Accelerated K-Means Algorithms for Low-Dimensional Data on Parallel Shared-Memory Systems

Kwedlo, Wojciech; Łubowicz, Michał

doi:10.1109/access.2021.3080821

Cited by 7 publications

(3 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Algoritma K-Means dikenal sebagai metode pengelompokkan yang popular dan sering digunakan. K-Means juga dianggap sebagai salah satu dari sepuluh algoritma data mining terbaik [16]. K-Means adalah salah satu metode pengelompokan data yang mampu mengelompokkan data ke dalam dua atau lebih kelompok [15].…”

Section: K-meansunclassified

Perbandingan Metode K-Medoids dan Metode K-Means Dalam Analisis Segmentasi Pelanggan Mall

Rohman,

Wibowo

2024

SINTECH Journal

View full text Add to dashboard Cite

Memahami pelanggan sangat penting untuk mengelola operasi perusahaan. Dengan mengetahui dan memahami setiap pelanggan, dapat meningkatkan komunikasi layanan produk dengan menyesuaikan kebutuhan dan layanan kepada setiap pelanggan. Namun, analisis pelanggan sangat luas sehingga sulit untuk memahami kebutuhan masing-masing pelanggan. Hal ini dapat mencakup berbagai karakteristik dan perilaku pelanggan. Oleh karena itu, diperlukan segmentasi pelanggan untuk mengelompokkan pelanggan berdasarkan perilaku dan karakteristiknya. Tujuan dari penelitian ini adalah membandingkan metode clustering untuk mendapatkan metode yang lebih baik dan optimal dalam mengelompokkan cluster untuk segmentasi pelanggan. Dari permasalahan tersebut, peneliti menerapkan metode CRISP-DM dengan focus pada analisis cluster atau pengelompokkan dengan membandingkan algoritma K-Means dan K-Medoids terhadap Analisa segmentasi pelanggan pada mall. Pada penerapan perbandingan metode K-Means dan K-Medoids, digunakan metode elbow untuk menentukan jumlah cluster yang optimal. Hasil dari metode elbow menunjukkan bahwa penggunaan lima cluster untuk metode K-Means dan empat cluster untuk metode K-Medoids merupakan pilihan yang tepat dalam kasus ini. Langkah selanjutnya adalah mencari nilai Silhouette Coefficient setiap metode yang digunakan dalam perbandingan untuk menentukan metode clustering yang lebih optimal. Hasil nilai yang diperoleh dari metode Silhouette Coefficient masing-masing metode adalah k-means adalah 0,553 dan k-medoid adalah 0,485, sehingga algoritma pengelompokan segmentasi pelanggan terbaik pada penelitian ini adalah algoritma K-means karena memiliki nilai koefisien siluet maksimum.

show abstract

Section: K-meansunclassified

Perbandingan Metode K-Medoids dan Metode K-Means Dalam Analisis Segmentasi Pelanggan Mall

Rohman,

Wibowo

2024

SINTECH Journal

View full text Add to dashboard Cite

show abstract

“…However, the time complexity of such methods is at least proportional to the problem size, and the computational cost is enormous when the number of original scenarios is large. When processing sources and loads data of IES, Clustering and scenario reduction are very similar in basic ideas (Kwedlo and Łubowicz, 2021). The K-means clustering algorithm is an unsupervised learning algorithm and its computational complexity is not as sensitive to the size of the original scenario as traditional scenario reduction methods (Wang et al, 2018;Niu et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Two-stage scheduling of integrated energy systems based on a two-step DCGAN-based scenario prediction approach

Liu

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

Integrated energy systems (IESs) are developing rapidly as a supporting technology for achieving carbon reduction targets. Accurate IES predictions can facilitate better scheduling strategies. Recently, a newly developed unsupervised machine learning tool, known as Generative Adversarial Networks (GAN), has been used to predict renewable energy outputs and various types of loads for its advantage in that no prior assumptions about data distribution are required. However, the structure of the traditional GAN leads to the problem of uncontrollable generations, which can be improved in deep convolutional GAN (DCGAN). We propose a two-step prediction approach that takes DCGAN to achieve higher accuracy generation results and uses a K-means clustering algorithm to achieve scenario reduction. In terms of scheduling strategies, common two-stage scheduling is generally day-ahead and intraday stages, with rolling scheduling used for the intraday stage. To account for the impacts on the prediction accuracy of scheduling results, Conditional Value at Risk (CVaR) is added to the day-ahead stage. The intra-day prediction process has also been improved to ensure that the inputs for each prediction domain are updated in real-time. The simulations on a typical IES show that the proposed two-step scenario prediction approach can better describe the load-side demands and renewable energy outputs with significantly reduced computational complexity and that the proposed two-stage scheduling strategy can improve the accuracy and economy of the IES scheduling results.

show abstract

“…One way to improve performance is to combine the K-Means method with other methods, for example, semisupervised learning [14], feature selection [15], hybrids with other methods [16], using Fuzzy metrics [17], with weighted K-NN [18], combining with Multi-Column Matrices Selection [19], One-Class SVM [20][21], particle swarm optimization algorithm [22]. There are also researchers who improve the performance in terms of the speed of the K-Means method by parallelizing iterations [23]. The research was also carried out with improvements to the k-means algorithm, for example, selecting the number of clusters based on the density characterization of objects [24], determining the initial centroid using the maximin method [25], determining the number of clusters using the Maximum Stable Set Problem and Continuous Hopfield Network [26].…”

Section: Introductionmentioning

confidence: 99%

Proposed Modification of K-Means Clustering Algorithm with Distance Calculation Based on Correlation

Rachmatullah

2022

Jurnal Ilmiah Teknik Elektro Komputer Dan Informatika

View full text Add to dashboard Cite

Clustering is a technique in data mining that groups a set of data into groups (clusters) of similar data. In general, there are two methods of clustering, namely the hierarchical method and the partition method. One of the most commonly used partition clustering methods in clustering is K-Means. The use of K-means method has been widely used in various fields with various purposes. Many research has been carried out to improve the performance of the K-Means method, for example, by modifying the method of determining the initial centroid or determining the appropriate number of clusters. In this research, the modification of the K-Means algorithm was carried out in calculating the distance by considering the correlation value between attributes. Attributes that have a high correlation value are assumed to have similar characteristics so that they determine the location of data in a particular cluster. The steps of the proposed method are: calculating the correlation value between attributes, determining the cluster centroid, calculating the distance by considering the value of correlation, and determining the data into certain clusters. The first contribution of this research is to propose a new distance calculation technique in the K-Means algorithm by considering correlation and the second contribution is to apply the proposed algorithm to a specific dataset, namely Iris dataset. In this research, the performance calculation of the modified algorithm was also carried out. From the experimental results using the Iris dataset, the proposed modification of the K-Means algorithm has fewer iterations than the original K-Means method, so that it requires less processing time. The original K-Means method requires 8 iterations, while the proposed method requires only 6 iterations. The proposed method also produces a higher accuracy rate of 89.33% than the original K-Means method, which is 82.67%.

show abstract

Accelerated K-Means Algorithms for Low-Dimensional Data on Parallel Shared-Memory Systems

Cited by 7 publications

References 56 publications

Perbandingan Metode K-Medoids dan Metode K-Means Dalam Analisis Segmentasi Pelanggan Mall

Perbandingan Metode K-Medoids dan Metode K-Means Dalam Analisis Segmentasi Pelanggan Mall

Two-stage scheduling of integrated energy systems based on a two-step DCGAN-based scenario prediction approach

Proposed Modification of K-Means Clustering Algorithm with Distance Calculation Based on Correlation

Contact Info

Product

Resources

About