Classification-based symbolic indoor positioning over the Miskolc IIS Data-set

IF 16.4 1区化学 Q1 CHEMISTRY, MULTIDISCIPLINARY

Accounts of Chemical Research Pub Date : 2018-01-02 DOI:10.1080/17489725.2018.1455992

J. Tamás, Zsolt Tóth

{"title":"Classification-based symbolic indoor positioning over the Miskolc IIS Data-set","authors":"J. Tamás, Zsolt Tóth","doi":"10.1080/17489725.2018.1455992","DOIUrl":null,"url":null,"abstract":"Abstract Determination of indoor position is vital for the creation of smart environments. Symbolic indoor positioning algorithms determine the location as a well-defined part of the building, such as a room, a corridor or a floor. Performance analysis of classification-based symbolic indoor positioning methods are presented in this paper. Symbolic positioning can be considered as a classification task, where position denotes the category and the attributes are the measured values. Evaluation and comparison of the selected classification methods are performed over a hybrid data-set which was recorded by the ILONA (Indoor Localisation and Navigation) System. These experiments were performed in RapidMiner and the Weka framework. Accuracy is the base of comparison and the following classification methods were used: k–NN, Naive Bayes, Decision Tree, Rule Induction and Artificial Neural Network. Comparison is used to recommend a classification-based symbolic indoor positioning method to be implemented in the ILONA System. Experimental results show that the k–NN, Naive Bayes with 1 kernel and ANN classifiers achieved better than 90% accuracy. As a result of our experiments, k–NN, Naive Bayes with 1 kernel- and ANN-based classification methods are recommended.","PeriodicalId":1,"journal":{"name":"Accounts of Chemical Research","volume":null,"pages":null},"PeriodicalIF":16.4000,"publicationDate":"2018-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/17489725.2018.1455992","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Accounts of Chemical Research","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1080/17489725.2018.1455992","RegionNum":1,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CHEMISTRY, MULTIDISCIPLINARY","Score":null,"Total":0}

引用次数: 8

Abstract

Abstract Determination of indoor position is vital for the creation of smart environments. Symbolic indoor positioning algorithms determine the location as a well-defined part of the building, such as a room, a corridor or a floor. Performance analysis of classification-based symbolic indoor positioning methods are presented in this paper. Symbolic positioning can be considered as a classification task, where position denotes the category and the attributes are the measured values. Evaluation and comparison of the selected classification methods are performed over a hybrid data-set which was recorded by the ILONA (Indoor Localisation and Navigation) System. These experiments were performed in RapidMiner and the Weka framework. Accuracy is the base of comparison and the following classification methods were used: k–NN, Naive Bayes, Decision Tree, Rule Induction and Artificial Neural Network. Comparison is used to recommend a classification-based symbolic indoor positioning method to be implemented in the ILONA System. Experimental results show that the k–NN, Naive Bayes with 1 kernel and ANN classifiers achieved better than 90% accuracy. As a result of our experiments, k–NN, Naive Bayes with 1 kernel- and ANN-based classification methods are recommended.

查看原文本刊更多论文

Miskolc IIS数据集上基于分类的符号室内定位

室内位置的确定对于智能环境的创建至关重要。象征性的室内定位算法将位置确定为建筑物的一个明确的部分，例如房间，走廊或楼层。本文对基于分类的符号室内定位方法进行了性能分析。符号定位可以看作是一个分类任务，其中位置表示类别，属性是测量值。通过ILONA(室内定位和导航)系统记录的混合数据集，对选定的分类方法进行评估和比较。这些实验是在RapidMiner和Weka框架中进行的。准确率是比较的基础，使用了以下分类方法:k-NN、朴素贝叶斯、决策树、规则归纳和人工神经网络。通过比较，推荐了一种基于分类的室内符号定位方法在ILONA系统中实现。实验结果表明，k-NN、1核朴素贝叶斯和人工神经网络分类器的准确率均超过90%。根据我们的实验结果，推荐了k-NN、1核朴素贝叶斯和基于神经网络的分类方法。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Accounts of Chemical Research 化学-化学综合

CiteScore

31.40

自引率

1.10%

发文量

312

审稿时长

2 months

期刊介绍： Accounts of Chemical Research presents short, concise and critical articles offering easy-to-read overviews of basic research and applications in all areas of chemistry and biochemistry. These short reviews focus on research from the author’s own laboratory and are designed to teach the reader about a research project. In addition, Accounts of Chemical Research publishes commentaries that give an informed opinion on a current research problem. Special Issues online are devoted to a single topic of unusual activity and significance. Accounts of Chemical Research replaces the traditional article abstract with an article "Conspectus." These entries synopsize the research affording the reader a closer look at the content and significance of an article. Through this provision of a more detailed description of the article contents, the Conspectus enhances the article's discoverability by search engines and the exposure for the research.