An expanded prefix tree-based mining algorithm for sequential pattern maintenance with deletions

Sequential pattern mining is to discover frequent sequential patterns in a sequence database. The technique is applied to fields such as web click-stream mining, failure forecast, and traf- fic analysis. Conventional sequential pattern-mining approaches generally focus only the orders of items; however, the time interval between two consecutive events can be a valuable information when the time of the occurrence of an event is concerned. This study extends the concept of the well-known pattern growth approach, PrefixSpan algorithm, to propose a novel sequential pattern mining approach for sequential patterns with time intervals. Unlike the other time-interval sequential pattern-mining algorithms, the approach concerns the time for the next event to occur more than the timing information with its precedent events. To obtain a more reliable sequential pattern, a new measure of the confidence of a sequential pattern is defined. Experiments are conducted to evaluate the performance of the proposed approach.

Incremental sequential patterns for multivariate temporal association rules mining

One of the sub areas of the data mining includes sequential pattern mining. This mining algorithm is to find the repeating patterns after mining the sequence databases. These are used to find the relation between the various items in the data for different purposes. As these data keep changing according to the change in time, mining should be done on incremented or updated database to obtain the frequent sequential patterns. The proposed algorithm in this paper uses modified algorithm of sequential pattern mining including concepts of fuzzy space intervals. In this algorithm, frequently occurring sequential patterns in the sequence database are mined using apriori like method. Fuzzy theory is used for mining the space interval between the frequently occurring sequences. The sequentially occurring candidate patterns are found first. After that follows the frequently occurring sequential patterns, which are found by calculating the minimum fuzzy support along with the use of the fuzzy number. Each space cluster is found by fuzzy support computation. The final results comprises the frequently occurring fuzzy space sequentially based patterns. At last the outcome also confirms the excellence of the suggested MISPFSI algorithm.

Among various data mining techniques, sequential-pattern mining is used to discover the frequent subsequences from a sequence database. Most research handles the static database in batch mode to discover the desired sequential patterns. Transactions or customer sequences are, however, dynamically changed in real-world applications. In the past, the FUSP tree was designed to maintain and update the discovered information based on Fast UPdated (FUP) approach with sequence insertion and sequence deletion. The original customer sequences is still required to be rescanned if it is necessary. In this paper, the prelarge concept is adopted to maintain and update the built FUSP tree with sequence deletion. When the number of deleted customers is smaller than the safety bound of the prelarge concept, the original database is unnecessary to be rescanned but the sequential patterns can still be actually maintained and updated. Experiments are also conducted to show the performance of the proposed algorithm in terms of execution time and number of tree nodes.Keywordsprelarge conceptsequential patternsdeletiondynamic databasesFUSP tree

Sequential pattern mining is applicable in a wide range of applications since many types of data sets are in a time related format. Besides mining sequential patterns in a single dimension, mining multidimensional sequential patterns can give us more informative and useful patterns. Due to the huge increase in data volume and also quite large search space, efficient solutions for finding patterns in multidimensional sequence data are nowadays very important. For this reason, developing a parallel algorithm is necessary. In this paper, we present a multidimensional sequence model and a parallel algorithm follows the level-wise approach and all participating processors or workers generate candidate sequence and count their supports independently. Simulation experiments show good load balancing and scalable and acceptable speedup over different processors and problem sizes. dense data sets such as telecommunications, where there are many and long frequent patterns, performance of these algorithms degrades incredibly. On the one side, parallel and distributed computing is expected to relieve current mining methods from the sequential bottleneck, providing the ability to scale to massive datasets, and improving the response time. Achieving good performance on today's multiprocessor systems is a non-trivial task. The main challenges include synchronization and communication minimization, work-load balancing, find good data layout and data decomposition, and disk I/O minimization, which is especially important for data mining (4). On the other side, the basic single dimension can not satisfy the requirement of multi-attribute analysis, which is often the case in actual system practice. To address this problem, multidimensional sequence pattern mining is developed. The most time consuming operation in the discovery process of sequential patterns is the computation of the frequency of the occurrences of interesting subsequences in the sequence database. However, the number of sequential patterns grows exponentially and the task of finding all sequential patterns requires a lot of computational resources, which make it an ideal candidate for parallel processing. However, sequential pattern mining suffers from a scalability problem in both memory use and computational time when a dataset size is large. To perform mining on large datasets, we propose to parallelize this task. We demonstrate that our parallel algorithm can effectively alleviate the scalability problem. In this paper, we present a model for multidimensional sequence pattern and then propose a parallel algorithm for mining sequential patterns from multidimensional sequence data. The algorithm is based on the data parallelism strategy of pattern growth. The experimental results show that our parallel algorithms usually achieve good load balancing and scalability.

