Mini-batch K-means Research Articles

Monitoring and zoning soybean maturity using UAV remote sensing

Timely and accurate determination of the maturity status during the soybean harvest period is crucial for devising strategic harvesting plans, significantly enhancing the intelligent management of soybean production and minimizing losses. To explore the maturation dynamics of soybeans and pinpoint the precise maturity stage for optimal harvesting, we collected Unmanned Aerial Vehicle (UAV) remote sensing data, along with physical and chemical parameters, during the Beginning maturity(R7)-Full maturity(R8) stages from 2021 to 2022. We analyzed the variations in these parameters throughout the maturation period. Employing UAV multispectral technology and correlation analysis algorithms, we established a relationship between the spectral and physicochemical parameters during the maturation period, which led to the formulation of a soybean maturity evaluation index. Furthermore, we incorporated the concept of precision management zoning. In line with actual field production requirements, this index, combined with real-time moisture content, established a standard for grading soybean maturity. Additionally, our study examined the impact of spatial scale on maturity assessments by conducting a theoretical analysis of regionalized variables and analyzing the spatial correlations and variability of soybean maturity across different field plots. We determined the optimal theoretical model for various sampling distances, thereby establishing feasible zoning ranges. Comparative analysis of zoning algorithms, including Hierarchical Clustering (HC), K-Means, and its optimized versions K-Means++ and Mini Batch K-Means, was conducted using the partition performance index as the criterion. This analysis identified the most suitable algorithm for assessing soybean field maturity, which was subsequently verified through field tests. Results indicated that soybean leaf chlorophyll content and photosynthesis decreased sharply initially, then stabilized at a low rate. Water content in both soybean plants and seeds decreased rapidly before slowing, with plant dehydration rates exceeding those of the seeds. Green Normalized Difference Vegetation Index(GNDVI) showed a positive correlation with various physiological indicators, and soybean maturity was classified into three levels using the unit gridding management method, considering actual moisture content. Spatial correlation analysis of maturity variations in small and large test fields revealed Moran indices ranging from 0.78 to 0.95 and 0.70–0.90, respectively. Optimal detection ranges were determined to be 2.00–30.00 m for small fields and 2.00–67.00 m for large fields. The zoning categories for small and large fields were three and four, respectively. Comparative studies showed that the Mini Batch K-Means algorithm, an optimization of K-Means, achieved Calinski-Harabasz Index(CH) scores and silhouette coefficients of 10521.97, 109508.27, and 0.57, 0.54, respectively, indicating comparable zoning effectiveness to K-Means and K-Means++ and superiority over the HC algorithm. The zoning speeds were 12.50 s and 191.68 s, respectively, underscoring its efficiency in maturity zoning. Furthermore, zoning results corresponded well with actual soybean maturity. Terrain had little impact on soybean maturity, which was more susceptible to slope aspect. This study provides a theoretical foundation and practical guidelines for applying UAV remote sensing technology in determining soybean maturity and optimal harvesting periods, thereby reducing potential harvest losses.

Unsupervised method for detecting surface defects in steel based on joint optimization of pseudo-labeling and clustering

Abstract Advances in the field of measurement science and technology have improved the detection of defects in industrial production. One of the key challenges in steel plate surface defect detection is the need to quickly detect a small number of defects in an overwhelmingly defect-free sample. Unlike supervised learning, which relies heavily on precise sample labeling, unsupervised learning leverages its inherent learning capabilities for detection. This paper introduces an innovative method for smart steel diagnosis, integrating joint optimization of feature extraction and clustering. The proposed approach merges mini-batch K-Means clustering with a feature extraction network to acquire pseudo-label information for current images. It employs a multi-view transformation strategy, enabling classification through the optimized feedback from pseudo-labels. This method allows the network to self-optimize the distinction of image features through backpropagation. The method exhibits a mere 4% classification failure rate for steel surface images. This significant reduction in additional data processing requirements enhances the inspection system's efficiency and accuracy. Furthermore, the versatility of this method extends beyond steel defect diagnosis. It holds potential for application in various engineering domains, particularly in scenarios characterized by data imbalance.

Comparison of K-Means, Affinity Clustering, and Mini Batch K-Means Algorithms for Market Segmentation Analysis

Market segmentation is the process of dividing a market into homogeneous groups of buyers based on certain characteristics. Market segmentation is important for businesses to understand the needs and behaviors of their customers so that they can develop more effective marketing strategies.This study compares three clustering methods, namely K-Means Clustering, Affinity Propagation Clustering, and Mini Batch K-Means, in the context of market segmentation analysis. The data used is the marketing_campaign.csv dataset consisting of 29 columns and 2240 rows. Experiments were conducted to evaluate the performance of the three methods using the silhouette metric. The results of the experiments showed that Affinity Propagation produced the highest silhouette value of 0.5861, followed by K-Means with 0.4675, and Mini Batch K-Means with 0.4659. The finding indicates that Affinity Propagation can be a good choice for market segmentation analysis on that dataset. The results of this comparison provide insights into the strengths and weaknesses of each clustering method, helping users choose the approach that is most appropriate for their analytical goals. The study contributes to the practical understanding of the application of clustering techniques in the context of marketing.

Securing synthetic faces: A GAN-blockchain approach to privacy-enhanced facial recognition

In recent years, facial recognition technology has become increasingly integrated into society, making privacy protection crucial. Previous techniques offered minimal secrecy safeguards through simple obscuration methods. This paper addresses the strict privacy requirements of face image data by developing a novel framework that synergistically integrates Generative Adversarial Networks (GANs), clustering algorithms, and Blockchain technology. The methodology proposes a cutting-edge Privacy-Preserving Self-Attention GAN (PPSA-GAN) to generate realistic synthetic facial imagery. An integrated mini-batch K-means clustering algorithm anonymizes these images into distinct groupings, maximizing privacy preservation. Blockchain integration complements the system by fortifying trust through decentralized ledgers for transparent yet secure data storage and auditing. Rigorous benchmarking on the CelebA dataset confirms the PPSA-GAN architecture’s state-of-the-art performance, attaining an impressive Inception Score of 13.99 and a Fréchet Inception Distance of 35.50. The mini-batch clustering forms 125 distinct clusters, effectively anonymizing facial attributes within the synthetic images. Blockchain integration further bolsters privacy assurances via tamper-proof historical records, showcasing precision, recall, F1-score, and accuracy values of 0.948, 0.938, 0.943, and 0.947, respectively. This multifunctional framework represents a novel contribution, fostering an ethical technological ecosystem that balances progress and privacy. Prospective deployment horizons encompass identity verification, surveillance infrastructure, and augmentation of medical image repositories, seeding an enlightening future for facial recognition domains.

Debiased Novel Category Discovering and Localization

In recent years, object detection in deep learning has experienced rapid development. However, most existing object detection models perform well only on closed-set datasets, ignoring a large number of potential objects whose categories are not defined in the training set. These objects are often identified as background or incorrectly classified as pre-defined categories by the detectors. In this paper, we focus on the challenging problem of Novel Class Discovery and Localization (NCDL), aiming to train detectors that can detect the categories present in the training data, while also actively discover, localize, and cluster new categories. We analyze existing NCDL methods and identify the core issue: object detectors tend to be biased towards seen objects, and this leads to the neglect of unseen targets. To address this issue, we first propose an Debiased Region Mining (DRM) approach that combines class-agnostic Region Proposal Network (RPN) and class-aware RPN in a complementary manner. Additionally, we suggest to improve the representation network through semi-supervised contrastive learning by leveraging unlabeled data. Finally, we adopt a simple and efficient mini-batch K-means clustering method for novel class discovery. We conduct extensive experiments on the NCDL benchmark, and the results demonstrate that the proposed DRM approach significantly outperforms previous methods, establishing a new state-of-the-art.

IMPROVED PARALLEL BIG DATA CLUSTERING BASED ON K-MEDOIDS AND K-MEANS ALGORITHMS

In recent years, the amount of data created worldwide has grown exponentially. The increase in computational complexity when working with "Big data" leads to the need to develop new approaches for their clustering. The problem of massive data amounts clustering can be solved using parallel processing. Dividing the data into batches helps to perform clustering in a reasonable time. In this case, the reliability of the obtained result for each block will affect the performance of the entire dataset. The main idea of the proposed approach is to apply the k-medoids and k-means algorithms to parallel Big data clustering. The advantage of this hybrid approach is that it is based on the central object in the cluster and is less sensitive to outliers than k-means clustering. Experiments are conducted on real datasets, namely YearPredictionMSD and Phone Accelerometer. The proposed approach is compared with the k-means and MiniBatch k-means algorithms. Experimental results proved that the proposed parallel implementation of k-medoids with the k-means algorithm shows greater accuracy and works faster than the k-means algorithm.

