<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<item>
  <id>05721399</id>
  <dt>j</dt>
  <an>05721399</an>
  <augroup>
    <au>Korpela, Mikko</au>
    <au>M\"akinen, Harri</au>
    <au>N\"ojd, Pekka</au>
    <au>Hollm\'en, Jaakko</au>
    <au>Sulkava, Mika</au>
  </augroup>
  <ti>Automatic detection of onset and cessation of tree stem radius increase using dendrometer data.</ti>
  <so>Neurocomputing 73, No. 10-12, 2039-2046 (2010).</so>
  <py>2010</py>
  <pu>Elsevier Science Publishers B.V., Amsterdam</pu>
  <lagroup>
    <la>EN</la>
  </lagroup>
  <ccgroup>
  </ccgroup>
  <utgroup>
    <ut>CUSUM chart</ut>
    <ut>Mann-Kendall test</ut>
    <ut>time series segmentation</ut>
    <ut>Markov switching autoregressive model</ut>
    <ut>wood formation</ut>
  </utgroup>
  <cigroup>
  </cigroup>
  <ligroup>
    <li>doi:10.1016/j.neucom.2009.11.035</li>
  </ligroup>
  <abgroup>
    <ab>Summary: Dendrometers are devices, which measure continuously the stem radius of a tree. We studied the use of four data analysis methods for automatically and, thus, objectively determining the onset and cessation dates of radial increase based on dendrometer data. The cumulative sum chart, time series segmentation, Mann-Kendall test, and a Markov switching autoregressive model were compared. We used data measured in two stands in southern Finland to test the performance of the methods. Once configured properly, the cumulative sum chart produced results similar to those determined by an expert. The overall performance of the other methods was lower.</ab>
    <rv></rv>
  </abgroup>
</item>