Advanced kNN: A Mature Machine Learning Series
This addresses a limitation in kNN for classification tasks where unknown classes may appear, but it is incremental as it builds on the well-established kNN method.
The paper tackles the problem that kNN cannot classify instances outside predefined classes by proposing an Advanced kNN algorithm that identifies unknown instances, and results show it is significantly accurate for this task on three datasets.
k-nearest neighbour (kNN) is one of the most prominent, simple and basic algorithm used in machine learning and data mining. However, kNN has limited prediction ability, i.e., kNN cannot predict any instance correctly if it does not belong to any of the predefined classes in the training data set. The purpose of this paper is to suggest an Advanced kNN (A-kNN) algorithm that will be able to classify an instance as unknown, after verifying that it does not belong to any of the predefined classes. Performance of kNN and A-kNN is compared on three different data sets namely iris plant data set, BUPA liver disorder data set, and Alpha Beta detection data set. Results of A-kNN are significantly accurate for detecting unknown instances.