The Distance-Weighted k-Nearest-Neighbor Rule

By Sahibsingh A. Dudani. 1976

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges (2021, background): “Many variants of the original kNN classification scheme have been developed in the 1970s and 80s (Dudani, 1976; Fukunaga and Hostetler, 1973; Keller et al., 1985; Bezdek et al., 1986).”
An Introduction to Machine Learning (2017, methodology): “The weighted k-NN classifier described here was proposed by Dudani [23].”
Brain Computer Interfaces, a Review (2012, background): “The function defined by Equation (19) [226] meets this requirement:”
A Survey of the State of Explainable AI for Natural Language Processing (2020, methodology): “They are similar in spirit to nearest neighbor-based approaches (Dudani, 1976), and have been applied to different NLP tasks such as text classiﬁcation (Croce et al., 2019) and question answering (Abujabal et al., 2017).”
A Review and Empirical Evaluation of Feature Weighting Methods for a Class of Lazy Learning Algorithms (1997, methodology): “Other purely local (and lazy) approaches were recently introduced by Hastie and Tibshirani (1994) and by Friedman (1994). Hastie and Tibshirani (1994) compute a separate distance metric for each query through an iterative process.”
Machine Learning for Reliability Engineering and Safety Applications: Review of Current Status and Future Opportunities (2020, methodology): “Commonly used ML methods for classification problems include logistic regression [31], k-nearest neighbor (KNN) [32], support vector machine (SVM) [16], decision tree (DT) [16], boosted tree [33], and random forest (RF) [34].”
Performance evaluation and hyperparameter tuning of statistical and machine-learning models using spatial data (2018, methodology): “The original idea of the WKNN algorithm goes back to Dudani (1976).”
Explainable artificial intelligence for breast cancer: A visual case-based reasoning approach (2019, background): “Distance-weighted kNN (WkNN) [20] is a variant, in which the weight of a similar case is inversely proportional to the distance between the similar case and the query case.”
Local Manifold Learning-Based $k$ -Nearest-Neighbor for Hyperspectral Image Classification (2010, background): “Commonly, they are determined by the pairwise distances between a testing point and its neighbors [20], [21], ignoring neighborhood relationships and thereby potentially underutilizing available information.”