Generative AI is rapidly employed by software developers to generate code or other software artifacts.However,the analysis and assessment of generative AI with respect to requirements analysis and modeling tasks,espec...Generative AI is rapidly employed by software developers to generate code or other software artifacts.However,the analysis and assessment of generative AI with respect to requirements analysis and modeling tasks,especially with UML,has received little attention.This paper investigates the capabilities of generative AI to aid in the creation of three types of UML models:UML use case models,class diagrams,and sequence diagrams.For this purpose,we designed an AI-aided UML modeling task in our course on software requirements modeling.50 undergraduates who majored in Software Engineering at Wuhan University completed the modeling task and the corresponding online survey.Our findings show that generative AI can help create these three types of UML models,but its performance is limited to identifying essential modeling elements of these UML models.展开更多
Residential energy use accounts for a substantial portion of global consumption,making its reduction critical for sustainable architectural design.However,existing generative models for residential layouts often overl...Residential energy use accounts for a substantial portion of global consumption,making its reduction critical for sustainable architectural design.However,existing generative models for residential layouts often overlook energy performance,resulting in inefficient designs and costly revisions.To address this,we propose an AI-based framework that integrates generative model,energy prediction,and evolutionary optimization.Our framework comprises three components:(1)Energy prediction:a deep learning model trained on energy simulations of 71,125 floor plans from the RPLAN dataset predicts monthly energy consumption across five categories with over 99%accuracy.(2)Generative model:a diffusion-based layout generator uses room blocks and residential contours to create diverse,high-quality floor plans under spatial constraints.(3)Optimization:a genetic algorithm iteratively refines floor plans by selecting low-energy solutions and regenerating new options,guided by the predictive model.Experiments show that our method reduces energy consumption by 17.5%compared to the best baseline model under identical conditions,demonstrating its effectiveness in reducing residential energy use.Our key contributions include the use of room blocks as chromosomes for layout evolution,and the integration of AI-based prediction and generation for energy-aware residential design.展开更多
With the rapid advancement of global digitalization,artifcial intelligence(AI)technology is being widely applied across various fields.The Ministry of Education launched a special campaign in March 2024 to promote the...With the rapid advancement of global digitalization,artifcial intelligence(AI)technology is being widely applied across various fields.The Ministry of Education launched a special campaign in March 2024 to promote the integration,intelligence,and internationaliza-tion of digital education.In response,the School of Art at Anhui University of Finance and Economics has proposed the construction of an AIGC-aided design course teaching and experiment base.This project aims to integrate AI technologies into design educa-tion,enhancing students'practical training and fostering high-quality AI design talent.By building state-of-the-art teaching facilities and introducing cutting-edge AI tools,the base will provide students with immersive,hands--on learning experiences.The project em-phasizes interdisciplinary learning,blending traditional design education with advanced technologies,and seeks to promote collaboration between academia and industry.展开更多
文摘Generative AI is rapidly employed by software developers to generate code or other software artifacts.However,the analysis and assessment of generative AI with respect to requirements analysis and modeling tasks,especially with UML,has received little attention.This paper investigates the capabilities of generative AI to aid in the creation of three types of UML models:UML use case models,class diagrams,and sequence diagrams.For this purpose,we designed an AI-aided UML modeling task in our course on software requirements modeling.50 undergraduates who majored in Software Engineering at Wuhan University completed the modeling task and the corresponding online survey.Our findings show that generative AI can help create these three types of UML models,but its performance is limited to identifying essential modeling elements of these UML models.
基金supported by the Guangdong Basic and Applied Basic Research Foundation(2024A1515012595)Department of Education of Guangdong Province(2023ZDZX4078)Shenzhen Science and Technology Innovation Committee(WDZC20231129201240001).
文摘Residential energy use accounts for a substantial portion of global consumption,making its reduction critical for sustainable architectural design.However,existing generative models for residential layouts often overlook energy performance,resulting in inefficient designs and costly revisions.To address this,we propose an AI-based framework that integrates generative model,energy prediction,and evolutionary optimization.Our framework comprises three components:(1)Energy prediction:a deep learning model trained on energy simulations of 71,125 floor plans from the RPLAN dataset predicts monthly energy consumption across five categories with over 99%accuracy.(2)Generative model:a diffusion-based layout generator uses room blocks and residential contours to create diverse,high-quality floor plans under spatial constraints.(3)Optimization:a genetic algorithm iteratively refines floor plans by selecting low-energy solutions and regenerating new options,guided by the predictive model.Experiments show that our method reduces energy consumption by 17.5%compared to the best baseline model under identical conditions,demonstrating its effectiveness in reducing residential energy use.Our key contributions include the use of room blocks as chromosomes for layout evolution,and the integration of AI-based prediction and generation for energy-aware residential design.
基金2024 Ministry of Education Industry-University Collaborative Education Program:Construc-tion of an AIGC-Assisted Design Course Teaching and Experimentation Base(Project No.240902206025125)a collaboration between Anhui University of Finance and Economics and Portum Technology(Shenzhen)Co.,Ltd.This article is translated by Costume and Culture Studies based on the author’s project proposal.
文摘With the rapid advancement of global digitalization,artifcial intelligence(AI)technology is being widely applied across various fields.The Ministry of Education launched a special campaign in March 2024 to promote the integration,intelligence,and internationaliza-tion of digital education.In response,the School of Art at Anhui University of Finance and Economics has proposed the construction of an AIGC-aided design course teaching and experiment base.This project aims to integrate AI technologies into design educa-tion,enhancing students'practical training and fostering high-quality AI design talent.By building state-of-the-art teaching facilities and introducing cutting-edge AI tools,the base will provide students with immersive,hands--on learning experiences.The project em-phasizes interdisciplinary learning,blending traditional design education with advanced technologies,and seeks to promote collaboration between academia and industry.
