Search

Your search keyword '"Yan,Xiaomin"' showing total 218 results
Start Over Author "Yan,Xiaomin" Search Limiters Peer Reviewed
218 results on '"Yan,Xiaomin"'

18. CAT-RFE: ensemble detection framework for click fraud

Author

Yixiang LU, Guanggang GENG, Zhiwei YAN, Xiaomin ZHU, Xinchang ZHANG

Subjects
click fraud detection, catboost, recursive feature elimination, ensemble learning, Electronic computers. Computer science, QA75.5-76.95
Abstract

Click fraud is one of the most common methods of cybercrime in recent years, and the Internet advertising industry suffers huge losses every year because of click fraud.In order to effectively detect fraudulent clicks within massive clicks, a variety of features that fully combine the relationship between advertising clicks and time attributes were constructed.Besides, an ensemble learning framework for click fraud detection was proposed, namely CAT-RFE ensemble learning framework.The CAT-RFE ensemble learning framework consisted of three parts: base classifier, recursive feature elimination (RFE) and voting ensemble learning.Among them, the gradient boosting model suitable for category features-CatBoost was used as the base classifier.RFE was a feature selection method based on greedy strategy, which can select a better feature combination from multiple sets of features.Voting ensemble learning was a learning method that combined the results of multiple base classifiers by voting.The framework obtained multiple sets of optimal feature combinations in the feature space through CatBoost and RFE, and then integrated the training results under these feature combinations through voting to obtain integrated click fraud detection results.The framework adopted the same base classifier and ensemble learning method, which not only overcame the problem of unsatisfactory integrated results due to the mutual constraints of different classifiers, but also overcame the tendency of RFE to fall into a local optimal solution when selecting features, so that it had better detection ability.The performance evaluation and comparative experimental results on the actual Internet click fraud dataset show that the click fraud detection ability of the CAT-RFE ensemble learning framework exceeds that of the CatBoost method, the combined method of CatBoost and RFE, and other machine learning methods, proving that the framework has good competitiveness.The proposed framework provides a feasible solution for Internet advertising click fraud detection.

Published
2022
Full Text
View/download PDF

27. Red Blood Cell Distribution Width Predicts Mortality in Hospitalized Patients with Severe Fever with Thrombocytopenia Syndrome.

Author

Zhang, Shaoqiu, Zhang, Qun, Wang, Jian, Pan, Yifan, Zhang, Zhiyi, Geng, Yu, Jia, Bei, Tian, Bing, Xiong, Yali, Yan, Xiaomin, Li, Jie, Wang, Huali, Huang, Rui, and Wu, Chao

Subjects
PROPORTIONAL hazards models, ERYTHROCYTES, RECEIVER operating characteristic curves, MORTALITY risk factors, HOSPITAL patients
Abstract

Background: Severe fever with thrombocytopenia syndrome (SFTS) is an emerging epidemic infectious disease with high mortality rate. This study aimed to investigate the association of red blood cell distribution width (RDW) and mortality risk in hospitalized SFTS patients. Methods: Clinical data of SFTS patients was retrospectively collected from three hospitals between October 2010 and August 2022. Cox proportional hazards model was used to identity the risk factors for fatal outcome. The predictive value of RDW for fatal outcome was evaluated by the receiver operating characteristic (ROC) analysis and Kaplan–Meier methods. Results: Of 292 patients, the median age was 61.5 years. Non-survivors showed higher RDW value than survivors (13.6% vs.13.0%, P < 0.001). The mortality rate was 44.8% in patients with elevated RDW compared to 18.4% of patients with normal RDW, with a relative risk (RR) of 2.439. Elevated RDW was an independent risk factor of mortality (hazards ratio: 1.167, P = 0.019). Patients with elevated RDW had a higher cumulative mortality than patients with normal RDW. The area under the ROC curve (AUC) of RDW for the prediction of mortality was 0.690 (P < 0.001). Conclusion: Elevated RDW was associated with higher mortality risk for patients hospitalized for SFTS. RDW may be helpful for risk stratification in SFTS patients. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

39. Clinical and virological course of patients with coronavirus disease 2019 in Jiangsu province, China: a retrospective, multi-center cohort study

Author

Huang, Rui, Zhu, Li, Xue, Leyang, Yan, Xuebing, Wang, Jian, Huang, Songping, Zhang, Biao, Xu, Tianmin, Ji, Fang, Li, Chunyang, Ming, Fang, Zhao, Yun, Li, Yang, Cheng, Juan, Wang, Yinling, Shao, Huaping, Hong, Shuqin, Chen, Kang, Zhao, Xiang-an, Sang, Dawen, Zou, Lei, Zhao, Haiyan, Guan, Xinying, Chen, Xiaobing, Xu, Biyun, Xia, Juan, Chen, Yuxin, Yan, Xiaomin, Wei, Jie, Liu, Jiacheng, Liu, Longgen, Zhu, Chuanwu, and Wu, Chao

