W. Gong. Periodic pattern search in time-related data sets. M. Sc. Thesis, Simon Fraser University Canada Nov. 1997.  Home/Search   Document Details and Download   Summary   Related Articles   Check

.... and adjustment of concept hierarchies [16] mining multi level association rules [15] meta rule guided mining of associations [22] incremental and distributed mining of associations [8, 7] constraint pushing in association mining [10, 27] mining periodicity and similarity in time series data [11, 30], multi level classification and prediction [23, 6] spatial data cube construction [21] spatial association rule mining [24] OLAP mining [12] Weblog mining [31] etc. A data mining system, DBMiner [16, 14] has been constructed with our years of research and development. The system integrates ....

....whole sequence but not the periodicity of particular point segment in the sequence as illustrated in the above example. We examine the problem in two cases: mining periodicity (1) with a given period and (2) with an arbitrary period, and propose an OLAP based technique to mine such periodicity [11]. For user specified given period, such as per day, per week, per quarter, etc. the potential activity patterns can be aggregated with respect to the given period along the time dimension in a data cube. Such aggregation will indicate the patterns which are periodic with respect to the given ....

[Article contains additional citation context not shown here]

W. Gong. Periodic pattern search in time-related data sets. M. Sc. Thesis, Simon Fraser University Canada Nov. 1997.

....whole sequence but not the periodicity of particular point segment in the sequence as illustrated in the above example. We examine the problem in two cases: mining periodicity (1) with a given period and (2) with an arbitrary period, and propose an OLAP based technique to mine such periodicity [11]. For user specified given period, such as per day, per week, per quarter, etc. the potential activity patterns can be aggregated with respect to the given period along the time dimension in a data cube. Such aggregation will indicate the patterns which are periodic with respect to the given ....

....periods, similar OLAP based methods can apply with the augmentation of some cycle merging properties. Notice also with OLAP based cube manipulation, one can drill down, roll up, slice and dice the time related cubolds to find such periodicity patterns on the fly. A detailed study is presented in [11]. 3.5 Wavelet technique for similarity based time series analysis Similarity based time series mmlysis is to find similar time related patterns (trends, segments, etc. in a large time series database, such as stock market database. Traditional trend analysis techniques, such as Fourier ....

W. Gong. Periodic pattern search in time-related data sets. M. Sc. Thesis, Simon Fraser University, B.C., Canada, Nov. 1997.

....directed search in time series databases. Problems related to periodicity search is stated as problems of finding patterns occurring at regular intervals, which means given a sequence of events, we would like to find the patterns which repeat over time and their recurring intervals (period) Wan [18] has proposed some possible solution to the problem of finding periodic behaviors in large data sets. 2.4 The Similarity Based Queries There is a vast class of database applications where it is important to be able to pose queries in terms of similarity of objects, rather than equality or ....

W. Gong. Periodic pattern search in time-related data sets. In M.Sc. Thesis, Simon Fraser University, November 1997. BIBLIOGRAPHY 94

....page, following by a sequence of other local web page accesses forms a cycle. A data mining task needs to detect such cycles effectively for meaningful analysis. We have developed techniques on how to find such cycles and detect periodicity efficiently using data cube structure and OLAP techniques [8]. 3. trend analysis. With the accumulation of the discovered sequences and periods, analysis can be performed on them to discover patterns and trends with different interests. One kind of patterns which can be easily discovered is the repetition of similar web page accesses. For the same set of ....

W. Gong. Periodic pattern search in time-related data sets. In M.Sc. Thesis, Simon Fraser University, Burnaby, B.C., Canada, November 1997.

.... and adjustment of concept hierarchies [16] mining multi level association rules [15] meta rule guided mining of associations [22] incremental and distributed mining of associations [8, 7] constraint pushing in association mining [10, 27] mining periodicity and similarity in time series data [11, 30], multi level classification and prediction [23, 6] spatial data cube construction [21] spatial association rule mining [24] OLAP mining [12] Weblog mining [31] etc. A data mining system, DBMiner [16, 14] has been constructed with our years of research and development. The system integrates ....

....whole sequence but not the periodicity of particular point segment in the sequence as illustrated in the above example. We examine the problem in two cases: mining periodicity (1) with a given period and (2) with an arbitrary period, and propose an OLAP based technique to mine such periodicity [11]. For user specified given period, such as per day, per week, per quarter, etc. the potential activity patterns can be aggregated with respect to the given period along the time dimension in a data cube. Such aggregation will indicate the patterns which are periodic with respect to the given ....

[Article contains additional citation context not shown here]

W. Gong. Periodic pattern search in time-related data sets. M.Sc. Thesis, Simon Fraser University, B.C., Canada, Nov. 1997.

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