Education and Information Technologies, Год журнала: 2024, Номер unknown
Опубликована: Дек. 12, 2024
Язык: Английский
Systems, Год журнала: 2025, Номер 13(3), С. 174 - 174
Опубликована: Март 3, 2025
With the proliferation of artificial intelligence in education, AI-generated digital educational resources are increasingly being employed as supplements for university teaching and learning. However, this raises concerns about quality content produced. To conduct a comprehensive assessment, paper presents an evaluation index system by combining Delphi method Analytic Hierarchy Process. The initial indicators across dimensions content, expression, user technical aspects identified through systematic literature review recent research. Then, is utilized to modify according experts’ opinions two rounds questionnaire surveys. Subsequently, weight coefficients calculated using Finally, indicator evaluating developed, which comprises four twenty indicators. findings reveal that characteristics critical importance assessing resources, followed expression second most significant factor, with also recognized. Among second-level indicators, “authenticity”, “accuracy”, “legitimacy”, “relevance” accorded greater relative other proposed equips relevant stakeholders framework selecting high-quality AIGDERs steering AI tools line standards. some implications provided support selection guidance on aligning these
Язык: Английский
Процитировано
0
Acta Physica Sinica, Год журнала: 2025, Номер 74(10), С. 0 - 0
Опубликована: Янв. 1, 2025
The manta ray is a large marine species that exhibits both highly efficient gliding and agile flapping capabilities. It can autonomously switch between various motion modes, such as gliding, flapping, group swimming, based on ocean currents seabed conditions. To address the computational resource time constraints of traditional numerical simulation methods in modeling ray's 3D large-deformation flow field, this study proposes novel generative artificial intelligence approach denoising probabilistic diffusion model (surf-DDPM). This method predicts surface field by inputting set parameter variables. Initially, we establish for ray’s mode using immersed boundary spherical function gas kinetic scheme (IB-SGKS), generating an unsteady dataset comprising 180 sets under frequency conditions 0.3-0.9 Hz amplitude 0.1-0.6 body lengths. Data augmentation then performed. Subsequently, Markov chain noise process neural network generation are constructed. A pretrained embeds parameters step labels into data, which fed U-Net training. Notably, Transformer incorporated architecture to enable handling long-sequence data. Finally, examine impact hyperparameters performance visualize predicted pressure velocity fields multi-flapping postures were not included training set, followed quantitative analysis prediction accuracy, uncertainty, efficiency. results demonstrate proposed achieves fast accurate predictions characterized extensive high-dimensional upsampling. minimum PSNR SSIM values 35.931 dB 0.9524, respectively, with all data falling within 95% interval. Compared CFD simulations, AI enhances efficiency single-condition simulations 99.97%.
Язык: Английский
Процитировано
0
Electronics, Год журнала: 2025, Номер 14(4), С. 725 - 725
Опубликована: Фев. 13, 2025
Blue-and-white porcelain, as a representative of traditional Chinese craftsmanship, embodies rich cultural genes and possesses significant research value. Against the backdrop generative AI era, this study aims to optimize creative processes blue-and-white porcelain enhance efficiency accuracy complex artistic innovations. Traditional methods crafting encounter challenges in accurately efficiently constructing intricate patterns. This employs grounded theory conjunction with KANO-AHP hybrid model classify quantify core esthetic features thereby establishing multidimensional feature library its Subsequently, leveraging Stable Diffusion platform utilizing Low-Rank Adaptation (LoRA) technology, artificial intelligence (AIGC)-assisted workflow was proposed, capable restoring innovating enhances precision pattern innovation while maintaining consistency original style. Finally, by integrating principles sustainable design, explores new pathways for digital offering viable solutions contemporary reinvention crafts. The results indicate that AIGC technology effectively facilitates integration modern design approaches. It not only empowers inheritance continuation but also introduces ideas possibilities development craftsmanship.
Язык: Английский
Процитировано
0
Buildings, Год журнала: 2025, Номер 15(7), С. 1067 - 1067
Опубликована: Март 26, 2025
An analysis of the practice path and methodology system Artificial Intelligence Generated Content (AIGC) technology has been conducted in field inheritance innovation boundary paintings from Song Dynasty. This paper aims to provide valuable reference guidance for application AI Dynasty painting (Song painting) interior decoration design, so as promote effective integration traditional aesthetics modern design concepts. Firstly, natural processing language model is used generate index layer suitable indoor soft style paintings, Analytic Hierarchy Process weight classification select cue words generated image. Secondly, Midjourney images keywords. Finally, Stable Diffusion control transfer elements design. AIGC can effectively with elements, play a unique role pattern It provides an innovative art wealth possibilities painting. significant potential painting, which bring new ideas methods contribute wide development
Язык: Английский
Процитировано
0
Thinking Skills and Creativity, Год журнала: 2025, Номер unknown, С. 101862 - 101862
Опубликована: Май 1, 2025
Язык: Английский
Процитировано
0
Education and Information Technologies, Год журнала: 2024, Номер unknown
Опубликована: Дек. 12, 2024
Язык: Английский
Процитировано
2