Vertical Clustering of 3D Elliptical Helical Data

This research proposes an effective vertical clustering strategy of 3D data in an elliptical helical shape based on 2D geometry. The clustering object is an elliptical cross-sectioned metal pipe which is been bended in to an elliptical helical shape which is used in wearable muscle support designing for welfare industry. The aim of this proposed method is to maximize the vertical clustering (vertical partitioning) ability of surface data in order to run the product evaluation process addressed in research [2]. The experiment results prove that the proposed method outperforms the existing threshold no of clusters that preserves the vertical shape than applying the conventional 3D data. This research also proposes a new product testing strategy that provides the flexibility in computer aided testing by not restricting the sequence depending measurements which apply weight on measuring process. The clustering algorithms used for the experiments in this research are self-organizing map (SOM) and K-medoids.