Search

Erasable-itemset mining is a valuable method of pattern extraction for helping the manager of a factory analyze production planning. The erasable itemsets derived can be considered important production information regarding how to plan the production of a factory during an economic depression or financial shortage for the manager. After the erasable-itemset mining was proposed in 2009, several efficient mining approaches for finding erasable itemsets have been developed. However, these methods require a considerable amount of execution time when the amount of product data is large. Especially, manufacturing small amounts of versatile products has been a trend today, and it will generate a large product database. This paper adopts a bitmap representation for itemsets in an erasable-itemset mining algorithm to speed up the execution. Unlike the traditional bitmap meaning for frequent itemsets, a bitmap for erasable-itemset mining here denotes the relationship that a product includes at least one material (item) in a specified itemset. Using the bitmap representation can easily find the desired products to check, thus decreasing the scans of a database. Experimental evaluation on synthesized and real datasets was used to compare the proposed approach with the other two under different parameter values. The experimental results show that the proposed approach can make a good trade-off between execution time and memory usage.

Structural optimization is an important tool for structural designers that helps them to find innovative design solutions and structural forms with a better exploitation of materials as well as dec...

This paper proposes a new approach to a novel value network architecture for the game Go , called a multilabeled (ML) value network. In the ML value network, different values (win rates) are trained simultaneously for different settings of komi, a compensation given to balance the initiative of playing first. The ML value network has three advantages: 1) it outputs values for different komi; (2) it supports dynamic komi; and (3) it lowers the mean squared error (MSE). This paper also proposes a new dynamic komi method to improve game-playing strength. This paper also performs experiments to demonstrate the merits of the architecture. First, the MSE of the ML value network is generally lower than the value network alone. Second, the program based on the ML value network wins by a rate of 67.6% against the program based on the value network alone. Third, the program with the proposed dynamic komi method significantly improves the playing strength over the baseline that does not use dynamic komi, especially for handicap games. To our knowledge, up to date, no handicap games have been played openly by programs using value networks. This paper provides these programs with a useful approach to playing handicap games.

In order to better solve the problem of the reconfiguration of a large number of distributed power sources connected to the distribution network, an improved cuckoo search algorithm based on differential evolution was proposed to reconstruct the distribution network. In the early stage, random step size was improved for the reason of poor search performance of cuckoo algorithm. In the later stage, differential evolutionary algorithm was introduced for the defects with slow convergence speed and low optimization accuracy. Finally, an example of IEEE33 is given to demonstrate the effectiveness and feasibility of this method, and it can be better applied to the study of distribution network reconstruction.

In recent years, fuzzy utility mining has become an area of interest due to advancement of human reasoning. With regards to real applications, transactions in a database often involve things, such as transaction time, stamp, and much more. It is also noted that not all products in a store are displayed on the shelf, especially the seasonal ones. This paper, therefore, addresses these issues by presenting an effective framework called temporal-based fuzzy utility mining to give more attention to the transaction period of given items according to the concept of fuzzy utility mining. The temporal-based fuzzy utility mining proposed here is, however, a more complex approach when compared with the traditional fuzzy utility mining. A more complicated model for non-lost upper-bound fuzzy utility is thus proposed for effective mining. Furthermore, based on this model, a two-phase algorithm is developed for temporal-based fuzzy utility mining. Finally, the difference of fuzzy utility item sets with and without consideration of the lifetime of the items is shown by the experimental results under various experimental conditions.

Many of the strongest game playing programs use a combination of Monte Carlo tree search (MCTS) and deep neural networks (DNN), where the DNNs are used as policy or value evaluators. Given a limited budget, such as online playing or during the self-play phase of AlphaZero (AZ) training, a balance needs to be reached between accurate state estimation and more MCTS simulations, both of which are critical for a strong game playing agent. Typically, larger DNNs are better at generalization and accurate evaluation, while smaller DNNs are less costly, and therefore can lead to more MCTS simulations and bigger search trees with the same budget. This paper introduces a new method called the multiple policy value MCTS (MPV-MCTS), which combines multiple policy value neural networks (PV-NNs) of various sizes to retain advantages of each network, where two PV-NNs f_S and f_L are used in this paper. We show through experiments on the game NoGo that a combined f_S and f_L MPV-MCTS outperforms single PV-NN with policy value MCTS, called PV-MCTS. Additionally, MPV-MCTS also outperforms PV-MCTS for AZ training., Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI-19)

