Jingyi Ma

Jingyi Ma

Auto-generated profile, based on publicly available information

Jingyi Ma

School of Art Design and Media, East China University of Science and Technology, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 October 2024 in Textile Research Journal
Verified
Journal Article
Closed access
YCYumiao Chen
Yumiao Chen
JMJingyi Ma
Jingyi Ma
Artificial intelligence generation technology has brought new opportunities to the field of fashion design. Attribute knowledge has a significant impact on the overall effect of fashion design. Contemporary generative methods of fashion design frequently yield results lacking semantic information or missing specific attributes. To address the problem, this study aims for an intelligent generative method of fashion design through constructing prompt templates and a specific attribute low-rank adaption (LoRA) to combine fashion attribute knowledge into the generative process of the Stable Diffusion Model. First, a fashion attribute knowledge graph is constructed to establish prompt templates, and natural language descriptions are transformed into professional and complete prompt through GPT-4. Second, the fashion dataset is annotated with templates to filter specific attributes for LoRA training, followed by controlling fashion attributes in generation. Furthermore, analyses of the generation of women’s jacket designs show that the proposed method consistently improves the accuracy and stability of attributes in fashion design generation.

25 January 2021 in Journal of Physics D: Applied Physics
Verified
Journal Article
Closed access
PDF file
JMJingyi Ma
Jingyi Ma
XWXiaona Wang
Xiaona Wang
XZXiaohang Zong
Xiaohang Zong
LLLinli Li
Linli Li
HSHao Sun
Hao Sun
XFXiaoxing Fan
Xiaoxing Fan
Graphitic carbon nitride (g-C 3 N 4 ) usually shows a low photoelectrochemical (PEC) performance due to its poor conductivity. To improve the transfer of charge carriers generated by g-C 3 N 4 , a TiO 2 /g-C 3 N 4 composite photoanode was prepared by a facile co-electrodeposition method. The composite photoelectrodes exhibit an improved PEC performance compared to TiO 2 and g-C 3 N 4 . The PEC performance was optimized by varying the mass ratio of TiO 2 to g-C 3 N 4 , and a ratio of 1:1 gave the best photocurrent density of 1.81 mA cm −2 , which is 2.27 times larger than that of the pure TiO 2 photoanode under full-arc xenon light. Furthermore, compared with pure g-C 3 N 4 , the photocurrent density is greatly improved. The incident photocurrent efficiency reached 4.14% under irradiation with 365 nm monochromatic light. TiO 2 /g-C 3 N 4 exhibits a stable photocurrent density in a PEC reaction over 2 h. The enhanced PEC performance is attributed to the synergism between TiO 2 and g-C 3 N 4 semiconductors, which improves the interfacial charge transfer and inhibits the photogenerated electron–hole pair recombination.