An Improved Fuzzy <i>K</i>-Nearest Neighbor Algorithm for Imbalanced Data using Adaptive Approach

Patel, Harshita; Thakur, Ghanshyam Singh

doi:10.1080/03772063.2018.1462109

Cited by 15 publications

(7 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Patel and Thakur 60 have proposed an approach which takes an adaptive concept of different K values for different classes to calculate more accurate membership of data into classes merged with fuzzy nearest neighbor. Their results show the improved classification results on various imbalanced datasets.…”

Section: Review Of Solutions To the Problemmentioning

confidence: 99%

A review on classification of imbalanced data for wireless sensor networks

Patel

Rajput

Reddy

et al. 2020

International Journal of Distributed Sensor Networks

Self Cite

109

View full text Add to dashboard Cite

Classification of imbalanced data is a vastly explored issue of the last and present decade and still keeps the same importance because data are an essential term today and it becomes crucial when data are distributed into several classes. The term imbalance refers to uneven distribution of data into classes that severely affects the performance of traditional classifiers, that is, classifiers become biased toward the class having larger amount of data. The data generated from wireless sensor networks will have several imbalances. This review article is a decent analysis of imbalance issue for wireless sensor networks and other application domains, which will help the community to understand WHAT, WHY, and WHEN of imbalance in data and its remedies.

show abstract

Section: Review Of Solutions To the Problemmentioning

confidence: 99%

A review on classification of imbalanced data for wireless sensor networks

Patel

Rajput

Reddy

et al. 2020

International Journal of Distributed Sensor Networks

Self Cite

109

View full text Add to dashboard Cite

show abstract

“…Tables 4 and 5, it is clear that the performance of proposed LMDL method achieved better results in all datasets. Though the proposed LMDL achieved 55% F-measure in yeast dataset, the LMDL method achieved 69.58% G-mean when compared with existing method by Patel and Thakur [22]. When compared to the existing methods, the LMDL method achieved 100% AUC in glass dataset, whereas it provides poor performance in yeast dataset because of using high nonlinear data.…”

Section: Comparative Analysismentioning

confidence: 83%

“…Patel and Thakur [22] improved the fuzzy K-NN classification of imbalanced data with the help of adaptive K-NN, as this method tends to choose different values of K-based on its sizes. Compared to other simple fuzzy K-NN, acquired fuzzy memberships were more accurate for data instances in minority class using the adaptive K-NN.…”

Section: Sn Computer Sciencementioning

confidence: 99%

“…In this section, the results obtained by the LMDL are compared with existing methods such as random forest (RF) and synthetic minority over-sampling technique (SMO) in Sun et al [17], LEAT [21] and fuzzy adaptive K-NN by Patel and Thakur [22] for three parameters such as F-measure, G-mean and AUC in E-coli, yeast, glass and wine datasets. The performance of the LMDL for four datasets in different parameters is discussed in Tables 4 and 5.…”

Section: Comparative Analysismentioning

confidence: 99%

See 1 more Smart Citation

Imbalance Data Classification Using Local Mahalanobis Distance Learning Based on Nearest Neighbor

Siddappa

Kampalappa

2020

SN COMPUT. SCI.

View full text Add to dashboard Cite

In the dataset, any one of its classes is normally outnumbered by other classes and is known as class imbalance data. Many standard learning algorithms face the classification problem in performance due to imbalance data. The issues can be solved by many existing conventional methods such as cost-sensitive, sampling or ensemble methods. But these methods alter the original data distribution, which leads to loss of useful information of the users and it may cause unexpected errors or increase the problem of overfitting. In this research, local Mahalanobis distance learning (LMDL) method is applied in the nearest neighbor (NN) for improving the performance of the classification in the imbalance dataset. The multiple distance metrics are used in the LMDL to investigate the data effectively and obtain the relevant features based on the analysis. The distance metric uses the original data for learning the prototype and support the NN. A number of experiments on various datasets are conducted for validating the quality as well as the efficiency of the proposed LMDL method. The experimental results stated that the proposed LMDL achieved nearly 82% in E-coli dataset, 94% in breast cancer dataset and 98% in Iris dataset for all metrics such as accuracy, precision, recall and F-measure.

show abstract

“…It does not learn the training data; instead, it "memorizes" the training data collection, which is why Memory-Based Classification is often called that. It searches for the closest neighbors in the entire dataset to make an approximation [65].…”

Section: K-nearest Neighbor Classifiermentioning

confidence: 99%

Feature Selection Based Coral Reefs Optimization for Breast Cancer Classification

Abouelmagd¹,

Shams

El-Attar

et al. 2021

Studies in Computational Intelligence

View full text Add to dashboard Cite

Early detection of cancer cases is one of the most important things that help complete treatment and disappearance of this disease from the human body. Breast cancer is the most widespread invasive cancer in women, and after lung cancer, it is the second leading cause of cancer death in women. The first symptoms of breast cancer usually appear as an area of thickened tissue in the breast or a lump in the breast or an armpit. Consequently, many features can be found to indicate the existence of cancer or not. This chapter employs the coral reefs optimization (CRO) algorithm for feature selection; the CRO has shown to be very effective with various classification approaches. In this chapter, we used five standard classifiers: Logistic Regression (LR), K-nearest neighbor (KNN), Support Vector Machine with Radial Basis Function (SVM-RBF), Random Forest (RF), Decision Tree (DT). All These classifiers are presented with and without feature selection using the CRO algorithm. The results indicated that using the feature selection based on CRO achieved better results before the feature selection. The most common dataset called Breast Diagnostic Cancer Wisconsin (BDCW) is utilized to select the most significant and classify the cancer cases with a tested accuracy of 100%, 99.1%, 100%, 100%, and 100% using LR, KNN, SVM-RBF, RF, and DT respectively.

show abstract

An Improved Fuzzy K-Nearest Neighbor Algorithm for Imbalanced Data using Adaptive Approach

Cited by 15 publications

References 30 publications

A review on classification of imbalanced data for wireless sensor networks

A review on classification of imbalanced data for wireless sensor networks

Imbalance Data Classification Using Local Mahalanobis Distance Learning Based on Nearest Neighbor

Feature Selection Based Coral Reefs Optimization for Breast Cancer Classification

Contact Info

Product

Resources

About