Most of the existing studies in temporal data mining consider only lifespan of items to find general temporal association rules. However, an infrequent item for the entire time may be frequent within part of the time. We thus organize time into granules and consider temporal data mining for different levels of granules. Besides, an item may not be ready at the beginning of a store. In this paper, we use the first transaction including an item as the start point for the item. Before the start point, the item may not be brought. A three-phase mining framework with consideration of the item lifespan definition is designed. At last, experiments were made to demonstrate the performance of the proposed framework.

An effective form-finding method for form-fixed spatial network structures is presented in this paper. The adaptive form-finding method is introduced along with the example of designing an ellipsoidal network dome with bar length variations being as small as possible. A typical spherical geodesic network is selected as an initial state, having bar lengths in a limit group number. Next, this network is transformed into the ellipsoidal shape as desired by applying compressions on bars according to the bar length variations caused by transformation. Afterwards, the dynamic relaxation method is employed to explicitly integrate the node positions by applying residual forces. During the form-finding process, the boundary condition of constraining nodes on the ellipsoid surface is innovatively considered as reactions on the normal direction of the surface at node positions, which are balanced with the components of the nodal forces in a reverse direction induced by compressions on bars. The node positions are also corrected according to the fixed-form condition in each explicit iteration step. In the serial results of time history, the optimal solution is found from a time history of states by properly choosing convergence criteria, and the presented form-finding procedure is proved to be applicable for form-fixed problems.

This paper proposes a bitmap representation approach for modifying the erasable-itemset mining algorithm to increase its efficiency. The proposed approach uses the bitmap concept to save processing time. Through experimental evaluation, simulation datasets were used to compare the traditional erasable itemset mining and the proposed approach under various experimental conditions.

Different from full periodic patterns, partial periodic patterns could ignore the occurrence of some events in time positions. In this paper, we have presented a gradually pruning algorithm (GPA) for reducing the number of candidate patterns in the mining process. It is based on the two-phased periodic utility upper-bound (PUUB) model and could avoid information loss. Compared to the original approach without gradually pruning, the one proposed here could reduce the execution time but get the same desired results.

Weighted itemset mining has been a widely studied topic in data mining. The reason is that weighted itemset mining considers not only the occurrence of items in transactions but also the individual importance of items. The traditional upper-bound model can be used to handle the weighted itemset mining problem, but a large number of candidates are generated by the model. This work thus presents an improved model to enhance the effectiveness of reducing unpromising candidates. Besides, an effective strategy, projection-based pruning, is proposed as well to tighten upper-bounds of weighted supports for itemsets in the mining process, thus reducing the execution time further. Through a series of experimental evaluation, the results on synthetic and real datasets show that the proposed approach has good performance in both pruning effectiveness and execution efficiency under various parameter settings when compared to some other approaches.

Association-rule mining is used to mine the relationships among the occurrences itemsets in a transactional database. An item is treated as a binary variable whose value is one if it appears in a transaction and zero otherwise. In real-world appli- cations, several products may be purchased at the same time, with each product having an associated profit, quantity, and price. Association-rule mining from a binary database is thus not sufficient in some applications. Utility mining was thus proposed as an extension of frequent-itemset mining for considering various factors from the user. Most utility mining approaches can only process static databases and use batch processing. In real-world applications, transactions are dynamically inserted into or deleted from databases. The Fast UPdated (FUP) algorithm and the FUP2 algorithm were respectively proposed to handle trans- action insertion and deletion in dynamic databases. In this paper, a fast-updated high-utility itemsets for transaction deletion (FUP-HUI-DEL) algorithm is proposed to handle transaction deletion for efficiently updating discovered high utility itemsets in decremental mining. The two-phase approach in high utility mining is applied to the proposed FUP-HUI-DEL algorithm for preserving the downward closure property to reduce the number of candidates. The FUP2 algorithm for handling transaction deletion in association-rule mining is adopted in the proposed FUP-HUI-DEL algorithm to reduce the number of scans of the original database in high utility mining. Experiments show that the proposed FUP-HUI-DEL algorithm outperforms the batch two-phase approach.

