Dual Network Research Articles

Top-down approach making anisotropic, stable and flexible wood-based ionogels for wearable sensors

Ionogels exhibit outstanding ionic conductivity, thermal stability, and non-volatility, positioning them as highly promising for sensor devices rivaling hydrogels. However, the inherent limitation of most existing ionogels is that their strength and toughness are not ideal, which significantly hinders their widespread application. One possible method is using natural wood with anisotropic properties to reinforce ionogels. Herein, we reported a top-down approach to obtain a semi-dissolved wood template, in which the delignified balsa wood was heated and impregnated in an ionic liquid to partially dissolve the cellulose in the wood skeleton. Finally, acrylic acid was infiltrated into the wood template, and the wood-based ionogels with a dual network were successfully synthesized by in-situ polymerization. The prepared wood-based ionogels were significantly anisotropic with longitudinal strength up to 9.0 MPa and radial strength of 0.97 MPa. These wood ionogels also have translucency (53.9 %), anti-drying (remain stable at room temperature for more than 30 days), fatigue resistance (>500 loading cycles), and flexibility. In addition, they have excellent electrical conductivity (3.8 μS cm−1) with high sensitivity (GF = 8.6), making them ideal candidates for strain sensors capable of detecting a wide range of human activities. The preparation of gel using semi-dissolved wood as a template provides an advanced strategy for producing biomass-based flexible gel materials.

WGDPool: A broad scope extraction for weighted graph data

Graph pooling is a commonly used operation in graph neural networks to reduce the size of graph representation. To extract key information, pooling and representation need to be coupled. We propose a graph pooling method for weighted graphs called WGDPool (Weighted Graph Dual Pooling). Unlike traditional graph representation learning methods, the weight information of edges is also fed into convolutional graph neural networks (ConvGNN) to obtain graph representations. Dual branch convolutional graph neural networks is designed to learn the nodes’ and edges’ embeddings independently, and they are fused into a comprehensive representation of graph data. Pooling, as a tool of feature extraction and scale reduction of graph representation, adopts a differentiable version of k-means clustering and a multi-item parameterized loss function. Cut loss, orthogonality loss, clustering loss, and reconstruction loss are simultaneously considered. By parameterization, WGDPool is competent for diverse graph tasks. WGDPool outperformed other graph pooling methods in such common supervised and unsupervised tasks as biological or chemical classification, bibliography clustering and integrated circuit partition, demonstrating the effectiveness of our proposed pooling method.

A Soft-Switching Proportional Dimming LED Driver Based on Switched Capacitor

This paper proposes a switched capacitor-based soft-switching proportional dimming LED driver to address color-mixing LED applications. The driver utilizes a half-bridge switch structure and incorporates a switched capacitor to regulate the dual resonant network. This configuration facilitates current sharing across each resonant network and enables fixed proportion dimming between them. The common inductance leveraged in this design results in fewer switching devices, thereby enhancing efficiency. Furthermore, all switches and diodes achieve soft switching, contributing to high efficiency. Finally, this paper built a 19 W experimental prototype, and the maximum efficiency reached 95.56%, which verified the correctness and feasibility of the driver.

High‐Adhesion, Weather Resistance, Reusable PAM/Gly/Gel/TA/Fe3+ Biopolymer Dual‐Network Conductive Hydrogel for Flexible Bioelectrode

AbstractConductive hydrogel is considered a promising wearable sensor material. Developing flexible conductive hydrogel sensors with stretchability, adhesion, and stability remains challenging. In this study, a transparent, self‐adhesive, antifreeze, anti‐UV, stretchable, conductive, and reusable hydrogel with polyacrylamide/glycerol/gelatin/tannic acid/Fe3+ (PGGT‐Fe3+) structure is successfully constructed through a simple one‐pot polymerization method. The PGGT‐Fe3+ hydrogel is composed of dual networks of polyacrylamide and gelatin for organic cross‐linking, using water/glycerol as the dispersion medium, and incorporates a viscous substance: tannic acid, and a conductive substance: metal ions (Fe3+). Due to the introduction of the abundant amino, carboxylic acid, and hydroxyl functional groups on gelatin and tannic acid, the PGGT‐Fe3+ hydrogel exhibits excellent and repeatable adhesion capabilities on various surfaces (including glass, metal, plastic, and pigskin) with maximum adhesion strength of 98 kPa when attached to pigskin. Furthermore, based on the stable conductive network and high conductivity, the hydrogel not only exhibits strain sensitivity, fast response, and stability but also can stably collect epidermal bio signals. In conclusion, this work provides a new approach to the design and development of next‐generation multifunctional conductive hydrogels and opens up vast possibilities for their applications in the flexible electronics field.

Chinese text dual attention network for aspect-level sentiment classification.

English text has a clear and compact subject structure, which makes it easy to find dependency relationships between words. However, Chinese text often conveys information using situational settings, which results in loose sentence structures, and even most Chinese comments and experimental summary texts lack subjects. This makes it challenging to determine the dependency relationship between words in Chinese text, especially in aspect-level sentiment recognition. To solve this problem faced by Chinese text in the field of sentiment recognition, a Chinese text dual attention network for aspect-level sentiment recognition is proposed. First, Chinese syntactic dependency is proposed, and sentiment dictionary is introduced to quickly and accurately extract aspect-level sentiment words, opinion extraction and classification of sentimental trends in text. Additionally, in order to extract context-level features, the CNN-BILSTM model and position coding are also introduced. Finally, to better extract fine-grained aspect-level sentiment, a two-level attention mechanism is used. Compared with ten advanced baseline models, the model's capabilities are being further optimized for better performance, with Accuracy of 0.9180, 0.9080 and 0.8380 respectively. This method is being demonstrated by a vast array of experiments to achieve higher performance in aspect-level sentiment recognition in less time, and ablation experiments demonstrate the importance of each module of the model.

FF-STGCN: A usage pattern similarity based dual-network for bike-sharing demand prediction.

Accurate bike-sharing demand prediction is crucial for bike allocation rebalancing and station planning. In bike-sharing systems, the bike borrowing and returning behavior exhibit strong spatio-temporal characteristics. Meanwhile, the bike-sharing demand is affected by the arbitrariness of user behavior, which makes the distribution of bikes unbalanced. These bring great challenges to bike-sharing demand prediction. In this study, a usage pattern similarity-based dual-network for bike-sharing demand prediction, called FF-STGCN, is proposed. Inter-station flow features and similar usage pattern features are fully considered. The model includes three modules: multi-scale spatio-temporal feature fusion module, bike usage pattern similarity learning module, and bike-sharing demand prediction module. In particular, we design a multi-scale spatio-temporal feature fusion module to address limitations in multi-scale spatio-temporal accuracy. Then, a bike usage pattern similarity learning module is constructed to capture the underlying correlated features among stations. Finally, we employ a dual network structure to integrate inter-station flow features and similar usage pattern features in the bike-sharing demand prediction module to realize the final prediction. Experiments on the Citi Bike dataset have demonstrated the effectiveness of our proposed model. The ablation experiments further confirm the indispensability of each module in the proposed model.

Advancing image captioning with V16HP1365 encoder and dual self-attention network

Advancing image captioning with V16HP1365 encoder and dual self-attention network

Independent Dual Graph Attention Convolutional Network for Skeleton-Based Action Recognition

Graph convolutional networks (GCNs) have been widely adopted in skeleton-based action recognition, achieving impressive outcomes. However, the convolution operations in GCNs fail to make full use of the original input data, which restricts its ability to accurately capture the correlation within the skeleton. To solve this issue, this study introduces an independent dual graph attention convolutional network (IDGAN). Specifically, IDGAN additionally incorporates an instinctive attention module that leverages self-attention to capture the correlation among the joints in the original input skeleton. In addition, two independent convolutional operations are used to process two self-attention modules, respectively, to further refine the relationship between skeleton joints. Extensive experiments on several publicly available datasets show that IDGAN outperforms most state-of-the-art algorithms.

Underwater image restoration based on dual information modulation network

The presence of light absorption and scattering in underwater conditions results in underwater images with missing details, low contrast, and color bias. The current deep learning-based methods bring unlimited potential for underwater image restoration (UIR) tasks. These methods, however, do not adequately take into account the inconsistency of the attenuation of different color channels and spatial regions when performing image restoration. To solve these gaps, we propose a dual information modulation network (DIMN) for accurate UIR tasks. To be specific, we design a multi-information enhancement module (MIEM), empowered by spatial-aware attention block (SAAB) and multi-scale structural Transformer block (MSTB), to guide the inductive bias of image degradation processes under nonhomogeneous media distributions. SAAB focuses on different spatial locations, capturing more spatial-aware cues to correct color deviations and recover details. MSTB utilizes the difference and complementarity between features at different scales to effectively complement the network’s structural and global perceptual capabilities, enhancing image sharpness and contrast further. Experimental results reveal that the proposed DIMN exceeds most state-of-the-art UIR methods. Our code and results are available at: https://github.com/wwaannggllii/DIMN.

DBSTGNN-Att: Dual Branch Spatio-Temporal Graph Neural Network with an Attention Mechanism for Cellular Network Traffic Prediction

As network technology continues to develop, the popularity of various intelligent terminals has accelerated, leading to a rapid growth in the scale of wireless network traffic. This growth has resulted in significant pressure on resource consumption and network security maintenance. The objective of this paper is to enhance the prediction accuracy of cellular network traffic in order to provide reliable support for the subsequent base station sleep control or the identification of malicious traffic. To achieve this target, a cellular network traffic prediction method based on multi-modal data feature fusion is proposed. Firstly, an attributed K-nearest node (KNN) graph is constructed based on the similarity of data features, and the fused high-dimensional features are incorporated into the graph to provide more information for the model. Subsequently, a dual branch spatio-temporal graph neural network with an attention mechanism (DBSTGNN-Att) is designed for cellular network traffic prediction. Extensive experiments conducted on real-world datasets demonstrate that the proposed method outperforms baseline models, such as temporal graph convolutional networks (T-GCNs) and spatial–temporal self-attention graph convolutional networks (STA-GCNs) with lower mean absolute error (MAE) values of 6.94% and 2.11%, respectively. Additionally, the ablation experimental results show that the MAE of multi-modal feature fusion using the attributed KNN graph is 8.54% lower compared to that of the traditional undirected graphs.

Localized Magnetopause Erosion at Geosynchronous Orbit by Reconnection

AbstractThis study presents observations of magnetopause reconnection and erosion at geosynchronous orbit, utilizing in situ satellite measurements and remote sensing ground‐based instruments. During the main phase of a geomagnetic storm, Geostationary Operational Environmental Satellites (GOES) 15 was on the dawnside of the dayside magnetopause (10.6 MLT) and observed significant magnetopause erosion, while GOES 13, observing duskside (14.6 MLT), remained within the magnetosphere. Combined observations from the THEMIS satellites and Super Dual Auroral Radar Network radars verified that magnetopause erosion was primarily caused by reconnection. While various factors may contribute to asymmetric erosion, the observations suggest that the weak reconnection rate on the duskside can play a role in the formation of asymmetric magnetopause shape. This discrepancy in reconnection rate is associated with the presence of cold dense plasma on the duskside of the magnetosphere, which limits the reconnection rate by mass loading, resulting in more efficient magnetopause erosion on the dawnside.

Channel based approach via faster dual prediction network for video anomaly detection

Channel based approach via faster dual prediction network for video anomaly detection

Unifying convolution and transformer: a dual stage network equipped with cross-interactive multi-modal feature fusion and edge guidance for RGB-D salient object detection

Unifying convolution and transformer: a dual stage network equipped with cross-interactive multi-modal feature fusion and edge guidance for RGB-D salient object detection

DI-VTR: Dual inter-modal interaction model for video-text retrieval

Video-text retrieval is a challenging task for multimodal information processing due to the semantic gap between different modalities. However, most existing methods do not fully mine the intra-modal interactions, as with the temporal correlation of video frames, which results in poor matching performance. Additionally, the imbalanced semantic information between videos and texts also leads to difficulty in the alignment of the two modalities. To this end, we propose a dual inter-modal interaction network for video-text retrieval, i.e., DI-VTR. To learn the intra-modal interaction of video frames, we design a contextual-related video encoder to obtain more fine-grained content-oriented video representations. We also propose a dual inter-modal interaction module to accomplish accurate multilingual alignment between the video and text modalities by introducing multilingual text to improve the representation ability of text semantic features. Extensive experimental results on commonly-used video-text retrieval datasets, including MSR-VTT, MSVD and VATEX, show that the proposed method achieves significantly improved performance compared with state-of-the-art methods.

Remaining Useful Life Prediction of Lithium-Ion Batteries: A Temporal and Differential Guided Dual Attention Neural Network

Remaining Useful Life Prediction of Lithium-Ion Batteries: A Temporal and Differential Guided Dual Attention Neural Network

Dual Spatial Attention Network for Underwater Object Detection With Sonar Imagery

Dual Spatial Attention Network for Underwater Object Detection With Sonar Imagery

Lifelong Dual Generative Adversarial Nets Learning in Tandem.

