This article introduces a novel micro-optical electromechanical system safety and arming (S&A) device that utilizes both electrothermal and centrifugal actuators to ensure the reliability and ...efficiency of the device. The S&A device comprises a pair of V-shaped latching actuators, a pair of U-shaped latching actuators, a reverse blocking actuator, a centrifugal alignment actuator, and two sets of status monitoring units. The V- and U-shaped latching actuators serve as safety features to prevent accidental triggering, while the centrifugal alignment actuator aligns the optical fibers. The mechanical responses of the device under dual-environment loads are analyzed using a finite element model, while a theoretical model is introduced to predict the centrifugal acceleration required for alignment. The device is fabricated using deep reactive ion etching on silicon-on-insulator wafers. Experimental tests confirm the effectiveness of the safety features and the device's capability to transmit high-power optical energy. The optical efficiency ranges from 71.8% to 76.4% (1.17-1.44 dB insertion loss), and the maximum power transfer is 902 mW from an 1180 mW input.
•Proposing a backbone network based on improved Swin Transformer.•Applying the backbone to the data augmentation and recognition of leaf diseases.•Developing leaf extraction module to extract leaf ...region in an unsupervised way.•Constructing a novel GAN to generate diseased images from healthy ones.•Enhancing recognition performance of practical cucumber leaf diseases.
The deep learning methods based on convolutional neural network (CNN) have been widely explored in dataset augmentation and recognition of plant leaf diseases. The recently developed transformer-based models such as Swin Transformer (SwinT) show competitive and even better performance on various visual benchmarks compared with CNN due to their inherent attention mechanism and ability to learn long-range dependency among pixels. In this paper, a backbone network based on improved SwinT was proposed and applied to the data augmentation and recognition of practical cucumber leaf diseases. Firstly, the patch partition of SwinT was improved by step-wise small patch embeddings for enhancing the ability of feature extraction without increasing the number of parameters. Secondly, the leaf extraction module composed of the proposed backbone network and Grad-CAM was integrated into the Generation Adversarial Network (GAN) to construct STA-GAN (SwinT-based and Attention-guided GAN), which generated diseased spots only in the leaf region of healthy images with complex background for augmenting the disease dataset. Finally, by means of transfer learning, the augmented datasets were used to train the recognition model of cucumber leaf diseases with the proposed backbone network. From the experimental results, it has been demonstrated that STA-GAN exhibited stronger ability to generate high-quality images than LeafGAN, even only approximated when LeafGAN consumed much more training images. Additionally, with STA-GAN, the disease recognition accuracies reached 98.97%, 96.81%, 94.85% and 90.01% when improved SwinT, original SwinT, EfficientNet-B5 and ResNet-101 were employed as the backbone of recognition model respectively, increasing by 2.17%, 3.62%, 2.13% and 11.23% compared with LeafGAN, revealing that the approaches based on improved SwinT could indeed help in boosting the performance of both data augmentation and recognition of practical cucumber leaf diseases. The proposed approach has the potential of dealing with the common challenge of insufficient data size and complex background in other similar plant science tasks.
Precise pear detection and recognition is an essential step toward modernizing orchard management. However, due to the ubiquitous occlusion in orchards and various locations of image acquisition, the ...pears in the acquired images may be quite small and occluded, causing high false detection and object loss rate. In this paper, a multi-scale collaborative perception network YOLOv5s-FP (Fusion and Perception) was proposed for pear detection, which coupled local and global features. Specifically, a pear dataset with a high proportion of small and occluded pears was proposed, comprising 3680 images acquired with cameras mounted on a ground tripod and a UAV platform. The cross-stage partial (CSP) module was optimized to extract global features through a transformer encoder, which was then fused with local features by an attentional feature fusion mechanism. Subsequently, a modified path aggregation network oriented to collaboration perception of multi-scale features was proposed by incorporating a transformer encoder, the optimized CSP, and new skip connections. The quantitative results of utilizing the YOLOv5s-FP for pear detection were compared with other typical object detection networks of the YOLO series, recording the highest average precision of 96.12% with less detection time and computational cost. In qualitative experiments, the proposed network achieved superior visual performance with stronger robustness to the changes in occlusion and illumination conditions, particularly providing the ability to detect pears with different sizes in highly dense, overlapping environments and non-normal illumination areas. Therefore, the proposed YOLOv5s-FP network was practicable for detecting in-field pears in a real-time and accurate way, which could be an advantageous component of the technology for monitoring pear growth status and implementing automated harvesting in unmanned orchards.
Precise recognition of maize growth stages in the field is one of the critical steps in conducting precision irrigation and crop growth evaluation. However, due to the ever-changing environmental ...factors and maize growth characteristics, traditional recognition methods usually suffer from limitations in recognizing different growth stages. For the purpose of tackling these issues, this study proposed an improved U-net by first using a cascade convolution-based network as the encoder with a strategy for backbone network replacement to optimize feature extraction and reuse. Secondly, three attention mechanism modules have been introduced to upgrade the decoder part of the original U-net, which highlighted critical regions and extracted more discriminative features of maize. Subsequently, a dilation path of the improved U-net was constructed by integrating dilated convolution layers using a multi-scale feature fusion approach to preserve the detailed spatial information of in-field maize. Finally, the improved U-net has been applied to recognize different growth stages of maize in the field. The results clearly demonstrated the superior ability of the improved U-net to precisely segment and recognize maize growth stage from in-field images. Specifically, the semantic segmentation network achieved a mean intersection over union (mIoU) of 94.51% and a mean pixel accuracy (mPA) of 96.93% in recognizing the maize growth stage with only 39.08 MB of parameters. In conclusion, the good trade-offs made in terms of accuracy and parameter number demonstrated that this study could lay a good foundation for implementing accurate maize growth stage recognition and long-term automatic growth monitoring.
