Comparison of machine learning approaches for radioisotope identification using NaI(TI) gamma-ray spectrum

Qi, Sheng; Zhao, Wei; Chen, Ye; Chen, Wenzhuo; Li, Jinglun; Zhao, Hui; Xiao, Wuyun; Ai, Xianyun; Zhang, Kun; Wang, Shanqiang

doi:10.1016/j.apradiso.2022.110212

Cited by 7 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reason that KNN performs badly is that the data set does not have a discriminating distance. In addition, based on previous research, MLP was also found to be superior for predicting the production process of biodiesel [4]. During the process of coding, it also shows that MLP has better accuracy for larger data sizes but the speed is slower.…”

Section: Analysis and Discussionmentioning

confidence: 78%

“…The result shows that MLP is good at predicting categorical and continuous variables [4]. The reason that KNN performs badly is that the data set does not have a discriminating distance.…”

Section: Analysis and Discussionmentioning

confidence: 97%

“…The prior layer receives inputs from its counterparts in the following layer. Before sending it to neurons in the subsequent layer, it analyzes the information by utilizing the activation function [4]. A hidden layer lies between the input layer and the output layer.…”

Section: Methodsmentioning

confidence: 99%

“…While different machine learning-based classifiers perform differently for different situations. Sometimes, one of the machine learning algorithms gives better accuracy in rightfully classifying the fault in some datasets, whereas at another instant, it performs weakly for a different data set [4]. Therefore, this paper will focus on the suitability of different classifiers for four different data sets from medicine, music, material, and plant areas.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Comparison study of data adaptability based on k-nearest neighbor(KNN), multilayer perceptron(MLP), and decision tree(DT)

Liu

2023

ACE

View full text Add to dashboard Cite

In the current context of increasingly popular and developed human-computer interaction, machine learning (ML) and data mining are becoming more and more important in various areas, such as image detecting, medicine, and commercial companies. Different researchers from various fields have considered ways to improve the correctness rate for data mining. This paper used data sets from Kaggle and UCI machine learning repository, by applying k-nearest neighbor (KNN), multilayer perceptron (MLP), and decision tree (DT) classifiers to these data sets, the confusion matrix shows the result of the correctness rate for different classifiers under these data sets. As a result, the confusion matrices have shown that data adaptability is based on the data sets characteristics which rely on different classifiers specialties.

show abstract

Section: Analysis and Discussionmentioning

confidence: 78%

“…The result shows that MLP is good at predicting categorical and continuous variables [4]. The reason that KNN performs badly is that the data set does not have a discriminating distance.…”

Section: Analysis and Discussionmentioning

confidence: 97%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations