In the contemporary context, pest detection is progressively moving toward automation and intelligence. However, current pest detection algorithms still face challenges, such as lower accuracy and slower operation speed in detecting small objects. To address this issue, this study presents a crop pest target detection algorithm, GLU-YOLOv8, designed for complex scenes based on an enhanced version of You Only Look Once version 8 (YOLOv8). The algorithm introduces the SCYLLA-IOU (SIOU) loss function, which enhances the model generalization to various pest sizes and shapes by ensuring smoothness and reducing oscillations during training. Additionally, the algorithm incorporates the Convolutional Block Attention Module (CBAM) and Locality Sensitive Kernel (LSK) attention mechanisms to boost the pest target features. A novel Gated Linear Unit CONV (GLU-CONV) is also introduced to enhance the model’s perceptual and generalization capabilities while maintaining performance. Furthermore, GLU-YOLOv8 includes a small-object detection layer with a feature map size of 160 × 160 to extract more features of small-target pests, thereby improving detection accuracy and enabling more precise localization and identification of small-target pests. The study conducted a comparative analysis between the GLU-YOLOv8 model and other models, such as YOLOv8, Faster RCNN, and RetinaNet, to evaluate detection accuracy and precision. In the Scolytidae forestry pest dataset, GLU-YOLOv8 demonstrated an improvement of 8.2% in mAP@0.50 for small-target detection compared to the YOLOv8 model, with a resulting mAP@0.50 score of 97.4%. Specifically, on the IP102 dataset, GLU-YOLOv8 outperforms the YOLOv8 model with a 7.1% increase in mAP@0.50 and a 5% increase in mAP@0.50:0.95, reaching 58.7% for mAP@0.50. These findings highlight the significant enhancement in the accuracy and recognition rate of small-target detection achieved by GLU-YOLOv8, along with its efficient operational performance. This research provides valuable insights for optimizing small-target detection models for various pests and diseases.

In this paper, a fuzzy failure mode and effects analysis (FMEA) method is proposed by combining fault theory and a failure analysis method. The method addresses the problem of board thickness control failure and the problem of thickness deviation defect blanking, which can occur during continuous hot pressing (CHP) process, which is one of the most important processes in the production of medium-density fiberboard (MDF). The method combines the fault analysis with the Hamming code method and using the Hamming code to calculate and represent the cylinder array of the continuous hot-pressed thickness control execution unit to analyze and process the potential fixed thickness failure modes in MDF hot press production, and then summarizes the decision rules for controlling the board thickness and the level of sheet deviation. By combining the fuzzy FMEA method of the Hamming code and the logical OR operation of the experimental analysis, the method of thickness deviation and recognition control fault information for the CHP of MDF, which is proposed in this paper, permits the increase of the number of error levels, which makes optimization for controller more convenient and improves the efficiency to recognize errors.

With the continuous development of robotic technology, there is an increasing demand for efficient, smooth, and precise trajectory planning and interpolation. For the robot manipulators with 6 rotational (6R) joints, smooth task paths are crucial for high-quality task and precise dynamic trajectory tracking. However, nonlinear mapping between joint and cartesian space complicates feedrate scheduling under joint constraints. Existing methods, like S-shape feedrate profiles or time-optimal approaches, are inefficient or compromise trajectory stability. This paper proposes a segment-based dynamically adaptive smooth look-ahead feedrate scheduling method based on local dynamic window and a Maximum Velocity Curve (MVC) for 6R robot manipulators. It balances the efficiency and stability of motion execution while considering spline trajectory and joint constraints. Five types of segmented velocities under the local dynamic window are identified, with adaptive smoothing strategies developed. Feedrate remains constant within segments and transitions smoothly between them, enhancing trajectory quality. The results of the smoothing preprocessing can be directly used for feedrate profile generation, ensuring smooth, non-oscillating motion while meeting performance and constraint requirements, which is better suited for real-time interpolation. Simulation and experimentation confirm the proposed method’s effectiveness. Note to Practitioners —The motivation of this article stems from the need to develop a feedrate scheduling method with joint jerk constraints of 6R robot manipulators for practical tasks like polishing, engraving, welding, and spraying. 6R robots, due to their nonlinear coupling kinematics, often fail to meet joint constraints. Existing methods, inefficient or requiring frequent changes in joint acceleration/jerk for time optimality, adversely affect task quality. To balance smoothness and operational efficiency for 6R robot tasks, we propose the segmented dynamic adaptive look-ahead smoothing feedrate scheduling with joint jerk constraints of 6R robot manipulators, ensuring trajectory execution within joint limits and balancing smoothness and operational efficiency, which is better suited for real-time interpolation. This method can be of great interest to readers working on precision manufacturing and robotics feedrate profile generation method.

