K-nearest neighbor

By Leif E. Peterson. 2009

2,383 citations recorded by the source corpus.

Classification is a systematic grouping of objects into certain groups based on the same characteristics. The classification method used in this research are naive Bayes and K-Nearest Neighbor which has a relatively high degree of accuracy. This research aims to compare the level of classification accuracy on the status data of value-added tax (VAT) payment. The data used is data on corporate taxpayers at Samarinda Ulu Tax Office in 2018 with the status of VAT payment being compliant or non-compliant and used 3 independent variables are income, type of business entity and tax reported status. Measurement of accuracy using APER in the Naive Bayes method is 17.07% and in K-Nearest Neighbor method is 19,51%. The comparison results of accuracy measurements between the two methods show that the naive Bayes method has a higher level of accuracy than the K-Nearest Neighbor method

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Artificial Intelligence

1. Yi Luo
2. Nima Mesgarani
3. Zerina Mašetić
4. Sheng Jin
5. Shijian Lu
6. Jingyi Zhang
7. Jiaxing Huang
8. Hongyi Liu

In Computer Vision and Pattern Recognition

1. Yi Luo
2. Sheng Jin
3. Nima Mesgarani
4. Shijian Lu
5. Jingyi Zhang
6. Jiaxing Huang
7. Hongyi Liu
8. Zerina Mašetić

Citations in the corpus

• Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation (2018, methodology): “The encoder and decoder basis functions are sorted based on the Euclidian similarity, which is found using an unsupervised clustering algorithm [53].”
• Gesture recognition for human-robot collaboration: A review (2017, methodology): “K-Nearest Neighbours (KNN) algorithm is a fundamental and basic gesture classi fi cation algorithm that classi fi es input data according to the closest training examples (Peterson, 2009).”
• Congestive heart failure detection using random forest classifier (2016, methodology): “The first step is to reduce the dimension of feature space by using distance function (commonly used Euclidian distance) between a test set and specified training set [26]:”
• Vision-Language Models for Vision Tasks: A Survey (2023, background): “Before the deep learning era [4], visual recognition studies rely heavily on feature engineering with hand-crafted features [9], [38] and lightweight learning models [7], [8], [39] that classify the hand-crafted features into pre-defined semantic categories.”
• Detection (2020, positive): “In order to solve the supervised binary classification problem, we resort to multiple ML classifiers: k-Nearest-Neighbors (kNN) [26], Gaussian Naive Bayes (GNB) [27], decision tree (DT) [28], random forest (RF) [29], and eX-treme Gradient Boosting (XGB) [30].”