Explore the vast range of titles available.

Aim: Recent studies increasingly use statistical methods to infer biotic interactions from co-occurrence information at a large spatial scale. However, disentangling biotic interactions from other factors that can affect co-occurrence patterns at the macroscale is a major challenge. Approach: We present a set of questions that analysts and reviewers should ask to avoid erroneously attributing species association patterns to biotic interactions. Our questions relate to the appropriateness of data and models, the causality behind a correlative signal, and the problems associated with static data from dynamic systems. We summarize caveats reported by macroecological studies of biotic interactions and examine whether conclusions on the presence of biotic interactions are supported by the modelling approaches used. Findings: Irrespective of the method used, studies that set out to test for biotic interactions find statistical associations in species' co-occurrences. Yet, when compared with our list of questions, few purported interpretations of such associations as biotic interactions hold up to scrutiny. This does not dismiss the presence or importance of biotic interactions, but it highlights the risk of too lenient interpretation of the data. Combining model results with information from experiments and functional traits that are relevant for the biotic interaction of interest might strengthen conclusions. Main conclusions: Moving from species- to community-level models, including biotic interactions among species, is of great importance for process-based understanding and forecasting ecological responses. We hope that our questions will help to improve these models and facilitate the interpretation of their results. In essence, we conclude that ecologists have to recognize that a species association pattern in joint species distribution models will be driven not only by real biotic interactions, but also by shared habitat preferences, common migration history, phylogenetic history and shared response to missing environmental drivers, which specifically need to be discussed and, if possible, integrated into models.

Classification of land use and land cover from remote sensing images has been widely used in natural resources and urban information management. The variability and complex background of land use in high-resolution imagery poses greater challenges for remote sensing semantic segmentation. To obtain multi-scale semantic information and improve the classification accuracy of land-use types in remote sensing images, the deep learning models have been wildly focused on. Inspired by the idea of the atrous-spatial pyramid pooling (ASPP) framework, an improved deep learning model named RAANet (Residual ASPP with Attention Net) is constructed in this paper, which constructed a new residual ASPP by embedding the attention module and residual structure into the ASPP. There are 5 dilated attention convolution units and a residual unit in its encoder. The former is used to obtain important semantic information at more scales, and residual units are used to reduce the complexity of the network to prevent the disappearance of gradients. In practical applications, according to the characteristics of the data set, the attention unit can select different attention modules such as the convolutional block attention model (CBAM). The experimental results obtained from the land-cover domain adaptive semantic segmentation (LoveDA) and ISPRS Vaihingen datasets showed that this model can enhance the classification accuracy of semantic segmentation compared to the current deep learning models.

In Europe, forest management has controlled forest dynamics to sustain commodity production over multiple centuries. Yet over-regulation for growth and yield diminishes resilience to environmental stress as well as threatens biodiversity, leading to increasing forest susceptibility to an array of disturbances. These trends have stimulated interest in alternative management systems, including natural dynamics silviculture (NDS). NDS aims to emulate natural disturbance dynamics at stand and landscape scales through silvicultural manipulations of forest structure and landscape patterns. We adapted a \"Comparability Index\" (CI) to assess convergence/divergence between natural disturbances and forest management effects. We extended the original CI concept based on disturbance size and frequency by adding the residual structure of canopy trees after a disturbance as a third dimension. We populated the model by compiling data on natural disturbance dynamics and management from 13 countries in Europe, covering four major forest types (i.e., spruce, beech, oak, and pine-dominated forests). We found that natural disturbances are highly variable in size, frequency, and residual structure, but European forest management fails to encompass this complexity. Silviculture in Europe is skewed toward even-aged systems, used predominately (72.9% of management) across the countries assessed. The residual structure proved crucial in the comparison of natural disturbances and silvicultural systems. CI indicated the highest congruence between uneven-aged silvicultural systems and key natural disturbance attributes. Even so, uneven-aged practices emulated only a portion of the complexity associated with natural disturbance effects. The remaining silvicultural systems perform poorly in terms of retention compared to tree survivorship after natural disturbances. We suggest that NDS can enrich Europe's portfolio of management systems, for example where wood production is not the primary objective. NDS is especially relevant to forests managed for habitat quality, risk reduction, and a variety of ecosystem services. We suggest a holistic approach integrating NDS with more conventional practices.