Real life sequential databases are usually not static. They tend to grow incrementally. So after every update a frequent pattern may no longer remains frequent while some infrequent patterns may appear as frequent in updated database. It is not a good idea to mine sequential database from scratch every time as the update occurs. It would be better if we can use the knowledge of already mined sequential patterns to find the complete set of sequential patterns for updated database. An incremental mining algorithm does the same thing. The main goal of an incremental mining algorithm is to reduce the time taken to find out the frequent patterns significantly i.e. it should mine the set of frequent patterns in significantly less time than a non-incremental mining algorithm. In this work we have approached using weight constraints, in time and space, of an idea of already existing algorithm called WSM.

In this paper, we introduce a new framework for discovering and using symmetries in sequential pattern mining tasks. Symmetries are permutations between items that leave invariant the sequential database. Symmetries present several potential benefits. They can be seen as a new kind of structural patterns expressing regularities and similarities between items. As symmetries induce a partition of the sequential patterns into equivalent classes, exploiting them would allow to improve the pattern enumeration process, while reducing the size of the output. To this end, we first address the problem of symmetry discovery from database of sequences. Then, we first show how Apriori-like algorithms can be enhanced by dynamic integration of the detected symmetries. Secondly, we provide a second symmetry breaking approach allowing to eliminate symmetries in a pre-processing step by reformulating the sequential database of transactions. Our experiments clearly show that several sequential pattern mining datasets contain such symmetry-based regularities. We also experimentally demonstrate that using such symmetries would results in significant reduction of the search space on some datasets.

The purpose of mining sequential patterns problem with weighted constraints is to find high-valued patterns, including infrequent patterns but having items which appear in the pattern of high importance in the sequence database (SD). Therefore, weighted sequential pattern mining will collect a set of more complete patterns with items of low support but of high importance. This paper proposes a new algorithm called WSPM_PreTree to find highly weighted sequential patterns. To collect a set of complete sequential patterns with the stricter weighted constraints of sequential patterns, the proposed algorithm uses both the minimum support constraint and the actual values of items appearing in the SD. To increase the performance of the finding weighted sequential patterns process, the algorithm uses the parent–child relationship on the prefix tree structure to create candidates and combines the weighted mean of the sequential 1-patterns that is calculated from the actual value of items in the SD as conditions to find the weighted sequential patterns. Experimental results show that the proposed algorithm is more efficient than sequential patterns mining with weight constraint (SPMW) algorithm [Ref. 20 ] in the runtime.

In data mining field, sequential pattern mining can be applied in divers applications such as basket analysis, web access patterns analysis, and quality control in manufactory engineering, etc. Many methods have been proposed for mining sequential patterns. However, conventional methods only consider the occurrences of itemsets in customer sequences. The sequential patterns discovered by these methods are called as positive sequential patterns, i.e., such sequential patterns only represent the occurrences of itemsets. In practice, the absence of a frequent itemset in a sequence may imply significant information. We call a sequential pattern as negative sequential pattern, which also represents the absence of itemsets in a sequence. The two major difficulties in mining sequential patterns, especially negative ones, are that there may be huge number of candidates generated, and most of them are meaningless. In this paper, we proposed a method for mining strong positive and negative sequential patterns, called PNSPM. In our method, the absences of itemsets are also considered. Besides, only sequences with high degree of interestingness will be selected as strong sequential patterns. An example was taken to illustrate the process of PNSPM. The result showed that PNSPM could prune a lot of redundant candidates, and could extract meaningful sequential patterns from a large number of frequent sequences.

The rapid evolution of the Internet has resulted in the availability of huge volumes of online learning resources on the web. However, many learners encounter difficulties in retrieval of suitable online learning resources due to information overload. Besides, different learners have different learning needs arising from their differences in learner’s context and sequential access pattern behavior. Traditional recommender systems such as content based and collaborative filtering (CF) use content features and ratings, respectively, to generate recommendations for learners. However, for accurate and personalized recommendation of learning resources, learner’s context and sequential access patterns should be incorporated into the recommender system. Traditional recommendation techniques do not incorporate the learner’s context and sequential access patterns in computing learner similarities and providing recommendations; hence, they are likely to generate inaccurate recommendations. Furthermore, traditional recommender systems provide unreliable recommendations in cases of high rating sparsity. In this paper, we propose a hybrid recommendation approach combining context awareness, sequential pattern mining (SPM) and CF algorithms for recommending learning resources to the learners. In our recommendation approach, context awareness is used to incorporate contextual information about the learner such as knowledge level and learning goals; SPM algorithm is used to mine the web logs and discover the learner’s sequential access patterns; and CF computes predictions and generates recommendations for the target learner based on contextualized data and learner’s sequential access patterns. Evaluation of our proposed hybrid recommendation approach indicated that it can outperform other recommendation methods in terms of quality and accuracy of recommendations.