Data-driven strategies for digital native market segmentation using clustering

The rapid growth of internet users and social networking sites presents significant challenges for entrepreneurs and marketers. Understanding the evolving behavioral and psychological patterns across consumer demographics is crucial for adapting business models effectively. Particularly, the emergence of new firms targeting adolescents and future generations underscores the importance of comprehending online consumer behavior and communication dynamics. To tackle these challenges, we introduce a Machine Learning-based Digital Native Market Segmentation designed to cater specifically to the interests of digital natives. Leveraging an open-access prototype dataset from social networking sites (SNS), our study employs a variety of clustering techniques, including Kmeans, MiniBatch Kmeans, AGNES, and Fuzzy C-means, to uncover hidden interests of teenage consumers from SNS data. Through rigorous evaluation of these clustering approaches by default parameters, we identify the optimal number of clusters and group consumers with similar tastes effectively. Our findings provide actionable insights into business impact and critical patterns driving future marketing growth. In our experiment, we systematically evaluate various clustering techniques, and notably, the Kmeans cluster outperforms others, demonstrating strong segmentation ability in the digital market. Specifically, it achieves silhouette scores of 63.90% and 58.06% for 2 and 3 clusters, respectively, highlighting its effectiveness in segmenting the digital market.

A Natural-Language-Processing-Based Method for the Clustering and Analysis of Movie Reviews and Classification by Genre

Reclassification of massive datasets acquired through different approaches, such as web scraping, is a big challenge to demonstrate the effectiveness of a machine learning model. Notably, there is a strong influence of the quality of the dataset used for training those models. Thus, we propose a threshold algorithm as an efficient method to remove stopwords. This method employs an unsupervised classification technique, such as K-means, to accurately categorize user reviews from the IMDb dataset into their most suitable categories, generating a well-balanced dataset. Analysis of the performance of the algorithm revealed a notable influence of the text vectorization method used concerning the generation of clusters when assessing various preprocessing approaches. Moreover, the algorithm demonstrated that the word embedding technique and the removal of stopwords to retrieve the clustered text significantly impacted the categorization. The proposed method involves confirming the presence of a suggested stopword within each review across various genres. Upon satisfying this condition, the method assesses if the word’s frequency exceeds a predefined threshold. The threshold algorithm yielded a mapping genre success above 80% compared to precompiled lists and a Zipf’s law-based method. In addition, we employed the mini-batch K-means method for the clustering formation of each differently preprocessed dataset. This approach enabled us to reclassify reviews more coherently. Summing up, our methodology categorizes sparsely labeled data into meaningful clusters, in particular, by using a combination of the proposed stopword removal method and TF-IDF. The reclassified and balanced datasets showed a significant improvement, achieving 94% accuracy compared to the original dataset.

Designing an AI purchasing requisition bundling generator

Following the design science methodology, a recommender system has been created with the research objective of finding a novel approach to the bundling problem in order to generate data-driven insights identifying cost potentials across an organization. In this study, a concept that has been implemented in business-to-business marketing at IBM is taken over to procurement in the automotive industry to provide decision support. Thereby, this work builds on information processing theory to utilize artificial intelligence technologies, i.e., natural language processing and supervised learning to augment the skills of buyers, whereby design principles were derived for information technology providers and procurement organizations in private and public settings worldwide. As a key finding, overall, Mini Batch K-means was the most performative model among the selected clustering algorithms. Furthermore, through actively making use of purchasing requisition data typically available in enterprise resource planning systems, the bundling generator artifact can lead to significant improvements in strategic planning and commodity management resulting in better utilization of buyer’s capacities, tender designs, and thus procurement’s value contribution in the transformation toward industry 4.0. The empirical study contributes to the literature on bundling and spend analysis, which has predominantly relied on historical data. By incorporating requisition data, which poses inherent challenges of precision and information-richness, this work expands this traditional approach with a forward-looking perspective.

Unsupervised Learning Based on Meibography Enables Subtyping of Dry Eye Disease and Reveals Ocular Surface Features.

