Generative Artificial Intelligence‒Driven Human-Machine Co-Creation for Responsive Interactive Installation Art Design

Generative Artificial Intelligence (AI) is revolutionizing traditional art by transforming static creations into interactive. This research proposes a responsive and emotionally adaptive interactive art framework using a hybrid Improved Brain Storm Optimization–tuned Bi-directional Gated Recurrent Unit (IBSO-Bi-GRU) model. The process begins with comprehensive data collection, such as motion capture, facial expressions, sound patterns, and environmental variables. For feature extraction, Convolutional Neural Networks (CNNs) are utilized to learn spatial hierarchies from visual and environmental data. The IBSO algorithm intelligently tunes the Bi-GRU network's hyper-parameters while the Bi-GRU captures bi-directional temporal dependencies in sequential user behaviour. Evaluation metrics include F1-score, accuracy, recall, and precision, ranging from 94% to 97%. The results confirm that human-machine co-creation, powered by generative AI and deep learning (DL) optimization, establishes a new creative paradigm and elevates engagement in interactive art design.