A network analysis (NA) of keyword co-occurrences for a broad collection of Data envelopment analysis (DEA) papers in the period 2008-2017 is carried out. The raw keywords have been cleaned up and standardized to consolidate and increase the consistency of the keywords. The resulting network has been characterized using network-level as well as node-level NA measures. Although the size of the network steadily increases with time, the average path length does not, showing its small world character. The disassortativity of the network indicates that the keywords used in a given paper generally include one or more common, frequently-used terms plus other less common terms that refer to the specific context of the research. The evolving nature of the keyword network is highlighted with some DEA keywords staying at the top of the ranking during the whole period and other emerging topics significantly increasing their strength during this period. The community structure of the network, which reflects the field's knowledge structure, is also presented. The identified communities generally include specific DEA methodology terms, linked with corresponding application areas as well as with some geographical references. Also, the ego-network of some sample keywords is shown, and some research gaps in DEA are identified.
Abstract. Genetic Programming can be used to evolve Fuzzy Rulebased classifiers [7]. Fuzzy GP depends on a grammar defining valid expressions of fuzzy classifiers, and guarantees that all individuals in the population are valid instances of it all along the evolution process. This is accomplished by restricting crossover and mutation so that they only take place at points of the derivation tree representing the same non-terminal, thus generating valid subtrees [13]. In Fuzzy GP, terminal symbols are fuzzy constants and variables that are chosen beforehand. In this work we propose a method for evolving both fuzzy membership functions of the variables and the Rule Base. Our method extends the GA-P hybrid method [6] by introducing a new grammar with two functional parts, one for the Fuzzy Rule Base (GP Part), and the other for the constants that define the shapes of the fuzzy sets involved in the Fuzzy Rule Base (GA Part). We have applied this method to some classical benchmarks taken from the collection of test data at the UCI Repository of Machine Learning Databases [9].
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.