Feature Information Research Articles

An Ontology-Based Vehicle Behavior Prediction Method Incorporating Vehicle Light Signal Detection.

Although deep learning techniques have potential in vehicle behavior prediction, it is difficult to integrate traffic rules and environmental information. Moreover, its black-box nature leads to an opaque and difficult-to-interpret prediction process, limiting its acceptance in practical applications. In contrast, ontology reasoning, which can utilize human domain knowledge and mimic human reasoning, can provide reliable explanations for the speculative results. To address the limitations of the above deep learning methods in the field of vehicle behavior prediction, this paper proposes a front vehicle behavior prediction method that combines deep learning techniques with ontology reasoning. Specifically, YOLOv5s is first selected as the base model for recognizing the brake light status of vehicles. In order to further enhance the performance of the model in complex scenes and small target recognition, the Convolutional Block Attention Module (CBAM) is introduced. In addition, so as to balance the feature information of different scales more efficiently, a weighted bi-directional feature pyramid network (BIFPN) is introduced to replace the original PANet structure in YOLOv5s. Next, using a four-lane intersection as an application scenario, multiple factors affecting vehicle behavior are analyzed. Based on these factors, an ontology model for predicting front vehicle behavior is constructed. Finally, for the purpose of validating the effectiveness of the proposed method, we make our own brake light detection dataset. The accuracy and mAP@0.5 of the improved model on the self-made dataset are 3.9% and 2.5% higher than that of the original model, respectively. Afterwards, representative validation scenarios were selected for inference experiments. The ontology model created in this paper accurately reasoned out the behavior that the target vehicle would slow down until stopping and turning left. The reasonableness and practicality of the front vehicle behavior prediction method constructed in this paper are verified.

Multi-scale sensing and multi-dimensional feature enhancement for surface defect detection of hot-rolled steel strip

ABSTRACT Surface defect detection of hot-rolled steel strip is a crucial process in its production. Aiming at the problem of poor detection accuracy caused by complex shape of defect features and imbalance between object scale and feature scale, this paper proposes a multi-scale sensing and multi-dimensional feature enhancement algorithm. Firstly, a multi-branch residual aggregation module (MRAM) is proposed, which uses the interactive features of different receptive fields between layers to capture global and local texture features, improving the feature extraction capability for defects of different scales. Then, the multi-dimensional attention enhancement head (MAEH) is proposed, which integrates feature information from different prediction branches and realises feature information enhancement in scale, space and channel dimensions for the aggregated information to improve the accuracy and robustness of steel surface defect detection. The results show that the proposed algorithm achieves 82.7% mAP and 89 FPS on the NEU-DET dataset, and 73.3% mAP and 94 FPS on the GC10-DET dataset. Compared with state-of-the-art algorithms, the proposed algorithm has the highest mAP, strong generalisation ability, and good real-time performance, which proves its effectiveness in detecting hot-rolled steel strip surface defects.

MixUNETR: A U-shaped network based on W-MSA and depth-wise convolution with channel and spatial interactions for zonal prostate segmentation in MRI

Magnetic resonance imaging (MRI) plays a pivotal role in diagnosing and staging prostate cancer. Precise delineation of the peripheral zone (PZ) and transition zone (TZ) within prostate MRI is essential for accurate diagnosis and subsequent artificial intelligence-driven analysis. However, existing segmentation methods are limited by ambiguous boundaries, shape variations and texture complexities between PZ and TZ. Moreover, they suffer from inadequate modeling capabilities and limited receptive fields. To address these challenges, we propose a Enhanced MixFormer, which integrates window-based multi-head self-attention (W-MSA) and depth-wise convolution with parallel design and cross-branch bidirectional interaction. We further introduce MixUNETR, which use multiple Enhanced MixFormers as encoder to extract features from both PZ and TZ in prostate MRI. This augmentation effectively enlarges the receptive field and enhances the modeling capability of W-MSA, ultimately improving the extraction of both global and local feature information from PZ and TZ, thereby addressing mis-segmentation and challenges in delineating boundaries between them. Extensive experiments were conducted, comparing MixUNETR with several state-of-the-art methods on the Prostate158, ProstateX public datasets and private dataset. The results consistently demonstrate the accuracy and robustness of MixUNETR in MRI prostate segmentation. Our code of methods is available at https://github.com/skyous779/MixUNETR.git.

