Next Article in Journal
Understory Vegetation Composition and Stand Are Mainly Limited by Soil Moisture in Black Locust Plantations of Loess Plateau
Next Article in Special Issue
Modelling the Material Resistance of Wood—Part 1: Utilizing Durability Test Data Based on Different Reference Wood Species
Previous Article in Journal
Root Rot Resistance Locus PaLAR3 Is Delivered by Somatic Embryogenesis (SE) Pipeline in Norway Spruce (Picea abies (L.) Karst.)
Previous Article in Special Issue
Studies into Fungal Decay of Wood In Ground Contact—Part 1: The Influence of Water-Holding Capacity, Moisture Content, and Temperature of Soil Substrates on Fungal Decay of Selected Timbers
Article

Application of Unsupervised Anomaly Detection Techniques to Moisture Content Data from Wood Constructions

1
XLAB d.o.o, Pot za Brdom 100, SI-1000 Ljubljana, Slovenia
2
Department for Wood Science and Technology, Biotechnical Faculty, University of Ljubljana, SI-1000 Ljubljana, Slovenia
*
Author to whom correspondence should be addressed.
Academic Editor: Samuel L. Zelinka
Forests 2021, 12(2), 194; https://doi.org/10.3390/f12020194
Received: 7 January 2021 / Revised: 2 February 2021 / Accepted: 3 February 2021 / Published: 8 February 2021
(This article belongs to the Special Issue Modeling the Performance of Wood and Wood Products)
Wood is considered one of the most important construction materials, as well as a natural material prone to degradation, with fungi being the main reason for wood failure in a temperate climate. Visual inspection of wood or other approaches for monitoring are time-consuming, and the incipient stages of decay are not always visible. Thus, visual decay detection and such manual monitoring could be replaced by automated real-time monitoring systems. The capabilities of such systems can range from simple monitoring, periodically reporting data, to the automatic detection of anomalous measurements that may happen due to various environmental or technical reasons. In this paper, we explore the application of Unsupervised Anomaly Detection (UAD) techniques to wood Moisture Content (MC) data. Specifically, data were obtained from a wood construction that was monitored for four years using sensors at different positions. Our experimental results prove the validity of these techniques to detect both artificial and real anomalies in MC signals, encouraging further research to enable their deployment in real use cases. View Full-Text
Keywords: wood moisture monitoring; Unsupervised Anomaly Detection (UAD); Moisture Content (MC) data; wooden facade and windows wood moisture monitoring; Unsupervised Anomaly Detection (UAD); Moisture Content (MC) data; wooden facade and windows
Show Figures

Figure 1

MDPI and ACS Style

García Faura, Á.; Štepec, D.; Cankar, M.; Humar, M. Application of Unsupervised Anomaly Detection Techniques to Moisture Content Data from Wood Constructions. Forests 2021, 12, 194. https://doi.org/10.3390/f12020194

AMA Style

García Faura Á, Štepec D, Cankar M, Humar M. Application of Unsupervised Anomaly Detection Techniques to Moisture Content Data from Wood Constructions. Forests. 2021; 12(2):194. https://doi.org/10.3390/f12020194

Chicago/Turabian Style

García Faura, Álvaro, Dejan Štepec, Matija Cankar, and Miha Humar. 2021. "Application of Unsupervised Anomaly Detection Techniques to Moisture Content Data from Wood Constructions" Forests 12, no. 2: 194. https://doi.org/10.3390/f12020194

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop