Coordination Modulation Research Articles

Research on a phonocardiogram and electrocardiogram signal classification algorithm based on global group coordinate attention mechanism and multi-scale feature fusion

Purpose In recent years, the incidence of cardiovascular disease has continued to rise, and early screening and prevention are especially critical. Phonocardiography (PCG) and electrocardiography (ECG), as simple, cost-effective and non-invasive tests, are important tools for clinical analysis. However, it is difficult to fully reflect the complexity of the cardiovascular system using PCG or ECG tests alone. Combining the multimodal signals of PCG and ECG can provide complementary information to improve the detection accuracy. Therefore, the purpose of this paper is to propose a multimodal signal classification method based on continuous wavelet transform and improved ResNet18. Design/methodology/approach The classification method is based on the ResNet18 backbone, and the ResNet18 network is improved by embedding the global grouped coordinate attention mechanism module and the improved bidirectional feature pyramid network. Firstly, a data acquisition system was built using a MEMS-integrated PCG-ECG sensor to construct a private data set. Second is the time-frequency transformation of PCG and ECG synchronized signals on public and private data sets using continuous wavelet transform. Finally, the time-frequency images are categorized. Findings The global grouped coordinate attention mechanism and bidirectional feature pyramid network modules proposed in this paper significantly enhance the model’s performance. On public data sets, the method achieves precision, sensitivity, specificity, accuracy and F1 score of 97.96%, 98.51%, 97.58%, 98.08% and 98.23%, respectively, which represent improvements of 3.54%, 3.92%, 4.18%, 4.03% and 3.72% compared to ResNet18. Additionally, it demonstrates a clear advantage over existing mainstream algorithms. On private data sets, the method’s five metrics are 98.15%, 98.76%, 98.08%, 98.42% and 98.45%, further validating the model’s generalization ability. Originality/value The method proposed in this paper not only improves the accuracy and efficiency of the test but also provides an effective solution for early screening and prevention of cardiovascular diseases.

Real-Time Accurate Apple Detection Based on Improved YOLOv8n in Complex Natural Environments

Efficient and accurate apple detection is crucial for the operation of apple-picking robots. To improve detection accuracy and speed, we propose a lightweight apple-detection model based on the YOLOv8n framework. The proposed model introduces a novel Self-Calibrated Coordinate (SCC) attention module, which enhances feature extraction, especially for partially occluded apples, by effectively capturing spatial and channel information. Additionally, we replace the C2f module within the YOLOv8n neck with a Partial Convolution Module improved with Reparameterization (PCMR), which accelerates detection, reduces redundant computations, and minimizes both parameter count and memory access during inference. To further optimize the model, we fuse multi-scale features from the second and third pyramid levels of the backbone architecture, achieving a lightweight design suitable for real-time detection. To address missed detections and misclassifications, Polynomial Loss (PolyLoss) is integrated, enhancing class discrimination for different apple subcategories. Compared to the original YOLOv8n, the improved model increases the mAP by 2.90% to 88.90% and improves the detection speed to 220 FPS, which is 30.55% faster. Additionally, it reduces the parameter count by 89.36% and the FLOPs by 2.47%. Experimental results demonstrate that the proposed model outperforms mainstream object-detection algorithms, including Faster R-CNN, RetinaNet, SSD, RT-DETR-R18, RT-DETR-R34, YOLOv5n, YOLOv6-N, YOLOv7-tiny, YOLOv8n, YOLOv9-T and YOLOv11n, in both mAP and detection speed. Notably, the improved model has been used to develop an Android application deployed on the iQOO Neo6 SE smartphone, achieving a 40 FPS detection speed, a 26.93% improvement over the corresponding deployment of YOLOv8n, enabling real-time apple detection. This study provides a valuable reference for designing efficient and lightweight detection models for resource-constrained apple-picking robots.

Optimizing photocatalysis via electron spin control.