Cross-domain transfer fault diagnosis by class-imbalanced deep subdomain adaptive network

In variable working conditions and class imbalances, fault diagnosis in gearbox systems becomes difficult due to the difficulty in learning the classification boundaries of the minority class. Moreover, the diversity in fault mode distributions under various working conditions poses significant challenges for domain adaptation. To this end, this work proposed a Class-imbalanced Deep Subdomain Adaptive Network (CIDSAN) for complex cross-domain fault diagnosis scenarios involving feature and label shifts. We design a convolutional neural network embedded with SimAM (SimAM-CNN) to extract global feature information from time-domain vibration signals. Subsequently, a novel cost-sensitive classifier is presented for class re-weighting, along with a Joint Supervised Classifier that refines intra-class and inter-class distances by re-weighting class weights in the latent space using cost-sensitive classifiers while leveraging LDAM regularization to adjust classification boundaries. Diagnostic case studies on two datasets under various working conditions validate the effectiveness and superiority of the proposed approach. The code https://github.com/Zjy0121/CIDSAN.

AFGN: Adaptive Filtering Graph Neural Network for Few-Shot Learning

The combination of few-shot learning and graph neural networks can effectively solve the issue of extracting more useful information from limited data. However, most graph-based few-shot models only consider the global feature information extracted by the backbone during the construction process, while ignoring the dependency information hidden within the features. Additionally, the essence of graph convolution is the filtering of graph signals, and the majority of graph-based few-shot models construct fixed, single-property filters to process these graph signals. Therefore, in this paper, we propose an Adaptive Filtering Graph Convolutional Neural Network (AFGN) for few-shot classification. AFGN explores the hidden dependency information within the features, providing a new approach for constructing graph tasks in few-shot scenarios. Furthermore, we design an adaptive filter for the graph convolution of AFGN, which can adaptively adjust its strategy for acquiring high and low-frequency information from graph signals based on different few-shot episodic tasks. We conducted experiments on three standard few-shot benchmarks, including image recognition and fine-grained categorization. The experimental results demonstrate that our AFGN performs better compared to other state-of-the-art models.

Named Entity Recognition for Equipment Fault Diagnosis Based on RoBERTa-wwm-ext and Deep Learning Integration

Equipment fault diagnosis NER is to extract specific entities from Chinese equipment fault diagnosis text, which is the premise of constructing an equipment fault diagnosis knowledge graph. Named entity recognition for equipment fault diagnosis can also provide important data support for equipment maintenance support. Equipment fault diagnosis text has complex semantics, fuzzy entity boundaries, and limited data size. In order to extract entities from the equipment fault diagnosis text, this paper presents an NER model for equipment fault diagnosis based on RoBERTa-wwm-ext and Deep Learning network integration. Firstly, this model uses the RoBERTa-wwm-ext to extract context-sensitive embeddings of text sequences. Secondly, the context feature information is obtained through the BiLSTM network. Thirdly, the CRF is combined to output the label sequence with a constraint relationship, improve the accuracy of sequence labeling task, and complete the entity recognition task. Finally, experiments and predictions are carried out on the constructed dataset. The results show that the model can effectively identify five types of equipment fault diagnosis entities and has higher evaluation indexes than the traditional model. Its precision, recall, and F1 value are 94.57%, 95.39%, and 94.98%, respectively. The case study proves that the model can accurately recognize the entity of the input text.

Enhanced knowledge graph recommendation algorithm based on multi-level contrastive learning

Integrating the Knowledge Graphs (KGs) into recommendation systems enhances personalization and accuracy. However, the long-tail distribution of knowledge graphs often leads to data sparsity, which limits the effectiveness in practical applications. To address this challenge, this study proposes a knowledge-aware recommendation algorithm framework that incorporates multi-level contrastive learning. This framework enhances the Collaborative Knowledge Graph (CKG) through a random edge dropout method, which constructs feature representations at three levels: user-user interactions, item-item interactions and user-item interactions. A dynamic attention mechanism is employed in the Graph Attention Networks (GAT) for modeling the KG. Combined with the nonlinear transformation and Momentum Contrast (Moco) strategy for contrastive learning, it can effectively extract high-quality feature information. Additionally, multi-level contrastive learning, as an auxiliary self-supervised task, is jointly trained with the primary supervised task, which further enhances recommendation performance. Experimental results on the MovieLens and Amazon-books datasets demonstrate that this framework effectively improves the performance of knowledge graph-based recommendations, addresses the issue of data sparsity, and outperforms other baseline models across multiple evaluation metrics.

Cnn-assisted multi-hop graph attention network for hyperspectral image classification

ABSTRACT Recently, the convolutional neural network (CNN) has gained widespread adoption in the hyperspectral image (HSI) classification owing to its remarkable feature extraction capability. However, the fixed acceptance domain of CNN restricts it to Euclidean image data only, making it difficult to capture complex information in hyperspectral data. To overcome this problem, much attention has been paid to the graph attention network (GAT), which can effectively model graph structure and capture complex dependencies between nodes. However, GAT usually acts on superpixel nodes, which may lead to the loss of pixel-level information. To better integrate the advantages of both, we propose a CNN-assisted multi-hop graph attention network (CMGAT) for HSI classification. Specifically, a parallel dual-branch architecture is first constructed to simultaneously capture spectral-spatial features from hyperspectral data at the superpixel and pixel levels using GAT and CNN, respectively. On this basis, the multi-hop and multi-scale mechanisms are further employed to construct a multi-hop GAT module and a multi-scale CNN module to capture diverse feature information. Secondly, an attention module is cascaded before the multi-scale CNN module to improve classification performance. Eventually, the output information from the two branches is weighted and fused to produce the classification result. We performed experiments on four benchmark HSI datasets, including Indian Pines (IP), University of Pavia (UP), Salinas Valley (SV) and WHU-Hi-LongKou (LK). The results demonstrate that the proposed method outperforms several deep learning methods, achieving overall accuracies of 95.67%, 99.04%, 99.55% and 99.51%, respectively, even with fewer training samples.

Remote sensing scene classification based on contextual attention mechanism of lie group space

ABSTRACT High-resolution remote sensing (HRRS) scene classification is based on the semantic information in the image and its contextual spatial correlation, labelling different semantic categories for different HRRS. Convolutional neural networks (CNN) have been widely studied and applied in remote sensing scene classification in recent years. However, most of the existing CNN models focus on the global and high-level semantic features, ignoring the shallower feature information. In addition, complex background information and variable scales lead to a series of problems with large intra-class differences and high inter-class similarities, which also brings challenges to scene classification. To address the above problems and challenges, a scenario classification model based on the contextual spatial attention and channel attention mechanism of Lie Group manifold space learning is proposed in this study. In this model, we fully explore the multi-scale features of the scene (shallower-level and high-level) and propose a novel contextual spatial attention mechanism and channel attention mechanism. Extensive experimentation was carried out on the Union Remote Sensing Image Data Set (URSIS), which improved by 7.13% compared with the classical model. The experimental results showed that compared with other state-of-the-art remote sensing scene classification models, our proposed method has achieved significant improvement in classification accuracy and performance.

A chest imaging diagnosis report generation method based on dual-channel transmodal memory network

Medical imaging is critical for clinical diagnosis. In the past few years, medical imaging data has been steadily growing at an annual rate of 30%, while the annual growth rate in the number of radiologists is only 4. 1%. The traditional manual methods of chest imaging reports result in high information load and workload with low relevance of images and texts. Here we propose a chest CT imaging diagnosis report generation network to effectively integrate image and text feature information, improve the relevance of the cross-modal networks and automatically generate imaging diagnosis reports. The network includes three major modules: a novel ResNetII for information extraction, an image–text dual-channel transmodal memory network (DCTMN), and a dual-channel decoder module combined with LSTM gate. We validate the effectiveness of the proposed network on the IU X-ray and the MIMIC-CXR datasets. Our analysis indicates that the proposed method can strengthen the relationship between chest imaging and text information, ultimately achieving the automatic generation of chest imaging diagnosis reports.

