Mining Partially Periodic Event Patterns with Unknown Periods

2018

Periodic frequent pattern mining, the process of finding frequent patterns which occur periodically in databases, is an important data mining task for various decision making. Though several algorithms have been proposed for their discovery, most employ a two stage process to evaluate the periodicity of patterns. That is, by firstly deriving the set of periods of a pattern from its coverset, and subsequently evaluating the periodicity from the derived set of periods. This two step process thus make algorithms for discovering periodic frequent patterns both time and memory inefficient in the discovery process. In this paper, we present solutions to reduce both runtime and memory consumption in periodic frequent pattern mining. We achieve this by evaluating the periodicity of patterns without deriving the set of periods from their coversets. Our experimental results show that our proposed solutions are efficient both in reducing the runtime and memory consumption in the discovery of p...

International Journal of Data Warehousing and Mining, 2014

Partial periodic patterns are commonly seen in real-world applications. The major problem of mining partial periodic patterns is the efficiency problem due to a huge set of partial periodic candidates. Although some efficient algorithms have been developed to tackle the problem, the performance of the algorithms significantly drops when the mining parameters are set low. In the past, the authors have adopted the projection-based approach to discover the partial periodic patterns from single-event time series. In this paper, the authors extend it to mine partial periodic patterns from a sequence of event sets which multiple events concurrently occur at the same time stamp. Besides, an efficient pruning and filtering strategy is also proposed to speed up the mining process. Finally, the experimental results on a synthetic dataset and real oil price dataset show the good performance of the proposed approach.

Journal of Intelligent Computing

Pattern with time period is more valuable because it can better describe objective knowledge. Previous studies on periodic patterns from market basket data focus on patterns without considering the items with their purchased quantities. But in real-life transactions, an item could be purchased multiple times in a transaction and different items may have different quantity in the transactions. To solve this problem, we incorporate the concept of transaction frequency (TF) and database frequency (DF) of an item in a time interval. Our algorithm works in two phases. In first phase we mined locally frequent item sets along with the set of intervals and their database frequency range and second phase mines the two types of periodic patterns (cyclic and acyclic) from the list of intervals. Experimental results are provided to validate the study.

IEEE Transactions on Knowledge and Data Engineering, 2015

Advanced technology in GPS and sensors enables us to track physical events, such as human movements and facility usage. Periodicity analysis from the recorded data is an important data mining task which provides useful insights into the physical events and enables us to report outliers and predict future behaviors. To mine periodicity in an event, we have to face real-world challenges of inherently complicated periodic behaviors and imperfect data collection problem. Specifically, the hidden temporal periodic behaviors could be oscillating and noisy, and the observations of the event could be incomplete. In this paper, we propose a novel probabilistic measure for periodicity and design a practical algorithm, ePeriodicity, to detect periods. Our method has thoroughly considered the uncertainties and noises in periodic behaviors and is provably robust to incomplete observations. Comprehensive experiments on both synthetic and real datasets demonstrate the effectiveness of our method.

Journal of Information and Telecommunication

Periodic frequent pattern (PFP) mining, the process of discovering frequent patterns that occur at regular periods in databases, is an important data mining task for various decision-making. Although several algorithms have been proposed for discovering PFPs, most of these algorithms often employ a two-stage approach to mining these periodic frequent patterns. That is, by firstly deriving the set of periods of a pattern from its coverset and subsequently evaluating the patterns' periodicity from the derived set of periods. This two-stage approach in discovering periodic frequent patterns as a result make existing algorithms inefficient in both runtime and memory usage. This paper presents solutions towards reducing the runtime, as well as, memory usage in discovering periodic frequent patterns. This is achieved by evaluating the periodicity of patterns without deriving the set of periods from their coversets. Experimental analysis on benchmark datasets show that the proposed solutions are efficient in reducing both the runtime and memory usage in mining periodic frequent patterns.

Lecture Notes in Computer Science, 2014

Periodic-frequent patterns are an important class of regularities that exist in a transactional database. Informally, a frequent pattern is said to be periodic-frequent if it appears at a regular interval specified by the user (i.e., periodically) in a database. A pattern-growth algorithm, called PFP-growth, has been proposed in the literature to discover the patterns. This algorithm constructs a tid-list for a pattern and performs a complete search on the tid-list to determine whether the corresponding pattern is a periodic-frequent or a non-periodic-frequent pattern. In very large databases, the tid-list of a pattern can be very long. As a result, the task of performing a complete search over a pattern's tid-list can make the pattern mining a computationally expensive process. In this paper, we have made an effort to reduce the computational cost of mining the patterns. In particular, we apply greedy search on a pattern's tid-list to determine the periodic interestingness of a pattern. The usage of greedy search facilitate us to prune the non-periodic-frequent patterns with a sub-optimal solution, while finds the periodic-frequent patterns with the global optimal solution. Thus, reducing the computational cost of mining the patterns without missing any knowledge pertaining to the periodic-frequent patterns. We introduce two novel pruning techniques, and extend them to improve the performance of PFP-growth. We call the algorithm as PFP-growth++. Experimental results show that PFP-growth++ is runtime efficient and highly scalable as well.

Proceedings 15th International Conference on Data Engineering (Cat. No.99CB36337), 1999

Partial periodicity search, i.e., search for partial periodic patterns in time-series databases, is an interesting data mining problem. Previous studies on periodicity search mainly consider finding full periodic patterns, where every point in time contributes (precisely or approximately) to the periodicity. However, partial periodicity is very common in practice since it is more likely that only some of the time episodes may exhibit periodic patterns.

Icde, 1999

Partial periodicity search, i.e., search for partial periodic patterns in time-series databases, is an interesting data mining problem. Previous studies on periodicity search mainly consider finding full periodic patterns, where every point in time contributes (precisely or approximately) to the periodicity. However, partial periodicity is very common in practice since it is more likely that only some of the time episodes may exhibit periodic patterns.

Lecture Notes in Computer Science, 2004

The problem of partial periodic pattern mining in a discrete data sequence is to find subsequences that appear periodically and frequently in the data sequence. Two essential subproblems are the efficient mining of frequent patterns and the automatic discovery of periods that correspond to these patterns. Previous methods for this problem in event sequence databases assume that the periods are given in advance or require additional database scans to compute periods that define candidate patterns. In this work, we propose a new structure, the abbreviated list table (ALT), and several efficient algorithms to compute the periods and the patterns, that require only a small number of passes. A performance study is presented to demonstrate the effectiveness and efficiency of our method.

ECAI, 2002

Abstract. Periodicity search in time series is a problem that has been investigated by mathematicians in various areas, such as statistics, economics, and digital signal processing. For large databases of time series data, scalability becomes an issue that traditional techniques fail to address. In existing time series mining algorithms for detecting periodic patterns, the period length is userspecified. This is a drawback especially for datasets where no period length is known in advance. We propose an algorithm that ...