Continually capturing novel concepts without forgetting is one of the most critical functions sought for in artificial intelligence systems. However, even the most advanced deep learning networks are prone to quickly forgetting previously learned knowledge after training with new data. The proposed lifelong dual generative adversarial networks (LD-GANs) consist of two generative adversarial networks (GANs), namely, a Teacher and an Assistant teaching each other in tandem while successively learning a series of tasks. A single discriminator is used to decide the realism of generated images by the dual GANs. A new training algorithm, called the lifelong self knowledge distillation (LSKD) is proposed for training the LD-GAN while learning each new task during lifelong learning (LLL). LSKD enables the transfer of knowledge from one more knowledgeable player to the other jointly with learning the information from a newly given dataset, within an adversarial playing game setting. In contrast to other LLL models, LD-GANs are memory efficient and does not require freezing any parameters after learning each given task. Furthermore, we extend the LD-GANs to being the Teacher module in a Teacher-Student network for assimilating data representations across several domains during LLL. Experimental results indicate a better performance for the proposed framework in unsupervised lifelong representation learning when compared to other methods.

A recommender system-using novel deep network collaborative filtering

<p>The recommendation model aims to predict the user’s preferred items among million through analyzing the user-item relations; furthermore, Collaborative Filtering has been utilized as one of the successful recommendation approaches in last few years; however, it has the issue of sparsity. This research work develops a deep network collaborative filtering (DeepNCF), which incorporates graph neural network (GNN), and novel network collaborative filtering (NCF) for performance enhancement. At first user-item dual network is constructed, thereafter-custom weighted dual mode modularity is developed for edge clustering. Furthermore, GNN is utilized for capturing the complex relation between user and item. DeepNCF is evaluated considering the two distinctive. The experimental analysis is carried out on two datasets for Amazon and movielens dataset for recall@20 and recall@50 and the normalized discounted cumulative gain (NDCG) metric is evaluated for Amazon Dataset for NDCG@20 and NDCG@50. The proposed method outperforms the most relevant research and is accurate enough to give personalized recommendations and diversity.</p>

A fusion TFDAN-Based framework for rotating machinery fault diagnosis under noisy labels

Traditional fault diagnosis (FD) for rotating machinery solely based on vibration signals has problems such as inconvenient collection, low accuracy, and poor robustness. This article proposes a fusion framework based on tensor fusion and dual attention network (TFDAN), utilizing acoustic and vibration signals from two datasets of centrifugal pumps and cylindrical roller bearings. Firstly, continuous wavelet transform (CWT) is used to transform two original signals into two-dimensional time–frequency maps to highlight time–frequency features. Then, the images are fed into the fusion framework, where tensor fusion can construct the corresponding time–frequency maps of the working conditions into multi-channel datasets, enhancing the feature connections between acoustic and vibration signals. The dual attention network takes on the fused samples, extracts local features of the image using its positional attention module, and further aggregates feature correlations between channels using its channel attention mechanism. Finally, in order to simulate the actual production situation, different proportions of noisy labels are added to the dataset. In response to the impact of noisy labels, we incorporate an improved contrastive regularization function (ICRF) into the model, fully utilizing its advantage of preventing overfitting of noisy labels. The effectiveness of our proposed method has been demonstrated through two experimental cases. Compared with other methods, our method has better performance in terms of diagnostic accuracy and robustness to noisy labels.

DTT-CGINet: A Dual Temporal Transformer Network with Multi-Scale Contour-Guided Graph Interaction for Change Detection

Deep learning has dramatically enhanced remote sensing change detection. However, existing neural network models often face challenges like false positives and missed detections due to factors like lighting changes, scale differences, and noise interruptions. Additionally, change detection results often fail to capture target contours accurately. To address these issues, we propose a novel transformer-based hybrid network. In this study, we analyze the structural relationship in bi-temporal images and introduce a cross-attention-based transformer to model this relationship. First, we use a tokenizer to express the high-level features of the bi-temporal image into several semantic tokens. Then, we use a dual temporal transformer (DTT) encoder to capture dense spatiotemporal contextual relationships among the tokens. The features extracted at the coarse scale are refined into finer details through the DTT decoder. Concurrently, we input the backbone’s low-level features into a contour-guided graph interaction module (CGIM) that utilizes joint attention to capture semantic relationships between object regions and the contour. Then, we use the feature pyramid decoder to integrate the multi-scale outputs of the CGIM. The convolutional block attention modules (CBAMs) employ channel and spatial attention to reweight feature maps. Finally, the classifier discriminates change pixels and generates the final change map of the difference feature map. Several experiments have demonstrated that our model shows significant advantages over other methods in terms of efficiency, accuracy, and visual effects.