Clustering algorithm is one of the most widely used and influential analysis techniques. With the advent of deep learning, deep embedding clustering algorithms have rapidly evolved and yield promising results. Much of the success of these algorithms depends on the potential expression captured by the autoencoder network. Therefore, the quality of the potential expression directly determines the algorithm’s performance. In view of this, researchers have proposed many improvements. Although the performance has been slightly improved, they all have one shortcoming, that is, too much emphasis is placed on the original data reconstruction ability during the process of feature expression, which greatly limits the further expression of potential features according to specific clustering tasks. Moreover, there is a large amount of noise in the original data, so blindly emphasizing reconstruction will only backfire. Hence, we innovatively propose a deep embedding clustering algorithm based on residual autoencoder (DECRA) after in-depth research. Specifically, a novel autoencoder network with residual structure is proposed and introduced into deep embedded clustering tasks. The network introduces an adaptive weight layer in feature representation z, which can make it have good robustness, generalization for specific tasks, and adaptive learning of better feature embeddings according to category classification. In this paper, the reasons for the validity of this structure are explained theoretically, and comprehensive experiments on six benchmark datasets including various types show that the clustering performance of the DECRA is very competitive and significantly superior to the most advanced methods.

In the field of fisheries, detecting the distribution of fish underwater is an important task for achieving accurate bait feeding. However, the current deep neural networks for fish detection are significantly more computationally intensive than previous methods due to their increased network depths. Additionally, drawbacks such as the difficulty of balancing accuracy and real-time performance limit the deployment of these algorithms in fishery end devices. To address this problem, this paper proposes an improved You Only Look Once version 5 (YOLOv5)-based underwater fish detection method called RC_YOLOv5. First, the Res2Net residual structure is introduced to represent multiscale features at a finer granularity and increase the perceptual field of the network while reducing the computational power of the model. Second, a coordinate attention mechanism is introduced to suppress the interference of the background and help the network locate its target more accurately. Finally, coordinate attention is embedded into the tail of Res2Net to form a residual attention structure, and this structure is used to replace the original bottleneck structure in the YOLOv5 model to improve its accuracy. Experiments show that the proposed model has good performance on a self-built fish dataset, reaching 95.7% and 95.4% precision and mean average precision (mAP), respectively. Compared with those of the original model, the precision of the proposed approach improves by 1.6%, the mAP improves by 0.6%, the number of computations is reduced by 22.2%, the model size is reduced by 23.5%, the detection rate reaches 263 frames per second (FPS) and the performance is better than that of other mainstream detection models. This method enables accurate and rapid fish detection in fisheries.

Image steganography is a process of embedding a secret image into a cover image to achieve secret transmission and accurately recovering a secret image from a stego image. To further investigate the high invisibility and extraction accuracy of steganography, this study presents RISRANet, a reversible image steganography network utilizing residual structure and mixed attention mechanism, markedly enhancing both the fidelity of stego image and the accuracy of restoring secret image. The network uses INN as the overall framework, adopts a double-branch structure, extracts deep features using the mixed attention mechanism, and employs channel shuffle to promote information interaction between different features. This paper introduces dilated convolution to design a multi-scale convolution attention module that combines feature information from different scales, highlights essential features, and precisely locates the ideal embedding position. In addition, the residual structure is constructed to allow for feature reuse, and the structural similarity is introduced into the loss function to improve the accuracy of information recovery. The experimental results suggest that the framework achieves secure hiding and lossless extraction of secret images, superior to comparative algorithms in multiple evaluation metrics.