This study aimed to establish an image-based classification that can reveal the clinical characteristics of patients with dry eye using unsupervised learning methods. In this study, we analyzed 82,236 meibography images from 20,559 subjects. Using the SimCLR neural network, the images were categorized. Data for each patient were averaged and subjected to mini-batch k-means clustering, and validated through consensus clustering. Statistical metrics determined optimal category numbers. Using a UNet model, images were segmented to identify meibomian gland (MG) areas. Clinical features were assessed, including tear breakup time (BUT), tear meniscus height (TMH), and gland atrophy. A thorough ocular surface evaluation was conducted on 280 cooperative patients. SimCLR neural network achieved clustering patients with dry eye into six image-based subtypes. Patients in different subtypes harbored significantly different noninvasive BUT, significantly correlated with TMH. Subtypes 1 and 5 had the most severe MG atrophy. Subtype 2 had the highest corneal fluorescent staining (CFS). Subtype 4 had the lowest TMH, whereas subtype 5 had the highest. Subtypes 3 and 6 had the largest MG areas, and the upper MG areas of a person's bilateral eyes were highly correlated. Image-based subtypes are related to meibum quality, CFS, and morphological characteristics of MG. In this study, we developed an unsupervised neural network model to cluster patients with dry eye into image-based subtypes using meibography images. We annotated these subtypes with functional and morphological clinical characteristics.

CLUSTERING AND MULTINOMIAL LOGIT ANALYSIS OF FACTORS INFLUENCING HOUSEHOLD RESIDENTIAL LOCATION CHOICE IN THE WASHINGTON METROPOLITAN AREA

The vast range of location alternatives and the preference heterogeneity have made it challenging to model, analyse, and predict the location choice process. In this study, we propose a two-step analytical model to focus on lowering the magnitude of these choices. The Transportation Planning Board's 2007-2008 household survey was used in the Washington metropolitan area, consisting of 3722 Traffic Analysis Zones (TAZ). First, location choice alternatives were clustered based on TAZs into homogeneous groups. These TAZs were categorized based on accessibility to public transport, population density, and employment density. Then, the Multinomial Logit (MNL) model was employed to allow the interpretation of the relationship between the clustered areas and the socio-economic characteristics. Four clustering algorithms were compared in terms of efficiency, and the mini-batch k-means performed the best based on the silhouette coefficient. Overall, households tend to prefer suburban areas as household size and the number of owned vehicles increase. Urban areas were selected with an increase in income, number of household workers, number of unemployed looking for a job, number of part-time employees, number of retirees, and the presence of university students. This paper contributes to the current trend of using unsupervised algorithms in the urban planning literature.

PFA-Nipals: An Unsupervised Principal Feature Selection Based on Nonlinear Estimation by Iterative Partial Least Squares

Unsupervised feature selection (UFS) has received great interest in various areas of research that require dimensionality reduction, including machine learning, data mining, and statistical analysis. However, UFS algorithms are known to perform poorly on datasets with missing data, exhibiting a significant computational load and learning bias. In this work, we propose a novel and robust UFS method, designated PFA-Nipals, that works with missing data without the need for deletion or imputation. This is achieved by considering an iterative nonlinear estimation of principal components by partial least squares, while the relevant features are selected through minibatch K-means clustering. The proposed method is successfully applied to select the relevant features of a robust health dataset with missing data, outperforming other UFS methods in terms of computational load and learning bias. Furthermore, the proposed method is capable of finding a consistent set of relevant features without biasing the explained variability, even under increasing missing data. Finally, it is expected that the proposed method could be used in several areas, such as machine learning and big data with applications in different areas of the medical and engineering sciences.

Pulse wave analysis as a tool for the evaluation of resuscitation therapy in septic shock

