Asset Details
Do you wish to reserve the book?
AIGC Enabling Non-Genetic Design Methods and Practices
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
AIGC Enabling Non-Genetic Design Methods and Practices
Do you wish to request the book?
AIGC Enabling Non-Genetic Design Methods and Practices
Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Journal Article
AIGC Enabling Non-Genetic Design Methods and Practices
2024
Overview
Artificial Intelligence Generated Content (AIGC) technology aligns seamlessly with the design requirements of non-genetic heritage, offering a viable pathway for its modernization. This paper delineates the specific design needs of non-genetic heritage and utilizes a diffusion model to create themed images and animations related to this heritage. Additionally, AIGC is employed to enhance the creation of virtual reality interactive imagery. The Long Short-Term Memory (LSTM) network is deployed to classify time-series gesture data, facilitating the training and categorization of Chinese Sign Language (CSL) gestures for virtual interactive engagement with non-heritage themes. We have integrated the AIGC operation process into the theme of non-genetic inheritance, thereby constructing a robust development trajectory for AIGC-enhanced non-genetic heritage. The experimental setup is crafted to ascertain the optimal number of iterations and training durations through the control variable method. We evaluate the efficacy of the diffusion model for anti-implicit writing analysis and the performance of the speech recognition, text dialogue, and text response modules within the non-heritage multimodal interactive framework using Word Error Rate (WER) and Mean Opinion Score (MOS). A descriptive analysis of users’ interactive experiences with non-heritage content is also conducted. The results indicate that the speech recognition module achieved a WER of 0.365, while the text response module garnered an MOS of 4.49 with a standard deviation of 0.56. This multimodal, non-heritage virtual interaction, leveraging multiple modalities, enriches users’ experiences and deepens their understanding and appreciation of non-heritage content. Consequently, this enhances the high-quality development of non-genetic heritage.
Publisher
Sciendo,De Gruyter Brill Sp. z o.o., Paradigm Publishing Services
Subject
We currently cannot retrieve any items related to this title. Kindly check back at a later time.