@inproceedings { , title = {A preliminary study on Hybrid Spill-Tree Fuzzy k-Nearest Neighbors for big data classification}, abstract = {The Fuzzy k Nearest Neighbor (Fuzzy kNN) classifier is well known for its effectiveness in supervised learning problems. kNN classifies by comparing new incoming examples with a similarity function using the samples of the training set. The fuzzy version of the kNN accounts for the underlying uncertainty in the class labels, and it is composed of two different stages. The first one is responsible for calculating the fuzzy membership degree for each sample of the problem in order to obtain smoother boundaries between classes. The second stage classifies similarly to the standard kNN algorithm but uses the previously calculated class membership degree. To deal with very large datasets, distributed versions of the Fuzzy kNN algorithm have been proposed. However, existing approaches remain not fully scalable as they aim to replicate the exact behavior of the Fuzzy kNN. In this work, we present an approximate and distributed Fuzzy kNN approach based on Hybrid Spill-Tree implemented under Apache Spark. The aim of this model is to alleviate the scalability problems and to deal with big datasets maintaining high accuracy. In our experiments, we compare in precision and runtime with the Fuzzy kNN for big data problems existing in the literature, running with datasets of up to 11 million instances. The results show an improvement in the runtime and accuracy with respect to the previous exact model.}, conference = {2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)}, doi = {10.1109/FUZZ-IEEE.2018.8491595}, isbn = {978-1-5090-6021-4}, organization = {Rio de Janeiro, Brazil}, pages = {1-8}, publicationstatus = {Published}, publisher = {Institute of Electrical and Electronics Engineers}, url = {https://nottingham-repository.worktribe.com/output/1175103}, year = {2018}, author = {Maillo, Jesus and Luengo, Julián and Garcia, Salvador and Herrera, Francisco and Triguero, Isaac} }