Objective. Pulse wave analysis (PWA) can provide insights into cardiovascular biomechanical properties. The use of PWA in critically ill patients, such as septic shock patients, is still limited, but it can provide complementary information on the cardiovascular effects of treatment when compared to standard indices outlined in international guidelines. Previous works have highlighted how sepsis induces severe cardiovascular derangement with altered arterial blood pressure waveform morphology and how resuscitation according to standard haemodynamic targets is not able to restore the physiological functioning of the cardiovascular system. The aim of this work is to test the effectiveness of PWA in characterizing arterial waveforms obtained from a swine experiment involving polymicrobial septic shock and resuscitation with different drugs. Methods. During the experiment, morphological aortic waveform features, such as indices related to the dicrotic notch and inflection point, were extracted by means of PWA techniques. Finally, all the PWA indices were used to compute a clustering classification (mini batch K-means) of the pigs according to the different phases of the experiment. This analysis aimed to test if PWA features alone could be used to distinguish between the different responses to the administered therapies. Results. The PWA indices highlighted different cardiovascular conditions of the pigs in response to different treatments, despite the mean haemodynamic values typically used to guide therapy administration being similar in all animals. The clustering algorithm was able to distinguish between the different phases of the experiment and the different responses of the animals based on the unique information derived from the aortic PWA. Conclusion. Even when used alone, PWA indices were highly informative when assessing therapy responses in cases of septic shock. Significance. A complex pathological condition like septic shock requires extensive monitoring without neglecting important information from commonly measured signals such as arterial blood pressure. Future studies are needed to understand how individual differences in the response to therapy are associated with different cardiovascular conditions that may become specific therapy targets.

Predictive business intelligence dashboard for food and beverage business

This research was conducted to provide an example of predictive business intelligence (BI) dashboard implementation for the food and beverage business (businesses that sell fast-expired goods). This research was conducted using data from a bakery's transactional database. The data are used to perform demand forecasting using extreme gradient boosting (XGBoost), and recency, frequency, and monetary value (RFM) analysis using mini batch k-means (MBKM). The data are processed and displayed in a BI dashboard created using Microsoft Power BI. The XGBoost model created resulted in a root mean square error (RMSE) value of 0.188 and an R2 score of 0.931. The MBKM model created resulted in a Dunn index value of 0.4264, a silhouette score value of 0.4421, and a Davies-Bouldin index value of 0.8327. After the BI dashboard is evaluated by the end user using a questionnaire, the BI dashboard gets a final score of 4.77 out of 5. From the BI dashboard evaluation, it was concluded that the predictive BI dashboard succeeded in helping the analysis process in the bakery business by: accelerating the decision-making process, implementing a data-driven decision-making system, and helping businesses discover new insights.

B-144 A Comparative Analysis of Unsupervised Machine Learning Algorithms for Polyploidy Analysis Using Flow Cytometry

Abstract Background Recently, there has been a growing interest in using cell differentiation inducers to produce platelets in vitro by inducing megakaryocytic differentiation in cell lines. During this process, cells undergo polyploidization through endomitosis. To measure the degree of polyploidy, cell cycle analysis by flow cytometry is commonly used. However, manual gating can be time-consuming and prone to human error, especially when analyzing large datasets. To address this issue, this study aimed to compare the performance of unsupervised machine learning algorithms for polyploidy analysis of flow cytometry data. Methods The K562 cell line (Korea Cell Line Bank, Korea) was cultured under four conditions, including 1 nM and 2.5 nM of PMA (phorbol 12-myristate 13-acetate; Sigma Aldrich, USA) and 5 μg/mL of phytosphingosine (TCI, Japan), for four days. Propidium iodide (Sigma Aldrich, USA) was used to stain the cells for ploidy analysis, and flow cytometry (Navios, Beckman Coulter Inc, USA) was used to obtain the intensity values. Twelve flow cytometry measurements were obtained for K562 cells cultured under four different conditions, with each condition tested in triplicate. Unsupervised machine learning algorithms, including K-Means, Bisecting K-Means (BKM), Mini Batch K-Means (MBKM), Agglomerative Clustering (AC), Gaussian Mixture Models (GMM), K-Medoids, and Partitioning Around Medoids (PAM), were used to generate boundaries among three clusters (2n, 4n, and ≥8n). The boundary values generated by each algorithm were comparatively analyzed by calculating the standard derivation index (SDI) on each boundary. The concordance of each algorithm with manual gating of flow cytometry data was evaluated by calculating residual errors. Results A total of 168 SDI values were obtained from seven different unsupervised machine learning algorithms for two boundaries among 2n, 4n, and ≥8n clusters of four culture conditions in triplicate. When comparing the average (±95% confidence interval) of SDI for each algorithm for the entire dataset, K-Means showed the most acceptable average SDI value of −0.07 (±0.17) with the narrowest confidence interval followed by −0.13 (±0.54) of AC, −0.26 (±0.18) of MBKM, −0.53 (±0.2) of K-Medoids, −0.58 (±0.2) of PAM, 0.74 (±0.3) of GMM, and 0.84 (±0.35) of BKM. In addition, the average (±95% confidence interval) of the absolute value of the residual errors of each algorithm was calculated, with K-Means showing the lowest value of 6.67 (±2.3), indicating higher concordance with manual gating. AC, MBKM, K-Medoids, PAM, BKM, and GMM had higher average residual errors of 10.04 (±2.5), 10.46 (±4.07), 11.13 (±4.65), 12.04 (±4.83), 12.54 (±3.0), and 12.75 (±3.5), respectively. Conclusion K-means demonstrated the best performance for clustering each ploidy among the seven unsupervised machine learning algorithms tested for the flow cytometry data. In addition, the algorithms achieved acceptable concordance with manual gating in most cases in this study. Therefore, unsupervised machine learning algorithms show promise in automating the gating of flow cytometry data for polyploidy analysis and measuring megakaryocytic differentiation in cell lines.

