With the development of unmanned aerial vehicle (UAV) technology, deep learning is becoming more and more widely used in object detection in UAV aerial images; however, detecting and identifying small objects in low-illumination scenes is still a major challenge. Aiming at the problem of low brightness, high noise, and obscure details of low-illumination images, an object detection algorithm, LI-YOLO (Low-Illumination You Only Look Once), for UAV aerial images in low-illumination scenes is proposed. Specifically, in the feature extraction section, this paper proposes a feature enhancement block (FEB) to realize global receptive field and context information learning through lightweight operations and embeds it into the C2f module at the end of the backbone network to alleviate the problems of high noise and detail blur caused by low illumination with very few parameter costs. In the feature fusion part, aiming to improve the detection performance for small objects in UAV aerial images, a shallow feature fusion network and a small object detection head are added. In addition, the adaptive spatial feature fusion structure (ASFF) is also introduced, which adaptively fuses information from different levels of feature maps by optimizing the feature fusion strategy so that the network can more accurately identify and locate objects of various scales. The experimental results show that the mAP50 of LI-YOLO reaches 76.6% on the DroneVehicle dataset and 90.8% on the LLVIP dataset. Compared with other current algorithms, LI-YOLO improves the mAP 50 by 3.1% on the DroneVehicle dataset and 6.9% on the LLVIP dataset. Experimental results show that the proposed algorithm can effectively improve object detection performance in low-illumination scenes.
Background: Intrinsically disordered proteins possess flexible 3-D structures, which makes them play an important role in a variety of biological functions. Molecular recognition features (MoRFs) act as an important type of functional regions, which are located within longer intrinsically disordered regions and undergo disorder-to-order transitions upon binding their interaction partners. Results: We develop a method, MoRFCNN, to predict MoRFs based on sequence properties and convolutional neural networks (CNNs). The sequence properties contain structural and physicochemical properties which are used to describe the differences between MoRFs and non-MoRFs. Especially, to highlight the correlation between the target residue and adjacent residues, three windows are selected to preprocess the selected properties. After that, these calculated properties are combined into the feature matrix to predict MoRFs through the constructed CNN. Comparing with other existing methods, MoRFCNN obtains better performance. Conclusions: MoRFCNN is a new individual MoRFs prediction method which just uses protein sequence properties without evolutionary information. The simulation results show that MoRFCNN is effective and competitive.
To facilitate the sensor fabrication and sensing operation in microstructured optical fiber-based surface plasmon resonance (SPR) sensors for high refractive index (RI) detection, we propose a special hollow fiber-based SPR sensor that comprises an opening on its body side and a thin gold layer coated on its outer surface. The analyte is able to flow into the hollow core through the side-opening to form new fiber core, with the Gaussian-like mode propagating in it. We investigate the sensing performance of the proposed sensor in a higher RI range of 1.48 to 1.54 at two feasible schemes: one is to only fill the fiber core with analyte (Scheme A), and the other is to directly immerse the sensor in the analyte (Scheme B). The results demonstrate that our sensor exhibits higher wavelength sensitivity at Scheme A with a maximum wavelength sensitivity of 12,320 nm/RIU, while a greater amplitude sensitivity was found at Scheme B with a maximum amplitude sensitivity of 1146 RIU−1. Our proposed sensor features the advantages of simple fabrication, flexible operation, easy analyte filling and replacing, enhanced real-time detection capabilities, high RI detection, and very high wavelength sensitivity and amplitude sensitivity, which makes it more competitive in SPR sensing applications.
With the rapid advancement of UAV, image matching algorithms for visual navigation have been increasingly widely used. However, extensive research demonstrate that existing algorithms exhibit insufficient matching accuracy and long response time in challenging aerial scenes, which cannot meet the accuracy requirements of UAV visual navigation. In this paper, we propose an efficient image matching method for UAV visual navigation, named as DALGlue, based on convolutional neural network feature extraction algorithm and feature matching network with linear attention mechanism. DALGlue uses dual-tree complex wavelet transform to preprocess the collected aerial images, which enhances structural information and fine details. Compared with directly processing raw images, dual-tree complex wavelet transform module solves the problem of edge blurring in UAV dynamic flight. Then, an adaptive spatial feature fusion module is developed to extract features from images and calculate feature points and descriptors. In addition, we employ linear attention mechanism to aggregate image features, which can effectively reduce computational costs while improving network characteristics. Finally, the Sinkhorn algorithm is used to calculate the allocation matrix and output optimal assignment. DALGlue demonstrates a unique balance between accuracy and real-time performance, which can be operate under strict computational and memory constraints. In comparison to the state-of-the-art method LightGlue, the experimental results show that DALGlue obtains 11.8% points improvement in MMA. On the MegaDepth-1500 benchmark, DALGlue achieves the AUC@5 °/10 °/20 ° values of 57.01, 73.00, and 84.11 respectively, which effectively improved match precision.
1 January 2021 in Computational Intelligence and Neuroscience
Intrinsically disordered proteins (IDPs) possess at least one region that lacks a single stable structure in vivo, which makes them play an important role in a variety of biological functions. We propose a prediction method for IDPs based on convolutional neural networks (CNNs) and feature selection. The combination of sequence and evolutionary properties is used to describe the differences between disordered and ordered regions. Especially, to highlight the correlation between the target residue and adjacent residues, multiple windows are selected to preprocess the protein sequence through the selected properties. The shorter windows reflect the characteristics of the central residue, and the longer windows reflect the characteristics of the surroundings around the central residue. Moreover, to highlight the specificity of sequence and evolutionary properties, they are preprocessed, respectively. After that, the preprocessed properties are combined into feature matrices as the input of the constructed CNN. Our method is training as well as testing based on the DisProt database. The simulation results show that the proposed method can predict IDPs effectively, and the performance is competitive in comparison with IsUnstruct and ESpritz.
Molecular recognition features (MoRFs) can facilitate specific protein-protein interactions by undergoing disorder-to-order transitions when binding to their protein partners. Thus, it is essential to accurately predict MoRFs. In this paper, we propose an innovative MoRFs prediction method, named MoRFs_TransFuse, based on multimodal feature fusion and a lightweight Transformer network. To construct high-quality biological features, MoRFs_TransFuse innovatively integrates physicochemical properties, evolutionary features, and pre-trained model embeddings, while retaining optimal feature combinations through multi-window extraction and Random Forest secondary screening. In terms of architecture, MoRFs_TransFuse overcomes the limitations of modeling long-range dependencies by using a self-attention mechanism to accurately capture long-range residue associations in protein sequences. Comparative experiments on benchmark datasets show that MoRFs_TransFuse significantly outperforms existing single component and combined component predictors. Additionally, the lightweight design greatly improves computational efficiency while ensuring prediction accuracy.