Abstract
Objectives Tablet appearance may generate different patient reactions and affect patient confidence in treatment. Consequently, in order to improve the treatment effect, the tablet’s form should be designed to meet the patients’ emotional expectations. Therefore, this paper proposes a method to optimize the design of tablet form based on grey theory and particle swarm optimization.
Methods The target image is determined and the design elements of the tablet’s form are decomposed to establish the set of design parameters. The patients’ image perceptions can be obtained through a questionnaire. Then, using grey theory, a correlation model between the tablet’s form and the patients’ emotional images can be built, also allowing evaluation of patient perceptions of tablet form. Finally, it sets typical tablet samples as the initial population and sets the evaluation model as a moderate function, so as to employ particle swarm optimization to optimize tablet form design.
Results The results show that, by using grey theory, the correlation model between the tablet’s form and the patient’s image perception can be built with fewer samples and then the image evaluation system can be set up with good generalization ability. By using particle swarm optimization, creative thinking can be stimulated and a product form optimization system set up with parallel characteristics.
Conclusions This paper applies artificial intelligence to study the laws of patients’ image perceptions of tablet form, and proposes a tablet form optimization design method based on grey theory and particle swarm optimization. In the case of a children’s tablet, this method was shown to efficiently and exactly produce a tablet form design scheme which satisfied the patients’ emotional needs. This method can enhance the success rate of tablet form design and provides an effective approach for solving the large-scale design issue of tablet form.
Acknowledgments This research was financially supported by the National Natural Science Foundation of China (Grant No. 51575158) and Hebei Province Natural Science Foundation of China (Grant No. E2016202058).