Mining useful information from large databases has become an important research issue in recent years. Among the classes of derived knowledge, sequential patterns can be used to discover customer behaviors to facilitate efficient decision-making. The fast updated frequent-pattern (FUFP)-tree algorithm has been proposed to efficiently mine frequent itemsets through transaction insertion in incremental mining. The present study extends this algorithm to develop an incremental fast updated sequential-pattern (FUSP)-tree algorithm for efficiently handling sequential patterns whether the newly inserted transactions are from customers already in the database or from new customers. An FUSP-tree structure is designed to make the update process easier. The FUSP-growth algorithm is proposed for mining frequent sequences (sequential patterns) from the FUSP-tree. Experimental results show that the proposed FUSP-tree algorithm has good performance for incrementally handling newly inserted transactions.

We introduce a new research work, on-shelf utility mining with negative item values.We propose a TS-HOUN algorithm for mining the new type of utility itemsets.The derived itemsets are expected to be more reliable in terms of business.The synthetic and real datasets are used to show the TS-HOUN is effective.Experiments show that TS-HOUN can find more utility itemsets with negative values. On-shelf utility mining has recently received interest in the data mining field due to its practical considerations. On-shelf utility mining considers not only profits and quantities of items in transactions but also their on-shelf time periods in stores. Profit values of items in traditional on-shelf utility mining are considered as being positive. However, in real-world applications, items may be associated with negative profit values. This paper proposes an efficient three-scan mining approach to efficiently find high on-shelf utility itemsets with negative profit values from temporal databases. In particular, an effective itemset generation method is developed to avoid generating a large number of redundant candidates and to effectively reduce the number of data scans in mining. Experimental results for several synthetic and real datasets show that the proposed approach has good performance in pruning effectiveness and execution efficiency.

Weighted sequential pattern mining has recently been discussed in the field of data mining. Different from traditional sequential pattern mining, this kind of mining considers different significances of items in real applications, such as cost or profit. Most of the related studies adopt the maximum weighted upper-bound model to find weighted sequential patterns, but they generate a large number of unpromising candidate subsequences. In this study, we thus propose an efficient approach for finding weighted sequential patterns from sequence databases. In particular, a tightening strategy in the proposed approach is proposed to obtain more accurate weighted upper-bounds for subsequences in mining. Through the experimental evaluation, the results also show the proposed approach has good performance in terms of pruning effectiveness and execution efficiency.

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.

Partial periodic pattern mining has recently become an important issue in the field of data mining due to its wide applications in many businesses. A partial periodic pattern considers part of but not all the events within a specific period length, repeating with high frequency in an event sequence. Traditional partial periodic pattern mining, however, only considered the frequencies of patterns, but did not consider events that might have different importance. The study thus proposes a weighted partial periodic patterns mining algorithm to resolve this problem. To increase the efficiency, the two-phase upper-bound weighted model based on segmental maximum weights is adopted to prune unimportant candidates in early stage. Then the weighted partial periodic patterns are discovered from the candidate patterns. Finally, the experimental results on synthetic datasets and a real oil dataset show that the weighted partial periodic pattern mining is more practical to assist users for decision making.

Through the development of computer image processing technology and UAV technology, after installing high-definition cameras on UAVs and taking high-resolution images, the technology of directly generating DOM images in the surveyed areas using software has been well-developed. However, under the emergency conditions such as dealing with disasters, the long-term processing time required for aerial surveys of UAVs has become a major efficiency constraint to surveying and mapping. This paper focuses on the rapid mapping and mosaicking of survey images from unmanned aerial vehicles under emergency conditions, and elaborates current research status, difficulties and resolvents of the rapid mapping of existing UAVs.