•Proposed a multimodal fusion encoder utilizing two-stage RGB-D-NIR fusion.•Analyzed the contributions of MLP, ViT, and CNN-based architectures to the detection performance.•Developed ...deployment-suitable YOLO-DNA with better robustness and performance.•Achieved significant increase in mAP0.5 and mAP0.5:0.95 over mainstream lightweight models.•Constructed a multimodal dataset of tomatoes including RGB, depth, and near-infrared modalities.
Accurate and efficient tomato detection is essential for the practical deployment of robotic picking in practical agricultural applications, but it still remains significantly challenging to detect tomatoes in complex scenarios with fluctuating light, overlapping fruits, and occlusion from branches and leaves when solely using RGB images. The recent development of RGB-D sensors has brought one promising opportunity to adopt multimodal fusion for implementing high-quality fruit detection. However, the feasibility of the existing multimodal fusion and feature extraction architectures for lightweight tomato detection tasks, especially in complex agricultural scenarios, raises questions that need to be explored. As a remedy, we proposed a multimodal fusion encoder that leveraged depth and near-infrared modalities to assist RGB images in making full use of multimodal data. Moreover, the encoder contained a plug-and-play structure capable of being implemented as MLP-based (Multi-Layer Perceptron), ViT-based (Vision Transformer), or CNN-based (Convolutional Neural Networks) architectures. Furthermore, we developed a lightweight experimental detection framework based on YOLOv7-tiny by means of integrating the multimodal fusion encoder, and YOLO-DNA (Depth and Near-infrared Assisted) was put forward based on the MLP-based architecture after conducting comprehensive analysis of the aforementioned three architectures. In addition, a tomato multimodal dataset containing visible, depth, and near-infrared images was established. Experimental results demonstrated that YOLO-DNA achieved mAP0.5 of 98.13% and mAP0.5:0.95 of 74.0%, an average increase of 5.01% in mAP0.5 and 14.55% in mAP0.5:0.95 over mainstream lightweight detection models, with a detection speed of 37.12 FPS, meeting the demand of real-time tomato detection. This finding has the potential to advance research on fruit detection in the field of intelligent agricultural harvesting.
Mesenchymal transition (MES transition) is a hallmark of glioblastoma multiforme (GBM), however, the mechanism regulating the process remains to be elucidated. Here we report that FoxM1 drives ...ADAM17/EGFR activation loop to promote MES transition in GBM. Firstly, FoxM1 expression was positively associated with ADAM17 expression, and their expression was correlated with the mesenchymal features and overall patient survival of GBM. Overexpressing FoxM1 or ADAM17 increased the mesenchymal phenotype of glioma cells, which could be reversed by silencing FoxM1 or ADAM17. Importantly, FoxM1 bound to the ADAM17 promoter to transcriptionally upregulate its expression. Using gain- and loss-of-function studies, we showed that FoxM1/ADAM17 axis promoted the MES transition in glioma cells. Moreover, tissue microarray analysis and orthotopic xenograft model further confirmed that FoxM1/ADAM17 axis played key roles in malignancy of GBM. Mechanistically, FoxM1/ADAM17 axis activated the EGFR/AKT/GSK3β signaling pathway and ADAM17/EGFR/GSK3β axis could maintain FoxM1 stability in glioma cells. Taken together, our study demonstrated that FoxM1/ADAM17 feedback loop controlled the MES transition and regulated the progression of GBM, raising the possibility that deregulation of this loop might improve the durability of therapies in GBM.
This study proposes a novel multifunctional synergistic antibacterial phototherapy technique for the rapid healing of bacteria-infected wounds. By binding PEGylated phthalocyanines to the surface of ...graphene oxide via noncovalent functionalization, the photothermal conversion efficiency of the obtained nanocomposites can be significantly increased, which shows that the sample temperature can achieve nearly 100 °C after only 10 min of 450 nm light illumination at a concentration ≥25 μg/mL. Moreover, the nanocomposites can rapidly generate singlet oxygen under 680 nm light irradiation and physically cut bacterial cell membranes. The triple effects are expected to obtain a synergistic antibacterial efficiency and reduce the emergence of bacterial resistance. After dual-light irradiation for 10 min, the generation of hyperthermia and singlet oxygen can cause the death of Gram-positive and Gram-negative bacteria. The results of an in vivo experiment revealed that the as-prepared nanocomposites combined with dual-light-triggered antibacterial therapy can effectively restrain the inflammatory reaction and accelerate the healing of bacteria-infected wounds. These were confirmed by the examination of pathological tissue sections and inflammatory factors in rats with bacteria-infected wounds. This nanotherapeutic platform is a potential photoactivated antimicrobial strategy for the prevention and treatment of bacterial infection.