http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
User Bias Drift Social Recommendation Algorithm based on Metric Learning
Jianli Zhao,Tingting Li,Shangcheng Yang,Hao Li,Baobao Chai 한국인터넷정보학회 2022 KSII Transactions on Internet and Information Syst Vol.16 No.12
Social recommendation algorithm can alleviate data sparsity and cold start problems in recommendation system by integrated social information. Among them, matrix-based decomposition algorithms are the most widely used and studied. Such algorithms use dot product operations to calculate the similarity between users and items, which ignores user’s potential preferences, reduces algorithms’ recommendation accuracy. This deficiency can be avoided by a metric learning-based social recommendation algorithm, which learns the distance between user embedding vectors and item embedding vectors instead of vector dot-product operations. However, previous works provide no theoretical explanation for its plausibility. Moreover, most works focus on the indirect impact of social friends on user’s preferences, ignoring the direct impact on user’s rating preferences, which is the influence of user rating preferences. To solve these problems, this study proposes a user bias drift social recommendation algorithm based on metric learning (BDML). The main work of this paper is as follows: (1) the process of introducing metric learning in the social recommendation scenario is introduced in the form of equations, and explained the reason why metric learning can replace the click operation; (2) a new user bias is constructed to simultaneously model the impact of social relationships on user’s ratings preferences and user’s preferences; Experimental results on two datasets show that the BDML algorithm proposed in this study has better recommendation accuracy compared with other comparison algorithms, and will be able to guarantee the recommendation effect in a more sparse dataset.
Ziwei Sun,Qingtao Liu,Zhen Wang,Baobao Zhao,Quan Feng,Yanyan Sun,Min Zhong 한국고분자학회 2023 Macromolecular Research Vol.31 No.12
A hierarchical chitosan/polyvinyl alcohol/polyethylene glycol/nonwoven fabric (CS/PVA/PEG/NWF) micro/nanofiber composite membrane (CM) was prepared via electrospinning as a potential wound dressing. The polyester/viscose NWF acting as a substrate to receive the nanofiber layer was modified by alkali deweighting. Meanwhile, PEG with various additive amount was used to afford morphological regulation and control. As a result, the NWF modified with 7.5% NaOH solution exhibited a good hydrophilia and a superior dimensional stability based on smaller elongation at break and higher peel strength. In addition, the morphology of the nanofiber layer was closely related to PEG content. CS/PVA/PEG nanofiber with smaller diameter was spun when PEG content reached to 3.0%. Accordingly, the micro/nanofiber CM showed an opportune water absorption and good air permeability. Furthermore, neither hemolysis nor cytotoxicity phenomena appeared for the resultant CM, since the hemolysis rate and the cell viability were less than 5% and more than 70%, respectively.
Tissue distribution of marbofloxacin in pigs after a single intramuscular injection
Fan Yang,Yiming Liu,Zhili Li,Yuqin Wang,Baobao Liu,Zhensheng Zhao,Bianhua Zhou,Guoyong Wang 대한수의학회 2017 Journal of Veterinary Science Vol.18 No.2
Tissue distribution of marbofloxacin was studied in pigs after a single intramuscular injection at 2.5 mg/kg body weight. Samples of plasma, muscle, liver, kidney, heart, lung, and muscle at the injection site were randomly collected from five pigs at 2, 6, 10, 24, 48, 72, and 96 h after administration. Marbofloxacin concentrations were determined by using high-performance liquid chromatography with ultraviolet detection and were subjected to non-compartmental analysis to obtain kinetic parameters. The elimination half-life (t1/2lz) of marbofloxacin at the injection site was 22.12 h, while those in kidney, plasma, liver, lung, heart, and muscle were 16.75, 21.48, 21.84, 24.00, 24.45, and 28.91 h, respectively. Areas under the concentration-time curve from 0 h to ∞ (AUC0–∞s) were calculated to be 31.17 hㆍmgㆍmL−1 for plasma and 32.97, 33.92, 34.78, 37.58, 42.02, and 98.80 hㆍmgㆍg−1 for heart, muscle, lung, liver, kidney, and injection site, respectively. The peak concentration (Cmax) of marbofloxacin was 1.62 µg/mL in plasma and 1.71, 1.74, 1.86, 1.93, 2.45, and 7.64 µg/g in heart, lung, muscle, kidney, liver, and injection site, respectively. The results show that marbofloxacin was fast absorbed, extensively distributed, and slowly eliminated from pigs after a single intramuscular administration.