Double Branch Research Articles

Double red giant branch and red clump features of Galactic disc stellar populations with Gaia gspspec

The bimodality of the Milky Way disc, in the form of a thick short disc and a thinner more radially extended one, encrypts the complex internal evolution of our Galaxy and its interaction with the environment. To disentangle the different competing physical processes at play in Galactic evolution, a detailed chrono-chemical-kinematical and dynamical characterisation of the disc bimodality is necessary, including high number statistics. Here, we make use of an extremely precise sub-sample of the Gaia DR3 catalogue of stellar chemo-physical parameters. The selected database is composed of 408 800 stars with a median uncertainty of 10 K, 0.03, and 0.01 dex in and respectively. The stellar parameter precision allows us to break the age-metallicity degeneracy of disc stars. For the first time, the disc bimodality in the Kiel diagram of giant stars is observed, getting rid of interstellar absortion issues. This bimodality produces double red giant branch sequences and red clump features for mono-metallicity populations. A comparison with BaSTI isochrones allows us to demonstrate that an age gap is needed to explain the evolutionary sequence separation, in agreement with previous age-metallicity relations obtained using sub-giant stars. A bimodal distribution in the stellar mass- plane is observed at constant metallicity. Finally, a selection of stars with 0.03 dex shows that the most metal-rich population in the Milky Way disc presents an important proportion of stars with ages in the range of 5-13 Gyr, in agreement with previous literature findings. This old, extremely metal-rich population is possibly a mix of migrated stars from the internal Galactic regions, and old disc stars formed before the last major merger of the Milky Way. The Gaia Kiel diagrams of disc mono-abundance stellar populations reveal a complex, non-linear age-metallicity relation crafted by internal and external processes of Galactic evolution. Their detailed analysis opens new opportunities to reconstruct the puzzle of the Milky Way disc bimodality.

A double communication branch between musculocutaneous and median nerves: first case report, anatomical study, and comprehensive review of clinical implications.

According to the literature, the brachial plexus presents a high rate of anatomical variations in the human neural system. The musculocutaneous nerve, a vital component of the brachial plexus, exhibits significant anatomical variations that hold clinical relevance across multiple medical disciplines. This case report, with a comprehensive review, explores the different variations in the course, branching patterns, and clinical implications of the musculocutaneous nerve. Understanding these variations is essential for surgeons, radiologists, and clinicians to enhance surgical precision, improve diagnostic accuracy, and reduce the risk of iatrogenic complications. During an anatomical dissection we observed a very rare anatomical variation of the musculocutaneous nerve. Based on this discovery, we performed research in the literature with the aim of finding if this variation has been previously described. Firstly, we identified various classifications of anatomical variations of communicating branches between the musculocutaneous and median nerves, and then we observed that these variations corresponded to various rates of frequency. Our finding is a rare undescribed anatomical variant within the variants classified as Type II according to Le Minor, which is observed in 6.8-10.7% of cases. The peculiar position of anatomical variations and anastomosis has clinical and functional relevance. Healthcare professionals must be aware of these variations to minimize surgical complications, accurately diagnose neurovascular pathologies, and optimize patient management. Further research into the genetic and embryological underpinnings of these variations may provide additional insights into this intriguing aspect of human anatomy.

DBCvT: Double Branch Convolutional Transformer for Medical Image Classification

Convolutional Neural Networks (CNNs) are extensively utilized in medical disease diagnosis, demonstrating the prominent performance in most cases. However, medical image processing based on deep learning faces some challenges. The limited availability and time-consuming annotations of medical image data restrict the scale and accuracy of model training. Data diversity and complexity further complicate these challenges. In order to address these issues, we introduce the Double Branch Convolutional Transformer (DBCvT), a hybrid CNN-Transformer feature extractor, which can better capture diverse fine-grained features and remain suitable for small datasets. In this model, separable downsampling convolution (SDConv) is used to mitigate excessive information loss during downsampling in standard convolutions. Additionally, we propose the Dual branch Channel Efficient multi-head Self-Attention (DCESA) mechanism to enhance the self-attention efficiency, consequently elevating network performance and effectiveness. Moreover, we introduce a novel convolutional channel-enhanced Attention mechanism to strengthen inter-channel relationships within feature maps post self-attention. The experiments of DBCvT on various medical image datasets have demonstrated the outstanding classification performance and generalization capability of the proposed model.

Comprehensive analysis of thermal performance and low-grade energy charging efficiency of pipe-embedded building envelopes enhanced with single-level tree-shaped fin structures

Pipe-embedded walls (CnPWs) are structural and energy composite building components that can resist external disturbances by forming stealth thermal shielding layers. To tackle the mismatch between the heat charging rate and heat diffusion rate during energy charging processes, as well as the unsatisfactory robustness of stealth thermal shielding layers, the single-level tree-shaped metal finnd pipe-embedded walls (TfPWs) are proposed. To verify the effectiveness of TfPWs and obtain dynamic performances, a simulation study is conducted on 8 risk variables in 4 pairs through the validated numerical model. Results showed that the improved design was effective in obtaining more robust thermal shielding layers in auxiliary energy supply mode, the effect gained prominence as both the injection temperature and pipe spacing were augmented. In room heat load reduction mode, favorable benefits arise when pipe spacing exceeds 400 mm. The maximum increase rate of total injected energy under different reduction ratios of external insulation layer was 11.83%–31.91 %, while the maximum extra total heat loss was 5.33 %. Secondly, the trunk fins and branch fins played different roles in minimizing the excessive heat accumulation surrounding pipes, and the vertical and horizontal sizes of heat accumulation region mainly increased with the increase in trunk fin size and branch fin size respectively. Meanwhile, the utilization efficiency of fin material was higher when trunk fin size was smaller, and parameter combinations with trunk fin size of 0.2b and branch fin size of 0.4a/0.6a could achieve a better balance between material input and performance increase. Thirdly, the improvement effect of single left branch fin schemes was close to that of double branch fin schemes and significantly better than that of single right branch fin schemes. It was recommended to use single left branch fin schemes with an inclination angle of 60°. Finally, even if the reduction ratio of external insulation layer in different cities increased to 80 %, the inside surface temperature of TfPWs was still greater than room air. Taking CnPWs with standard external insulation layer as references, the TfPWs applied in Harbin, Beijing, and Shanghai could achieve similar or better results even when the reduction ratio of external insulation layer increased to 60 %, while TfPWs applied in Guangzhou could exhibit better performance even when the reduction ratio of external insulation layer increases to 80 %.

Classification of infection grade for anthracnose in mango leaves under complex background based on CBAM-DBIRNet

Anthracnose is one of the most harmful fungal diseases in mango orchards. Accurate and rapid detection of anthracnose infection grade for mango leaves in complex natural environments is a prerequisite of precise variable pesticide spraying by robots in intelligent orchards. In this paper, A lightweight double branch inverted residual attention network (CBAM-DBIRNet) model was proposed by combining the inverted residual network and the attention mechanism, which was used to detect the infection grade of anthracnose for mango leaves in natural environment. The model designed two parallel residual branch structures to extract multi-scale features of mango leaves with different infection grades through different dilation coefficients. The inverted residual structure and depthwise separable convolution were used to reduce the complexity of the model. The CBAM attention module was integrated into the model to suppress the interference of complex background information. The mango leaves collected in the natural orchard were used for experiments. The results showed that the accuracy, recall and F1 of the CBAM-DBIRNet model for the classification of anthracnose infection grade were 98.42 %, 97.80 % and 97.89 %, respectively. The model size and parameter were 0.64 MB and 0.15 M, respectively. This study provides technical support for smart orchard management and robotic precision variable application operations.

Research on microseismic signal identification through data fusion

The present study proposes a double-branch classification network, DPNet (Double Path Net), for the classification and identification of microseismic and blasting signals based on multimodal feature extraction. The vibration signals’ one-dimensional spectrogram and two-dimensional wavelet time–frequency graph are inputted into the double branch network. Subsequently, convolutional neural networks and ResNet are employed to extract the one-dimensional frequency features and two-dimensional time–frequency features of the vibration signals, respectively. Experimental results demonstrate that our proposed method achieves outstanding classification performance with an accuracy of 97.34% for microseismic signals and blasting signals. This research not only provides innovative solutions to practical problems but also introduces a novel idea of multimodal feature extraction at a theoretical level. By successfully applying it to efficiently classify complex signals in mining engineering, we offer a feasible solution that holds promising prospects for practical applications in this field.

A facial expression recognition network based on attention double branch enhanced fusion.

The facial expression reflects a person's emotion, cognition, and even physiological or mental state to a large extent. It has important application value in medical treatment, business, criminal investigation, education, and human-computer interaction. Automatic facial expression recognition technology has become an important research topic in computer vision. To solve the problems of insufficient feature extraction, loss of local key information, and low accuracy in facial expression recognition, this article proposes a facial expression recognition network based on attention double branch enhanced fusion. Two parallel branches are used to capture global enhancement features and local attention semantics respectively, and the fusion and complementarity of global and local information is realized through decision-level fusion. The experimental results show that the features extracted by the network are made more complete by fusing and enhancing the global and local features. The proposed method achieves 89.41% and 88.84% expression recognition accuracy on the natural scene face expression datasets RAF-DB and FERPlus, respectively, which is an excellent performance compared with many current methods and demonstrates the effectiveness and superiority of the proposed network model.

Fault diagnosis of hydroelectric units based on GASF and parallel CNN-GRU-MSA

Abstract Diagnosing the vibration signals of hydropower units is crucial for safe and stable operation. This paper proposes a fault diagnosis method for hydropower units based on Gramian Angular Summation Fields (GASF) and parallel convolutional neural networks-gated recurrent unit-multi-headed self-attention (CNN-GRU-MSA). The original data forms a double branch, and the first branch selects the original timing signal for feature extraction using GRU. The second branch converts the timing signal into a 2D image using GASF for feature extraction using CNN, and the merged signal is enhanced with MSA for feature values. The experimental results show that the accuracy of the method reaches 97.2%. In order to explore the generalization and practicability of the proposed model, the public dataset of Jiangnan University is introduced for re-analysis. The diagnostic result of 600 rpm is 98.5%, and the diagnostic result of 800 rpm and 1000 rpm is 100%, significantly better than the other comparative models. This study can be valuable to the hydropower unit’s fault diagnosis methods.

Evaluation of custom-made Relay® stent-grafts for aortic arch landing zones 0 and I: experience from two high-volume aortic centres.

To report experience with a Relay® stent-graft custom-made platform in treating different aortic arch pathology in 2 high-volume aortic centres. A retrospective analysis of all patients treated between July 2016 and July 2023 with custom-made Relay® stent-graft (custom-made device). Underlying aortic arch pathology was an aneurysm, penetrating aortic ulcer, and dissection. Three custom-made device designs were used: proximal scallop, fenestrations, and inner branches. The endpoints were technical success, perioperative stroke, death, and reintervention rate. Thirty-five patients (89% males) with a mean age of 70 ± 11 years were treated.Indication for treatment was penetrating aortic ulcer in 14 patients (40%), aneurysm in 11 patients (31%) and aortic dissection in 10 patients (29%). The technical success rate was 100%. Twenty-eight patients (80%) had proximal sealing in zone 0, and 7 (20%) had proximal sealing in zone 1. Nine patients (25.6%) had proximal scallops, 9 (25.6%) had 1 big fenestration and 17 (48.8%) had a branched device; 1 with single branch, 15 with double branches and 1 with triple branches. Thirty patients (86%) had previous or simultaneous left subclavian artery revascularization. No patient died during 30 days. Two patients (5.7%) had stroke postoperatively; both recovered without disabling deficits. The mean follow-up was 35 ± 26 months. Six patients (17.1%) died during follow-up. One patient required reinforcement of the bridging stent in the left common carotid artery and one additional vascular plugging of the left subclavian artery. Three patients received distal extension. The Relay® stent-graft custom-made platform showed a good performance in our study with a high technical success rate, low perioperative stroke and mortality, and low reintervention rates during the follow-up.

A double branches binary neural network with the application for garbage classification

A double branches binary neural network with the application for garbage classification

FDB-Net: Fusion double branch network combining CNN and transformer for medical image segmentation.

The rapid development of deep learning techniques has greatly improved the performance of medical image segmentation, and medical image segmentation networks based on convolutional neural networks and Transformer have been widely used in this field. However, due to the limitation of the restricted receptive field of convolutional operation and the lack of local fine information extraction ability of the self-attention mechanism in Transformer, the current neural networks with pure convolutional or Transformer structure as the backbone still perform poorly in medical image segmentation. In this paper, we propose FDB-Net (Fusion Double Branch Network, FDB-Net), a double branch medical image segmentation network combining CNN and Transformer, by using a CNN containing gnConv blocks and a Transformer containing Varied-Size Window Attention (VWA) blocks as the feature extraction backbone network, the dual-path encoder ensures that the network has a global receptive field as well as access to the target local detail features. We also propose a new feature fusion module (Deep Feature Fusion, DFF), which helps the image to simultaneously fuse features from two different structural encoders during the encoding process, ensuring the effective fusion of global and local information of the image. Our model achieves advanced results in all three typical tasks of medical image segmentation, which fully validates the effectiveness of FDB-Net.

Multicentre Experience with Novel Bidirectional Double Cuffed Inner Branches for Complex Endovascular Aortic Repair

This study aimed to report the initial experience with a novel bidirectional double cuff inner branch design for incorporation of renal and mesenteric arteries in patients undergoing fenestrated and branched endovascular aortic repair (F/BEVAR). A retrospective review was undertaken of the experience of F/BEVAR with grafts integrating at least one bidirectional double cuffed inner branch implanted at three tertiary aortic centres between March 2022 and June 2023. All consecutive patients were included. Baseline characteristics, operative data, and follow up data were collected. Results were presented as number or median (interquartile range) unless otherwise stated. Thirteen patients (10 male; median age 72 [68, 77] years) had F/BEVAR using a total of 15 bidirectional double cuffed inner branches (30 cuffs). Indications for bidirectional doubled cuffed inner branches included cranial vessel orientation or double renal arteries in four patients each, common coeliomesenteric trunk in three patients, and early renal artery bifurcation, renal artery origin from a false lumen requiring a flexible route for catheterisation, and surplus configuration in one patient each. Twenty three of the 30 cuffs were used, whereas the remaining seven cuffs were intentionally occluded with vascular plugs. Target vessel incorporation was successful in all bidirectional branches. There was one technical failure related to unsuccessful catheterisation of a left renal artery targeted through a unidirectional caudal inner branch. During a median follow up of seven months there were no instances of target vessel instability or re-interventions and two patients died of causes unrelated to the bidirectional branches. The results of the use of bidirectional double cuff inner branches are promising, with high technical success and no short term branch related complications in this preliminary experience. This could potentially expand the applicability of branch endografting of complex endovascular aortic repairs, but long term results are still missing.

Multi-fault diagnosis of district heating system based on PCA_BP neural network

To diagnose multiple faults (blockage and leakage) of a district heating system (MFDHS) in a timely and accurate manner, a new multi-fault diagnosis method is proposed that considers fault diagnosis as a classification problem based on principal component analysis (PCA) and a Back Propagation (BP) neural network. Using this method, a simulation model of heating-network faults is constructed and fault experiments are conducted. Based on the simulation model and experiments, the experimental (ED) and model (MD) datasets are effectively constructed followed by the construction of substitute datasets(SD) that replaces the experimental data with model data. PCA and data standardization are then adopted to process all the datasets. Finally, three BP neural network classification models are trained and tested using the three datasets. To demonstrate the effectiveness of this method, four experimental heating networks, namely a single heat source and branch (SHB), single heat source and single loop (SHSL), double heat source and branch (DHB), and double heat source and double loop (DHDL), are discussed as case studies. The results show that the relative errors of the experimental and simulation data for the pressures and flow rates are less than 5%. The highest prediction accuracy is obtained when the fault to the normal data are 95–5% under training sets to testing sets of 70–30%, while for the four heating networks, the prediction accuracy of the method built with ED is 99.93%, 99.99%, 99.84%, and 99.66% respectively, whereas it reaches 99.99% for MD. The accuracies are 99.99%, 98.13%, 97.4%, and 99.99%, respectively, with MD serving as the training set while another 11400 sets of experimental data serve as the testing set. Accordingly, the accuracy ranges from 95.56% to 88.03%, 97.85–93.29%, 95.65–85.71%, and 100–84.82%, with SD serving as the training set and another 11400 sets of experimental data serving as the testing set.

CPW-Fed UWB-MIMO Antenna with Triple-band Notched and High Isolation using Double Y-shaped Decoupling Structure

A ultra-wideband (UWB) multiple-input-multiple-output (MIMO) antenna using double Y-shaped decoupling structure with high isolation and triple notched-band is presented. The designed antenna composed of two orthogonally placed monopole elements, coplanar ground and double Y-shaped branch. The defected substrate structure is used to achieve miniaturization. By slotting successively C-shaped slot, semi-circular slot and rectangular slot on the radiation patch and the ground, achieved three notched bands at 3.5 GHz WiMAX, 5.25 GHz WLAN, and 7.5 GHz X-band. The proposed antenna can operate in range of 2.56-12 GHz with triple notched bands of 3.31-3.96 GHz, 4.58-5.67 GHz and 6.57-8.16 GHz. Considering all the results, it can be concluded that the antenna presented has a great performance in terms of good radiation, high isolation (>24 dB), a low level ECC (<0.01) and a high DG level (>9.99), which proves the presented antenna has good prospect in UWB-MIMO systems.

A spatio‐temporal graph convolutional approach to real‐time load forecasting in an edge‐enabled distributed Internet of Smart Grids energy system

SummaryAs the edge nodes of the Internet of Smart Grids (IoSG), smart sockets enable all kinds of power load data to be analyzed at the edge, which create conditions for edge calculation and real‐time (RT) load forecasting. In this article, an edge‐cloud computing analysis energy system is proposed to collect and analyze power load data, and a combination of graph convolutional network (GCN) with LSTM, called KGLSTM is used to achieve mid‐long term mixed sequential mode RT forecasting. In the proposed edge‐cloud framework, distributed intelligent sockets are regarded as edge nodes to collect, analyze and upload data to cloud services for further processing. The proposed KGLSTM network adopts a double branch structure. One branch extracts the data characteristics of mid‐short term time‐series data through an encoding–decoding LSTM module; the other branch extracts the data features of long term timing data through an adapted GCN. GCN is used to extract spatial correlations between different nodes. In addition, by combining a dynamic weighted loss function, the accuracy of peak forecasting is effectively improved. Finally, through various experimental indicators, this article shows that KGLSTM and weighted KGLSTM have achieved significant performance improvement over recent methods in mid‐long term time‐series forecasting and peak forecasting.

Double branch synergies with modal reinforcement for weakly supervised temporal action detection

Weakly supervised Temporal Action localization (WTAL) aims to locate the action instances and identify their corresponding labels. Most current methods rely on a Multi-Instance Learning (MIL) framework to predict start and end boundaries of each action in a video. However, they have shortcomings of incomplete positioning and context confusion. Therefore, we propose an algorithm of Double Branch Synergies with Modal Reinforcement (DBSMR), which utilizes long-short temporal attention to model contextual relationships and refines segmental features to encourage more distinguishable segment classification. In terms of blur boundaries between actions and camouflage background in complex scenes and easily resulting in wrong positioning, we construct a sparse graph focusing on the effective representation of context motion by optical flow modal learning, further enhancing the representation of the active region to be examined, and suppressing the interference from the background. Finally, with the idea of ”All roads lead to Rome”, we design motion-guided loss constraints to balance the long-short temporal module and graph reinforcement module, by which the two branches can converge to almost the same detection goal, thus to achieve an agreement of near ground truth localization result. The algorithm achieves mAP of 69.1% and 42.0% detection performances on the THUMOS14 and ActivityNet1.2 datasets respectively. We also verify its effectiveness by comparing it with the state-of-the-art methods.

Portrait Semantic Segmentation Method Based on Dual Modal Information Complementarity

Semantic segmentation of human images is a research hotspot in the field of computer vision. At present, the semantic segmentation models based on U-net generally lack the ability to capture the spatial information of images. At the same time, semantic incompatibility exists because the feature maps of encoder and decoder are directly connected in the skip connection stage. In addition, in low light scenes such as at night, it is easy for false segmentation and segmentation accuracy to appear. To solve the above problems, a portrait semantic segmentation method based on dual-modal information complementarity is proposed. The encoder adopts a double branch structure, and uses a SK-ASSP module that can adaptively adjust the convolution weights of different receptor fields to extract features in RGB and gray image modes respectively, and carries out cross-modal information complementarity and feature fusion. A hybrid attention mechanism is used in the jump connection phase to capture both the channel and coordinate context information of the image. Experiments on human matting dataset show that the PA and MIoU coefficients of this algorithm model reach 96.58% and 94.48% respectively, which is better than U-net benchmark model and other mainstream semantic segmentation models.

Double Branches and Stages Neural Network for Joint Acoustic Echo and Noise Suppression

Double Branches and Stages Neural Network for Joint Acoustic Echo and Noise Suppression

DBARCT: Road Extraction Based on Double Branch Architecture and Random Block Coding Transformer

DBARCT: Road Extraction Based on Double Branch Architecture and Random Block Coding Transformer

LDHD‐Net: A Lightweight Network With Double Branch Head for Feature Enhancement of UAV Targets in Complex Scenes

The development of small UAV technology has led to the emergence of new challenges in UAV countermeasures. The timely detection of UAVs can effectively prevent potential infringements on airspace and privacy. Currently, methods based on deep learning demonstrate excellent performance in target detection. However, in complex scenes, there is a tendency for false alarms (FAs) and misdetections to occur at a higher rate. To solve these problems, we propose a lightweight infrared small target detection algorithm LDHD‐Net. First, we design a novel Ghost‐Shuffle module in the backbone network to enhance the network feature extraction capability. Meanwhile, we remove redundant layers from the network to make the backbone network more lightweight. Second, we design a hierarchical attention enhancement module in the neck network to improve the saliency of UAV targets and reduce background noise interference. In addition, we design a novel small target detection structure and prediction heads in the shallow layers of the network to improve small target detection accuracy. Finally, we design a novel attention dual‐branch head to reduce interference between different tasks and improve the real‐time performance of algorithm detection. The experimental results show that compared with the original model, inference time remains essentially the same, LDHD‐Net parameters are only 3.9 M and AP improves by 12.6%. Compared to SOTA methods, LDHD‐Net shows better performance on SIDD and Anti‐UAV410 datasets. The algorithm effectively improves the accuracy and real‐time detection of UAVs in complex scenes.