This paper introduces our work regarding the mining of decision activity logs generated by the users of a decision support system-like environment. We will show that a DSS can be modified in order to become "deci...
详细信息
ISBN:
(纸本)9783642154010
This paper introduces our work regarding the mining of decision activity logs generated by the users of a decision support system-like environment. We will show that a DSS can be modified in order to become "decision-aware. If the system offers support for all the data and information needs of the decision maker, how the user interacts with the software can provide us with a new perspective over the implicit and explicit knowledge employed in the decision process, as well as the decision patterns and strategies used for that decisional situation. All this valuable information will be stored as activity logs. Those logs need to be mined in order to build a graphical representation of the decision process. As proof-of-concept we focus on the enterprise loan contracting decision situation. We will show some of the models we created using several process mining algorithms and our own approach. Based on those models, we argue the new insights we can provide into the decision making process and the knowledge that is now explained and depicted as diagrams.
Motivation: Microbial phenotypes are typically due to the concerted action of multiple gene functions, yet the presence of each gene may have only a weak correlation with the observed phenotype. Hence, it may be more ...
详细信息
Motivation: Microbial phenotypes are typically due to the concerted action of multiple gene functions, yet the presence of each gene may have only a weak correlation with the observed phenotype. Hence, it may be more appropriate to examine co-occurrence between sets of genes and a phenotype (multiple-to-one) instead of pairwise relations between a single gene and the phenotype. Here, we propose an efficient class association rule mining algorithm, NETCAR, in order to extract sets of COGs (clusters of orthologous groups of proteins) associated with a phenotype from COG phylogenetic profiles and a phenotype profile. NETCAR takes into account the phylogenetic co-occurrence graph between COGs to restrict hypothesis space, and uses mutual information to evaluate the biconditional relation. Results: We examined the mining capability of pairwise and multiple-to-one association by using NETCAR to extract COGs relevant to six microbial phenotypes (aerobic, anaerobic, facultative, endospore, motility and Gram negative) from 11 969 unique COG profiles across 155 prokaryotic organisms. With the same level of false discovery rate, multiple-to-one association can extract about 10 times more relevant COGs than one-to-one association. We also reveal various topologies of association networks among COGs (modules) from extracted multiple-to-one correlation rules relevant with the six phenotypes;including a well-connected network for motility, a star-shaped network for aerobic and intermediate topologies for the other phenotypes. NETCAR outperforms a standard CAR mining algorithm, CARAPRIORI, while requiring several orders of magnitude less computational time for extracting 3-COG sets.
In order to improve the quality of the recommended result, the Personalized Recommendation System should identify the similarity degree of visitor's accessing behavior so as to predict customers interests. The key...
详细信息
ISBN:
(纸本)9781424420209
In order to improve the quality of the recommended result, the Personalized Recommendation System should identify the similarity degree of visitor's accessing behavior so as to predict customers interests. The key technology is to calculate the similar distance among different objects over either all or only a subset of the dimensions. This paper, first of all, analyses the commonly-used methods and points out their shortages, and then proposes an improved Apriori-Based Personal Recommendation algorithm for E-commerce. This algorithm considers overall the minable data source, users' Similarity Metric and K-Support Bound to get the data of those access web pages, construct a matrix model having relatively high purchasing power about customer behavior, get the similar access behavior over the all or partial property space with high efficiency, help the customer find out the merchandise he wishes to buy through the mine of the similar pattern character between latent buyer and high buyer, promote customer satisfaction and truly promote the sale achievements for the enterprise.
The association rule mining is an important research subject of knowledge discovery. Aiming at the common method of mining for attributes of quantitative type in database, we analyze the existing defects and put forwa...
详细信息
ISBN:
(纸本)0780378652
The association rule mining is an important research subject of knowledge discovery. Aiming at the common method of mining for attributes of quantitative type in database, we analyze the existing defects and put forward a method of applying fuzzy set theory to association rules mining. Due to the problem that each attribute's importance is different in specific purpose mining, we put forward a solution by assigning corresponding weight to attribute of different importance. Basing on the above idea, we put forward a mining algorithm using fuzzy weighted association rules and through the given experiment we testify the feasibility of the algorithm. and point out the existing defect of the algorithm demanding improvement in future.
暂无评论