Solar-driven photocatalytic technology holds significant potential for addressing energy crisis and mitigating global warming, yet is limited by light absorption, charge separation, and surface reaction kinetics. The past several years has witnessed remarkable progress in optimizing photocatalysis via electron spin control. This approach enhances light absorption through energy band tuning, promotes charge separation by spin polarization, and improves surface reaction kinetics via strengthening surface interaction and increasing product selectivity. Nevertheless, the lack of a comprehensive and critical review on this topic is noteworthy. Herein, we provide a summary of the fundamentals of electron spin control and the techniques employed to scrutinize the electron spin state of active sites in photocatalysts. Subsequently, we highlight advanced strategies for manipulating electron spin, including doping design, defect engineering, magnetic field regulation, metal coordination modulation, chiral-induced spin selectivity, and combined strategies. Additionally, we review electron spin control-optimized photocatalytic processes, including photocatalytic water splitting, CO2 reduction, pollutant degradation, and N2 fixation, providing specific examples and detailed discussion on underlying mechanisms. Finally, we outline perspectives on further enhancing photocatalytic activity through electron spin manipulation. This review seeks to offer valuable insights to guide future research on electron spin control for improving photocatalytic applications.

Electro-tactile modulation of muscle activation and intermuscular coordination in the human upper extremity

Electro-tactile stimulation (ETS) can be a promising aid in augmenting sensation for those with sensory deficits. Although applications of ETS have been explored, the impact of ETS on the underlying strategies of neuromuscular coordination remains largely unexplored. We investigated how ETS, alone or in the presence of mechano-tactile environment change, modulated the electromyogram (EMG) of individual muscles during force control and how the stimulation modulated the attributes of intermuscular coordination, assessed by muscle synergy analysis, in human upper extremities. ETS was applied to either the thumb or middle fingertip which had greater contact with the handle, grasped by the participant, and supported a target force match. EMGs were recorded from 11 arm muscles of 15 healthy participants during three-dimensional exploratory force control. EMGs were modeled as the linear combination of muscle co-activation patterns (the composition of muscle synergies) and their activation profiles. Individual arm muscle activation changed depending on the ETS location on the finger. The composition of muscle synergies was conserved, but synergy activation coefficients altered reflecting the effects of electro-tactile modulation. The mechano-tactile modulation tended to decrease the effects of ETS on the individual muscle activation and synergy activation magnitude. This study provides insights into sensory augmentation and its impact on intermuscular coordination in the human upper extremity.

Michael and Schiff-Base Reactions-Assisted Fluorescence Sensor Based on the MOF Nanosheet Microspheres for the Effective Discrimination and Detection of Hydroquinone and Catechol.

A novel sensing platform was constructed for the recognition and identification of dihydroxybenzene isomers based on the MOF-0.02TEA fluorescence sensor with the morphology of nanosheet microspheres through coordination modulation. Based on the sensing principle that the amino group on the MOF-0.02TEA can make the Michael reaction with o-benzoquinone and p-benzoquinone, which were individually the oxidation intermediate of catechol and hydroquinone, the fluorescence intensity of MOF-0.02TEA could be quenched through the inner filter effect (IFE) without the interference from resorcinol. Besides, catechol and hydroquinone could be further distinguished with the assistance of the Schiff-base reaction by introducing o-phenylenediamine (OPD) to the detection system. The MOF-0.02TEA sensor exhibited good selectivity, and the detection limits for catechol and hydroquinone were 90.5 nmol/L and 0.52 μmol/L (S/N = 3), respectively. Moreover, the sensor could be used for the determination of dihydroxybenzene isomers in tap water and lake water.

Multi-view brain functional connectivity and hierarchical fusion for EEG-based emotion recognition

Emotional states evolve gradually from their onset to full manifestation, reflected in changes in brain functional connectivity. Existing research often focuses only on the final emotional state, missing the rich, dynamic information of emotional evolution. This paper proposes a novel network framework leveraging global and local brain functional connectivity through a multi-view approach. We introduce a global and local connectivity modeling method using electroencephalogram signals to simulate brain connectivity changes across time and specific moments. A residual-based local detail feature extractor combined with a coordinate attention module captures long-range dependencies and maintains positional accuracy. A global feature extractor is also designed for the effective extraction of emotional information. Finally, a hierarchical multi-scale cross-attention feature fusion module integrates features across different levels to enhance emotion recognition performance and robustness. Extensive experiments on three publicly available datasets demonstrate the framework’s superiority and generalization capability.

Viscoelastic Soft Solid Electrolytes Enable Fast Zinc Ion Conductance and Highly Stable Zinc Metal Anode

AbstractAchieving both high ionic conductance and stable Zn metal anode simultaneously remains a challenge with current liquid and solid electrolytes. Here, a viscoelastic soft solid electrolyte (VSSE) strategy is presented that effectively balances Zn ion conduction and Zn anode stability. The VSSE is created by nano‐SiO2 inducing a liquid‐to‐solid transition in a liquid solution containing Zn(BF4)2 salt dissolved in an oligomer (glycerol polyoxyethylene‐b‐oxypropylene ether, GPE) and water. The plentiful oxygen functional group in VSSE provides enough hydrogen bonding sites for water molecules to be completely hydrogen‐bonded to form a state without free water. The bound water serves as a Zn‐O coordination modulator that can weaken the strong Zn‐O coordination, lowering the dissociation energy for Zn ions, realizing fast Zn ion decoupling motion mode. Consequently, the VSSE gives impressive Zn ion conductance of (2.28 ± 0.07) ×10−3 S cm−1 at room temperature 10–1000 times higher than reported solid polymer electrolytes. Simultaneously, the restricted molecular activity of bound water allows for excellent storage/cycle life of the Zn metal anode, which is confirmed by remarkably improved storage life (720 h), shelving‐recovery lifespan (850–1200 h), and cycling life (1400–2050 h). This study offers fresh perspectives on multifunctional electrolyte design strategies based on soft‐matter science.

The Impact of High-Flow Nasal Oxygen Therapy on Swallowing Function and Aspiration in Patients and Healthy Adults: A Scoping Review.

High-flow nasal oxygen therapy (HFNO) is highly versatile and employed in varied situations, including after extubation, in cases of respiratory failure, and at the end of life. However, its impact on swallowing function is not yet elucidated. Therefore, this scoping review aimed to clarify how HFNO affects swallowing function and whether itposes a risk for aspiration pneumonia. We searched thedatabasesMEDLINE via PubMed, CINAHL, Web of Science, and Cochrane Central Register of Controlled Trials (CENTRAL) from inception till June 5, 2024, to gather relevant studies. No language restrictions were applied. The eligibility criteria were as follows: (1) studies involving adults using HFNO, (2) studies examining swallowing function and the occurrence of pneumonia, and (3) excluding gray literature such as conference proceedings. A total of 1449 articles were initially identified, of which 12 that met theinclusion criteria were included in the final analysis. Of them, five involved healthy adults, whereas seven involved patients. Six studies investigated the effects of flow rate on the swallowing function, five studies on healthy adults, and one on patients. The review findings indicated that as the flow rate increased, the swallowing function was affected by the shortening of the latency time of the swallowing response and laryngeal vestibular closure time. Additionally, the increase in the flow rate caused modulation of the swallowing-breathing coordination. However, none of the studies reported that HFNO increases the incidence of pneumonia. The increased flow rates of HFNO affect the swallowing function; however, the actual impact on patients is currently unknown. This study involved a small number of healthy adults; therefore, further research based on the patient characteristics is warranted.

CCW-YOLO: A Modified YOLOv5s Network for Pedestrian Detection in Complex Traffic Scenes

In traffic scenes, pedestrian target detection faces significant issues of misdetection and omission due to factors such as crowd density and obstacle occlusion. To address these challenges and enhance detection accuracy, we propose an improved CCW-YOLO algorithm. The algorithm first introduces a lightweight convolutional layer using GhostConv and incorporates an enhanced C2f module to improve the network’s detection performance. Additionally, it integrates the Coordinate Attention module to better capture key points of the targets. Next, the bounding box loss function CIoU loss at the output of YOLOv5 is replaced with WiseIoU loss to enhance adaptability to various detection scenarios, thereby further improving accuracy. Finally, we develop a pedestrian count detection system using PyQt5 to enhance human–computer interaction. Experimental results on the INRIA public dataset showed that our algorithm achieved a detection accuracy of 98.4%, representing a 10.1% improvement over the original YOLOv5s algorithm. This advancement significantly enhances the detection of small objects in images and effectively addresses misdetection and omission issues in complex environments. These findings have important practical implications for ensuring traffic safety and optimizing traffic flow.

Category-Level Pose Estimation and Iterative Refinement for Monocular RGB-D Image

Category-level pose estimation is proposed to predict the 6D pose of objects under a specific category and has wide applications in fields such as robotics, virtual reality, and autonomous driving. With the development of VR/AR technology, pose estimation has gradually become a research hotspot in 3D scene understanding. However, most methods fail to fully utilize geometric and color information to solve intra-class shape variations, which leads to inaccurate prediction results. To solve the above problems, we propose a novel pose estimation and iterative refinement network, use an attention mechanism to fuse multi-modal information to obtain color features after a coordinate transformation, and design iterative modules to ensure the accuracy of object geometric features. Specifically, we use an encoder-decoder architecture to implicitly generate a coarse-grained initial pose and refine it through an iterative refinement module. In addition, due to the differences between rotation and position estimation, we design a multi-head pose decoder that utilizes the local geometry and global features. Finally, we design a transformer-based coordinate transformation attention module to extract pose-sensitive features from RGB images and supervise color information by correlating point cloud features in different coordinate systems. We train and test our network on the synthetic dataset CAMERA25 and the real dataset REAL275. Experimental results show that our method achieves state-of-the-art performance on multiple evaluation metrics.

DDKG: A Dual Domain Knowledge Guidance strategy for localization and diagnosis of non-displaced femoral neck fractures

X-ray is the primary tool for diagnosing fractures, crucial for determining their type, location, and severity. However, non-displaced femoral neck fractures (ND-FNF) can pose challenges in identification due to subtle cracks and complex anatomical structures. Most deep learning-based methods for diagnosing ND-FNF rely on cropped images, necessitating manual annotation of the hip location, which increases annotation costs. To address this challenge, we propose Dual Domain Knowledge Guidance (DDKG), which harnesses spatial and semantic domain knowledge to guide the model in acquiring robust representations of ND-FNF across the whole X-ray image. Specifically, DDKG comprises two key modules: the Spatial Aware Module (SAM) and the Semantic Coordination Module (SCM). SAM employs limited positional supervision to guide the model in focusing on the hip joint region and reducing background interference. SCM integrates information from radiological reports, utilizes prior knowledge from large language models to extract critical information related to ND-FNF, and guides the model to learn relevant visual representations. During inference, the model only requires the whole X-ray image for accurate diagnosis without additional information. The model was validated on datasets from four different centers, showing consistent accuracy and robustness. Codes and models are available at https://github.com/Yjing07/DDKG.

Research and application on deep learning-based point cloud completion for marine structures with point coordinate fusion and coordinate-supervised point cloud generator

The problem of missing point clouds is prevalent in the actual point clouds of Marine Structures (MS) obtained based on three-dimensional laser scanning technology. To achieve the completion tasks for MS, this paper proposes a deep learning network, MS-PCN, and builds a point cloud completion dataset, MS-dataset. MS-PCN employs both point coordinate fusion module and coordinate-supervised point cloud generator to improve the accuracy of point cloud completion for MS. Extensive experiments conducted on MS-dataset and public dataset ShapeNet-55 demonstrate the effectiveness of MS-PCN in point cloud completion within scenarios featuring MS as well as its generalizability in other scenarios. MS-PCN achieved a Chamfer Distance (CD) of 0.31 and an F-score of 0.58 on MS-dataset and a CD of 0.70 and an F-score of 0.505 on ShapeNet-55 dataset. Furthermore, point cloud completion could serve as a valuable precursor to the surface reconstruction of MS, improving its reconstruction accuracy and visualization effects.

Asymmetric coordinative modulation boosting the activity and thermal stability of Pt1/CeO2 for CO oxidation under harsh condition

Supported metal catalysts play a central role in chemical industry, but it remains a formidable challenge to realize high activity while maintaining atomically dispersed status to maximize atom efficiency under harsh conditions. Herein, a novel strategy of constructing asymmetric coordination Pt active sites via coating N-doped carbon onto ceria supported Pt single atoms (Pt1/CeO2@CN) is proposed, through which superior low-temperature CO oxidation activity and satisfactory thermal stability are achieved simultaneously. Experimental and density functional theory results confirm that the unique asymmetric N2-Pt1-O2 coordinative configuration on Pt1/CeO2@CN tailors the electronic properties of Pt 5d states, increasing the turnover frequency by 15 times for CO oxidation at 120 °C compared with that on Pt1/CeO2 and sustaining the atomically dispersed status of Pt at as high as 400 °C under H2-containing atmosphere. This strategy suggests a promising avenue to fabricating highly active and stable supported metal catalysts for practical applications under harsh conditions.

A Cloud Detection Network Based on Adaptive Laplacian Coordination Enhanced Cross-Feature U-Net.

Cloud cover experiences rapid fluctuations, significantly impacting the irradiance reaching the ground and causing frequent variations in photovoltaic power output. Accurate detection of thin and fragmented clouds is crucial for reliable photovoltaic power generation forecasting. In this paper, we introduce a novel cloud detection method, termed Adaptive Laplacian Coordination Enhanced Cross-Feature U-Net (ALCU-Net). This method augments the traditional U-Net architecture with three innovative components: an Adaptive Feature Coordination (AFC) module, an Adaptive Laplacian Cross-Feature U-Net with a Multi-Grained Laplacian-Enhanced (MLE) feature module, and a Criss-Cross Feature Fused Detection (CCFE) module. The AFC module enhances spatial coherence and bridges semantic gaps across multi-channel images. The Adaptive Laplacian Cross-Feature U-Net integrates features from adjacent hierarchical levels, using the MLE module to refine cloud characteristics and edge details over time. The CCFE module, embedded in the U-Net decoder, leverages criss-cross features to improve detection accuracy. Experimental evaluations show that ALCU-Net consistently outperforms existing cloud detection methods, demonstrating superior accuracy in identifying both thick and thin clouds and in mapping fragmented cloud patches across various environments, including oceans, polar regions, and complex ocean-land mixtures.

MRS‐Net: Brain tumour segmentation network based on feature fusion and attention mechanism

AbstractAccurate segmentation of brain tumor magnetic resonance imaging (MRI) is crucial for treatment planning. Addressing the challenges of complex tumor structures and inadequate cross‐channel information utilization in Unet‐based segmentation, this paper proposes the multi‐scale residual brain tumor MRI segmentation network (MRS‐Net) incorporating an attention mechanism to enhance segmentation accuracy. First, the double residual feature fusion module is utilized to enhance the fusion of feature information between different levels. Second, the Atrous Spatial Pyramid Pooling is introduced as a bridging module of the network to capture the features at different scales of the image, so as to enhance the extraction capability of the network for detailed features. Finally, the inverted residual coordinate attention module replaces the direct splicing in Unet to fuse the large feature information at each level and scale, thus enhancing the model's ability to recognize the spatial location information of brain tumors. The Dice coefficients, positive predictive values (PPVs), sensitivities (Sensitivity) and Hausdorff distance (HD), which are the four evaluation indexes, reach 84.54%, 87.43%, 88.37% and 2.248, respectively, which are improved by 1.85%, 2.11%, 2.88% and 6.0%, respectively, compared with Unet. The experimental results show that MRS‐Net achieves better brain tumor image segmentation.

The impact of amorphous-crystal interface on photoresponse in oxide semiconductor InGaZnO4

The photoresponse of an oxide semiconductor is influenced by lattice distortion, which can be adjusted through atomic coordination status. Typically, the modulation of atomic coordination and photoresponse involves introducing oxygen vacancy (VO) density. In addition to VO, the interface exhibits varying degrees of lattice distortion and may offer an efficient means for modulating photoresponse. Therefore, investigating the interface dependence of photoresponse is both warranted and lacking in current research. Herein, we utilize an amorphous-crystal interface in an InGaZnO4 film to modulate its photoresponse. Compared to films without such interfaces, those with interfaces demonstrate a higher illumination-to-dark current ratio and a slower decay rate of photocurrent upon removal of illumination.

