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

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.

Keywords:

• Indoor positioning
• data mining
• classification

Acknowledgements

This research was supported by the European Union and the Hungarian State, co-financed by the European Regional Development Fund in the framework of the GINOP-2.3.4-15-2016-00004 project, aimed to promote the cooperation between the higher education and the industry.

Notes

No potential conflict of interest was reported by the authors.

Additional information

Funding

The described article/presentation/study was carried out as part of the EFOP-3.6.1-16-00011 ‘Younger and Renewing University – Innovative Knowledge City – institutional development of the University of Miskolc aiming at intelligent specialisation’ project implemented in the framework of the Szechenyi 2020 program. The realisation of this project is supported by the European Union, co-financed by the European Social Fund.