Data mining has been studied for a long time. Its goal is to help market managers find relationships among items from large databases and thus increase sales volume. Association-rule mining is one of the well known and commonly used techniques for this purpose. The Apriori algorithm is an important method for such a task. Based on the Apriori algorithm, lots of mining approaches have been proposed for diverse applications. Many of these data mining approaches focus on positive association rules such as ''if milk is bought, then cookies are bought''. Such rules may, however, be misleading since there may be customers that buy milk and not buy cookies. This paper thus takes the properties of propositional logic into consideration and proposes an algorithm for mining highly coherent rules. The derived association rules are expected to be more meanful and reliable for business. Experiments on two datasets are also made to show the performance of the proposed approach.

In traditional association rule mining, most algorithms are designed to discover frequent itemsets from a binary database. Utility mining was thus proposed to measure the utility values of purchased items for revealing high utility itemsets from a quantitative database. In the past, a two-phase high utility mining algorithm was thus proposed for efficiently discovering high utility itemsets from a quantitative database. In dynamic data mining, transactions may be inserted, deleted, or modified from a database. In this case, a batch mining procedure must rescan the whole updated database to maintain the up-to-date information. Designing an efficient approach for handling dynamic databases is thus a critical research issue in utility mining. In this paper, an incremental mining algorithm is proposed for efficiently maintaining discovered high utility itemsets based on pre-large concepts. Itemsets are first partitioned into three parts according to whether they have large (high), pre-large, or small transaction-weighted utilization in the original database and in inserted transactions. Individual procedures are then executed for each part. Experimental results show that the proposed incremental high utility mining algorithm outperforms existing algorithms.

Recently, utility mining has widely been discussed in the field of data mining. It finds high utility itemsets by considering both profits and quantities of items in transactional data sets. However, most of the existing approaches are based on the principle of levelwise processing, as in the traditional two-phase utility mining algorithm to find a high utility itemsets. In this paper, we propose an efficient utility mining approach that adopts an indexing mechanism to speed up the execution and reduce the memory requirement in the mining process. The indexing mechanism can imitate the traditional projection algorithms to achieve the aim of projecting sub-databases for mining. In addition, a pruning strategy is also applied to reduce the number of unpromising itemsets in mining. Finally, the experimental results on synthetic data sets and on a real data set show the superior performance of the proposed approach.

Association-rule mining, which is based on frequency values of items, is the most common topic in data mining. In real-world applications, customers may, however, buy many copies of products and each product may have different factors, such as profits and prices. Only mining frequent itemsets in binary databases is thus not suitable for some applications. Utility mining is thus presented to consider additional measures, such as profits or costs according to user preference. In the past, a two-phase mining algorithm was designed for fast discovering high utility itemsets from databases. When data come intermittently, the approach needs to process all the transactions in a batch way. In this paper, an incremental mining algorithm for efficiently mining high utility itemsets is proposed to handle the above situation. It is based on the concept of the fast-update (FUP) approach, which was originally designed for association mining. The proposed approach first partitions itemsets into four parts according to whether they are high transaction-weighted utilization itemsets in the original database and in the newly inserted transactions. Each part is then executed by its own procedure. Experimental results also show that the proposed algorithm executes faster than the two-phase batch mining algorithm in the intermittent data environment

Utility mining has recently been an emerging topic in the field of data mining. It finds out high utility itemsets by considering both the profits and quantities of items in transactions. It may have a bias if items are not always on shelf. In this paper, we thus design a new kind of patterns, named high on-shelf utility itemsets, which considers not only individual profit and quantity of each item in a transaction but also common on-shelf time periods of a product combination. We also propose a two-phased mining algorithm to effectively and efficiently discover high on-shelf utility itemsets. In the first phase, the possible candidate on-shelf utility itemsets within each time period are found level by level. In the second phase, the candidate on-shelf utility itemsets are further checked for their actual utility values by an additional database scan. At last, the experimental results on synthetic datasets also show the proposed approach has a good performance.

