Description: Data mining purpose is to find interesting patterns within great number of data. One of its functionality is association that is finding association rule which meet minimum support value (minsup) and minimum confidence (minconf). Association technique by using a minsup has been developed in many researches. Using single minimum support in data which frequency of items vary a great deal can make problems. If minsup is too high, there wouldn’t be found any rules contain rare item, if minsup is too low there would be too many rules find and some rules are meaningless.-Data mining purpose is to find interesting patterns within great number of data. One of its functionality is association that is finding association rule which meet minimum support value (minsup) and minimum confidence (minconf). Association technique by using a minsup has been developed in many researches. Using single minimum support in data which frequency of items vary a great deal can make problems. If minsup is too high, there wouldn’t be found any rules contain rare item, if minsup is too low there would be too many rules find and some rules are meaningless. Platform: |
Size: 666624 |
Author:andik |
Hits:
Description: matlab 关于association rule 的自己写的函数，有3个文件,
association.m：h = association(m, i, j)
i=>j, m是数据，h是support和confidence，该函数只适用于单个数据
ass_item: h=ass_itset(m, a, b)
同上，但是可用于多个数据（m为数组）
assrule: h = assrule(m, threshold1, threshold2)
该函数用于classification， 得到规则，threshold1为要求的support,threshold2为要求的confidence，h 则为符合要求的规则及其support和confidence，前2列为规则，后2列为其support和confidence-matlab on the association rule to write functions, there are 3 files, association.m: h = association (m, i, j) i => j, m is the data, h is the support and confidence, this function applies only to a single Data
ass_item: h = ass_itset (m, a, b) it is the same as above, but it can be used for multiple data (m can be matrix)
assrule: h = assrule (m, threshold1, threshold2) the function used for classification,get the rules, threshold1 is the require of support, threshold2 is the required of confidence, h is the rules and their support and confidence, the former two columns as a rule, the latter two columns as one of its support and confidence Platform: |
Size: 1024 |
Author:张天为 |
Hits:
Description: 26 Feb 2008 ... Apriori-T (Apriori Total) is an Association Rule Mining (ARM) algorithm, developed by the LUCS-KDD research team. ... using the "Total support" tree data structure (T-tree). ... The code can be documented using Java Doc. -26 Feb 2008 ... Apriori-T (Apriori Total) is an Association Rule Mining (ARM) algorithm, developed by the LUCS-KDD research team. ... using the "Total support" tree data structure (T-tree). ... The code can be documented using Java Doc. ... Platform: |
Size: 77824 |
Author:natarajan |
Hits:
Description: 主要介绍在大型数据库中发现知识（Knowledge Discovery in Large Databases, KDD）的各种技术，是专门针对决策支持中的各类问题进行讨论的高端课程。面向对象为软件工程专业硕士研究生。
本课程讲授的主要内容包括：数据预处理、数据仓库及OLAP、概念描述型数据挖掘、关联规则挖掘、分类挖掘和预测以及聚类挖掘，涉及的领域包括数理统计、概率论、机器学习、信息论、集合论等等。-Introduces knowledge discovery in large databases (Knowledge Discovery in Large Databases, of KDD), a variety of technology, specifically for decision support in all kinds of problems discussed in high-end courses. Object-oriented software engineering graduate. This course will include: data preprocessing, data warehousing and OLAP, the concept of descriptive data mining, association rule mining, classification mining and prediction, and clustering mining in the areas of mathematical statistics, probability theory, machine learning, information theory , set theory, and so on. Platform: |
Size: 3781632 |
Author:onlearning |
Hits:
Description: Apriori算法[1]是一种最有影响的挖掘布尔关联规则频繁项集的算法。其核心是基于两阶段频集思想的递推算法。该关联规则在分类上属于单维、单层、布尔关联规则。在这里，所有支持度大于最小支持度的项集称为频繁项集，简称频集。-Apriori algorithm [1] is one of the most influential association rule mining algorithm Boolean frequent item sets. Its core is based on a two-stage frequency set recursive algorithm ideas. The association rules on classification is one-dimensional, single, Boolean association rules. Here, all support is greater than the minimum support itemset is called frequent item sets, referred to as the frequency set.generated in two phases to detect and plot. And algorithms have been widely applied to business, network security and other fields. Platform: |