A Zero-Watermarking Algorithm Based on Vortex-like Texture Feature Descriptors

For effective copyright protection of digital images, this paper proposes a zero-watermarking algorithm based on local image feature information. The feature matrix of the algorithm is derived from the keypoint set determined by the Speeded-Up Robust Features (SURF) algorithm, and it calculates both the gradient feature descriptors and the vortex-like texture feature (VTF) descriptors of the keypoint set. Unlike traditional texture feature descriptors, the vortex-like texture feature descriptors proposed in this paper contain richer information and exhibit better stability. The advantage of this algorithm lies in its ability to calculate the keypoints of the digital image and provide a stable vector description of the local features of these keypoints, thereby reducing the amount of erroneous information introduced during attacks. Analysis of experimental data shows that the algorithm has good effectiveness, distinguishability, security, and robustness.

ASANet: Asymmetric Semantic Aligning Network for RGB and SAR image land cover classification

Synthetic Aperture Radar (SAR) images have proven to be a valuable cue for multimodal Land Cover Classification (LCC) when combined with RGB images. Most existing studies on cross-modal fusion assume that consistent feature information is necessary between the two modalities, and as a result, they construct networks without adequately addressing the unique characteristics of each modality. In this paper, we propose a novel architecture, named the Asymmetric Semantic Aligning Network (ASANet), which introduces asymmetry at the feature level to address the issue that multi-modal architectures frequently fail to fully utilize complementary features. The core of this network is the Semantic Focusing Module (SFM), which explicitly calculates differential weights for each modality to account for the modality-specific features. Furthermore, ASANet incorporates a Cascade Fusion Module (CFM), which delves deeper into channel and spatial representations to efficiently select features from the two modalities for fusion. Through the collaborative effort of these two modules, the proposed ASANet effectively learns feature correlations between the two modalities and eliminates noise caused by feature differences. Comprehensive experiments demonstrate that ASANet achieves excellent performance on three multimodal datasets. Additionally, we have established a new RGB-SAR multimodal dataset, on which our ASANet outperforms other mainstream methods with improvements ranging from 1.21% to 17.69%. The ASANet runs at 48.7 frames per second (FPS) when the input image is 256 × 256 pixels.

Two-stage deep image restoration network with application to single image shadow removal

In this paper, we introduce a two-stage deep learning-based image restoration network and its application to remove shadow information from a single image, named by ESCNet (Encoder-decoder based Shadow removal with Colorization Network). Most existed single image-based shadow removal methods may suffer from that the shadow contains multiple regions of different colors or rich image details. To tackle with the problems, our key idea is to first remove shadow(s) from an image followed by repainting the shadow-removed region(s) in this image. To accomplish this, we present a deep two-stage network, cascading a shadow removal network (SRN) and a colorization network (CN). The presented encoder-decoder-based SRN with fusion of global and local feature information is used to remove the shadow(s) in the grayscale domain of the input image while recovering the image details for the shadow-removed region(s). Then the proposed CN aims at repainting the removed shadow region(s) via re-colorization. The proposed deep model has been well trained and well evaluated on the two well-known public datasets, i.e., ISTD (Image Shadow Triplets Dataset) and SRD (Shadow Removal Dataset). Experimental results have shown that the proposed method outperforms the compared state-of-the-art (SOTA) shadow removal approaches quantitatively and qualitatively.

TC-DTA: Predicting Drug-Target Binding Affinity With Transformer and Convolutional Neural Networks.

Bioinformatics is a rapidly evolving field that applies computational methods to analyze and interpret biological data. A key task in bioinformatics is identifying novel drug-target interactions (DTIs), which plays a crucial role in drug discovery. Most computational approaches treat DTI prediction as a binary classification problem, determining whether drug-target pairs interact. However, with the growing availability of drug-target binding affinity data, this binary task can be reframed as a regression problem focused on drug-target affinity (DTA). DTA quantifies the strength of drug-target binding, offering more detailed insights than DTI and serving as a valuable tool for virtual screening in drug discovery. Accurately predicting compound interactions with targets can accelerate the drug development process. In this study, we introduce a deep learning model named TC-DTA for DTA prediction, leveraging convolutional neural networks (CNN) and the encoder module of the transformer architecture. We begin by extracting raw drug SMILES strings and protein amino acid sequences from the dataset, which are then represented using various encoding methods. Subsequently, we employ CNN and the transformer's encoder module to extract features from the drug SMILES strings and protein sequences, respectively. Finally, the feature information is concatenated and input into a multi-layer perceptron to predict binding affinity scores. We evaluated our model on two benchmark DTA datasets, Davis and KIBA, comparing it with methods such as KronRLS, SimBoost, and DeepDTA. Our model, TC-DTA, outperformed these baseline methods based on evaluation metrics like Mean Squared Error (MSE), Concordance Index (CI), and Regression towards the Mean Index ( rm2 ). These results highlight the effectiveness of the Transformer's encoder and CNN in extracting meaningful representations from sequences, thereby enhancing DTA prediction accuracy. This deep learning model can accelerate drug discovery by identifying drug candidates with high binding affinity to specific targets. Compared to traditional methods, machine learning technology offers a more effective and efficient approach to drug discovery.