It’s of great significance for wind power integration into grid to forecast wind power. Based on forecasting wind power by BP neural network, the article introduces global optimization algorithm, Imperialist Competitive Algorithm (ICA) to provide optimized initial weights of BP neural network. Thus, it can overcome the entrapment in local optical optimum of BP neural network. Compared with BP neural network, it is found that the performances of ICA-BP neural network, which are training, testing and forecasting of wind power, are much better.

A GA-based privacy preserving utility mining method is proposed to find appropriate transactions to be inserted into the database for hiding sensitive high utility itemsets. It maintains the low information loss while providing information to the data demanders and protects the high-risk information in the database. A flexible evaluation function with three factors is designed in the proposed approach to evaluate whether the processed transactions are required to be inserted. Three different weights are, respectively, assigned to the three factors according to users. Moreover, the downward closure property and the prelarge concept are adopted in the proposed approach to reduce the cost of rescanning database, thus speeding up the evaluation process of chromosomes.

According to multi-site relationship, this work presents a new issue named online multi-site utility mining, which considers not only quantities and profits of items in transactions but also online mining in a multi-site environment, to effectively address the distributed utility mining in multiple sites. In addition, an effective online framework, namely TP-OMU (Three-Phase Online Multi-site Utility mining algorithm), is proposed for coping with this problem, and the predicting strategy is designed to reduce the number of unpromising candidates by their utility upper-bounds in mining. Finally, the experimental results show TP-OMU has good efficiency in comparison with the traditional two-phase utility mining approach.

In our previous approach, we proposed an apriori-based algorithm for mining highly coherent association rules, and it is time-consuming. In this paper, we present an efficient mining approach, which is a projection-based technique, to speed up the execution of finding highly coherent association rules. In particular, an indexing mechanism is designed to help find relevant transactions quickly from a set of data, and a pruning strategy is proposed as well to prune unpromising candidate itemsets early in mining. The experimental results show that the proposed algorithm outperforms the traditional mining approach for a real dataset.

Most of the existing studies in utility mining use a single minimum utility threshold to determine whether an item is a high utility item. This way is, however, hard to reflect the nature of items. This work thus presents another viewpoint about defining the minimum utilities of itemsets. The maximum constraint is adopted, which is well explained in the text and suitable to some mining domains when items have different utility values. In addition, an effective two-phase mining approach is proposed to cope with the problem of multi-criteria utility mining under maximum constraints. The experimental results show the performance of the proposed approach.

In this paper, a GA-based privacy-preserving utility mining method is proposed to delete appropriate transactions for hiding sensitive high utility itemsets from a database. The downward closure property and the pre-large concepts are adopted in the proposed algorithm to reduce the cost of rescanning databases. Experiments are also conducted to evaluate the performance of the proposed approach in execution time and the amount of side-effects.

This work handles fuzzy utility sequential pattern mining, which applies the fuzzy set concept to find interesting high utility sequential patterns with linguistic meaning. In particular, a new fuzzy utility function is developed to evaluate the linguistic benefit of a pattern in a sequence, and an effective approach is developed to find high fuzzy utility sequential patterns from a quantitative sequence database. The experimental results show the proposed approach has good performance under various parameter settings.

In the past, an incremental algorithm for mining high utility itemsets was proposed to derive high utility itemsets in an incrementally inserted way. In real-world applications, transactions are not only inserted into but also deleted from a database. In this paper, a maintenance algorithm is thus proposed for reducing the execution time of maintaining high utility itemsets due to transaction deletion. Experimental results also show that the proposed maintenance algorithm runs much faster than the batch approach.

In this work, a decoder chip for time-invariant tail-biting LDPC convolutional code (TB-LDPC-CC) is proposed. By modifying the layered decoding scheduling, the proposed decoding algorithm can achieve twice faster decoding convergence than the conventional flooding scheduling. Furthermore, 30.77% storage requirement is also reduced due to adaptive channel value addressing employed in memory-based decoder design. The multiple frame sizes handling ability can lower the power and adapt to multiple applications. By integrating these techniques, a TB-LDPC-CC decoder chip supporting three frame sizes is implemented in UMC 90nm CMOS technology. The decoder containing 4 processors occupies 2.18mm2 area and provides maximum throughput 3.66Gb/s under 0.8V supply and 305MHz with a 18.8pJ/bit/proc energy efficiency.

