Using machine learning on sensor data

Author

Moraru, Alexandra ; Pesko, Marko ; Porcius, Maria ; Fortuna, Carolina ; Mladenic, Dunja

Author_Institution

J. Stefan Inst., Ljubljana, Slovenia

fYear

2010

fDate

21-24 June 2010

Firstpage

573

Lastpage

578

Abstract

Developing hardware, algorithms and protocols, as well as collecting data in sensor networks are all important challenges in building good systems. We describe a vertical system integration of a sensor node and a toolkit of machine learning algorithms. Based on a dataset that combines sensor data with additional introduced data we predict the number of persons in a closed space. We analyze the dataset and evaluate the performance of two types of machine learning algorithms on this dataset: classification and regression.

Keywords

data acquisition; data analysis; learning (artificial intelligence); performance evaluation; wireless sensor networks; classification; closed space; data collecting; dataset; machine learning; performance evaluation; regression; sensor data; sensor networks; vertical system integration; Bayesian methods; Classification algorithms; Decision trees; Humidity; Prediction algorithms; Temperature measurement; Temperature sensors; data mining; machine learning; prediction; sensor node;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Technology Interfaces (ITI), 2010 32nd International Conference on

Conference_Location

Cavtat/Dubrovnik

ISSN

1330-1012

Print_ISBN

978-1-4244-5732-8

Type

conf

Filename

5546471