| Yamanishi, K., and Takeuchi, J. 2002. A unifying framework for detecting outliers and change points from non-stationary time series data. In Proc. of the Eighth ACM SIGKDD, ACM Press. 676-681. |
....work is Hidher [11] who proposed a model of continuous pattern discovery from unbounded data stream, and presented adaptive online algorithm for mining association rules. Parthasarathy et al. 17] and Mannila et al. 14] studied mining of sequential patterns and episode patterns. Yamanishi et al. [21] presented an efficient online outlier detection system SmartSifter with a forgetting mechanism. Zaki [22] and Asai et al. 4] independently developed efficient pattern search techniques, called rightmost expansion, for semi structured data, which is a generalization of the set enumeration tree ....
....the count and the frequency of T at time i, reap. Online Model (OL) In this model motivated by Hidher [11] we count the number of distinct root occurrences of T in )i. The frequency of T at time i is: freqi(T) counti(T) i hiti) T) i Forgetting Model (FG) In the forgetting model, e.g. [21], the contribution of the past event decays exponentially fast. For positive number 0 1 called a forgetting factor, the frequency of 7 is defined by: g I i hiti) T) 1) freq ,i(T) i J ,y 3 . Although we used a simplified normalization factor Zi i instead of a more precise one Zi i ....
K. Yamanishi, J. Takeuchi, A Unifying Framework for Detecting Out- liers and Change Points from Non-Stationary Time Series Data, In Pro. SIGKDD-2002.
No context found.
Yamanishi, K., and Takeuchi, J. 2002. A unifying framework for detecting outliers and change points from non-stationary time series data. In Proc. of the Eighth ACM SIGKDD, ACM Press. 676-681.
No context found.
Yamanishi, K., and Takeuchi, J. A unifying framework for detecting outliers and change points from nonstationary time series data. In Proc. of the Eighth ACM SIGKDD, ACM Press. 676-681. 2002
No context found.
K. Yamanishi, J. Takeuchi, A Unifying Framework for Detecting Outliers and Change Points from Non-Stationary Time Series Data, In Proc. SIGKDD-2002.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC