Data mining is the technique to find hidden patterns from a very large volume of historical data. Association rule is a type of data mining that correlates one set of items or events with another set of items or events. Another data mining strategy is clustering technique. This technique is used to create partitions so that all members of each set are similar according to a specified set of metrics. Both the association rule mining and clustering helps in more effective individual and group decision making for optimal inventory control. Owing to the above facts, association rules are mined from each cluster to find frequent items and then loss profit is calculated for each frequent item. Initially, the clustering algorithm is used to partition the transactional database into different clusters. Apriori, a classic data mining algorithm is utilized for mining association rules from each cluster to find frequent items. Later the loss profit is calculated for each frequent item. The obtained loss profit is used to rank frequent items in each cluster. Thus, the ranking of frequent items in each cluster using the proposed approach greatly facilitate optimal inventory control. An example is illustrated to validate the results.
Timely identification of newly emerging trends is needed in business process. Data mining techniques like clustering, association rule mining, classification, etc. are very important for business support and decision making. This paper presents a method for redesigning the ordering policy by including cross-selling effect. Initially, association rules are mined on the transactional database and EOQ is estimated with revenue earned. Then, transactions are clustered to obtain homogeneous clusters and association rules are mined in each cluster to estimate EOQ with revenue earned for each cluster. Further, this paper compares ordering policy for imperfect quality items which is developed by applying rules derived from apriori algorithm viz. a) without clustering the transactions, and b) after clustering the transactions. A numerical example is illustrated to validate the results.
A mobile ad hoc network (MANET) is considered as an autonomous network, which consists of mobile nodes, which communicate with each other over wireless links. When there is no fixed infrastructure, nodes have to cooperate in order to incorporate the necessary network functionality. Ad hoc on Demand Distance Vector (AODV) protocol is one of the primary principal routing protocols implemented in Ad hoc networks. The security of the AODV protocol is threaded by a specific kind of attack called ‘Black Hole’ attack. This paper presents a technique to prevent the Black hole attack by implementing negotiation with neighbors who claim to maintain a route to destination. Negotiation process is strengthen by apriori method to judge about suspicious node. Apriori algorithm is an effective association rule mining method with relatively low complexity, which is proper for MANETs. To achieve more improvement, fuzzy version of ADOV is used. The simulation results indicate that the proposed protocol provides more securable routing and also more efficiency in terms of packet delivery, overhead and detection rate than the conventional AODV and fuzzy AODV in the presence of Black hole attacks.