基于快速傅里叶变换的KNN在枪械声音分类中的分析

2021 4th International Conference of Computer and Informatics Engineering (IC2IE) Pub Date : 2021-09-14 DOI:10.1109/ic2ie53219.2021.9649269

Muhammad Ari Afriansyah, Opim Salim Sitompul, S. Suwilo

{"title":"基于快速傅里叶变换的KNN在枪械声音分类中的分析","authors":"Muhammad Ari Afriansyah, Opim Salim Sitompul, S. Suwilo","doi":"10.1109/ic2ie53219.2021.9649269","DOIUrl":null,"url":null,"abstract":"K-Nearest Neighbor (KNN) is an algorithm that is able to recognize an object with the training and testing data. Sound is one of the objects that can be classified with KNN. one example of the sound of a sharp weapon varies in sound based on its type. So that in this paper, do a classification to recognize sound based on the type of weapon tested with several distance formulas. The variation of the tested distance formula shows different results, the Euclidian distance formula is better than the Chebyshev distance formula and the Monkowski distance formula. Comparison of accuracy 0.31667: 0.25833: 0.24583, comparison of precision 0.30878: 0.25855: 0.22838, comparison of recall 0.31667: 0.25833: 0.24583, comparison of F1-Score 0.30884: 0.25833: 0.23066.","PeriodicalId":178443,"journal":{"name":"2021 4th International Conference of Computer and Informatics Engineering (IC2IE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Analysis of KNN in Classification of Firearms Sounds using Fast Fourier Transform\",\"authors\":\"Muhammad Ari Afriansyah, Opim Salim Sitompul, S. Suwilo\",\"doi\":\"10.1109/ic2ie53219.2021.9649269\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"K-Nearest Neighbor (KNN) is an algorithm that is able to recognize an object with the training and testing data. Sound is one of the objects that can be classified with KNN. one example of the sound of a sharp weapon varies in sound based on its type. So that in this paper, do a classification to recognize sound based on the type of weapon tested with several distance formulas. The variation of the tested distance formula shows different results, the Euclidian distance formula is better than the Chebyshev distance formula and the Monkowski distance formula. Comparison of accuracy 0.31667: 0.25833: 0.24583, comparison of precision 0.30878: 0.25855: 0.22838, comparison of recall 0.31667: 0.25833: 0.24583, comparison of F1-Score 0.30884: 0.25833: 0.23066.\",\"PeriodicalId\":178443,\"journal\":{\"name\":\"2021 4th International Conference of Computer and Informatics Engineering (IC2IE)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-09-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 4th International Conference of Computer and Informatics Engineering (IC2IE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ic2ie53219.2021.9649269\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 4th International Conference of Computer and Informatics Engineering (IC2IE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ic2ie53219.2021.9649269","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

k -最近邻(KNN)算法是一种能够利用训练和测试数据识别目标的算法。声音是可以用KNN分类的对象之一。例如，尖锐武器的声音因其类型而异。因此，本文采用几种距离公式对武器类型进行分类识别。实验距离公式的变化显示出不同的结果，欧几里得距离公式优于切比雪夫距离公式和蒙可夫斯基距离公式。准确率0.31667:0.25833:0.24583、精密度0.30878:0.25855:0.22838、召回率0.31667:0.25833:0.24583、F1-Score 0.30884: 0.25833: 0.23066的比较。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Analysis of KNN in Classification of Firearms Sounds using Fast Fourier Transform

K-Nearest Neighbor (KNN) is an algorithm that is able to recognize an object with the training and testing data. Sound is one of the objects that can be classified with KNN. one example of the sound of a sharp weapon varies in sound based on its type. So that in this paper, do a classification to recognize sound based on the type of weapon tested with several distance formulas. The variation of the tested distance formula shows different results, the Euclidian distance formula is better than the Chebyshev distance formula and the Monkowski distance formula. Comparison of accuracy 0.31667: 0.25833: 0.24583, comparison of precision 0.30878: 0.25855: 0.22838, comparison of recall 0.31667: 0.25833: 0.24583, comparison of F1-Score 0.30884: 0.25833: 0.23066.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2021 4th International Conference of Computer and Informatics Engineering (IC2IE)

自引率

0.00%

发文量