Recommendation Algorithm for Multi-Task Learning with Directed Graph Convolutional Networks

Autor: Lifeng Yin, Jianzheng Lu, Guanghai Zheng, Huayue Chen, Wu Deng

Publikováno v: Applied Sciences, Vol 12, Iss 18, p 8956 (2022)

As an important branch of machine learning, recommendation algorithms have attracted the attention of many experts and scholars. The current recommendation algorithms all more or less have problems such as cold start and single recommended items. In

Externí odkaz: https://doaj.org/article/feefeb47396741648ace86a1a35fc0b0

Session-Enhanced Graph Neural Network Recommendation Model (SE-GNNRM)

Autor: Lifeng Yin, Pengyu Chen, Guanghai Zheng

Publikováno v: Applied Sciences, Vol 12, Iss 9, p 4314 (2022)

Session-based recommendation aims to predict anonymous user actions. Many existing session recommendation models do not fully consider the impact of similar sessions on recommendation performance. Graph neural networks can better capture the conversi

Externí odkaz: https://doaj.org/article/c27b4046419a43228ce6a264277ddc1d

Improved DeepLabV3+ image Semantic Segmentation Algorithm

Autor: Yuzhe Song, Guanghai Zheng, Xin Zhang

Publikováno v: 2022 IEEE 5th International Conference on Information Systems and Computer Aided Education (ICISCAE).

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::6911ab5f112e9973da44eb2294493e1d
https://doi.org/10.1109/iciscae55891.2022.9927609

Microstructure and Flight Behaviors of Droplet and its Solidification in Twin-Wire Arc Sprayed Ni-Al Composite Coatings

Autor: Jingshun Liu, Jianfei Sun, Lunyong Zhang, Guanghai Zheng, Limin Gao, Yongdong Wang, Hongxian Shen, Jixiao Wang

Publikováno v: Materials Research, Vol 21, Iss 3 (2018)
Materials Research, Issue: ahead, Published: 19 MAR 2018
Materials Research v.21 n.3 2018
Materials research (São Carlos. Online)
Universidade Federal de São Carlos (UFSCAR)
instacron:ABM ABC ABPOL
Materials Research, Volume: 21, Issue: 3, Article number: e20170394, Published: 19 MAR 2018

Droplet flight and solidification behaviors during twin-wire arc sprayed (TWAS) composite coatings were systematically investigated. Both theoretical model and numerical method were established for calculating the droplet deformation, breakup and sol

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eb54256b3b0606ab8e3882331982939a
http://www.scielo.br/scielo.php?script=sci_arttext&pid=S1516-14392018000300022&tlng=en

Application and Research of the Train Fault Diagnosis Based on Improved BP Neural Network Algorithm

Autor: Guanghai Zheng, Yingwei Qu, Yinnan Yan

Publikováno v: 2012 International Conference on Control Engineering and Communication Technology.

Traditional BP model of neural network is easy to get a local minimum rather than the global optimal solution. As the training times increases, the learning efficiency is falling low, so as the convergence rate. Improvement on the traditional model o

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::b443354cecaf1adf7f29cec3e8f47ec2
https://doi.org/10.1109/iccect.2012.26