High-Dimensional Data Analysis Using Parameter Free Algorithm Data Point Positioning Analysis
Open Access
- 16 May 2024
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 14 (10) , 4231
Abstract
Clustering is an effective statistical data analysis technique; it has several applications, including data mining, pattern recognition, image analysis, bioinformatics, and machine learning. Clustering helps to partition data into groups of objects with distinct characteristics. Most of the methods for clustering use manually selected parameters to find the clusters from the dataset. Consequently, it can be very challenging and time-consuming to extract the optimal parameters for clustering a dataset. Moreover, some clustering methods are inadequate for locating clusters in high-dimensional data. To address these concerns systematically, this paper introduces a novel selection-free clustering technique named data point positioning analysis (DPPA). The proposed method is straightforward since it calculates 1-NN and Max-NN by analyzing the data point placements without the requirement of an initial manual parameter assignment. This method is validated using two well-known publicly available datasets used in several clustering algorithms. To compare the performance of the proposed method, this study also investigated four popular clustering algorithms (DBSCAN, affinity propagation, Mean Shift, and K-means), where the proposed method provides higher performance in finding the cluster without using any manually selected parameters. The experimental finding demonstrated that the proposed DPPA algorithm is less time-consuming compared to the existing traditional methods and achieves higher performance without using any manually selected parameters.Keywords
Funding Information
- Zayed University (R21043)
This publication has 44 references indexed in Scilit:
- Performance evaluation results of evolutionary clustering algorithm star for clustering heterogeneous datasetsData in Brief, 2021
- A multidisciplinary ensemble algorithm for clustering heterogeneous datasetsNeural Computing and Applications, 2021
- Optimal experiment design for identification of ARX models with constrained output in non-Gaussian noiseApplied Mathematical Modelling, 2016
- Identification of time‐varying OE models in presence of non‐Gaussian noise: Application to pneumatic servo drivesInternational Journal of Robust and Nonlinear Control, 2016
- Concept lattice reduction using fuzzy K-Means clusteringExpert Systems with Applications, 2010
- Multi-modality video shot clustering with tensor representationMultimedia Tools and Applications, 2008
- A cluster ensemble method for clustering categorical dataInformation Fusion, 2005
- Categorical data visualization and clustering using subjective factorsData & Knowledge Engineering, 2005
- Clustering categorical data: an approach based on dynamical systemsThe VLDB Journal, 2000
- Silhouettes: A graphical aid to the interpretation and validation of cluster analysisJournal of Computational and Applied Mathematics, 1987