Creat membership Creat membership
Sign in

Forgot password?

Confirm
  • Forgot password?
    Sign Up
  • Confirm
    Sign In
home > search

Now showing items 65 - 80 of 139

  • A modified approach to speed up genetic-fuzzy data mining with divide-and-conquer strategy

    V.S. Tseng   Tzung-Pei Hong   Chun-Hao Chen  

    In the past; we proposed a fuzzy data-mining algorithm for extracting both association rules and membership functions from quantitative transactions based on the divide-and-conquer strategy. In this paper; an enhanced approach; called the cluster-based genetic-fuzzy mining algorithm; is thus proposed to speed up the evaluation process and keep nearly the same quality of solutions as the previous one. It first divides the chromosomes in a population into k clusters by the A-means clustering approach and evaluates each individual according to its own information and the information of the cluster it belongs to. The final best sets of membership functions in all the populations are then gathered together for mining fuzzy association rules. Experimental results also show the effectiveness and efficiency of the proposed approach.
    Download Collect
  • Mining up-to-date knowledge from log data

    Shyue-Liang Wang   Yi-Ying Wu   Tzung-Pei Hong  

    In this paper; a new concept of up-to-date patterns is proposed; which is a hybrid of the association rules and temporal mining. An up-to-date pattern is composed of an itemset and its up-to-date lifetime; in which the user-defined minimum support threshold must be satisfied. The proposed approach can mine more useful large itemsets than the conventional ones which discover large itemsets valid only for the entire database. Experimental results also show the performance of the proposed approach.
    Download Collect
  • Learning Fuzzy Rules from Incomplete Quantitative Data by Rough Sets

    Tzung-Pei Hong   Li-Huei Tseng   Been-Chian Chien  

    In this paper; we deal with the problem of learning from incomplete quantitative data sets based on rough sets. Quantitative values are first transformed into fuzzy sets of linguistic terms using membership functions. Unknown attribute values are then assumed to be any possible linguistic terms and are gradually refined according to the fuzzy incomplete lower and upper approximations derived from the given quantitative training examples. The examples and the approximations then interact on each other to derive certain and possible rules and to estimate appropriate unknown values. The rules derived can then serve as knowledge concerning the incomplete quantitative data set.
    Download Collect
  • Maintenance of multiple-level association rules for record modification

    Tzung-Pei Hong   Tzu-Jung Huang   Chao-Sheng Chang  

    In the past, researchers usually assumed databases were static and items lay on the same level to simplify the mining problem. Modification of records with item taxonomy is, however, commonly seen in real-world applications. In this paper, we thus attempt to extend Han and Fu's approach and our previous concept of pre-large itemsets to maintain discovered multiple-level association rules for record modification. The concept of pre-large itemsets is used to reduce the need for rescanning original databases and to save maintenance costs. A pre-large itemset is not truly large, but promises to be large in the future. An algorithm is proposed based on the concept to achieve this purpose. The proposed algorithm doesn't need to rescan the original database until a number of records have been modified.
    Download Collect
  • Splitting and merging version spaces to beam disjunctive concepts

    Tzung-Pei Hong   Shian-Shyong Tseng  

    We have modified the original version space strategy in order to learn disjunctive concepts incrementally and without saving past training instances. The algorithm time complexity is also analyzed, and its correctness is proven.
    Download Collect
  • Extracting membership functions in fuzzy data mining by Ant Colony Systems

    Yu-Lung Wu   Min-Thai Wu   Shyue-Liang Wang   Ya-Fang Tung   Tzung-Pei Hong  

    Ant Colony Systems (ACS) have been successfully applied to optimization problems in recent years. However; few works have been done on applying ACS to data mining. This paper proposes an ACS-based algorithm to extract membership functions in fuzzy data mining. The membership functions are first encoded into binary bits and then fed into the ACS to search for the optimal set of membership functions. An example is given to demonstrate the proposed algorithm. Numerical experiments are also made to show the performance of the proposed approach.
    Download Collect
  • Mining coverage-based fuzzy rules by evolutional computation

