Wood Species Classification Utilizing Ensembles of Convolutional Neural Networks Established by Near-Infrared Spectra and Images Acquired from Korean Softwood Lumber

In this study, 65 kinds of wood samples were classified by using artificial neural networks based on the measured value of wood thermal physical parameters. First, the thermal conductivities and the thermal diffusion coefficients of the wood samples were measured. The transient temperature rise curve of wood samples during the test process was recorded, and the characteristic values of the transient temperature rise curve were extracted by logarithmic curve fitting. The emissivity spectrum representing the thermal physical properties of wood surface was measured, and the characteristic spectral data were selected according to the principal component analysis. An artificial neural network model was established based on the extracted feature values and characteristic spectral data to classify the wood species. The experimental results showed that the comprehensive correct classification rate of the proposed wood classification method was 99.85%. In addition, the proposed wood classification method was compared with a wood classification method based on laser induced breakdown spectrum and near infrared spectrum, which indicates the feasibility of wood classification based on the values of wood thermal physical properties.

Section: Resultsmentioning

confidence: 99%

Section: Comparison Of Different Modelsmentioning

confidence: 98%

Section: Comparison Of Different Modelsmentioning

confidence: 99%

Section: Comparison Of Different Modelsmentioning

confidence: 99%

Section: Comparison Of Different Modelsmentioning

confidence: 99%

See 3 more Smart Citations

Wood classification study based on thermal physical parameters with intelligent method of artificial neural networks

Cao

Zhou

Liu

et al. 2022

Prediction of withdrawal resistance of self-tapping screws in softwood structural lumber

Lee,

Kim

2024

The withdrawal resistance of self-tapping screws (STS) in Korean structural softwood in the vertical fiber direction was examined. Four representative softwood species were selected based on their specific gravity. Three STS fastener diameters were used for an STS penetration depth of 50 mm. The withdrawal capacity tended to increase with the specific gravity of the specimens and as the diameter of the STS increased. Primarily, the difference in strength was maximized as the STS diameter increased from 8 to 10 mm. Predictive experimental equations were proposed based on the experimental values of the relationship between the specific gravity of the structural material and the withdrawal resistance according to the diameter of the STS. The values were compared with the predicted values calculated using fastener and screw prediction equations proposed by the National Design Specification for Wood Construction (NDS) and European Standards (EN). The results calculated using the NDS prediction equations yielded a peak difference of 43% compared with the experimental withdrawal capacity, whereas the EN prediction equations yielded a difference of 0.7 to 1.14 times the experimental values. The ratios between the withdrawal capacity predicted by the proposed prediction equations and the experimental withdrawal capacity were the most similar, ranging from 0.80 to 1.15.

Convolutional neural network performance and the factors affecting performance for classification of seven Quercus species using sclereid characteristics in the bark

Kim,

Purusatama,

Savero

et al. 2023

Based on the sclereids in the bark of oak species, a convolutional neural network (CNN) was employed to validate species classification performance and its influencing factors. Three optimizers including stochastic gradient descent (SGD), adaptive moment estimation (Adam), root mean square propagation (RMSProp), and dataset augmentation were adopted. The accuracy and loss stabilized at approximately 15 to 20 and 70 to 80 epochs for the augmented and non-augmented condition, respectively. In the last five epochs, the RMSProp-augmented condition achieved the highest accuracy of 89.8%, whereas the Adam-augmented condition achieved the lowest accuracy of 73.8%. Regarding the loss, SGD-non-augmented condition was the lowest at 0.498, whereas Adam-augmented condition was the highest at 2.740. The highest accuracy was influenced by RMSProp at 0.194. Dataset augmentation had a significant influence on accuracy at 0.456. Homogeneous subsets among the validation conditions indicated that the accuracy and loss were classified into the same subset using an augmented dataset during the training, regardless of the optimizer. Only Adam and RMSProp with non-augmented datasets were categorized into the same subset during the test. Hence, species classification using CNN and sclereid characteristics in the bark was feasible, and RMSProp with augmented datasets showed optimal performance for species classification.