Knowledge Discovery from Health Data Using Weighted Aggregation Classifiers
نویسندگان
چکیده
Introduction. The automatic construction of classifiers is an important research problem in data mining, since it provides not only a good prediction but provides also a characterization of a given data in the form easily understood by a human. A decision tree [4] is a classifier widely used in real applications, which are easy to understand, and efficiently constructed by using a method based on entropy heuristics [4]. Fukuda et al. [1] have proposed an efficient algorithm (called DT in this abstract) for constructing a small and accurate decision tree with numeric attributes using optimized two-dimensional numeric association rules as node labels. A problem is that at each node, DT generates many rules for possible pairs of numeric and ordered attributes, but selects only one optimized rule among them. Since this generation is time consuming, the construction may be inefficient when there are many numeric and ordered attributes. A possible approach is to build a one-level decision tree such as 1R [2]. We take another approach to aggregate the decisions made by all generated rules.
منابع مشابه
Knowledge discovery from patients’ behavior via clustering-classification algorithms based on weighted eRFM and CLV model: An empirical study in public health care services
The rapid growing of information technology (IT) motivates and makes competitive advantages in health care industry. Nowadays, many hospitals try to build a successful customer relationship management (CRM) to recognize target and potential patients, increase patient loyalty and satisfaction and finally maximize their profitability. Many hospitals have large data warehouses containing customer ...
متن کاملKnowledge discovery from patients’ behavior via clustering-classification algorithms based on weighted eRFM and CLV model: An empirical study in public health care services
The rapid growing of information technology (IT) motivates and makes competitive advantages in health care industry. Nowadays, many hospitals try to build a successful customer relationship management (CRM) to recognize target and potential patients, increase patient loyalty and satisfaction and finally maximize their profitability. Many hospitals have large data warehouses containing customer ...
متن کاملApplying aggregation operators to data mining: modelling using quasi-weighted means
Data fusion methods are useful tools in data mining and knowledge discovery to build models of the data and to extract useful information from raw data. This work is devoted to one family of aggregation operators. The so-called, quasi-weighted means. In this work we present a methodology to learn the weights for these operators based on active set methods and the gradient descent.
متن کاملThe NTU Toolkit and Framework for High-Level Feature Detection at TRECVID 2007
In TRECVID 2007 high-level feature (HLF) detection, we extend the well-known LIBSVM and develop a toolkit specifically for HLF detection. The package shortens the learning time and provides a framework for researchers to easily conduct experiments. We efficiently and effectively aggregate detectors of training past data to achieve better performances. We propose post-processing techniques, conc...
متن کامل