The piece "The Floating Continental Shelf" is crafted from a synthesis of imagery derived from Google Globe View, employing Stable Diffusion and the Control Net tool as an artistic rendition. The artist selected three distinct continental shelves as the basis for this creation, which underwent material preparation, image preprocessing, SD generation, and multi-image synthesis stages, resulting in a total of 8 finalized images. Employing a fusion of photography, AIGC generation, and printing concepts, the work represents an amalgamation of these three elements. Leveraging the artist's photographic expertise, the piece is stylized to convey the grandeur inherent in geographic landscapes.

Glance through while dazed is a set of six sheets of generative art, based on the understanding of vision and perception in the 21st chapter of the Tao Te Ching, through which the author wishes to respond to the perception that there are ambiguous rules between the world of experience and the world of perception. All the images of the basic elements in this work are generated from stable diffusion model. The descriptions of these basic elements are derived from the author's descriptions of real world streets, which are random and unpredictable. In the end, 400+ images were generated by describing the appearance of dozens of streets. During the compositing stage, the author selected 20-30 clips for each piece and then stacked the selected images. The stacked images are abstract and also present an overall tone, with each clip added affecting the final result.

As society evolves, more and more individuals recognize that chronic tension is one of the primary causes of mental health issues. In tandem with the maturation of biofeedback research, biofeedback technology has been applied to relaxation training and stress management. The purpose of the study was to use the design thinking methodology to create an interactive system design that incorporates biofeedback techniques with traditional breathing relaxation techniques to reduce stress and enhance concentration. In this paper, we evaluated and reflected on the prototype design through user testing. The results indicate that the design of this interactive system is not only acceptable and promising, but also capable of producing a novel calming experience.

This paper explores the interaction between human gesture and acousto-optic system through developing the interactive musical installation MOONMENT that outputs interactive music and light according to user's gestures. Based on interaction design principles and embodied metaphor theory, we present development process of the concept ideation, prototyping, and user testing. This work has various application potentials and can generate acousto-optic effects following the actions of singers, dancers, and actors. This study opens up new possibilities for future research in designing new interfaces of musical expression.

Human body motion pattern recognition in video images is an important research direction in the field of pattern recognition. It has a very broad application prospect in many fields such as intelligent video surveillance, human-computer interaction, motion analysis, video retrieval, etc. Research has also received extensive attention from scholars at home and abroad. Pattern recognition is essentially a branch of artificial intelligence. It has its unique role in the field of artificial intelligence. Accurate recognition of human body motion patterns in video images is of great help in image classification, retrieval, human tracking and video surveillance. Based on the human visual perception mechanism, this paper proposes a human behavior recognition algorithm based on semantic saliency map. Through the combination of sliding window and similarity measure, the behavioral region that best exhibits the semantic features of the image is found, which is the semantically significant region. The semantic significant region and the original image are used as the dual input source to study the human behavior recognition, and the image is enhanced. The utilization of significant regional information better reveals the identifiable area of the image and contributes to the recognition of human behavior.