Data sources for outbreak detection nowadays not only focus on emergency department or hospital-based data but also grocery data. However, the size of huge data, may consume higher time and extreme number of discovered pattern. Unfortunately not all the discovered pattern from the frequent mining is interesting pattern. Hence frequent pattern mining algorithms producing numbers of frequent pattern, still parameter uses in minimum support and which frequent itemset producing better pattern remains fairly open. It is important to gains some limitation of minimum support to be applied to the frequent mining algorithm so that we not end up at compiling higher patterns including a normal pattern. We propose a procedure based on quick parameter setting to estimate minimum support and also frequent itemset. Our empirical validation shown the procedure will extract ranging minimum support and frequent itemset to be considered to generate interesting pattern.Keywords-frequent pattern mining, minimum support, frequent itemset.
Abstract:Dengue is a critical communicable and vector-borne disease and is becoming a serious concern in Malaysia. It is important to have an early detection system that could provide immediate action, such as the control of dengue transmission at a specific location. However, the available strategy and action may give long-term effects to the community since inaccurate decision making or prediction may lead to other circumstances. Moreover, the need to have a system that can detect the outbreak in a reasonable amount of time is critical. In this study, a nature-inspired computing technique, the artificial immune system (AIS), is used for dengue outbreak detection. One of the variants of the AIS algorithms, called the negative selection algorithm (NSA), has been widely applied in anomaly detection and fault detection. This study aims to employ the NSA for dengue outbreak detection.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.