Big data analytics by automated generation of fuzzy rules for Network Forensics Readiness

详细信息    查看全文

• 作者：Andrii Shalaginov ; ^{andrii.shalaginov@ccis.no}Author Vitae ; Katrin FrankeAuthor Vitae
• 关键词：Big data ; Soft Computing ; Neuro-Fuzzy ; Intrusion detection ; Self-organizing feature maps ; Computational forensics
• 刊名：Applied Soft Computing
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：52
• 期：Complete
• 页码：359-375
• 全文大小：2073 K
• 卷排序：52

文摘

Conventional Neuro-Fuzzy is inapplicable for large-scale Network Forensics Readiness. Lower optimal size of Self-Organizing Map produces more generalized rules. The new fuzzy patches construction method uses χ2 test for parameter estimation. Modified Gaussian membership function better describes correlation in data. Proposed modifications can improve real-time forensically-sound evidence collection.