Recency, Frequency, Monetary Value, Clustering, and Internal and External Indices for Customer Segmentation from Retail Data

While there are several ways to identify customer behaviors, few extract this value from information already in a database, much less extract relevant characteristics. This paper presents the development of a prototype using the recency, frequency, and monetary attributes for customer segmentation of a retail database. For this purpose, the standard K-means, K-medoids, and MiniBatch K-means were evaluated. The standard K-means clustering algorithm was more appropriate for data clustering than other algorithms as it remained stable until solutions with six clusters. The evaluation of the clusters’ quality was obtained through the internal validation indexes Silhouette, Calinski Harabasz, and Davies Bouldin. When consensus was not obtained, three external validation indexes were applied: global stability, stability per cluster, and segment-level stability across solutions. Six customer segments were obtained, identified by their unique behavior: lost customers, disinterested customers, recent customers, less recent customers, loyal customers, and best customers. Their behavior was evidenced and analyzed, indicating trends and preferences. The proposed method combining recency, frequency, monetary value (RFM), K-means clustering, internal indices, and external indices achieved return rates of 17.50%, indicating acceptable selectivity of the customers.

Clustering and Risk Analysis of The Earthquake in Sulawesi Using Mini Batch K-Means, K-Medoids, and Maximum Likelihood Method

Abstract: The earthquake events have been widely analyzed using a statistical approach. Therefore, the sole purpose of this research is clustering and risk analysis of earthquake events based on the combination of machine learning and statistics. The machine learning, conducted by Mini Batch K-Means and K-Medoids, is validated by the Davies-Bouldin index method to earthquake events cluster. Furthermore, the statistics approach conducted by the maximum likelihood method is to estimate the b-value and a-value of earthquake events. The data used in the earthquake events analysis in Sulawesi have a magnitude 5 SR during the period 1980-2022. The results show that the Mini Batch K-Means method is more efficient and accurate than the K-Medoids, and can cluster the earthquakes, namely cluster 0 below 100 km (shallow earthquake), cluster 1 above 100 km to 350 km (medium earthquake), cluster 2 above 350 km (deep earthquake), while K-Medoids method has two clusters namely cluster 0 below 100 km (shallow earthquake), and cluster 1 above 100 km to 350 km. The regions with b-value and a-value less than 0.9 and 7.5, respectively, and in cluster 0, namely the western part of North Sulawesi, Gorontalo, Middle Sulawesi, and West Sulawesi Province, are as vulnerable to earthquake disasters. Meanwhile, the region in cluster 1 and cluster 2 with b-value and a-value more than 0.9 and 7.5 respectively namely South Sulawesi, the Northern part of North Sulawesi, and Southeast Sulawesi Province, are categorized as minor earthquake disasters. Furthermore, the clustering and risk analysis based on these methods results are good performance, which has recognised cluster and vulnerability of the earthquake events.Abstrak: Kejadian gempa bumi telah banyak dianalisis dengan menggunakan pendekatan statistik. Oleh karena itu, tujuan penelitian untuk menganalisis kejadian gempa dengan menggunakan kombinasi pendekatan machine learning dengan statistik. Pendekatan machine learning dilakukan dengan metode baru yakni metode Mini Batch K-Means dan K-Medoids yang divalidasi dengan metode Davies-Bouldin indeks yang digunakan untuk mengklaster kejadian gempa, sedangkan pendekatan secara statistik dilakukan dengan metode maximum likelihood untuk mengestimasi kerentanan gempa bumi berdasarkan nilai-b dan nilai-a. Data yang digunakan yakni data kejadian gempa di Sulawesi dengan magnitudo ≥ 5 SR dengan periode 1980-2022. Hasil menunjukan bahwa metode Mini Batch K-Means lebih effisien dan akurat dibandingkan dengan metode K-Medoids, dan mengklasifikasi tiga klaster kedalaman gempa, yakni klaster 0 dengan kedalaman kurang dari 100 km (gempa dangkal), klaster 1 dengan kedalaman diantara 100 km dengan 350 km (gempa menengah), klaster 2 dengan kedalaman lebih dari 350 km (gempa dalam). Sementara metode K-Medoids dua klaster kedalama gempa, yakni klaster 0 dengan kedalaman dibawah 100 km (gempa dangkal), dan klaster 1 dengan kedalaman lebih dari 100 km. Beberapa wilayah yang mempunyai nilai-b dan nilai-a secara berurutan kurang dari 0,9 dan 7,5 dan termasuk ke dalam klaster 0, yakni Provinsi Sulawesi Utara bagian barat, Gorontalo, Sulawesi Tengah, dan Sulawesi Barat dikategorikan rawan terhadap bencana gempa; Sedangkan wilayah yang termasuk ke dalam klaster 1 dan klaster 2 dengan nilai-b dan nilai-a secara berurutan lebih dari 0,9 dan 7,5 yakni Provinsi Sulawesi Selatan, Sulawesi Utara bagian Utara, dan Sulawesi Tenggara dikategorikan sebagai rendah terhadap bencana gempa. Dengan demikian, kedua metode dapat digunakan untuk meng-klaster gempa dan identifikasi kerentanan kejadian gempa bumi.

