Abstract
A transfer learning system was designed to predict Xylosma racemosum compression strength. Near-infrared (NIR) spectral data for Acer mono and its compression strength values were used to resolve the weak generalization problem caused by using a X. racemosum dataset alone. Transfer component analysis and principal component analysis are domain adaption and feature extraction processes to enable the use of A. mono NIR spectral data to design the transfer learning system. A five-layer neural network relevant to the X. racemosum dataset, was fine-tuned using the A. mono dataset. There were 109 A. mono samples used as the source dataset and 79 X. racemosum samples as the target dataset. When the ratio of the training set to the test set was 1:9, the correlation coefficient was 0.88, and mean square error was 8.84. The results show that NIR spectral data of hardwood species are related. Predicting the mechanical strength of hardwood species using multi-species NIR spectral datasets will improve the generalization ability of the model and increase accuracy.
Highlights
IntroductionHigh specific gravity, texture, and anti-corrosion and water resistance characteristics, the species is commonly used for furniture and structural material
Xylosma racemosum is widely distributed in Northeast China
We proposed basing the transfer learning system on two species of hardwood data; NIR spectral data and corresponding compression strength values for A. mono were used to establish a compression strength prediction model for X. racemosum
Summary
High specific gravity, texture, and anti-corrosion and water resistance characteristics, the species is commonly used for furniture and structural material. Compression strength is one of the most important mechanical properties of tree species; traditional compression strength testing is time-consuming and costly (Rakotovololonalimanana et al 2015). The species has natural heterogeneous or diverse polymer characteristics and mechanical parameters because of inner defects and other factors. Near-infrared (NIR) spectroscopy is a nondestructive, economical and reliable approach to evaluate various properties of organic materials. The wavelength range of the NIR spectrum is 770–2500 nm and reflects the molecular hydrogen groups O–H, N–H, C–H vibrational information that illustrates their structure. Because NIR spectral absorption peaks differ for thevarious molecular hydrogen groups, complex materials and their physical and biological information can be chemically analyzed
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