Size: 43008 |
Author:alan |
Hits:
Description: 多层次关联规则挖掘算法：cumulate 可以支持跨层的关联规则挖掘。数据集为T10I4D100K，概念层次树有10个根节点，分三层。-Multi-level association rule mining algorithm: cumulate to support cross-layer association rule mining. Dataset T10I4D100K, has 10 concept hierarchy tree root, divided into three layers. Platform: |
Size: 1027072 |
Author:姜杉 |
Hits:
Description: 多最小支持度关联规则挖掘算法，数据集为T10I4D100K,多最小支持度阈值文件为MS-change-Multiple minimum supports association rule mining algorithm, the data set is T10I4D100K, more than the minimum support threshold file for the MS-change Platform: |
Size: 940032 |
Author:姜杉 |
Hits:
Description: 支持多最小支持度多层次的关联规则挖掘，数据集为T10I4D100K，多最小支持度阈值为MSchange-Support multiple minimum supports multi-level association rule mining, data set T10I4D100K, more than the minimum support threshold MSchange Platform: |
Size: 1064960 |
Author:姜杉 |
Hits:
Description: 机器学习领域经典分类算法综述，包括Decision Tree（ＩＤ３、C4.5(C5.0)、CART、PUBLIC、SLIQ和SPRINT算法），三种典型贝叶斯分类器（朴素贝叶斯算法、TAN算法、贝叶斯网络分类器），k-近邻 、 基于数据库技术的分类算法（ MIND算法、GAC-RDB算法），基于关联规则（CBA:Classification Based on Association Rule）的分类（Apriori算法），支持向量机分类，基于软计算的分类方法（粗糙集（rough set）、遗传算法、模糊逻辑、人工神经网络算法）。-Classical machine learning classification algorithms overview。 Including Decision Tree (ID3, C4.5 (C5.0), CART, PUBLIC, SLIQ and SPRINT algorithm), three typical Bayesian classifier (Naive Bayes algorithm, TAN algorithm Bayesian network classifiers), k-nearest neighbor based classification algorithm (MIND algorithm, GAC-RDB algorithms) database technology, based on association rules (CBA: classification (Apriori algorithm) Classification Based on Association Rule), and support vector machine classification, classification method based on soft computing (rough sets (rough set), genetic algorithms, fuzzy logic, artificial neural network algorithm).... Platform: |
Size: 30720 |
Author:MM |
Hits:
Description: 本文提出来一种基于关联规则挖掘的二进制粒子群优化算法（BPSO），该算法与apriori算法不同，在从交易数据集中提取关联规则的过程中不需要给定支持度与置信度的阈值。-In this paper, we developed a binary particle swarm optimization (BPSO) based association rule miner.
Our BPSO based association rule miner generates the association rules from the transactional database by
formulating a combinatorial global optimization problem, without specifying the minimum support and
minimum confi dence unlike the a priori algorithm. Platform: |
Size: 211968 |
Author:xiaowei |
Hits:
Description: Association rule mining can be used to discover interesting
rules large s easily for better decision making in most
real world applications except the financial market. This is because
the investors are interested in high profit and low risk trading results
more than in those of high confidence and high support. Based on a
working model of profit mining, we propose an effective algorithm for
investors to find trading rules that include information on profit, risk,
and win rate. This mining approach works well not only in the stock
market, but also in the futures and other markets. -Association rule mining can be used to discover interesting
rules large s easily for better decision making in most
real world applications except the financial market. This is because
the investors are interested in high profit and low risk trading results
more than in those of high confidence and high support. Based on a
working model of profit mining, we propose an effective algorithm for
investors to find trading rules that include information on profit, risk,
and win rate. This mining approach works well not only in the stock
market, but also in the futures and other markets. Platform: |
Size: 216064 |
Author:varun |
Hits:
Description: 关联规则挖掘算法的matlab程序，我编写了Apriori算法的temp步骤，可以自动生成关联规则，计算支持度、置信度以及tmep1检测，很好的小程序。-Association rule mining algorithm matlab program, I wrote temp step Apriori algorithm can automatically generate association rules, computing support, confidence and tmep1 detection, good little program. Platform: |
Size: 9216 |
Author:shiyulong_bt |
Hits:
Search - association rule support