Long non-coding RNAs (long ncRNAs, lncRNAs) of all kinds have been implicated in a range of cell developmental processes and diseases, while they are not translated into proteins. Inferring diseases associated lncRNAs by computational methods can be helpful to understand the pathogenesis of diseases, but those current computational methods still have not achieved remarkable predictive performance: such as the inaccurate construction of similarity networks and inadequate numbers of known lncRNA–disease associations. In this research, we proposed a lncRNA–disease associations inference based on integrated space projection scores (LDAI-ISPS) composed of the following key steps: changing the Boolean network of known lncRNA–disease associations into the weighted networks via combining all the global information (e.g., disease semantic similarities, lncRNA functional similarities, and known lncRNA–disease associations); obtaining the space projection scores via vector projections of the weighted networks to form the final prediction scores without biases. The leave-one-out cross validation (LOOCV) results showed that, compared with other methods, LDAI-ISPS had a higher accuracy with area-under-the-curve (AUC) value of 0.9154 for inferring diseases, with AUC value of 0.8865 for inferring new lncRNAs (whose associations related to diseases are unknown), with AUC value of 0.7518 for inferring isolated diseases (whose associations related to lncRNAs are unknown). A case study also confirmed the predictive performance of LDAI-ISPS as a helper for traditional biological experiments in inferring the potential LncRNA–disease associations and isolated diseases.

To address the issues of target feature blurring and increased false detections caused by high compression rates in deepfake videos, as well as the high computational resource requirements of existing face extractors, we propose a lightweight face extractor to assist deepfake detection, GCS-YOLOv8. Firstly, we employ the HGStem module for initial downsampling to address the issue of false detections of small non-face objects in deepfake videos, thereby improving detection accuracy. Secondly, we introduce the C2f-GDConv module to mitigate the low-FLOPs pitfall while reducing the model’s parameters, thereby lightening the network. Additionally, we add a new P6 large target detection layer to expand the receptive field and capture multi-scale features, solving the problem of detecting large-scale faces in low-compression deepfake videos. We also design a cross-scale feature fusion module called CCFG (CNN-based Cross-Scale Feature Fusion with GDConv), which integrates features from different scales to enhance the model’s adaptability to scale variations while reducing network parameters, addressing the high computational resource requirements of traditional face extractors. Furthermore, we improve the detection head by utilizing group normalization and shared convolution, simplifying the process of face detection while maintaining detection performance. The training dataset was also refined by removing low-accuracy and low-resolution labels, which reduced the false detection rate. Experimental results demonstrate that, compared to YOLOv8, this face extractor achieves the AP of 0.942, 0.927, and 0.812 on the WiderFace dataset’s Easy, Medium, and Hard subsets, representing improvements of 1.1%, 1.3%, and 3.7% respectively. The model’s parameters and FLOPs are only 1.68 MB and 3.5 G, reflecting reductions of 44.2% and 56.8%, making it more effective and lightweight in extracting faces from deepfake videos.

Pest control in economic forests is a crucial aspect of sustainable forest resource management, yet it faces bottlenecks such as low efficiency and high miss rates for small objects. Based on the RT-DETR model, this paper proposes LightFAD-DETR, a lightweight architecture integrated with feature aggregation diffusion, designed for complex economic forest scenarios. Firstly, by employing the YOLOv9 lightweight backbone network to compress the computational base load, we introduce the RepNCSPELAN4-CAA module, which integrates re-parameterization techniques and one-dimensional strip convolution. This enhances the model’s ability for cross-regional modeling of slender insect morphologies. Secondly, a feature aggregation diffusion network is designed, incorporating a dimension-aware selective integration mechanism. This dynamically fuses shallow detail features with deep semantic features, effectively mitigating information loss for small objects occluded by foliage. Finally, a re-parameterized batch normalization technique is introduced to reconstruct the AIFI module. Combined with a progressive training strategy, this eliminates redundant parameters, thereby enhancing inference efficiency on edge devices. Experimental validation demonstrates that compared to the baseline RT-DETR model, LightFAD-DETR achieves a 1.4% improvement in ${mAP}_{0.5:0.95}$, while reducing parameters by 41.7% and computational load by 35.0%. With an inference speed reaching 106.3 FPS, the method achieves balanced improvements in both accuracy and lightweight design.

High-resolution remote sensing imagery comprises spatial structure features of multispectral bands varying in scale, color, and shape. These heterogeneous geographical features introduce grave challenges to the fine segmentation required for classification applications in remote sensing imagery, where direct application of traditional image classification models fails to deliver optimal results. To overcome these challenges, a multispectral, multi-label model, MMDL-Net, has been developed. This model is integrated with the multi-label BigEarthNet dataset, primarily employed for land cover classification research in remote sensing imagery, with each image composed of 13 spectral bands and spatial resolutions of 10 m, 20 m, and 60 m. To effectively utilize the information across these bands, a multispectral stacking module has been introduced to concatenate this spectral information. To proficiently process three distinct large-scale remote sensing image datasets, a multi-label classification module has been incorporated for training and inference. To better learn and represent the intricate features within the images, a twin-number residual structure has been proposed. The results demonstrate that the MMDL-Net model achieves a top accuracy of 83.52% and an F1 score of 77.97%, surpassing other deep learning models and conventional methods, thereby exhibiting exceptional performance in the task of multispectral multi-label classification of remote sensing imagery.

Visible and near-infrared (Vis–NIR) spectroscopy enables the rapid prediction of soil properties but faces three limitations with conventional machine learning: information loss and overfitting from high-dimensional spectral features; inadequate modeling of nonlinear soil–spectra relationships; and failure to integrate multi-scale spatial features. To address these challenges, we propose ReSE-AP Net, a multi-scale attention residual network with spatial pyramid pooling. Built on convolutional residual blocks, the model incorporates a squeeze-and-excitation channel attention mechanism to recalibrate feature weights and an atrous spatial pyramid pooling (ASPP) module to extract multi-resolution spectral features. This architecture synergistically represents weak absorption peaks (400–1000 nm) and broad spectral bands (1000–2500 nm), overcoming single-scale modeling limitations. Validation on the LUCAS2009 dataset demonstrated that ReSE-AP Net outperformed conventional machine learning by improving the R² by 2.8–36.5% and reducing the RMSE by 14.2–69.2%. Compared with existing deep learning methods, it increased the R² by 0.4–25.5% for clay, silt, sand, organic carbon, calcium carbonate, and phosphorus predictions, and decreased the RMSE by 0.7–39.0%. Our contributions include statistical analysis of LUCAS2009 spectra, identification of conventional method limitations, development of the ReSE-AP Net model, ablation studies, and comprehensive comparisons with alternative approaches.