    Tzung-Pei Hong   Yeong-Chyi Lee  

    The authors propose a novel mining approach based on the genetic process and an evaluation mechanism to automatically construct an effective fuzzy rule base. The proposed approach consists of three phases: fuzzy-rule generating, fuzzy-rule encoding and fuzzy-rule evolution. In the fuzzy-rule generating phase, a number of fuzzy rules are randomly generated. In the fuzzy-rule encoding phase, all the rules generated are translated into fixed-length bit strings to form an initial population. In the fuzzy-rule evolution phase, genetic operations and credit assignment are applied at the rule level. The proposed mining approach chooses good individuals in the population for mating, gradually creating better offspring fuzzy rules. A concise and compact fuzzy rule base is thus constructed effectively without human expert intervention.
    Download Collect
  • An Effective Attribute Clustering Approach for Feature Selection and Replacement

    Tzung-Pei Hong   Po-Cheng Wang   Yeong-Chyi Lee  

    Feature selection is an important pre-processing step in mining and learning. A good set of features can not only improve the accuracy of classification, but also reduce the time to derive rules. It is executed especially when the amount of attributes in a given training data is very large. In this paper, an attribute clustering method based on genetic algorithms is proposed for feature selection and feature replacement. It combines both the average accuracy of attribute substitution in clusters and the cluster balance as the fitness function. Experimental comparison with the k-means clustering approach and with all combinations of attributes also shows the proposed approach can get a good trade-off between accuracy and time complexity. Besides, after feature selection, the rules derived from only the selected features may usually be hard to use if some values of the selected features cannot be obtained in current environments. This problem can be easily solved in our proposed approach. The attributes with missing values can be replaced by other attributes in the same clusters. The proposed approach is thus more flexible than the previous feature-selection techniques.
    Download Collect
  • Integrating multiple knowledge sources using decision tables

    Tzung-Pei Hong   Shyue-Liang Wang   Jeun-Shing Tsai  

    Most integration methods proposed in the past needed domain experts to intervene during integration to resolve conflicts and contradictions. The integration time is thus very long due to the dialogue of the experts. We propose a genetic knowledge-integration method that automatically combines multiple decision tables into one integrated decision table. Our knowledge integration consists of four processes: translation, encoding, integration and post-processing. The translation process transforms each knowledge source into a uniform syntactical decision table. The encoding process encodes each decision table into a bit-string structure. The integration process chooses bit-string decision tables for "mating", gradually creating good offspring decision tables. The post-processing process further simplifies the decision table integrated. Our knowledge integration approach can effectively integrate multiple knowledge sources in an environment with good communication facilities of networks. This saves much time since experts may be geographically dispersed, and their deliberations may be very time-consuming.
    Download Collect
  • Time series data analysis for long term forecasting and scheduling of organizational resources - few cases

    Sunil Bhaskaran   Sheng Hsiung Chang   Wynne Hsu   Mong Li Lee   José Jacobo Zubcoff   Jesús Pardillo   Xiao Hu   Peng Xu   Shaozhi Wu   Shadnaz Asgari   Marvin Bergsneider   Zhe Song   Xiulin Geng   Andrew Kusiak   Chun-Hao Chen   Tzung-Pei Hong   Vincent S. Tseng   Huei-Wen Wu   Anthony J. T. Lee  

    Our society is increasingly influenced by modern information and communication technology (ICT); Data warehouse; data mining and time series data mining etc. Time series data mining can be treated as a subset of data mining domain. The nature of time series data is large data size; high dimensionality and necessary to update continuously. Time series data mining (TSDM) is a rapidly evolving research area in Computer Science. While processing data stored in a data base; if we consider the time at which the event happened; the information technology professional can generate more reliable and dependable information in comparison with conventional methods. Potentially; today; every stake holders has got the opportunity for time series data mining. In this paper I am introducing a methodology and a strategy for the effective planning of various organizational resources for different stake holders in the form of cases. Few of them are Information Technology professionals planning their hardware; software and network (bandwidth) requirement for the organizations. Another category of user is top level business executives; they are responsible for the long term strategic decision making of their business. The next category of users I am planing to cover in this paper is medical professionals or biological researchers and share traders (equity market).
    Download Collect
  • Maintenance of the Prelarge Trees for Record Deletion

    Chun-Wei Lin   Tzung-Pei Hong   Wen-Hsiang Lu  

    The frequent pattern tree (FP-tree) is an efficient data structure for association-rule mining without generation of candidate itemsets. It; however; needed to process all transactions in a batch way. In addition to record insertion; record deletion is also commonly seen in real-application. In this paper; we propose the structure of prelarge trees for efficiently handling deletion of records based on the concept of pre-large itemsets. Due to the properties of pre-large concepts; the proposed approach does not need to rescan the original database until a number of records have been deleted. The proposed approach can thus achieve a good execution time for tree construction especially when a small number of records are deleted each time. Experimental results also show that the proposed approach has a good performance for incrementally handling deleted records. Key-Words: data mining; FP-tree; Prelarge-tree algorithm; pre-large itemsets; record deletion.
    Download Collect
  • A Function-Based Classifier Learning Scheme Using Genetic Programming