Rapid and accurate identification and timely protection of crop disease is of great importance for ensuring crop yields. Aiming at the problems of large model parameters of existing crop disease recognition methods and low recognition accuracy in the complex background of the field, we propose a lightweight crop leaf disease recognition model based on improved ShuffleNetV2. First, the repetition number and the number of output channels of the basic module of the ShuffleNetV2 model are redesigned to reduce the model parameters to make the model more lightweight while ensuring the accuracy of the model. Second, the residual structure is introduced in the basic feature extraction module to solve the gradient vanishing problem and enable the model to learn more complex feature representations. Then, parallel paths were added to the mechanism of the efficient channel attention (ECA) module, and the weights of different paths were adaptively updated by learnable parameters, and then the efficient dual channel attention (EDCA) module was proposed, which was embedded into the ShuffleNetV2 to improve the cross-channel interaction capability of the model. Finally, a multi-scale shallow feature extraction module and a multi-scale deep feature extraction module were introduced to improve the model’s ability to extract lesions at different scales. Based on the above improvements, a lightweight crop leaf disease recognition model REM-ShuffleNetV2 was proposed. Experiments results show that the accuracy and F1 score of the REM-ShuffleNetV2 model on the self-constructed field crop leaf disease dataset are 96.72% and 96.62%, which are 3.88% and 4.37% higher than that of the ShuffleNetV2 model; and the number of model parameters is 4.40M, which is 9.65% less than that of the original model. Compared with classic networks such as DenseNet121, EfficientNet, and MobileNetV3, the REM-ShuffleNetV2 model not only has higher recognition accuracy but also has fewer model parameters. The REM-ShuffleNetV2 model proposed in this study can achieve accurate identification of crop leaf disease in complex field backgrounds, and the model is small, which is convenient to deploy to the mobile end, and provides a reference for intelligent diagnosis of crop leaf disease.

To address the challenge of high wind speed variability in wind farm planning, a small-sample-based spatio-temporal fusion and compression deep residual point prediction model, STiCDRS (Spatio-Temporal integration and Compression Deep Residual), is proposed. This model is designed to deeply explore the spatial and temporal characteristics within wind speed sequences to enhance the accuracy of point predictions. Initially, the spatio-temporal integration and compression deep residual network is employed to obtain point prediction results. Subsequently, an innovative hybrid model, STiCDRS-NKDE (STiCDRS-Nonparametric Kernel Density Estimation), is introduced to achieve interval predictions, thereby providing more reliable probabilistic forecasts of wind speed. The hyper-parameters of the model are optimized using Bayesian optimization, ensuring efficient and automated tuning. Finally, a case study involving wind speed forecasting at a wind farm in Inner Mongolia, China, is conducted, comparing the performance of the STiCDRS model with traditional models. Experimental results demonstrate that in comparison to other models, the proposed STiCDRS-NKDE model delivers superior point prediction accuracy, appropriate interval predictions, and reliable probabilistic forecasting outcomes, fully showcasing its significant potential in the domain of wind speed forecasting.

Facial expressions involve dynamic changes, and facial expression recognition based on static images struggles to capture the temporal information inherent in these dynamic changes. The resultant degradation in real-world performance critically impedes the integration of facial expression recognition systems into intelligent sensing applications. Therefore, this paper proposes a facial expression recognition method for image sequences based on the fusion of dual neural networks (ResNet and residual bidirectional GRU—Res-RBG). The model proposed in this paper achieves recognition accuracies of 98.10% and 88.64% on the CK+ and Oulu-CASIA datasets, respectively. Moreover, the model has a parameter size of only 64.20 M. Compared to existing methods for image sequence-based facial expression recognition, the approach presented in this paper demonstrates certain advantages, indicating strong potential for future edge sensor deployment.

Gait recognition is a biometric recognition technology, where the goal is to identify the subject by the subject’s walking posture at a distance. However, a lot of redundant information in gait sequence will affect the performance of gait recognition, and the most existing gait recognition models are overly complicated and parameterized, which leads to the low efficiency in model training. Consequently, how to reduce the complexity of the model and eliminate redundant information effectively in gait have become a challenging problem in the field of gait recognition. In this paper, we present a residual structure based gait recognition model, short for ResGait, to learn the most discriminative changes of gait patterns. To eliminate redundant information in gait, the soft thresholding is inserted into the deep architectures as a nonlinear transformation layer to improve gait feature learning capability from the noised gait feature map. Moreover, each sample owns unique set of thresholds, making the proposed model suitable for different gait sequences with different redundant information. Furthermore, residual link is introduced to reduce the learning difficulties and alleviate computational costs in model training. Here, we train the network in terms of various scenarios and walking conditions, and the effectiveness of the method is validated through abundant experiments with various types of redundant information in gait. In comparison to the previous state-of-the-art works, experimental results on the common datasets, CASIA-B and OUMVLP-Pose, show that ResGait has higher recognition accuracy under various walking conditions and scenarios.