To further enhance the performance of finding weighted frequent item sets, this work presents an effective upper-bound model for reducing unpromising candidates in mining process. To achieve this goal, a projection-based pruning strategy based on our previously proposed model is developed to gradually tighten the upper-bound value for each transaction. The experimental results show that the proposed approach can achieve good performance in efficiency.

Different from the existing algorithms, this work presents an efficient projection-based algorithm to find fuzzy frequent itemsets in quantitative databases. In particular, the proposed algorithm adopts the two strategies, indexing and pruning, to effectively speed up the execution efficiency in mining. In the experimental evaluation, the results on a synthetic dataset show the proposed algorithm executes faster than our previous algorithm.

Different from the existing studies, this work presents a new kind of rules with the concept of a hierarchy of time granules, namely hierarchical temporal association rules. The lifespan of an item in a time granule is calculated from the publication time of the item to the end time in the time granule. A three-phase mining framework is proposed to effectively and efficiently find this kind of rules from a temporal database. The experimental results show the performance of the proposed algorithm under the item lifespan definition.

In the data mining area, partial periodic pattern mining has become an important issue in many business applications. Although weighted sequential pattern mining algorithms have been widely discussed, until now, there is no further discussion in the field of weighed partial periodic pattern mining. Thus, this work introduces a new research issue, named weighted partial periodic pattern mining, which considers the individual significances of events in an event sequence. In addition, a projection-based mining algorithm is presented to effectively handle the weighted partial periodic pattern mining problem. The experimental results show the proposed algorithm is efficient.

In this paper, we propose an efficient projection-based algorithm to discover high sequential utility patterns from quantitative sequence databases. An effective pruning strategy in the proposed algorithm is designed to tighten upper-bounds for subsequences in mining. By using the strategy, a large number of unpromising subsequences could be pruned to improve execution efficiency. Finally, the experimental results on synthetic datasets show the proposed algorithm outperforms the previously proposed algorithm under different parameter settings.

In this paper the experimental and theoretical investigation of a curved cable-stayed bridge is presented as the result of a common research activity carried out between the University IUAV of Venice and the College of Civil Engineering of Tongji University, Shanghai, China. The experimental data were made available by the University IUAV of Venice on the basis of a number of ambient vibration tests carried out by the Politecnico di Milano. In-situ tests include monitoring performed in 2006, prior to opening of the bridge to traffic, and after in July 2010 and April 2011. Recorded data highlighted some differences in bridge response over the years, confirmed by changes in modal frequencies and variations of tension in some stays. Towards the aim of identifying the main causes of these variations, comparative analyses were performed though a tuned finite element model of the bridge, to be used as a base for future long-term monitoring of the investigated structure.

In this paper, a maintenance algorithm for average-utility mining is proposed to update derived high average-utility itemsets in dynamic databases. It first calculates the count difference of modified itemsets and then partitions them into four parts according to whether they are high upper-bound average-utility itemsets in the original database and whether their count difference is positive or negative. Each part is then processed in its own way. Experimental results show the proposed maintenance algorithm runs faster than the two-phase approach for mining high average-utility itemsets in dynamic databases.

In this paper, we try to improve the performance of utility mining. We propose a new projection-based mining algorithm and embed two pruning strategies in it to efficiently find high utility itemsets in a database. By using the two designed strategies, a large number of unpromising itemsets can be pruned away at an early stage, and the data size could recursively be reduced to save the scan time. Finally, the experimental results on synthetic datasets show the proposed algorithm runs faster than the other utility mining algorithms under different parameter settings.

In this paper, we propose an efficient mining approach which adopts an indexing mechanism to speed up the execution efficiency and reduce the memory requirement in the utility mining process. Besides, a pruning strategy is designed to reduce the number of unpromising itemsets for mining. The experimental results also show the performance of the proposed approach is better than that of traditional two-phase utility mining algorithm under different parameters.