Published
2021
Full Text
View/download PDF

44. Association of liver function and prognosis in patients with severe fever with thrombocytopenia syndrome.

Author

Zhang, Shaoqiu, Wang, Jian, Zhang, Qun, Pan, Yifan, Zhang, Zhiyi, Geng, Yu, Jia, Bei, Li, Yuanyuan, Xiong, Yali, Yan, Xiaomin, Li, Jie, Wang, Huali, Wu, Chao, and Huang, Rui

Subjects
EMERGING infectious diseases, PROPORTIONAL hazards models, PROGNOSIS, ALANINE aminotransferase, THROMBOCYTOPENIA
Abstract

Objectives: Severe fever with thrombocytopenia syndrome (SFTS) is an epidemic emerging infectious disease with high mortality rate. We investigated the association between liver injury and clinical outcomes in patients with SFTS. Methods: A total of 291 hospitalized SFTS patients were retrospectively included. Cox proportional hazards model was adopted to identify risk factors of fatal outcome and Kaplan-Meier curves were used to estimate cumulative risks. Results: 60.1% of patients had liver injury at admission, and the median alanine transaminase, aspartate aminotransferase (AST), alkaline phosphatase (ALP), and total bilirubin (TBil) levels were 76.4 U/L, 152.3 U/L, 69.8 U/L and 9.9 μmol/L, respectively. Compared to survivors, non-survivors had higher levels of AST (253.0 U/L vs. 131.1 U/L, P < 0.001) and ALP (86.2 U/L vs. 67.9 U/L, P = 0.006), higher proportion of elevated ALP (20.0% vs. 4.4%, P < 0.001) and liver injury (78.5% vs. 54.9%, P = 0.001) at admission. The presence of liver injury (HR 2.049, P = 0.033) at admission was an independent risk factor of fatal outcome. Conclusions: Liver injury was a common complication and was strongly associated with poor prognosis in SFTS patients. Liver function indicators should be closely monitored for SFTS patients. Author summary: Severe fever with thrombocytopenia syndrome (SFTS) is an emerging epidemic infectious disease with high mortality rate. However, the prevalence of liver injury and its association with the prognosis of SFTS patients has not been well characterized. In this multi-center cohort study, we found that the incidence of liver injury in non-survivors was significantly higher than that in survivors both at admission and during hospitalization. Patients with liver injury at admission had higher cumulative mortality risk than those without liver injury. Our study demonstrated that the presence of liver injury is strongly associated with poor prognosis in SFTS patients. Liver function should be closely monitored in SFTS patients, which may contribute to better management of SFTS. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

47. The Identification of a Cell Cycle Regulation Gene Cyclin E from Hong Kong Oysters (Crassostrea hongkongensis) and Its Protein Expression in Response to Salinity Stress.

Author

Qiu, Hengtong, Wang, Huan, Yan, Xiaomin, Hu, Lin, Huang, Yonglin, and Ye, Yanni

Subjects
CELL cycle regulation, CRASSOSTREA, GENETIC regulation, OYSTERS, PROTEIN expression, BIVALVE shells
Abstract

Hong Kong oysters (Crassostrea hongkongensis) are an important marine bivalve with nutritional and commercial value. The expanded off-bottom farming scale in recent years makes the oysters more susceptible to exposure to abiotic stresses, such as salinity stress, an important environmental factor that has been proven to have significant effects on oyster growth and development. However, the molecular mechanism is still unclear. Cyclin E is an important protein in the process of cell cycle regulation that is indispensable for propelling G1/S phase transition in a dose-dependent manner. In order to investigate whether the salinity stress affects cyclin E expression in oysters, the cDNA sequence of C. hongkongensis cyclin E (Ch-CCNE) was isolated from a gill cDNA library, and the 2.8 kbp length cDNA fragment contained a complete open reading frame (ORF) encoding 440 amino acid residues. Ch-CCNE mRNA was highly expressed in the gonad and low in the adductor mussel, mantle, gill, labial palp, and digestive gland. The recombinant CCNE protein was expressed and purified in a pET32a(+)-CCNE/Escherichia coli BL21(DE3) system via IPTG induction and was used for generating mice anti-Ch-CCNE antiserums. Western blot analysis showed that the CCNE protein in the gill was maintained at low expression levels under either hypo- (5 ppt) or hyper- (35 ppt) salinity, and could be produced at high levels under appropriate salinity during a 10-day exposure period. The immuno-localization indicated that the Ch-CCNE protein was distributed in the nucleus. These results suggested that either hypo- or hyper-salinity stress could inhibit the CCNE expression of Hong Kong oysters and their negative impact on cell division and proliferation. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results