A local search algorithm for k-means with outliers

Zhang, Zhen; Qi, Feng; Huang, Junyu; Guo, Yutian; Xu, Jinhui; Wang, Jianxin

doi:10.1016/j.neucom.2021.04.028

Cited by 26 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Outliers detection and elimination: outliers elimination helps to increase the accuracy of the classification model . Clustering-based approaches ( Borlea et al, 2021 ) can be used for outlier detection ( Zhang et al, 2021 ). However, for detecting anomalies in the adopted OSR dataset, we employed a tree-based approach, i.e., Isolation Forests algorithm ( Liu et al, 2008 ).…”

Section: The Proposed Methodologymentioning

confidence: 99%

Equilibrium-based COVID-19 diagnosis from routine blood tests: A sparse deep convolutional model

Altantawy

Kishk²

2023

Expert Systems with Applications

View full text Add to dashboard Cite

Section: The Proposed Methodologymentioning

confidence: 99%

Equilibrium-based COVID-19 diagnosis from routine blood tests: A sparse deep convolutional model

Altantawy

Kishk²

2023

Expert Systems with Applications

View full text Add to dashboard Cite

“…The distance is used as the classification standard to divide the data within a short distance into a cluster. The number of clusters K can be set manually according to different needs [ 22 , 23 ]. The specific process of the K -means clustering algorithm is as follows.…”

Section: Methodsmentioning

confidence: 99%

“…e number of clusters K can be set manually according to different needs [22,23]. e specific process of the K-means clustering algorithm is as follows.…”

Section: Analysis Of the Scale Of Classroom Student Behaviormentioning

confidence: 99%

The Cognitive Transformation of Japanese Language Education by Artificial Intelligence Technology in the Wireless Network Environment

Zhang

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

This study aims to solve the multiscale problems faced by the current classroom student behavior target detection based on the convolutional neural network (CNN) in the wireless network environment. Firstly, the recent reform of Japanese language education is introduced. Secondly, the multiscale problem research of classroom student behavior target detection is discussed. A CNN-based new extraction network is designed based on dilated convolution and pyramid features. An anchor reconstruction algorithm based on improved K-means clustering is presented for the self-made student behavior dataset. Finally, the performance of the designed algorithm is tested. The anchor reconstruction algorithm’s mean average precision is 83.2%, and the average intersection over union is 73.7%. The experimental results of this scheme outperform the original single-shot multibox detector and K-means algorithms. Compared with other algorithms, the designed multiscale detection algorithm of classroom student behavior has the best detection effect on Pascal visual object classes (VOC) dataset. The detection accuracy of the entire dataset is 79.8%. Overall, the multiscale detection algorithm for classroom student behavior has a better detection effect on the Pascal VOC dataset and has good generalization ability and robustness. This research can guide students to recognize their class status and make corresponding adjustments to improve their learning efficiency, which has essential research significance and application value.

show abstract

“…K-means algorithm, also known as the K-means algorithm, is a typical distance-based clustering algorithm, which is widely used in clustering and outlier identification problems due to its clear structure and fast convergence speed [28,29].…”

Section: Outlier Recognition Based On K-means Algorithmmentioning

confidence: 99%

Study on the Law of Harmful Gas Release from Limnoperna fortunei (Dunker 1857) during Maintenance Period of Water Tunnel Based on K-Means Outlier Treatment

Wang

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

It is of great significance for air pollution control and personnel safety guarantee to master the release characteristics of harmful gases in the process of Limnoperna fortunei corruption. In view of the lack of research on the environmental pollution caused by the corruption of Limnoperna fortunei, a model experiment was designed to study the three harmful gases of NH3, H2S, and CH4 in the putrid process of Limnoperna fortunei by considering the density of Limnoperna fortunei and the time of leaving water. The results show that: (1) The recognition and processing of outliers based on wavelet decomposition and K-means algorithm can effectively reduce the standard deviation and coefficient of variation of the data set and improve the accuracy of the data set. (2) The variation of NH3 and H2S gas concentrations with the time of water separation satisfies polynomial linear regression (R2 > 99%). (3) At a density of 0.5–7.0 × 104 mussels/m2, the highest concentration of NH3 reached 47.9777–307.9454 mg/m3 with the increase in the density of Limnoperna fortunei and the extension of the time away from water, far exceeding the occupational exposure limit of NH3 of 30 mg/m3, potentially threatening human health and safety. The highest detection value of H2S concentration is 0.1909–5.0946 mg/m3, and the highest detection concentration of CH4 is 0.02%, both of which can be ignored.

show abstract

A local search algorithm for k-means with outliers

Cited by 26 publications

References 23 publications

Equilibrium-based COVID-19 diagnosis from routine blood tests: A sparse deep convolutional model

Equilibrium-based COVID-19 diagnosis from routine blood tests: A sparse deep convolutional model

The Cognitive Transformation of Japanese Language Education by Artificial Intelligence Technology in the Wireless Network Environment

Study on the Law of Harmful Gas Release from Limnoperna fortunei (Dunker 1857) during Maintenance Period of Water Tunnel Based on K-Means Outlier Treatment

Contact Info

Product

Resources

About