Fangshu Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Fangshu Chen has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Huaizhong Lin
College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China
4 shared publications Dongming Lu
Zhejiang University
2 shared publications- Dongming Lu
Zhejiang University
2 shared publications Yunjun Gao
Zhejiang University
2 shared publications- Yunjun Gao
Zhejiang University, Hangzhou, China
2 shared publications - Hanyan Xiao
State Grid Jiangsu Electric Power Research Institute,Nanjing,China,211103
1 shared publication
Latest Publications
- Open Access
- 27 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 401-406
GUFAD: A Graph-based Unsupervised Fraud Account Detection Framework
The detection of fraud accounts at scenarios of registration and login is a critical task for Internet enterprises, which can help to avoid economic losses at a very early stage. In industry, most companies tend to deploy supervised models such as rule-based models. However, these methods are significantly restricted in scalability since they highly rely on domain knowledge and manual annotations. Therefore, we designed a novel account graph analysis approach for uncovering fraudulent patterns. The framework explores an advanced feature-account bigraph to calculate the aggregation of accounts and applies a community detection algorithm to detect organized fraud groups. Next, a graph embedding and clustering algorithm is introduced to further analyze the types of aggregated communities, which can help to reduce account misclassification. Furthermore, a novelty method POMV is designed to explore the patterns of missing values. And two dynamic feature aggregation methods based on multi-granularity sliding windows are proposed to construct expressive features that can help to improve the quality of the account graph. The proposed framework achieves 0.82 F1_Score on average, which significantly outperforms the off-the-shelf models by 3% to 16%.
- 27 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 401-406
Open AccessGUFAD: A Graph-based Unsupervised Fraud Account Detection Framework
The detection of fraud accounts at scenarios of registration and login is a critical task for Internet enterprises, which can help to avoid economic losses at a very early stage. In industry, most companies tend to deploy supervised models such as rule-based models. However, these methods are significantly restricted in scalability since they highly rely on domain knowledge and manual annotations. Therefore, we designed a novel account graph analysis approach for uncovering fraudulent patterns. The framework explores an advanced feature-account bigraph to calculate the aggregation of accounts and applies a community detection algorithm to detect organized fraud groups. Next, a graph embedding and clustering algorithm is introduced to further analyze the types of aggregated communities, which can help to reduce account misclassification. Furthermore, a novelty method POMV is designed to explore the patterns of missing values. And two dynamic feature aggregation methods based on multi-granularity sliding windows are proposed to construct expressive features that can help to improve the quality of the account graph. The proposed framework achieves 0.82 F1_Score on average, which significantly outperforms the off-the-shelf models by 3% to 16%.
- Open Access
- 14 November 2021
- Published by African Journals Online (AJOL) in Tropical Journal of Pharmaceutical Research
- Vol. 20 (9) , 1999-2004
Efficacy and prognosis following combined cinepazaide maleate/nimodipine therapy in cerebral vasospasm patients after hemorrhage
Purpose: To investigate the efficacy and prognosis following treatment of cerebral vasospasm (CVS) patients with a combination of cinnarizide maleate and nimodipine after subarachnoid hemorrhage (SAH). Methods: Eighty-eight patients with CVS after SAH were selected and divided into control group (CG) and study group (EG), each with 44 patients (n = 44). Patients in CG were treated with intravenous infusion of cinnarizide maleate, while those in EG received intravenous infusion of cinnarizide maleate together, and their clinical efficacy and prognosis were compared. Results: Compared with CG, total treatment effectiveness (response) in EG was significantly higher, while levels of inflammatory factors were lower (p < 0.05). Serum protein levels of S100 β and ET-1, and MCA blood flow velocity in EG were notably lower (p < 0.05), but GCS scores were higher compared with CG (p < 0.05). The NIHSS scores were lower and BI indices were higher in EG than in CG (p < 0.05). Conclusion: Treatment of CVS patients after SAH using a combination of cinnarizide maleate and nimodipine effectively reduces the levels of inflammatory factors, improves quality of prognosis, and relieves symptoms of CVS, when compared with administration of cinnarizide maleate only. Therefore, the combination treatment is recommended for the management of CVS after SAH.
- 14 November 2021
- Published by African Journals Online (AJOL) in Tropical Journal of Pharmaceutical Research
- Vol. 20 (9) , 1999-2004
Open AccessEfficacy and prognosis following combined cinepazaide maleate/nimodipine therapy in cerebral vasospasm patients after hemorrhage
Purpose: To investigate the efficacy and prognosis following treatment of cerebral vasospasm (CVS) patients with a combination of cinnarizide maleate and nimodipine after subarachnoid hemorrhage (SAH). Methods: Eighty-eight patients with CVS after SAH were selected and divided into control group (CG) and study group (EG), each with 44 patients (n = 44). Patients in CG were treated with intravenous infusion of cinnarizide maleate, while those in EG received intravenous infusion of cinnarizide maleate together, and their clinical efficacy and prognosis were compared. Results: Compared with CG, total treatment effectiveness (response) in EG was significantly higher, while levels of inflammatory factors were lower (p < 0.05). Serum protein levels of S100 β and ET-1, and MCA blood flow velocity in EG were notably lower (p < 0.05), but GCS scores were higher compared with CG (p < 0.05). The NIHSS scores were lower and BI indices were higher in EG than in CG (p < 0.05). Conclusion: Treatment of CVS patients after SAH using a combination of cinnarizide maleate and nimodipine effectively reduces the levels of inflammatory factors, improves quality of prognosis, and relieves symptoms of CVS, when compared with administration of cinnarizide maleate only. Therefore, the combination treatment is recommended for the management of CVS after SAH.
- 19 December 2018
- Published by Springer Nature in Knowledge and Information Systems
- Vol. 61 (2) , 873-903
GOAL: a clustering-based method for the group optimal location problem
- 19 December 2018
- Published by Springer Nature in Knowledge and Information Systems
- Vol. 61 (2) , 873-903
GOAL: a clustering-based method for the group optimal location problem
- 1 January 2016
- Published by Elsevier in Expert Systems with Applications
- Vol. 43, 93-108
Capacity constrained maximizing bichromatic reverse nearest neighbor search
- 1 January 2016
- Published by Elsevier in Expert Systems with Applications
- Vol. 43, 93-108
Capacity constrained maximizing bichromatic reverse nearest neighbor search
- 19 October 2015
- Published by Springer Nature in GeoInformatica
- Vol. 20 (3) , 351-384
Finding optimal region for bichromatic reverse nearest neighbor in two- and three-dimensional spaces
- 19 October 2015
- Published by Springer Nature in GeoInformatica
- Vol. 20 (3) , 351-384
Finding optimal region for bichromatic reverse nearest neighbor in two- and three-dimensional spaces
- 1 January 2013
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 146-160
OptRegion: Finding Optimal Region for Bichromatic Reverse Nearest Neighbors
- 1 January 2013
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 146-160
OptRegion: Finding Optimal Region for Bichromatic Reverse Nearest Neighbors