Multilayer Aggregates Research Articles

Design of Chinese painting style classification model based on multi-layer aggregation CNN

This study delves deeply into exploring the artistic value of traditional Chinese painting (TCP) and aims to bridge the gap between its fundamental characteristics and the realm of human emotions. To achieve this, a novel convolutional neural network (CNN)-based classification model for TCP emotions is proposed. By thoroughly analyzing the distinct emotional mapping relationships inherent in TCP, a comprehensive framework is developed. Notably, emotional feature regions are accurately extracted using image saliency, and a multi-layer aggregation recalibrated emotional feature module is seamlessly integrated into the CNN network structure. This integration strengthens the activation of features that significantly influence TCP emotions. Moreover, a method of multi-category weighted activation localization is skillfully employed to classify Chinese painting emotions within the CMYK (cyan magenta yellow black) color space. The empirical results convincingly demonstrate that our algorithm surpasses existing approaches such as VGG-19, GoogLeNet, ResNet-50, and WSCNet in the task of TCP emotion recognition, achieving an impressive accuracy of 92.36%, the largest error is 0.191. This improvement signifies the advancements made by our model in accurately capturing and understanding the emotional nuances within TCP. By outperforming previous methods, our research contributes to the convergence of multimedia technology and cultural education.

Decoupled semantic graph neural network for knowledge graph embedding

Knowledge graph embedding (KGE) learns an embedding space for a more accurate representation of entities and relations. Although the KGE model has proliferated, it often fails to fully capture the rich semantics in knowledge graphs. Some studies attempt to apply decoupling methods to decompose node representations, yet they neglect the semantic noise generated during the decoupled process. To address these issues, we introduce the decoupled semantic graph network for KGE (named DSGNet), which employs a novel approach that combines semantic decoupling with structural awareness. DSGNet begins by projecting the knowledge graph into distinct semantic spaces, ensuring minimal correlation between them to achieve effective semantic decoupling. To mitigate semantic noise, a top-k sampling technique is applied to the decoupled graphs. DSGNet then aggregates these different semantic graphs using a relation-aware aggregation module, followed by a multi-layer aggregation process for enhanced node representation. The extensive experiments demonstrate that DSGNet performs competitively on two popular datasets. We make our code publicly available at https://github.com/HubuKG/DSGNet.

Research on group decision optimization and influence analysis in social network based on machine learning

With the rapid development of online social networks, the research on group decision-making in social networks has attracted extensive attention. Social networks facilitate interaction and behavior between individuals, businesses, and organizations. However, traditional group decision-making methods often ignore the social relationships between group members and fail to fully consider the impact of these relationships on subgroup division. In this work, we propose a novel model approach that combines graph neural networks and deep learning techniques to capture and analyze complex relational structures in social networks. The model uses node features and edge features to optimize the group decision-making process and effectively evaluate the influence between individuals through multi-layer network embedding and aggregation operations. Experimental analysis results show that the proposed method performs well in improving the accuracy and efficiency of decision-making, and significantly improves the quality of decision-making.

A study on the emulsification ability and oil displacement efficiency of polymeric surfactant in porous media

In order to comprehensively comprehend the distinctions in solution properties, emulsification characteristics, and oil displacement efficiency between polymeric surfactant(DG-1) and traditional polymers or surfactants, a comparative analysis was initially conducted on the microstructure, main functional group types, and macroscopic properties. Subsequently, core displacement experiments were employed to elucidate the emulsification capability, emulsion stability, and oil displacement properties of polymeric surfactants. The microscopic displacement experiment was ultimately conducted to investigate the residual oil displacement process in the core following polymer displacement by DG-1, thereby elucidating the underlying mechanisms of microscopic oil displacement by DG-1. The results indicate DG-1 has a molecular structure with a regional network aggregation state as a whole, and a multi-layer aggregation and overlapping structure in space. DG-1exhibits higher viscosity and lower interfacial tension due to the larger molecular coil dimension compared to the equivalent concentration of polymers. The emulsification ability of DG-1 is robust, with emulsion stability positively correlated to oil-polymer ratio and concentration while negatively correlated to migration distance. Core displacement experiments results indicate the polymer-surfactant system (SP) and DG-1 exhibited comparable oil displacement effects, with oil recovery of 54.5 % and 52.4 %, respectively, both surpassing the recovery achieved by the polymer alone (46.9 %). In heterogeneous reservoirs, SP acts as the dominant displacer in regions with moderate and high permeability, whereas DG-1 assumes dominance in regions with moderate and low permeability. The microscopic displacement experiments revealed that DG-1 activated the clustered residual oil as the predominant type of residual oil in porous media, followed by columnar and block residual oil, with film residual oil exhibiting the least activation. Primary mechanisms for oil displacement include extended sweeping volume, shear and carrying effects on the residual oil, and eddy displacement of the residual oil by the emulsion.

