1. NCCU Academic Hub
  2. 學術產出
  3. 資訊學院
  4. 期刊論文
  5. Item

學術產出-期刊論文

文章檢視/開啟

書目匯出

Google ScholarTM

政大圖書館

引文資訊

TAIR相關學術產出

題名 UNSUPERVISED LEARNING BASED DISTRIBUTED DETECTION OF GLOBAL ANOMALIES
作者 徐國偉
ZHOU,JUNLIN;ALEKSANDAR LAZAREVIC;HSU,KUO-WEI;JAIDEEP SRIVASTAVA;FU,YAN;WU,YUE
貢獻者 資科系
關鍵詞 Distributed anomaly detection; global anomalies; combining models
日期 2010-11
上傳時間 21-八月-2014 14:47:04 (UTC+8)
摘要 Anomaly detection has recently become an important problem in many industrial and financial applications. Very often, the databases from which anomalies have to be found are located at multiple local sites and cannot be merged due to privacy reasons or communication overhead. In this paper, a novel general framework for distributed anomaly detection is proposed. The proposed method consists of three steps: (i) building local models for distributed data sources with unsupervised anomaly detection methods and computing quality measure of local models; (ii) transforming local unsupervised local models into sharing models; and (iii) reusing sharing models for new data and combining their results by considering both quality and diversity of them to detect anomalies in a global view. In experiments performed on synthetic and real-life large data set, the proposed distributed anomaly detection method achieved prediction performance comparable or even slightly better than the global anomaly detection algorithm applied on the data set obtained when all distributed data set were merged.
關聯 International Journal of Information Technology and Decision Making (IJITDM),9(6)935-957
資料類型 article
dc.contributor 資科系en_US
dc.creator (作者) 徐國偉zh_TW
dc.creator (作者) ZHOU,JUNLIN;ALEKSANDAR LAZAREVIC;HSU,KUO-WEI;JAIDEEP SRIVASTAVA;FU,YAN;WU,YUEen_US
dc.date (日期) 2010-11en_US
dc.date.accessioned 21-八月-2014 14:47:04 (UTC+8)-
dc.date.available 21-八月-2014 14:47:04 (UTC+8)-
dc.date.issued (上傳時間) 21-八月-2014 14:47:04 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/69122-
dc.description.abstract (摘要) Anomaly detection has recently become an important problem in many industrial and financial applications. Very often, the databases from which anomalies have to be found are located at multiple local sites and cannot be merged due to privacy reasons or communication overhead. In this paper, a novel general framework for distributed anomaly detection is proposed. The proposed method consists of three steps: (i) building local models for distributed data sources with unsupervised anomaly detection methods and computing quality measure of local models; (ii) transforming local unsupervised local models into sharing models; and (iii) reusing sharing models for new data and combining their results by considering both quality and diversity of them to detect anomalies in a global view. In experiments performed on synthetic and real-life large data set, the proposed distributed anomaly detection method achieved prediction performance comparable or even slightly better than the global anomaly detection algorithm applied on the data set obtained when all distributed data set were merged.en_US
dc.format.extent 128 bytes-
dc.format.mimetype text/html-
dc.language.iso en_US-
dc.relation (關聯) International Journal of Information Technology and Decision Making (IJITDM),9(6)935-957en_US
dc.subject (關鍵詞) Distributed anomaly detection; global anomalies; combining modelsen_US
dc.title (題名) UNSUPERVISED LEARNING BASED DISTRIBUTED DETECTION OF GLOBAL ANOMALIESen_US
dc.type (資料類型) articleen