Tampere University of Technology

TUTCRIS Research Portal

Classifying soil stoniness based on the excavator boom vibration data in mounding operations

Research output: Contribution to journalArticleScientificpeer-review

Standard

Classifying soil stoniness based on the excavator boom vibration data in mounding operations. / Melander, Lari; Ritala, Risto; Strandström, Markus.

In: Silva Fennica, Vol. 53, No. 2, 10068, 2019.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

APA

Vancouver

Author

Bibtex - Download

@article{4a5e35e0da0744968aa038f2f318153c,
title = "Classifying soil stoniness based on the excavator boom vibration data in mounding operations",
abstract = "The stoniness index of forest soil describes the stone content in the upper soil layer at depths of 20–30 centimeters. This index is not available in any existing map databases, and traditional measurements for the stoniness of the soil have always necessitated laborious soil-penetration methods. Knowledge of the stone content of a forest site could be of use in a variety of forestry operations. This paper presents a novel approach to obtaining automatic measurements of soil stoniness during an excavator-based mounding operation. The excavator was equipped with only a low-cost inertial measurement unit and a satellite navigation receiver. Using the data from these sensors and manually conducted soil stoniness measurements, supervised machine learning methods were utilized to build a model that is capable of predicting the stoniness class of a given mounding location. This study compares different classifiers and feature selection methods to find the most promising solution for this learning problem. The discussion includes a proposition for a meaningful measurement resolution of the soil’s stoniness, and a practical method for evaluating the variability of the stone content of the soil. The results indicate that it is possible to predict the soil stoniness class with 70{\%} accuracy using only the inertial and location measurements.",
keywords = "Activity recognition, Spot mounding, Stoniness classification, Supervised machine learning",
author = "Lari Melander and Risto Ritala and Markus Strandstr{\"o}m",
year = "2019",
doi = "10.14214/sf.10068",
language = "English",
volume = "53",
journal = "Silva Fennica",
issn = "0037-5330",
publisher = "Suomen Mets{\"a}tieteellinen Seura ry",
number = "2",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Classifying soil stoniness based on the excavator boom vibration data in mounding operations

AU - Melander, Lari

AU - Ritala, Risto

AU - Strandström, Markus

PY - 2019

Y1 - 2019

N2 - The stoniness index of forest soil describes the stone content in the upper soil layer at depths of 20–30 centimeters. This index is not available in any existing map databases, and traditional measurements for the stoniness of the soil have always necessitated laborious soil-penetration methods. Knowledge of the stone content of a forest site could be of use in a variety of forestry operations. This paper presents a novel approach to obtaining automatic measurements of soil stoniness during an excavator-based mounding operation. The excavator was equipped with only a low-cost inertial measurement unit and a satellite navigation receiver. Using the data from these sensors and manually conducted soil stoniness measurements, supervised machine learning methods were utilized to build a model that is capable of predicting the stoniness class of a given mounding location. This study compares different classifiers and feature selection methods to find the most promising solution for this learning problem. The discussion includes a proposition for a meaningful measurement resolution of the soil’s stoniness, and a practical method for evaluating the variability of the stone content of the soil. The results indicate that it is possible to predict the soil stoniness class with 70% accuracy using only the inertial and location measurements.

AB - The stoniness index of forest soil describes the stone content in the upper soil layer at depths of 20–30 centimeters. This index is not available in any existing map databases, and traditional measurements for the stoniness of the soil have always necessitated laborious soil-penetration methods. Knowledge of the stone content of a forest site could be of use in a variety of forestry operations. This paper presents a novel approach to obtaining automatic measurements of soil stoniness during an excavator-based mounding operation. The excavator was equipped with only a low-cost inertial measurement unit and a satellite navigation receiver. Using the data from these sensors and manually conducted soil stoniness measurements, supervised machine learning methods were utilized to build a model that is capable of predicting the stoniness class of a given mounding location. This study compares different classifiers and feature selection methods to find the most promising solution for this learning problem. The discussion includes a proposition for a meaningful measurement resolution of the soil’s stoniness, and a practical method for evaluating the variability of the stone content of the soil. The results indicate that it is possible to predict the soil stoniness class with 70% accuracy using only the inertial and location measurements.

KW - Activity recognition

KW - Spot mounding

KW - Stoniness classification

KW - Supervised machine learning

U2 - 10.14214/sf.10068

DO - 10.14214/sf.10068

M3 - Article

VL - 53

JO - Silva Fennica

JF - Silva Fennica

SN - 0037-5330

IS - 2

M1 - 10068

ER -