International Business Machines Corporation

Ryo Hirade

Tsuyoshi Ide

Hisashi Kashima

Hiroaki Etoh

Kunikazu Yoda

Toshiyuki Hama

A method for predicting a change-point in continuous time-series data by computer includes accepting an input of continuous time-series data in past w periods; and determining whether or not a change-point in time-series appears in future k periods; wherein determining further includes determining, by a plurality of preliminary classifiers on the basis of the continuous time-series data in the past w periods and their respective preliminary classification rules, whether or not the change-point appears in future (k+i) periods, where i=0, 1, . . . , m; and determining, by a secondary classifier on the basis of determinations made by the plurality of preliminary classifiers and a secondary classification rule, whether or not the change-point appears in future c periods.

Predicting change-points in continuous time-series data using two classifier stages

A system such as a Web-based system in which a plurality of computers interact with each other is monitored to detect online an anomaly. Transactions of a service provided by each of a plurality of computers to another computer are collected, a matrix of correlations between nodes in the system is calculated from the transactions, and a feature vector representing anode activity balance is obtained from the matrix. The feature vector is monitored using a probability model to detect a transition to an anomalous state.

Anomaly detection

Provides an analysis system for analyzing dependencies among server programs in a computer system, comprising: a transaction detection unit for detecting transactions that is processing of a service which each of the plurality of server programs performs by being called from any other server program; a child transaction candidate detection unit for detecting candidates for a child transaction of each detected transaction, the child transaction being called in the transaction concerned; and a calling frequency calculation unit for outputting service calling frequencies obtained by estimating a frequency at which each server program allows each of the other server programs to perform a service by calling the other program, the estimation being made based on the service detected in association with each transaction and on a service detected in association with the candidate for the child transaction of the transaction.

Computer operation analysis

A system such as a Web-based system in which a plurality of computers interact with each other is monitored to detect online an anomaly. Transactions of a service provided by each of a plurality of computers to another computer are collected, a matrix of correlations between nodes in the system is calculated from the transactions, and a feature vector representing a node activity balance is obtained from the matrix. The feature vector is monitored using a probability model to detect a transition to an anomalous state.

Determining a cache hit ratio of a caching device analytically and precisely. There is provided a cache hit ratio estimating apparatus for estimating the cache hit ratio of a caching device, caching access target data accessed by a requesting device, including: an access request arrival frequency obtaining section for obtaining an average arrival frequency measured for access requests for each of the access target data; an access request arrival probability density function generating section for generating an access request arrival probability density function which is a probability density function of arrival time intervals of access requests for each of the access target data on the basis of the average arrival frequency of access requests for the access target data; and a cache hit ratio estimation function generating section for generating an estimation function for the cache hit ratio for each of the access target data on the basis of the access request arrival probability density function for the plurality of the access target data.

Growing community of inventors

Miura, Japan

Ryo Hirade