MSAACNN for intense noise suppression in DAS-VSP records

Distributed optical fiber sensor (DAS) is an emerging acquisition technique and has begun to be widely applied in seismic exploration owing to its advantages in acquisition and deployment. Nonetheless, DAS record has a low signal-to-noise ratio (SNR) due to the intense background noise. How to suppress the DAS background noise and increase the SNR of the DAS records has gradually become one of the hot issues in the field of seismic data processing. To solve the challenging tasks in intense DAS noise suppression, a multiscale sparse asymmetric attention convolutional neural network (MSAACNN) is proposed. The network uses dilated convolutions to expand the receptive field and map more feature information. Moreover, asymmetric convolutions are introduced to form an asymmetric unit, aiming to strengthen the feature extraction ability and realize the interaction between feature information of different scales. Finally, a pyramid attention module is used to enhance the primary features and improve the network denoising performance. The experimental results show that MSAACNN can effectively suppress the complex background noise in DAS records, compared with the traditional denoising methods and typical convolutional neural network (CNN) architecture. Additionally, the recovered signal components in the processing results are clear and complete, with significantly improved SNR.

Real‐time semantic segmentation network for crops and weeds based on multi‐branch structure

AbstractWeed recognition is an inevitable problem in smart agriculture, and to realise efficient weed recognition, complex background, insufficient feature information, varying target sizes and overlapping crops and weeds are the main problems to be solved. To address these problems, the authors propose a real‐time semantic segmentation network based on a multi‐branch structure for recognising crops and weeds. First, a new backbone network for capturing feature information between crops and weeds of different sizes is constructed. Second, the authors propose a weight refinement fusion (WRF) module to enhance the feature extraction ability of crops and weeds and reduce the interference caused by the complex background. Finally, a Semantic Guided Fusion is devised to enhance the interaction of information between crops and weeds and reduce the interference caused by overlapping goals. The experimental results demonstrate that the proposed network can balance speed and accuracy. Specifically, the 0.713 Mean IoU (MIoU), 0.802 MIoU, 0.746 MIoU and 0.906 MIoU can be achieved on the sugar beet (BoniRob) dataset, synthetic BoniRob dataset, CWFID dataset and self‐labelled wheat dataset, respectively.

IDSV-GCN: Integrating Dual Syntactic Views Graph Convolutional Network for aspect-based sentiment analysis

Aspect-based sentiment analysis (ABSA) aims to predict the sentiment polarity towards given aspects in a sentence. Recent research has highlighted that graph neural networks based on syntactic dependency trees effectively convey rich syntactic information and are suitable for ABSA tasks. Most existing work typically adopt either dependency type or minimum distance between nodes in the original syntactic tree to construct different views. However, existing work overlooks the high-dimensional local feature information in dependency relations, resulting in inadequate exploration of this view. Meanwhile, most work ignores that the minimum distance view and the dependency view can be complementary and integrated in syntactic analysis. Unfortunately, directly adding the two views introduces noise issues, leading to unsatisfactory results after their integration. To address these issues, this paper introduces an integrating dual syntactic views graph convolutional network (IDSV-GCN) model that seamlessly integrates dependency type view and minimum distance view, enabling comprehensive utilization of syntactic structure and information. To better address the computation of weights in the dependency type view, we innovatively propose a fusion attention mechanism. This approach effectively captures both global and local feature information. To more effectively integrate the two views and reduce the impact of noise, we employ a syntactic mask layer to filter out noise in the dependency type view and highlighting important dependency feature information. Then, we construct a minimum distance weight matrix based on the matrix obtained from the dependency type view. Finally, we merge the two matrices and feed them into the GCN to facilitate the model’s learning of syntactic information. Experimental results on three widely-used benchmark datasets demonstrate that our proposed IDSV-GCN model outperforms state-of-the-art methods.