Whisper-SV: Adapting Whisper for low-data-resource speaker verification

Trained on 680,000 h of massive speech data, Whisper is a multitasking, multilingual speech foundation model demonstrating superior performance in automatic speech recognition, translation, and language identification. However, its applicability in speaker verification (SV) tasks remains unexplored, particularly in low-data-resource scenarios where labeled speaker data in specific domains are limited. To fill this gap, we propose a lightweight adaptor framework to boost SV with Whisper, namely Whisper-SV. Given that Whisper is not specifically optimized for SV tasks, we introduce a representation selection module to quantify the speaker-specific characteristics contained in each layer of Whisper and select the top-k layers with prominent discriminative speaker features. To aggregate pivotal speaker-related features while diminishing non-speaker redundancies across the selected top-k distinct layers of Whisper, we design a multi-layer aggregation module in Whisper-SV to integrate multi-layer representations into a singular, compacted representation for SV. In the multi-layer aggregation module, we employ convolutional layers with shortcut connections among different layers to refine speaker characteristics derived from multi-layer representations from Whisper. In addition, an attention aggregation layer is used to reduce non-speaker interference and amplify speaker-specific cues for SV tasks. Finally, a simple classification module is used for speaker classification. Experiments on VoxCeleb1, FFSVC, and IMSV datasets demonstrate that Whisper-SV achieves EER/minDCF of 2.22%/0.307, 6.14%/0.488, and 7.50%/0.582, respectively, showing superior performance in low-data-resource SV scenarios.

Combining dual attention mechanism and efficient feature aggregation for road and vehicle segmentation from UAV imagery

Unmanned aerial vehicles (UAVs) have gained significant popularity in recent years due to their ability to capture high-resolution aerial imagery for various applications, including traffic monitoring, urban planning, and disaster management. Accurate road and vehicle segmentation from UAV imagery plays a crucial role in these applications. In this paper, we propose a novel approach combining dual attention mechanisms and efficient multi-layer feature aggregation to enhance the performance of road and vehicle segmentation from UAV imagery. Our approach integrates a spatial attention mechanism and a channel-wise attention mechanism to enable the model to selectively focus on relevant features for segmentation tasks. In conjunction with these attention mechanisms, we introduce an efficient multi-layer feature aggregation method that synthesizes and integrates multi-scale features at different levels of the network, resulting in a more robust and informative feature representation. Our proposed method is evaluated on the UAVid semantic segmentation dataset, showcasing its exceptional performance in comparison to renowned approaches such as U-Net, DeepLabv3+, and SegNet. The experimental results affirm that our approach surpasses these state-of-the-art methods in terms of segmentation accuracy.

Combining transformer global and local feature extraction for object detection

Convolutional neural network (CNN)-based object detectors perform excellently but lack global feature extraction and cannot establish global dependencies between object pixels. Although the Transformer is able to compensate for this, it does not incorporate the advantages of convolution, which results in insufficient information being obtained about the details of local features, as well as slow speed and large computational parameters. In addition, Feature Pyramid Network (FPN) lacks information interaction across layers, which can reduce the acquisition of feature context information. To solve the above problems, this paper proposes a CNN-based anchor-free object detector that combines transformer global and local feature extraction (GLFT) to enhance the extraction of semantic information from images. First, the segmented channel extraction feature attention (SCEFA) module was designed to improve the extraction of local multiscale channel features from the model and enhance the discrimination of pixels in the object region. Second, the aggregated feature hybrid transformer (AFHTrans) module combined with convolution is designed to enhance the extraction of global and local feature information from the model and to establish the dependency of the pixels of distant objects. This approach compensates for the shortcomings of the FPN by means of multilayer information aggregation transmission. Compared with a transformer, these methods have obvious advantages. Finally, the feature extraction head (FE-Head) was designed to extract full-text information based on the features of different tasks. An accuracy of 47.0% and 82.76% was achieved on the COCO2017 and PASCAL VOC2007 + 2012 datasets, respectively, and the experimental results validate the effectiveness of our method.

