Artificial Neural Network Model for Indoor Decoration Intelligence Calculation and Automation Design.

Abstract

With the continuous development of science and technology, the indoor decoration industry has gradually changed toward mechanization, specialization, and intelligent direction. Based on the predecessor research, this study proposes an artificial neural network model for indoor decoration intelligence calculation and automation design. Based on scales, walls, doors, windows, and other specific components, digital image processing technology implements automatic identification of the apartment graph and completes the preprocessing of the floor plan map. Combined with the indoor decoration data set, the automated design model based on an artificial neural network is established, and the network structure and training process of the model are analyzed. Finally, the bedroom and the living room were experimentally designed. The results showed that as the number of training increased to 30 times, the MAE and MSE assessment indicators gradually decreased, and the error of the model was very small and gradually stabilized. This shows that artificial neural network automation design is better; second, artificial neural network algorithms can generate multiple layout schemes within 1 minute. The design layout is efficient and the plan is reasonable. It meets all requests such as circulation, openness, lighting, and functionality, saving a lot of human and time and providing users with more choices.