Development of a hand classification system for smart hand wearables

Research purpose: This study aimed to lay a research foundation for smart hand wearable design by classifying the right-hand data of 4545 adults aged 20 69. Further, increase practical applicability classification system, type discrimination method and regression equations dimensions each were presented. Methods: statistically analyzed eighth Size Korea with IBM SPSS Ver.26.0. Cluster analysis was performed classify both finger length circumference type. Discriminant conducted, yielding discriminant functions aid potential wearers in self-diagnosing their types. Linear yielded detailed pattern-making wearables. Results: The categorized into four types: Uphill type, Downhill Mountain Horizon men’s women’s hands. two types, Cone Cylinder function showed mean accuracy rate 89.9% explanatory power 72.9%. Conclusion: system proposed this improve fingertip fit products analyzing configuration motion tracking gloves or haptic gloves. In addition, considering designers wearables, types wearers’ self-diagnosis designers’ pattern making provided.