Concept Drift Detection via Improved Deep Belief Network

被引：0

作者：

Hatamikhah, Nafiseh ^{[1
]}

Barari, Morteza ^{[2
]}

Kangavari, Mohammad Reza ^{[3
]}

Keyvanrad, Mohammad Ali ^{[4
]}

机构：

[1] Shahid Beheshti Univ, Comp Engn Dept, Tehran, Iran

[2] Amirkabir Univ Technol, Elect Engn Dept, Tehran, Iran

[3] Univ Sci & Technol, Comp Engn Dept, Tehran, Iran

[4] Amirkabir Univ Technol, Comp Engn Dept, Tehran, Iran

来源：

26TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE 2018) | 2018年

关键词：

component; Streaming Data; Concept Drift; Streaming Algorithms; Deep Learning; Deep Belief Network;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

One of the issues raised in streaming data is concept drift detection. In fact, the process of concept drift comes from natural tendency events in the real world to change over time. For example, in data receiving from credit card transactions, detect when transactions rise suddenly, can help in identifying the fraud. In this paper regards to the importance of concept drift in streaming data, a solution to accurate diagnosis and timely is presented. This solution is based on ensemble algorithm and "streaming ensemble algorithm" (SEA) algorithm that SEA algorithm is used as one of the most commonly stream algorithms. This approach uses a deep belief network as a basic model in the SEA algorithm. In the method which is presented in this paper, we used the change of classification error on new data for concept drift detection. Analyzing the results shows that the proposed method compared with similar algorithms, in addition to a significant reduction in the runtime, improved F_measure criteria.

引用

页码：1703 / 1707

页数：5

共 50 条

[31] The Detection and Recognition of Bridges'Cracks Based on Deep Belief Network [J].

Wang Xuejun ;

Zhang Yan .

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND ENGINEERING (CSE) AND IEEE/IFIP INTERNATIONAL CONFERENCE ON EMBEDDED AND UBIQUITOUS COMPUTING (EUC), VOL 1, 2017, :768-771

[32] Deep belief network based detection and categorization of malicious URLs [J].

Selvaganapathy, ShymalaGowri ;

Nivaashini, Mathappan ;

Natarajan, HemaPriya .

INFORMATION SECURITY JOURNAL, 2018, 27 (03) :145-161

[33] Deep belief network based intrusion detection techniques: A survey [J].

Sohn, Insoo .

EXPERT SYSTEMS WITH APPLICATIONS, 2021, 167

[34] An Improved Deep Belief Network Prediction Model Based on Knowledge Transfer [J].

Zhang, Yue ;

Liu, Fangai .

FUTURE INTERNET, 2020, 12 (11) :1-18

[35] Improved Hierarchical Adaptive Deep Belief Network for Bearing Fault Diagnosis [J].

Shen, Changqing ;

Xie, Jiaqi ;

Wang, Dong ;

Jiang, Xingxing ;

Shi, Juanjuan ;

Zhu, Zhongkui .

APPLIED SCIENCES-BASEL, 2019, 9 (16)

[36] A Security Situation Prediction Method Based on Improved Deep Belief Network [J].

Li, Yufa ;

Zhou, Yuguang ;

Hu, Kewei ;

Sun, Ning ;

Ke, Kai .

PROCEEDINGS OF 2020 IEEE 2ND INTERNATIONAL CONFERENCE ON CIVIL AVIATION SAFETY AND INFORMATION TECHNOLOGY (ICCASIT), 2020, :594-598

[37] Nonlinear system identification method based on improved deep belief network [J].

Yang Man ;

Liu Ding ;

Zhao Xiaoguo .

2018 CHINESE AUTOMATION CONGRESS (CAC), 2018, :2379-2383

[38] An optimization-based deep belief network for the detection of phishing e-mails [J].

Arshey, M. ;

Viji, Angel K. S. .

DATA TECHNOLOGIES AND APPLICATIONS, 2020, 54 (04) :529-549

[39] Pedestrian, Bike, Motorcycle, and Vehicle Classification via Deep Learning: Deep Belief Network and Small Training Set [J].

Wu, Yen-Yi ;

Tsai, Chun-Ming .

PROCEEDINGS OF 2016 INTERNATIONAL CONFERENCE ON APPLIED SYSTEM INNOVATION (ICASI), 2016,

[40] Pedestrian detection for traffic safety based on Accumulate Binary Haar features and improved deep belief network algorithm [J].

Zhang, Yang ;

Xin, Dong-Rong ;

Wu, Yi-Hu .

TRANSPORTATION PLANNING AND TECHNOLOGY, 2016, 39 (08) :791-800

← 1 2 3 4 5 →