Exosomes are considered as potential biomarkers that can reflect information from their parent cell-associated cancer microenvironment. Recently, aptasensors have been widely used for cancer and tumor exosome detection. Aptamers related to exosome surface proteins are usually used to introduce a sequence; the aptamer is used for exosome recognition, and the introduced sequence is used to form G-quadruplexes and for signal amplification. In this paper, we found that the EpCAM aptamer is rich in guanine and unimolecular G-quadruplex with a two-layer G-tetrad under acidic conditions, and we investigated its topology, thermal stability and dissociation constant with hemin. Based on this, our proposed colorimetric aptamer sensor combines the unmodified EpCAM aptamer with hemin to construct a hemin/G-quadruplex DNAzyme and catalyze the TMB–H₂O₂ system to generate a strong colorimetric signal. Therefore, colorimetric signal changes were negatively correlated with the exosome concentration. The linear range of the 1 h assay was 10⁶–10⁸ particles per mL, and the detection limit was 3.94 × 10⁵ particles per mL. In addition, this method can detect exosomes in complex fetal bovine serum samples with good specificity and high sensitivity toward exosomes from breast, liver, and lung cancers with abnormal EpCAM protein expression.

In order to solve the problems of slow detection speed, large number of parameters and large computational volume of deep learning based gangue target detection method, we propose an improved algorithm for gangue target detection based on Yolov5s. First, the lightweight network EfficientVIT is used as the backbone network to increase the target detection speed. Second, C3_Faster replaces the C3 part in the HEAD module, which reduces the model complexity. once again, the 20 × 20 feature map branch in the Neck region is deleted, which reduces the model complexity; thirdly, the CIOU loss function is replaced by the Mpdiou loss function. The introduction of the SE attention mechanism makes the model pay more attention to critical features to improve detection performance. Experimental results show that the improved model size of the coal gang detection algorithm reduces the compression by 77.8%, the number of parameters by 78.3% the computational cost is reduced by 77.8% and the number of frames is reduced by 30.6%, which can be used as a reference for intelligent coal gangue classification.

An improved algorithm based on Yolov8s is proposed to address the slower speed, higher number of parameters, and larger computational cost of deep learning in coal gangue target detection. A lightweight network, Fasternet, is used as the backbone to increase the speed of object detection and reduce the model complexity. By replacing Slimneck with the C2F part in the HEAD module, the aim is to reduce model complexity and improve detection accuracy. The detection accuracy is effectively improved by replacing the Detect layer with Detect-DyHead. The introduction of DIoU loss function instead of CIoU loss function and the combination of BAM block attention mechanism makes the model pay more attention to critical features, which further improves the detection performance. The results show that the improved model compresses the storage size of the model by 28%, reduces the number of parameters by 28.8%, reduces the computational effort by 34.8%, and improves the detection accuracy by 2.5% compared to the original model. The Yolov8s-change model provides a fast, real-time and efficient detection solution for gangue sorting. This provides a strong support for the intelligent sorting of coal gangue.

To address the problem of forest fire detection, especially in complex conditions such as low light, smoke dispersion, and changes in flame size, which are prone to be affected by the environment and may lead to the omission of flames or smoke, a method named HCANet is proposed. This method combines visible light (RGB) images and infrared (IR) images and uses hierarchical fusion to enhance the detection capability. A middle-level fusion strategy is adopted, and two dedicated components, cross-modal discrimination (CDM) and dual-Enhanced cross-modal attention (DEA), are designed. CDM is used to enhance the complementary information exchange between different types of images, and DEA is used to dynamically adjust to reduce interference. These designs can better utilize the detailed features of RGB images and the thermal sensing characteristics of IR images. Experimental results show that HCANet performs well on the data set in this paper and other public multimodal data sets, significantly outperforming single-modal methods. It can effectively identify weak fire sources and diffuse smoke, significantly improving the detection accuracy and stability, and demonstrating good generalization ability in related tasks such as vehicle detection and small target detection.

To address the limitations of unimodal forest fire detection algorithms, which suffer from high false positive rates and insufficient robustness under complex illumination variations, smoke occlusion, and non-fire heat source interference, this paper proposes MFPNet, a functionally decoupled mid-fusion framework for visible-infrared dual-modal UAV forest fire detection. Unlike existing mid-fusion methods that either focus solely on local cross-modal complementarity or global semantic modeling, we explicitly decouple these two functionalities and synergistically stitch them at the P4/P5 feature pyramid levels through a parallel mechanism. Specifically, the feature complementary mapping module is introduced to explicitly model cross-modal complementarity and suppress modality-specific noise via bidirectional channel-spatial interaction, while the Pyramid Sparse Transformer module—integrated into a dual-modal mid-fusion pipeline in this study—performs efficient multi-scale global context modeling through high-level semantics-guided sparse attention with parameter sharing. By combining these two modules via carefully designed parallel stitching at the same mid-fusion stage, MFPNet achieves complementary performance gains beyond simple addition that neither module can deliver independently. This design provides a valuable reference for leveraging bimodal complementary advantages in UAV-based forest fire detection tasks. Extensive experiments on our proprietary forest fire dataset demonstrate that MFPNet improves mAP@0.5 from 78.0% (Mid-Fusion baseline) to 82.4 ± 0.38% while maintaining real-time inference at 108 FPS. Further validation on three public multimodal benchmarks shows consistent performance of the proposed functionally decoupled stitching strategy under the evaluated settings.

In order to solve the problems of slow detection speed, large number of parameters and large computational volume of deep learning based gangue target detection method, we propose an improved algorithm for gangue target detection based on Yolov5s. First, the lightweight network EfficientVIT is used as the backbone network to increase the target detection speed. Second, C3_Faster replaces the C3 part in the HEAD module, which reduces the model complexity. once again, the 20×20 feature map branch in the Neck region is deleted, which reduces the model complexity; thirdly, the CIOU loss function is replaced by the Mpdiou loss function. The introduction of the SE attention mechanism makes the model pay more attention to critical features to improve detection performance. Experimental results show that the improved model size of the coal gang detection algorithm reduces the compression by 77.8 percent, the number of parameters by 78.3 percent, the computational cost is reduced by 77.8 percent and the number of frames is reduced by 30.6 percent, which can be used as a reference for intelligent coal gangue classification.