MHGCN+: Multiplex Heterogeneous Graph Convolutional Network

Heterogeneous graph convolutional networks have gained great popularity in tackling various network analytical tasks on heterogeneous graph data, ranging from link prediction to node classification. However, most existing works ignore the relation heterogeneity with multiplex networks between multi-typed nodes and the different importance of relations in meta-paths for node embedding, which can hardly capture the heterogeneous structure signals across different relations. To tackle this challenge, this work proposes a M ultiplex H eterogeneous G raph C onvolutional N etwork (MHGCN+) for multiplex heterogeneous network embedding. Our MHGCN+ can automatically learn the useful heterogeneous meta-path interactions of different lengths with different importance in multiplex heterogeneous networks through multi-layer convolution aggregation. Additionally, we effectively integrate both multi-relation structural signals and attribute semantics into the learned node embeddings with both unsupervised and semi-supervised learning paradigms. Extensive experiments on seven real-world datasets with various network analytical tasks demonstrate the significant superiority of MHGCN+ against state-of-the-art embedding baselines in terms of all evaluation metrics. The source code of our method is available at: https://github.com/FuChF/MHGCN-plus .

DeepDynaForecast: Phylogenetic-informed graph deep learning for epidemic transmission dynamic prediction.

In the midst of an outbreak or sustained epidemic, reliable prediction of transmission risks and patterns of spread is critical to inform public health programs. Projections of transmission growth or decline among specific risk groups can aid in optimizing interventions, particularly when resources are limited. Phylogenetic trees have been widely used in the detection of transmission chains and high-risk populations. Moreover, tree topology and the incorporation of population parameters (phylodynamics) can be useful in reconstructing the evolutionary dynamics of an epidemic across space and time among individuals. We now demonstrate the utility of phylodynamic trees for transmission modeling and forecasting, developing a phylogeny-based deep learning system, referred to as DeepDynaForecast. Our approach leverages a primal-dual graph learning structure with shortcut multi-layer aggregation, which is suited for the early identification and prediction of transmission dynamics in emerging high-risk groups. We demonstrate the accuracy of DeepDynaForecast using simulated outbreak data and the utility of the learned model using empirical, large-scale data from the human immunodeficiency virus epidemic in Florida between 2012 and 2020. Our framework is available as open-source software (MIT license) at github.com/lab-smile/DeepDynaForcast.

Optical assembly of multi-particle arrays by opto-hydrodynamic binding of microparticles close to a one-dimensional chain of magnetic microparticles.

Two-dimensional materials possess a large number of interesting and important properties. Various methods have been developed to assemble two-dimensional aggregates. Assembly of colloidal particles can be achieved with laser-heating-induced thermal convective flow. In this paper, an opto-hydrodynamic binding method is proposed to assemble colloidal particles dispersed in a solution into multilayer structures. First, we use polystyrene (PS) microspheres to study the feasibility and characteristics of the assembly method. PS microspheres and monodispersed magnetic silica microspheres (SLEs) are dispersed in a solution to form a binary mixture system. Under the action of an external uniform magnetic field, SLEs in the solution form chains. An SLE chain is heated by a laser beam. Due to the photothermal effect, the SLE chain is heated to produce a thermal gradient, resulting in thermal convection. The thermal convection drives the PS beads to move toward the heated SLE chain and finally stably assemble into multilayer aggregates on both sides of the SLE chain. The laser power affects the speed and result of the assembly. When the laser power is constant, the degree of constraint of the PS microbeads in different layers is also different. At the same time, this method can also assemble the biological cells, and the spacing of different layers of cells can be changed by changing the electrolyte concentration of the solution. Our work provides an approach to assembling colloidal particles and cells, which has a potential application in the analysis of the collective dynamics of microparticles and microbes.