K-means variations analysis for translation of English Tafseer Al-Quran text

Text mining is a powerful modern technique used to obtain interesting information from huge datasets. Text clustering is used to distinguish between documents that have the same themes or topics. The absence of the datasets ground truth enforces the use of clustering (unsupervised learning) rather than others, such as classification (supervised learning). The “no free lunch” (NFL) theorem supposed that no algorithm outperformed the other in a variety of conditions (several datasets). This study aims to analyze the k-means cluster algorithm variations (three algorithms (k-means, mini-batch k-means, and k-medoids) at the clustering process stage. Six datasets were used/analyzed in chapter Al-Baqarah English translation (text) of 286 verses at the preprocessing stage. Moreover, feature selection used the term frequency–inverse document frequency (TF-IDF) to get the weighting term. At the final stage, five internal cluster validations metrics were implemented silhouette coefficient (SC), Calinski-Harabasz index (CHI), C-index (CI), Dunn’s indices (DI) and Davies Bouldin index (DBI) and regarding execution time (ET). The experiments proved that k-medoids outperformed the other two algorithms in terms of ET only. In contrast, no algorithm is superior to the other in terms of the clustering process for the six datasets, which confirms the NFL theorem assumption.

Advanced Spam Filtering in Electronic Mail Using Hybrid the Mini Batch K-Means Normalized Mutual Information Feature Elimination with Elephant Herding Optimization Technique

Advanced Spam Filtering in Electronic Mail Using Hybrid the Mini Batch K-Means Normalized Mutual Information Feature Elimination with Elephant Herding Optimization Technique

Feature selection using non-dominant features-guided search for gene expression profile data

AbstractGene expression profile data have high-dimensionality with a small number of samples. These data characteristics lead to a long training time and low performance in predictive model construction. To address this issue, the paper proposes a feature selection algorithm using non-dominant feature-guide search. The algorithm adopts a filtering framework based on feature sorting and search strategy to overcome the problems of long training time and poor performance. First, the feature pre-selection is completed according to the calculated feature category correlation. Second, a multi-objective optimization feature selection model is constructed. Non-dominant features are defined according to the Pareto dominance theory. Combined with the bidirectional search strategy, the Pareto dominance features under the current category maximum relevance feature are removed one by one. Finally, the optimal feature subset with maximum correlation and minimum redundancy is obtained. Experimental results on six gene expression data sets show that the algorithm is much better than Fisher score, maximum information coefficient, composition of feature relevancy, mini-batch K-means normalized mutual information feature inclusion, and max-Relevance and Min-Redundancy algorithms. Compared to feature selection method based on maximum information coefficient and approximate Markov blanket, the algorithm not only has high computational efficiency but also can obtain better classification capabilities in a smaller dimension.