In Dynamic Learning Pattern Recognition, the progress needs new ways of reliably detecting and describing dynamic patterns in big data. Additionally, based on the above research, this thesis proposes a novel cycle of the development of the dynamic learning pattern recognition through the combination of Enhanced Prefix Span Algorithm Model, as well as Long Short-Term Memory (LSTM) networks. An important part of our work in solving the issue of identifying dynamic patterns in textual data in online caselaw finding applications of sequential pattern mining methods and deep learning methods. On that basis, this study will then accelerate the traditional PrefixSpan algorithm to extract the sequential patterns of the data set taking into consideration the dynamic nature of the pattern. Then add LSTM networks to model and learn such sequential patterns and thus identify long term dependencies and time information. The suggested methodology has been researched and the performance of the designed methodology compared to other classifiers such as MultinomialNB, Logistical Regression. The findings demonstrate the high performance of the proposed model whose accuracy, recall, and F1-score are 98.45, 98.62, and 97.3, respectively. This study is to combine sequential pattern mining with the deep learning, which serves to the advancement of dynamic learning pattern recognition methods and to give certain promising suggestions in the cases such as natural language processing and predictive modeling. It is an effort by python implementation to promote the efficiency and precision of recognition of learning patterns in different modalities. Here, we apply it in assembling a sound framework of the effective recognition and adaptation to changing patterns within textual data to assist in enhancing and more efficient learning on a variety of modalities in different situations.

As an important branch of data mining, sequential patterns mining has been extensively studied. Based on sequential patterns mining, Structural Relation Patterns (SRPs) mining is proposed for mining relations among sequences, these relations are generally hidden behind sequential patterns. Upon the previous researches, the concepts of concurrent relation pattern and exclusive relation pattern are redefined; the definitions of ordered relation pattern and iterate relation pattern are given. The properties of SRPs are discussed, and they form a theoretical foundation for further study of structural relation patterns and relative mining algorithms. Beside, the thinking of mining associate relations among sequential patterns is proposed. SRPs mining is significant in practical applications same as sequential patterns mining.

The proposed system is mainly based on mining closed sequential web access patterns. Initially, the PrefixSpan algorithm is employed on the preprocessed web server log data for mining sequential web access patterns. Subsequently, with the aid of post-pruning strategy, the closed sequential web access patterns are discovered from the complete set of sequential web access patterns. Then, a pattern tree, a compact representation of closed sequential patterns, is constructed from the discovered closed sequential web access patterns. The Patricia trie based data structure is used in the construction of the pattern tree. For a given user’s web access sequence, the proposed system provides recommendations on the basis of the constructed pattern tree. The experimentation of the proposed system is performed using synthetic dataset and the performance of the proposed recommendation system is evaluated with precision, applicability and hit ratio

In this paper, we propose a new SQL based incremental distributed algorithm for predicting the next location of a mobile user in a mobile web environments. Parallel and Distributed data mining algorithm is applied on moving logs stored in geographically distributed data grid to generate the mobility pattern, which provides various location based services to the mobile users. One of the existing works for deriving mobility pattern is re-executing the algorithm from scratch results in excessive computation. In our work, we have designed new incremental algorithm by maintaining infrequent mobility patterns, which avoids unnecessary scan of full database. We built data grid system on a cluster of workstation using open source Globus Toolkit (GT) and Message Passing Interface extended with Grid Services (MPICH-G2). The experiments were conducted on original data sets with incremental addition of data and the computation time was recorded for each data sets. We analyzed our results with various sizes of data sets and it shows the time taken to generate mobility pattern by incremental mining algorithm is less than re-computing approach.

Sequential pattern mining is an important data mining task with applications in basket analysis, world wide web, medicine and telecommunication. This task is challenging because sequence databases are usually large with many and long sequences and the number of possible sequential patterns to mine can be exponential. We proposed a new sequential pattern mining algorithm called FAST which employs a representation of the dataset with indexed sparse id-lists to fast counting the support of sequential patterns. We also use a lexicographic tree to improve the efficiency of candidates generation. FAST mines the complete set of patterns by greatly reducing the effort for support counting and candidate sequences generation. Experimental results on artificial and real data show that our method outperforms existing methods in literature up to an order of magnitude or two for large datasets.