Design of Customized Garments Towards Sustainable Fashion Using 3D Digital Simulation and Machine Learning-Supported Human–Product Interactions

Abstract This paper put forward a new interactive design approach for customized garments towards sustainable fashion using machine learning techniques, including radial basis function artificial neural network (RBF ANN), genetic algorithms (GA), probabilistic (PNN), and support vector regression (SVR). First, RBF ANNs were employed to estimate the detailed human body dimensions fulfill consumers’ ergonomics requirements. Next, GA-based models developed generate formalized solutions following consumer profiles (demands). Afterwards, evaluation model was established quantitatively characterize relations between garment from generated solutions. The would be digitally demonstrated recommended results in descending order. Meanwhile, PNN-based created predict fitness based on virtual try-on. Moreover, SVR-based self-adjustment mechanism built control parameters according consumer’s feedback. Based these mathematical models, enhances interactions among digital demonstration, designer’s professional knowledge user’s perception find out most relevant solution. effectiveness of verified by real application case leisure pants customization. show that proposed method can powerfully designers’ quality personalized consumers more accurately, fast, intelligently, sustainably, compared with existing approaches. More importantly, it also establishes an effective reliable communication channel consumers, designers, pattern designer, producer.