Accurate and rapid identification of bacterial species is essential for public health, clinical diagnostics, and environmental monitoring. Although Raman spectroscopy offers a powerful, non-invasive alternative, reliance solely on spectral data often fails to distinguish species with highly similar signatures, particularly when the discriminating features are subtle. This difficulty is frequently compounded by a lack of integrated biological prior knowledge, which can hinder model performance. To address these challenges, we introduce BactoRamanBioNet, a novel multimodal neural network architecture. Our model employs a synergistic approach that utilizes a ResNet-Transformer architecture to capture complex spectral patterns and a CLIP text encoder to incorporate descriptive biological information, thereby enabling highly accurate multimodal classification of bacterial species. Empirical results demonstrate that BactoRamanBioNet achieves a classification accuracy of 98.2% and an F1-score of 98.0%. This performance surpasses the current state-of-the-art deep learning model, ResNet-1D, by 2.4% in accuracy and 2.0% in F1-score. Moreover, our model outperforms traditional classifiers, such as Support Vector Machine (SVM) and Random Forest (RF), by 9.8% and 7.9% in accuracy, respectively, while also exhibiting significant improvements in precision and recall. By establishing a new benchmark in performance and robustness, BactoRamanBioNet offers a powerful and reliable framework for automated microbiological analysis, paving the way for next-generation diagnostic systems.

In agricultural production, plant diseases and pests are among the major threats to crop yield and quality. Existing agricultural pest and disease identification methods have problems such as small target scales, complex background environments, and unbalanced sample distributions. This paper proposes a lightweight improved target detection model, YOLOv5s-LiteAttn. Based on YOLOv5s, the model introduces GhostConv and Depthwise Conv to reduce the number of parameters and computational complexity, and it combines CBAM and Coordinate Attention mechanisms to enhance the network’s feature representation capability. Experimental results show that, compared with the basic YOLOv5s model, the number of parameters of the improved model is reduced by 22.75%, and the computational load is reduced by 16.77%. At the same time, mAP@0.5–0.95 is increased by 3.3 percentage points, and recall is improved by 1.1 percentage points. In addition, the inference speed increases from 121 FPS to 142 FPS at an input resolution of 640 × 640, further confirming that the proposed model achieves a favorable trade-off between accuracy and efficiency. The average precision of YOLOv5s-LiteAttn is 97.1%, which outperforms the existing mainstream lightweight detection models. Moreover, an independent test set containing 4328 newly collected field images was established to evaluate generalization and practical applicability. Despite a slight performance decrease compared with the validation results, the model maintained an mAP@0.5–0.95 of 95.8%, significantly outperforming the baseline model, thereby confirming its robustness and cross-domain adaptability. These results confirm that the model has high precision and is lightweight, making it effective for the detection of agricultural diseases and pests.

Strawberry harvesting perception in greenhouse environments requires visual models that remain reliable under occlusion while staying compact enough for edge-side inference. To address this requirement, this study develops StrawPose-Lite, a lightweight pose network for strawberry picking point prediction based on YOLOv11n-pose. The network combines ADown and C3Ghost to reduce redundant computation while preserving informative structure, and it adopts a six-keypoint pose definition derived from strawberry phenotypic characteristics. In this representation, the pedicel–fruit junction is used as the final visual picking point, whereas the remaining peak, curvature, and bottom keypoints provide geometric support when the visible contour is incomplete. The keypoint branch is further enhanced by P2-guided multi-scale fusion and SimAM-based refinement to improve sensitivity to fine pedicel-related cues under strict lightweight constraints. On the public validation split, StrawPose-Lite contains 0.73 M parameters and requires 3.0 GFLOPs while achieving a pose mAP@0.5:0.95 of 79.2%. In the independent field deployment set, the TensorRT INT8 version achieved a pure network inference throughput of 277 FPS on a Jetson Orin NX 16G Super platform, with a measured total software latency of 5.01 ms under the embedded pipeline. These results indicate that StrawPose-Lite provides an effective balance between pose accuracy, model compactness, and edge-side inference speed for strawberry picking point perception on edge devices.

Background: Low‐dose computed tomography (LDCT) is widely used to reduce radiation exposure, but the reduced photon budget amplifies quantum noise and can introduce structured artifacts that obscure subtle boundaries and textures. Many deep learning denoisers process features in a single stream, which may encourage either over‐smoothing of weak anatomical edges or unstable texture synthesis. Purpose: To develop an LDCT denoising network that explicitly routes coarse structural content and fine details through dedicated pathways, aiming to suppress noise while preserving anatomically meaningful high‐frequency information. Methods: We propose FMDNet, a frequency‐aware encoder‐decoder equipped with an explicit coarse/detail routing block. A fixed low‐pass operator produces a coarse component, while the corresponding detail component is formed as an explicit residual (high = x—low). Each component is refined with depthwise operators and fused by a learned channel gate with channel attention. We evaluate FMDNet on the AAPM Mayo Clinic LDCT dataset and the LoDoPaB‐CT benchmark under a reproducible HU‐windowed protocol and supplement PSNR, SSIM, and RMSE with texture‐ and structure‐oriented analyses including HU line profiles and noise power spectrum (NPS), together with volume‐level paired tests and bootstrap confidence intervals on LoDoPaB‐CT. Results: Across both benchmarks, FMDNet achieves competitive quantitative fidelity and shows favorable results on complementary structure‐/texture‐oriented analyses. On Mayo, it improves mean PSNR, SSIM, and RMSE relative to strong learned baselines. On LoDoPaB‐CT, volume‐level analysis across 28 validation volumes confirms consistent improvements over Uformer with paired tests and bootstrap confidence intervals. Additional HU‐profile and NPS analyses provide complementary evidence of improved texture preservation and local structural fidelity relative to comparative methods. Conclusions: Explicitly separating coarse and detail residual components in feature space provides a practical inductive bias for LDCT denoising. When combined with gated fusion and multi‐scale supervision, this strategy improves quantitative fidelity and preserves fine structures without relying on adversarial texture synthesis; clinical diagnostic impact should be validated by reader studies.

Accurate high-throughput fruit detection is the core prerequisite for precision citrus management. Existing models face a critical trade-off between accuracy for small fruits and computational efficiency, restricting large-scale industry transformation. To resolve this, we propose Citrus-SGYOLOv2, an optimized deep learning architecture specifically engineered for high-throughput phenotypic monitoring. The primary contribution of this work lies in three synergistic innovations: a novel Symmetric Ghost Backbone that prunes architectural redundancy while maintaining hierarchical feature depth; a Citrus Color Prior Calibration Attention Mechanism (Citrus_SE) that embeds physiological chromaticity priors to suppress complex spectral noise from foliage; and a P2-layer-based full-scale fusion strategy designed to recover fine-grained spatial details lost during downsampling. Experiments on our self-built dataset show that Citrus-SGYOLOv2 achieves 95.54% mAP@50 and 77.13% mAP@50–95, outperforming YOLOv11s by 5.03 and 9.90 percentage points respectively. Notably, the model achieves a 48.8% reduction in parameters (4.84 M) while sustaining a high-throughput inference speed of 139.00 FPS. This research provides a robust and efficient foundational framework for intelligent yield estimation and precision orchard management.