The bZIP (basic leucine zipper) transcription factors have been identified as key regulators of plant responses to drought stress, which limits plant growth and yield. Overexpression of bZIP genes has shown potential in enhancing drought tolerance in various plant species. However, the constrained types of individual studies and inconsistencies among experimental approaches has resulted in a lack of statistical significance and limited the extrapolation of bZIP transcription factor overexpression for plant improvement. We conducted a meta-analysis to evaluate ten measured parameters of drought tolerance in bZIP transcription factor-expressing plants as well as moderators affecting the performance of transgenic plants. The results showed that seven parameters, including survival rate as well as the content of regulatory substances (proline accumulation, H₂O₂ concentration, CAT activity, POD activity, SOD activity and MDA accumulation), were most affected while the impact on physiological status indicators is not significant. In addition, donor/recipient species, treatment medium, duration and methods of simulating drought stress all significantly impacted the degree of drought stress tolerance in plants to some extent among the considered moderators. The findings underscore the potential of bZIP transcription factors as key targets for genetic engineering approaches aimed at improving plant resilience to water scarcity.

The 3D reconstruction of forests provides a strong basis for scientific regulation of tree growth and fine survey of forest resources. Depth estimation is the key to the 3D reconstruction of inter-forest scene, which directly determines the effect of digital stereo reproduction. In order to solve the problem that the existing stereo matching methods lack the ability to use environmental information to find the consistency of ill-posed regions, resulting in poor matching effect in regions with weak texture, occlusion and other inconspicuous features, LANet, a stereo matching network based on Linear-Attention mechanism is proposed, which improves the stereo matching accuracy by effectively utilizing the global and local information of the environment, thereby optimizing the depth estimation effect. An AM attention module including a spatial attention module (SAM) and a channel attention module (CAM) is designed to model the semantic relevance of inter-forest scenes from the spatial and channel dimensions. The linear-attention mechanism proposed in SAM reduces the overall complexity of Self-Attention from O(n²) to O(n), and selectively aggregates the features of each position by weighted summation of all positions, so as to learn rich contextual relations to capture long-range dependencies. The Self-Attention mechanism used in CAM selectively emphasizes interdependent channel maps by learning the associated features between different channels. A 3D CNN module is optimized to adjust the matching cost volume by combining multiple stacked hourglass networks with intermediate supervision, which further improves the speed of the model while reducing the cost of inferential calculation. The proposed LANet is tested on the SceneFlow dataset with EPE of 0.82 and three-pixel-error of 2.31%, and tested on the Forest dataset with EPE of 0.68 and D1-all of 2.15% both of which outperform some state-of-the-art methods, and the comprehensive performance is very competitive. LANet can obtain high-precision disparity values of the inter-forest scene, which can be converted to obtain depth information, thus providing key data for high-quality 3D reconstruction of the forest.

The three-dimensional reconstruction of forest ecological environment by low-altitude remote sensing photography from Unmanned Aerial Vehicles (UAVs) provides a powerful basis for the fine surveying of forest resources and forest management. A stereo vision system, D-SLAM, is proposed to realize simultaneous localization and dense mapping for UAVs in complex forest ecological environments. The system takes binocular images as input and 3D dense maps as target outputs, while the 3D sparse maps and the camera poses can be obtained. The tracking thread utilizes temporal clue to match sparse map points for zero-drift localization. The relative motion amount and data association between frames are used as constraints for new keyframes selection, and the binocular image spatial clue compensation strategy is proposed to increase the robustness of the algorithm tracking. The dense mapping thread uses Linear Attention Network (LANet) to predict reliable disparity maps in ill-posed regions, which are transformed to depth maps for constructing dense point cloud maps. Evaluations of three datasets, EuRoC, KITTI and Forest, show that the proposed system can run at 30 ordinary frames and 3 keyframes per second with Forest, with a high localization accuracy of several centimeters for Root Mean Squared Absolute Trajectory Error (RMS ATE) on EuRoC and a Relative Root Mean Squared Error (RMSE) with two average values of 0.64 and 0.2 for t_rel and R_rel with KITTI, outperforming most mainstream models in terms of tracking accuracy and robustness. Moreover, the advantage of dense mapping compensates for the shortcomings of sparse mapping in most Smultaneous Localization and Mapping (SLAM) systems and the proposed system meets the requirements of real-time localization and dense mapping in the complex ecological environment of forests.