Key points are not available for this paper at this time.
This study aims to explore the integration of Internet of Things (IoT) technology and artificial intelligence (AI) in art education, assessing its impact on learners’ experiences and learning outcomes. The study first proposes a digital teaching system that enables the IoT and Generative Adversarial Networks (GANs) to play a role in art education by monitoring students’ creative state in real-time, providing immediate feedback, and facilitating the generation of creative works. The system framework includes sensor nodes, an IoT platform, a GAN model, and a user interface to build a real-time interactive environment. Sensor nodes constantly collect physiological, movement, and environmental data from students, and the GAN model receives student data from the IoT platform, combining creative input from students to generate artwork in real-time. The generated works are transmitted to the discriminator through the IoT platform, which evaluates their quality and provides real-time feedback. Students interact with the system through the user interface, observe the generated artwork, adjust generator parameters, and propose new ideas. These interactions influence further artistic creation. The WikiArt public art creation dataset is selected to establish the experimental foundation, and the experimental evaluation focuses on image generation quality, system performance, and student learning outcomes. It is compared with Deep Convolutional Generative Adversarial Network (DCGAN) and Variational Autoencoder (VAE) models. The research results indicate that the designed IoT and GANs integrated system remarkably outperforms DCGAN and VAE in image generation quality, with an Inception Score of 4.5, which is more diverse and recognizable than other models. Regarding system performance, the IoT and GANs integrated system is significantly ahead in image generation speed and user interaction, with a transmission speed of up to 200 Mbps. Regarding student learning outcomes, the system performs excellently in emotional feedback, learning outcomes, and creative work quality, achieving 80% satisfaction and 90% positive feedback. Overall, the research conclusion clearly points out that the integration of IoT and GANs has a significant and comprehensive effect on improving the quality of art education. This study expands the field of art education by integrating IoT and GANs, enhancing students’ creative experiences, and providing innovative methods for art teaching in the digital age.
Fang et al. (Mon,) studied this question.