregation (EgAR‐WSN‐SAPrGAN‐ArVOA), reinforcement learning–based energy‐efficient optimized routing protocol in WSN (EgAR‐WSN‐RLGT‐BCSA), data aggregation including clustering protocol in WSN under machine learning (EgAR‐WSN‐AfNN), and optimum cluster along trusted path for routing formation with categorization of intrusion under machine learning categorization (EgAR‐WSN‐RsBPDT‐HoCSOA).

APPLICATION OF AGGLOMERATIVE HIERARCHICAL CLUSTERING IN GROUPING TOURISM INDUSTRY SMES IN EAST JAVA

This study addresses a significant research gap in the classification and evaluation of Small and Medium Enterprises (SMEs) within the tourism industry in East Java, specifically focusing on their marketing performance. The primary objective is to categorize these SMEs based on their marketing effectiveness, a critical factor for their competitiveness in the tourism sector. To achieve this, the research employs cluster analysis, utilizing Agglomerative Hierarchical Clustering techniques. The optimal clustering method was determined using the cophenetic correlation coefficient and cluster validation indices. Data for the analysis were collected through questionnaires, with a sample comprising 30 tourism SMEs across 11 regions in East Java, with responses from three employees per SME. The findings revealed two distinct clusters: SMEs with fairly good marketing performance and those with good marketing performance. The results suggest that while many SMEs in the tourism industry in East Java exhibit competitive marketing capabilities, there remains a subset that requires strategic improvements, particularly in spiritual marketing practices. This study's novelty lies in its approach to classifying tourism SMEs by marketing performance, providing a framework for targeted performance enhancement and industry strengthening in the region.