Traditionally, the utility of an itemset is the summation of the utilities of the itemset in transactions regardless of its length. The average utility measure was then proposed to reveal a better utility effect of combining several items than the utility measure. In this paper, a maintenance algorithm for high average-utility itemsets is proposed for reducing execution time when records are deleted. The proposed approach is designed based on the two-phase utility mining and the FUP (Fast UPdate) concept and can achieve a good performance especially when the knowledge changes only to a small extent.

In this paper, we handle a new kind of patterns named high on-shelf utility itemsets, which considers not only individual profit and quantity of each item in a transaction but also common on-shelf time periods of a product combination. We propose a three-scan mining approach to effectively and efficiently discover high on-shelf utility itemsets. The proposed approach adopts an itemset-generation mechanism to prune redundant candidates early and to systematically check the itemsets from transactions. The experimental results on synthetic datasets also show the proposed approach has a good performance.

In this paper, we design a new kind of patterns, named high transaction-weighted utility itemsets, which considers not only individual profits and quantities of the items in a transaction, but also the contribution of each transaction in a database. We also propose a two-phased mining algorithm to discover high transaction-weighted utility itemsets. The experimental results on synthetic datasets show the proposed approach has a good performance.

In recent years, with the development of the economy and the advancement of the national income, personal healthcare has been becoming an important issue. Since the health examination can help people understand their own health conditions clearly, many people make regularly health examinations to avoid missing the best treatment time. So the health examination is an important role for people’s health statuses. However, people only get aware of the result of health examination report but they are not clear whether their health trends are high-risk or not. In this paper, we proposed a novel framework for discovering health risk patterns and the relationships between the patterns and a target disease by mining historic health examination data. Moreover, a prediction model for the target disease can be constructed effectively by the discovered information. Through the framework, the physicians can early provide health alerts and medical treatments for people to effectively increase the quality of disease prevention.

In this paper, instead of proposing the fastest mining algorithm in the world, we present a new approach in mining association rules. We propose a new algorithm - GRA (Gradational Reduction Approach). It adopts three mechanisms to increase the performance of mining. First, GRA algorithm uses a hash based technique, Hash MAP, which is similar to Hash Table to increase the access efficiency. Second, GRA algorithm uses an infrequent itemsets filtering mechanism to avoid generating a great deal of infrequent sub-itemsets of transaction records. Third, in order to reduce the size of database, GRA algorithm uses gradational reduction mechanism which uses the frequent itemsets as the information of filtration mechanisms to erase the infrequent items from database at every phase. GRA algorithm can decrease a large number of non-frequent itemsets and increase the utility rate of memory.

The technology of data mining is more important in recent years, and it is generally applied to commercial forecast and decision supports. Sequential pattern mining algorithms in the field of data mining play one of the important roles. Many of sequential pattern mining algorithms were proposed to improve the efficiency of data mining or save the utility rate of memory. So, our major study tries to improve the efficiency of sequential pattern mining algorithms. We propose a new algorithm - GRS (A Gradational Reduction Approach for Mining Sequential Patterns) which is an efficient algorithm of mining sequential patterns. GRS algorithm uses gradational reduction mechanism to reduce the length of transactions and uses GraDec function to avoid generating large number of infrequent sequential patterns; and it is very suitable to mine the transactions of databases whose record lengths are very long. The GRS algorithm only generates some sequences which are very possible to be frequent. So, the GRS algorithm can decrease a large number of infrequent sequences and increase the utility rate of memory.

Utility mining has recently been an emerging topic in the field of data mining. It finds out high-utility itemsets by considering both the profits and quantities of items in transactions. In real applications, however, utility mining may have a bias if items are not always on shelf. On-shelf utility mining is then proposed, which considers not only individual profit and quantity of each item in a transaction but also common on-shelf time periods of a product combination. In the past, a two-phase on-shelf utility mining was proposed to discover the desired patterns in on-shelf utility mining. It, however, adopted the level-wise mining way to find the patterns. To speed up the execution efficiency, a three-scan mining approach is thus proposed in the paper to efficiently discover high on-shelf utility itemsets. The proposed approach utilizes an itemset-generation mechanism to prune redundant candidates early and to systematically check the itemsets from transactions. At last, the experimental result...