Plant image identification has become an interdisciplinary focus in both botanical taxonomy and computer vision. The first plant image dataset collected by mobile phone in natural scene is presented, which contains 10,000 images of 100 ornamental plant species in Beijing Forestry University campus. A 26-layer deep learning model consisting of 8 residual building blocks is designed for large-scale plant classification in natural environment. The proposed model achieves a recognition rate of 91.78% on the BJFU100 dataset, demonstrating that deep learning is a promising technology for smart forestry.

Wildlife is an important part of natural ecosystems and protecting wildlife plays a crucial role in maintaining ecological balance. The wildlife detection method for images and videos based on deep learning can save a lot of labor costs and is of great significance and value for the monitoring and protection of wildlife. However, the complex and changing outdoor environment often leads to less than satisfactory detection results due to insufficient lighting, mutual occlusion, and blurriness. The TMS-YOLO (Takin, Monkey, and Snow Leopard-You Only Look Once) proposed in this paper is a modification of YOLOv7, specifically optimized for wildlife detection. It uses the designed O-ELAN (Optimized Efficient Layer Aggregation Networks) and O-SPPCSPC (Optimized Spatial Pyramid Pooling Combined with Cross Stage Partial Channel) modules and incorporates the CBAM (Convolutional Block Attention Module) to enhance its suitability for this task. In simple terms, O-ELAN can preserve a portion of the original features through residual structures when extracting image features, resulting in more background and animal features. However, O-ELAN may include more background information in the extracted features. Therefore, we use CBAM after the backbone to suppress background features and enhance animal features. Then, when fusing the features, we use O-SPPCSPC with fewer network layers to avoid overfitting. Comparative experiments were conducted on a self-built dataset and a Turkish wildlife dataset. The results demonstrated that the enhanced TMS-YOLO models outperformed YOLOv7 on both datasets. The mAP (mean Average Precision) of YOLOv7 on the two datasets was 90.5% and 94.6%, respectively. In contrast, the mAP of TMS-YOLO in the two datasets was 93.4% and 95%, respectively. These findings indicate that TMS-YOLO can achieve more accurate wildlife detection compared to YOLOv7.

Recently, the deep neural network (DNN) has become one of the most advanced and powerful methods used in classification tasks. However, the cost of DNN models is sometimes considerable due to the huge sets of parameters. Therefore, it is necessary to compress these models in order to reduce the parameters in weight matrices and decrease computational consumption, while maintaining the same level of accuracy. In this paper, in order to deal with the compression problem, we first combine the loss function and the compression cost function into a joint function, and optimize it as an optimization framework. Then we combine the CUR decomposition method with this joint optimization framework to obtain the low-rank approximation matrices. Finally, we narrow the gap between the weight matrices and the low-rank approximations to compress the DNN models on the image classification task. In this algorithm, we not only solve the optimal ranks by enumeration, but also obtain the compression result with low-rank characteristics iteratively. Experiments were carried out on three public datasets under classification tasks. Comparisons with baselines and current state-of-the-art results can conclude that our proposed low-rank joint optimization compression algorithm can achieve higher accuracy and compression ratios.

Monitoring nocturnal animals in the field is an important task in ecological research and wildlife conservation, but the complexity of nocturnal images and low light conditions make it difficult to cope with traditional image processing methods. To address this problem, researchers have introduced infrared cameras to improve the accuracy of nocturnal animal behaviour observations. Object detection in nighttime images captured by infrared cameras faces several challenges, including low image quality, animal scale variations, occlusion, and pose changes. This study proposes the YOLOv8‐night model, which effectively overcomes these challenges by introducing a channel attention mechanism in YOLOv8. The model is more focused on capturing animal‐related features by dynamically adjusting the channel weights, which improves the saliency of key features and increases the accuracy rate in complex backgrounds. The main contribution of this study is the introduction of the channel attention mechanism into the YOLOv8 framework to create a YOLOv8‐night model suitable for object detection in nighttime images. When tested on nighttime images, the model performs well with a significantly higher mAP (0.854) than YOLOv8 (0.831), and YOLOv8‐night scores 0.856 on mAP_l, which is obviously better than YOLOv8 (0.833) in terms of processing large objects. The study provides a reliable technical tool for ecological research, wildlife conservation and environmental monitoring, and offers new methods and insights for the study of nocturnal animal behaviour.

Aiming to address the problems of the high bit error rate (BER) of demodulation or low classification accuracy of modulation signals with a low signal-to-noise ratio (SNR), we propose a double-residual denoising autoencoder method with a channel attention mechanism, referred to as DRdA-CA, to improve the SNR of modulation signals. The proposed DRdA-CA consists of an encoding module and a decoding module. A squeeze-and-excitation (SE) ResNet module containing one residual connection is modified and then introduced into the autoencoder as the channel attention mechanism, to better extract the characteristics of the modulation signals and reduce the computational complexity of the model. Moreover, the other residual connection is further added inside the encoding and decoding modules to optimize the network degradation problem, which is beneficial for fully exploiting the multi-level features of modulation signals and improving the reconstruction quality of the signal. The ablation experiments prove that both the improved SE module and dual residual connections in the proposed method play an important role in improving the denoising performance. The subsequent experimental results show that the proposed DRdA-CA significantly improves the SNR values of eight modulation types in the range of −12 dB to 8 dB. Especially for 16QAM and 64QAM, the SNR is improved by 8.38 dB and 8.27 dB on average, respectively. Compared to the DnCNN denoising method, the proposed DRdA-CA makes the average classification accuracy increase by 67.59∼74.94% over the entire SNR range. When it comes to the demodulation, compared with the RLS and the DnCNN denoising algorithms, the proposed denoising method reduces the BER of 16QAM by an average of 63.5% and 40.5%, and reduces the BER of 64QAM by an average of 46.7% and 18.6%. The above results show that the proposed DRdA-CA achieves the optimal noise reduction effect.

Plant identification is a fine-grained classification task which aims to identify the family, genus, and species according to plant appearance features. Inspired by the hierarchical structure of taxonomic tree, the taxonomic loss was proposed, which could encode the hierarchical relationships among multilevel labels into the deep learning objective function by simple group and sum operation. By training various neural networks on PlantCLEF 2015 and PlantCLEF 2017 datasets, the experimental results demonstrated that the proposed loss function was easy to implement and outperformed the most commonly adopted cross-entropy loss. Eight neural networks were trained, respectively, by two different loss functions on PlantCLEF 2015 dataset, and the models trained by taxonomic loss led to significant performance improvements. On PlantCLEF 2017 dataset with 10,000 species, the SENet-154 model trained by taxonomic loss achieved the accuracies of 84.07%, 79.97%, and 73.61% at family, genus and species levels, which improved those of model trained by cross-entropy loss by 2.23%, 1.34%, and 1.08%, respectively. The taxonomic loss could further facilitate the fine-grained classification task with hierarchical labels.