HADT: Image super-resolution restoration Using Hybrid Attention-Dense Connected Transformer Networks

Image super-resolution (SR) plays a vital role in vision tasks, in which Transformer-based methods outperform conventional convolutional neural networks. Existing work usually uses residual linking to improve the performance, but this type of linking provides limited information transfer within the block. Also, existing work usually restricts the self-attention computation to a single window to improve feature extraction. This means transformer-based networks can only use feature information within a limited spatial range. To handle the challenge, this paper proposes a novel Hybrid Attention-Dense Connected Transformer Network (HADT) to utilize the potential feature information better. HADT is constructed by stacking an attentional transformer block (ATB), which contains an Effective Dense Transformer Block (EDTB) and a Hybrid Attention Block (HAB). EDTB combines dense connectivity and swin-transformer to enhance feature transfer and improve model representation, and meanwhile, HAB is used for cross-window information interaction and joint modeling of features for better visualization. Based on the experiments, our method is effective on SR tasks with magnification factors of 2, 3, and 4. For example, using the Urban100 dataset in an experiment with an amplification factor of 4 our method has a PSNR value that is 0.15 dB higher than the previous method and reconstructs a more detailed texture.

ETFE: Efficient transformer with feature enhancement for semantic segmentation

Abstract Despite the powerful capabilities of Transformers in relation to modeling, their effectiveness in capturing multi-scale object features in image-based tasks is often limited. This limitation arises from the diverse shapes and distances between objects in natural scenes, which pose challenges for Transformers to accurately capture object sizes and distances. To overcome this problem, we propose an effective Transformer which extracts multi-scale features at different resolutions. First, we leverage a multi-head attention mechanism to extract richer semantic features at various resolutions. The semantic features are then passed through the Feature Gate to aggregate multi-scale semantic features. Finally, Attentional Feature Enhancement further strengthens the semantic information of target features, enabling the modeling of dependencies among multi-scale features. Comprehensive experiments conducted on the Cityscapes and ADE20K datasets have shown that our model outperforms competing methods in both performance and accuracy.

Improving fluid identification in well logging using Continuous Wavelet Transform and Vision Transformers: An innovative approach

Well logging fluid prediction is one of the key steps in assessing oil and gas reserves. By analyzing downhole logging data, different types of fluids contained in underground rocks, such as crude oil, natural gas, and water, can be determined. This information is crucial for assessing the abundance and recoverable reserves of oil and gas resources and helps guide oil and gas exploration and development work. We have introduced a novel model called CWT (Continuous Wavelet Transform)-ViT (Vision Transformer). CWT can simultaneously provide frequency information at different scales, enabling the model to analyze downhole logging data more comprehensively and accurately at different scales. Underground rock structures often exhibit features at multiple scales, and CWT can effectively capture these features, aiding in better differentiation of different types of fluids. The ViT model utilizes the Transformer architecture, allowing for global attention over input sequences without being limited by sequence length. This enables the model to comprehensively understand the overall information of downhole logging data and extract richer features. For complex geological structures and fluid distributions in geological exploration, the global attention mechanism helps the model better grasp the overall situation, thereby improving the accuracy of fluid prediction. When we used the CWT-ViT method for well logging fluid prediction, we achieved a high accuracy rate of 97.50% in the first dataset, which further improved to 97.77% in the second dataset. These results demonstrate the significant robustness and efficiency of the CWT-ViT method in lithology prediction using well logging data. We also conducted blind well experiments, and our CWT-ViT model outperformed other models, achieving a blind well prediction accuracy of 97.36%. Therefore, the experiments indicate that the key to improving accuracy in well logging fluid prediction with CWT lies in its multiscale analysis capability, effectively capturing different fluid characteristic frequencies. Additionally, CWT enhances signal features and removes noise, increasing the precision of fluid identification. Finally, the integration with ViT further optimizes fluid prediction performance, making it outstanding in complex geological environments. The advantages of ViT in fluid prediction include its excellent sequence modeling capability, effective handling of long-distance dependencies, and enhanced ability to capture fluid characteristics in complex well logging data.