    Jung-Yi Lin   Been-Chian Chien   Tzung-Pei Hong  

    Classification is an important research topic in knowledge discovery and data mining. Many different classifiers have been motivated and developed of late years. In this paper; we propose an effective scheme for learning multi-category classifiers based on genetic programming. For a k-class classification problem; a training strategy called adaptable incremental learning strategy and a new fitness function are used to generate k discriminating functions. The outputs of the discriminating functions are converged on a specified interval; and thus a data will be assigned into one of the classes by its outputs of discriminating functions. Furthermore; for resolving the case of conflicting; a method called Z-value measure is developed. In the experiments; the results show that the proposed GP-based classification method performs accurately and the Z-value measure works effective. (
    Download Collect
  • An Incremental High-Utility Mining Algorithm with Transaction Insertion

    Jerry Chun-Wei Lin   Wensheng Gan   Tzung-Pei Hong   Binbin Zhang  

    Association-rule mining is commonly used to discover useful and meaningful patterns from a very large database. It only considers the occurrence frequencies of items to reveal the relationships among itemsets. Traditional association-rule mining is; however; not suitable in real-world applications since the purchased items from a customer may have various factors; such as profit or quantity. High-utility mining was designed to solve the limitations of association-rule mining by considering both the quantity and profit measures. Most algorithms of high-utility mining are designed to handle the static database. Fewer researches handle the dynamic high-utility mining with transaction insertion; thus requiring the computations of database rescan and combination explosion of pattern-growth mechanism. In this paper; an efficient incremental algorithm with transaction insertion is designed to reduce computations without candidate generation based on the utility-list structures. The enumeration tree and the relationships between 2-itemsets are also adopted in the proposed algorithm to speed up the computations. Several experiments are conducted to show the performance of the proposed algorithm in terms of runtime; memory consumption; and number of generated patterns.
    Download Collect
  • A heuristic Palmer-based fuzzy flexible flow-shop scheduling algorithm

    Tzung-Pei Hong   Tzu-Ting Wang  

    In simple flow shop problems, each machine operation center includes just one machine. If at least one machine center includes more than one machine, the scheduling problem becomes a flexible flow-shop problem. In the previous paper, we have demonstrated how fuzzy concepts can easily be used in the Palmer algorithm for managing uncertain scheduling on flow-shop problems. This paper extends the application to fuzzy flexible flow-shops with more than two machine centers. A heuristic fuzzy flexible flow-shop scheduling algorithm is then designed since optimal solutions seem unnecessary for uncertain environments.
    Download Collect
  • Trade-Off Between Time Complexity and Accuracy of Perceptron Learning /sup */

    Tzung-Pei Hong   Shian-Shyong Tseng  

    In this paper, a modified perception leaning algorithm is proposed to reduce the computation time of learning. The proposed algorithm is easily programmed and can drastically decrease the time complexity of learning at the expense of only a little accuracy. Experimental results further show that this trade is worthy. Our proposed modified perceptron learning learning is then practical especially when noise exists in the training set or when the requirement of computational time is critical.
    Download Collect
  • Building a concise decision table for fuzzy rule induction

    Tzung-Pei Hong   Jyh-Bin Chen  

    Fuzzy systems that can automatically derive fuzzy if then rules and membership functions from numeric data have been developed previously. In this paper, we propose two new fuzzy learning methods for automatically deriving membership functions and fuzzy if-then rules from a set of given training examples. The proposed methods first select relevant attributes and build appropriate initial membership functions. They then simplify the intervals and the membership functions of each attribute before the decision table is formed. These attributes and membership functions are then used in a decision table to derive the final fuzzy if-then rules and membership functions. Experimental results on Iris data show that our methods can achieve a high accuracy. The proposed methods are thus useful in constructing membership functions and in managing uncertainty and vagueness. They can also reduce the time and effort needed to develop a fuzzy knowledge base.
    Download Collect
1 2 3 4 5 6 7 8 9

Contact

If you have any feedback, Please follow the official account to submit feedback.

Turn on your phone and scan

Submit Feedback