Skip to the main content

Original scientific paper

https://doi.org/10.2498/cit.1001913

Using Machine Learning on Sensor Data

Alexandra Moraru ; Jožef Stefan Institute, Ljubljana, Slovenia
Marko Pesko ; Jožef Stefan Institute, Ljubljana, Slovenia
Maria Porcius ; J. Stefan International Postgraduate School, Ljubljana, Slovenia
Carolina Fortuna ; Jožef Stefan Institute, Ljubljana, Slovenia
Dunja Mladenic ; Jožef Stefan Institute, Ljubljana, Slovenia


Full text: english pdf 366 Kb

page 341-347

downloads: 16.586

cite


Abstract

Extracting useful information from raw sensor data requires specific methods and algorithms. We describe a vertical system integration of a sensor node and a toolkit of machine learning algorithms for predicting the number of persons located in a closed space. The dataset used as input for the learning algorithms is composed of automatically collected sensor data and additional manually introduced data. We analyze the dataset and evaluate the performance of two types ofmachine learning algorithms on this dataset: classification and regression. With our system settings, the experiments show that augmenting sensor data with proper information can improve prediction results and also the classification algorithm performed better.

Keywords

sensor node; data mining; machine learning; prediction

Hrčak ID:

63904

URI

https://hrcak.srce.hr/63904

Publication date:

30.12.2010.

Visits: 19.057 *