Point cloud upsampling network based on pyramid pooling and self-attention mechanism

For the problems of irregular point cloud data and non-unique input size, a point-cloud upsampling network (PPSA-PU) based on Pyramid Pooling and Self-Attention mechanism is proposed. Multi-scale features are first extracted from the input point cloud using dense map convolution with different expansion rates, and the pyramid pooling module and self-attention mechanism are added. By applying the same pooling operation to regions of different sizes and numbers, the network is made to accept inputs of arbitrary size. Self-attention is used to weight the features to establish global correlation and improve the feature extraction capability. The features are then extended by the Self-Attention NodeShuffle (SA-NS) module, which uses a graph convolution layer to fuse neighbour information and learn new point features from the latent space. Finally, the coordinate reconstruction module is used to generate a dense up-sampled point cloud. Using the existing dataset to train and test the network and compare it with the existing up-sampling network, the experimental results show that PPSA-PU is better in terms of evaluation metrics and performance, and has better generalisation and robustness.

Early diagnosis of Alzheimer’s disease using a group self-calibrated coordinate attention network based on multimodal MRI

Convolutional neural networks (CNNs) for extracting structural information from structural magnetic resonance imaging (sMRI), combined with functional magnetic resonance imaging (fMRI) and neuropsychological features, has emerged as a pivotal tool for early diagnosis of Alzheimer’s disease (AD). However, the fixed-size convolutional kernels in CNNs have limitations in capturing global features, reducing the effectiveness of AD diagnosis. We introduced a group self-calibrated coordinate attention network (GSCANet) designed for the precise diagnosis of AD using multimodal data, including encompassing Haralick texture features, functional connectivity, and neuropsychological scores. GSCANet utilizes a parallel group self-calibrated module to enhance original spatial features, expanding the field of view and embedding spatial data into channel information through a coordinate attention module, which ensures long-term contextual interaction. In a four-classification comparison (AD vs. early MCI (EMCI) vs. late MCI (LMCI) vs. normal control (NC)), GSCANet demonstrated an accuracy of 78.70%. For the three-classification comparison (AD vs. MCI vs. NC), it achieved an accuracy of 83.33%. Moreover, our method exhibited impressive accuracies in the AD vs. NC (92.81%) and EMCI vs. LMCI (84.67%) classifications. GSCANet improves classification performance at different stages of AD by employing group self-calibrated to expand features receptive field and integrating coordinated attention to facilitate significant interactions among channels and spaces. Providing insights into AD mechanisms and showcasing scalability for various disease predictions.

Efficient urinary stone type prediction: a novel approach based on self-distillation

Urolithiasis is a leading urological disorder where accurate preoperative identification of stone types is critical for effective treatment. Deep learning has shown promise in classifying urolithiasis from CT images, yet faces challenges with model size and computational efficiency in real clinical settings. To address these challenges, we developed a non-invasive prediction approach for determining urinary stone types based on CT images. Through the refinement and improvement of the self-distillation architecture, coupled with the incorporation of feature fusion and the Coordinate Attention Module (CAM), we facilitated a more effective and thorough knowledge transfer. This method circumvents the extra computational expenses and performance reduction linked with model compression and removes the reliance on external teacher models, markedly enhancing the efficacy of lightweight models. achieved a classification accuracy of 74.96% on a proprietary dataset, outperforming current techniques. Furthermore, our method demonstrated superior performance and generalizability on two public datasets. This not only validates the effectiveness of our approach in classifying urinary stones but also showcases its potential in other medical image processing tasks. These results further reinforce the feasibility of our model for actual clinical deployment, potentially assisting healthcare professionals in devising more precise treatment plans and reducing patient discomfort.

Full-field displacement measurements of structural vibrations using a novel two-stage neural network

This paper presents a novel two-stage neural network for quantifying full-field displacements of vibrating structures. A graphics software was used to simulate structural vibrations with random displacement fields and generate image datasets through batch rendering. Subsequently, a two-stage neural network model comprising an object segmentation subnetwork for extracting structural shapes and an optical-flow subnetwork for identifying displacement fields was constructed. A coordinate convolution module was embedded in the optical-flow estimation model and the two subnetworks were integrated to develop a comprehensive model. An experiment was designed to monitor the vibration displacements in a cantilever column. The results showed that the proposed model achieved optimal recognition accuracy with a mean absolute error of 0.1477 pixels and root-mean-squared error of 0.2335 pixels. Additionally, it exhibited robustness to various lighting conditions. Furthermore, case studies on real-world structural vibration videos substantiated the practical engineering application value of the proposed model.