Search

The detection of defects in wood is valuable for promoting the efficient exploitation of wood. So it is significant to further increase the accuracy of the detection of wood defects and enhance the real-time detection. In this paper, the YOLOv5 convolutional neural network is applied to wood defects detection, and the model is modified for both the YOLOv5n and YOLOv5m scales. The SimAM attention model was first incorporated into the network, and the learning rate decay strategy was replaced with CosLR, with Ghost convolution employed to minimize the model parameters. Finally, the modified network was tested for five types of wood defects, including live-knot, resin, dead-knot, knot-with-crack, and crack. It is demonstrated that the improvements resulted in a 1.5% increase in mAP0.5:0.95 for YOLOv5n-C3Ghost and a 1.6% increase in mAP0.5:0.95 for YOLOv5m-C3Ghost. In addition, there is a 51% and 63% difference in the number of model parameters, and a decrease in inference time and floating point operations respectively. The experiments indicate that our improved method not only enhances the accuracy of YOLOv5 in detecting wood defects, but also enables a reduction in the volume and computational cost of the model parameters.

Wood is an indispensable non-renewable resource and plays an important role in our life. So, it is a necessity to apply accurate classification techniques. In this paper, a novel model of deep one-dimensional convolutional neural network NIR-VGGNet19 is proposed to classify seven pius wood by combining near-infrared spectroscopy. NIR-VGGNet19 uses a deep convolutional neural network to automatically extract features, eliminate noise, and solve the problem of spectral overlapping peaks; initially eliminates random noise by adding $1\times 7$ convolutional kernels; then uses an attention mechanism to extract more accurate features. According to the results, when NIR-VGGNet19 was tested against other methods, NIR-VGGNet19 had the highest classification accuracy, achieving 98.41% on the test set. In contrast, the accuracy of LeNet, AlexNet, VGGNet-19, ResNet-34, back propagation neural network, and support vector machine were 70.95%, 92.54%, 93.02%, 96.67%, 76.19%, and 71.26%, respectively. Thus, it suggests that the NIR-VGGNet19 can improve the accuracy of classifying wood of the homogeneous genus.

Previously works on analysing imperfect electricity markets have employed conventional game-theoretic approaches. However, such approaches necessitate that each strategic market player has full knowledge of the operating parameters and the strategies of its rivals as well as the computational algorithm of the market clearing process. This unrealistic assumption, along with the modeling and computational complexities, renders such approaches less applicable for conducting practical multi-period and multi-spatial equilibrium analysis. This paper proposes a novel multi-agent deep reinforcement learning (MA-DRL) based methodology, combining multi-agent intelligence, the deep policy gradient (DPG) method, and an innovative long short term memory (LSTM) based representation network for optimizing the offering strategies of multiple self-interested generation companies (GENCOs) as well as exploring the market outcome stemming from their interactions. The proposed approach is tailored to align with the nature of the examined problem by posing it, for the first time, in multi-dimensional continuous state and action spaces, enabling GENCOs to receive accurate feedback regarding the impact of their offering strategies on the market clearing outcome, and devise more profitable bidding decisions by exploiting the entire action domain, and thereby facilitates more accurate equilibrium analysis. The proposed LSTM-based representation network extracts discriminative features which further improves the learning performance and thus promises more profitable offerings strategies for each GENCO. Case studies demonstrate that the proposed method i) achieves a significantly higher profit than state-of-the-art RL methods for a single GENCO's optimal offering strategy problem and ii) outperforms the state-of-the-art equilibrium programming models in efficiently identifying an imperfect market equilibrium with/without network congestion. Quantitative economic analysis is carried out on the obtained equilibrium.