Transformer-Based Multi-layer Feature Aggregation and Rotated Anchor Matching for Oriented Object Detection in Remote Sensing Images

Transformer-Based Multi-layer Feature Aggregation and Rotated Anchor Matching for Oriented Object Detection in Remote Sensing Images

Influence of Surface Roughness on Interfacial Properties of Particle Networks

The behavior of colloidal particles near fluid interfaces has attracted significant scientific interest, as particles minimize the contact area between the two fluid phases, stabilizing interfacial systems. This study explores the influence of surface roughness on the properties of particle monolayers at the air–water interface, focusing on colloidal silica particles and fumed silica particles of similar hydrodynamic diameter. This research involves comparing low-surface-area (LSA) and medium-surface-area (MSA) fumed silica particles with spherical colloidal silica particles (250 nm in diameter). Utilizing a Langmuir trough, the interfacial particle networks are compressed and expanded. Analysis of surface pressure isotherms reveals that fumed silica particle monolayers form networks at a lower particle surface coverage compared to spherical particles. The spherical particle monolayer exhibits a higher apparent surface elasticity, indicating greater resistance to the applied compression compared to fumed silica networks. Additionally, monolayers formed by fumed silica particles display hysteresis even after successive compressions and expansions due to irreversible particle interlocking and the formation of multilayered aggregates. These findings provide insights into the impact of surface roughness on the behavior of particle monolayers at fluid interfaces, offering valuable information for designing and optimizing mechanisms involved in emulsion and foam stabilization.

Synergistic role of activated CD4+ memory T cells and CXCL13 in augmenting cancer immunotherapy efficacy

The development of immune checkpoint inhibitors (ICIs) has significantly advanced cancer treatment. However, their efficacy is not consistent across all patients, underscoring the need for personalized approaches. In this study, we examined the relationship between activated CD4+ memory T cell expression and ICI responsiveness. A notable correlation was observed between increased activated CD4+ memory T cell expression and better patient survival in various cohorts. Additionally, the chemokine CXCL13 was identified as a potential prognostic biomarker, with higher expression levels associated with improved outcomes. Further analysis highlighted CXCL13's role in influencing the Tumor Microenvironment, emphasizing its relevance in tumor immunity. Using these findings, we developed a deep learning model by the Multi-Layer Aggregation Graph Neural Network method. This model exhibited promise in predicting ICI treatment efficacy, suggesting its potential application in clinical practice.

SR-MACL: Session-Based Recommendation with Multi-layer Aggregation Augmentation in Contrastive Learning

Session-based recommendation (SBR) aims to predict the next item of interest in chronological order based on a given sequence of short-term behaviour of anonymous users. Due to the limited data available for short-term user interactions, its performance is more susceptible to data sparsity problems than traditional recommendation methods. Contrastive learning is often used to solve the data sparsity problem due to its ability to extract general features from the raw data. Existing session-based recommendation methods based on graph contrastive learning typically build graph contrastive learning by using information from other sessions to generate augmented views. While this avoids the problem that the use of dropout in traditional contrast learning methods can cause damage to the session context, it inevitably introduces irrelevant item information, which interferes with accurately modelling user interests and leads to sub-optimal model performance. To address these issues, we propose a new session recommendation method based on multi-layer aggregation augmentation contrastive learning, namely SR-MACL. In SR-MACL we construct a contrastive view by adding noise to the embedding representation and forming a contrastive embedding representation by multi-layer aggregation, which not only effectively solves the problem that traditional graph enhancement methods can destroy the context of the whole session, but also avoids the interference of irrelevant items. Experimental results on three real datasets have shown that SR-MACL can improve the accuracy of recommendation results and predict the user's next interaction more effectively.

Experimental analysis of compression bearing characteristics of multi-layer geogrid-encased aggregate column based on digital image measurement technology

Multi-layer geogrid-encased aggregate column(GEAC) has enhanced bearing performance, cost-effectiveness, and eco-friendliness for soft ground treatment due to the extra lateral confinement from the multi-layer geogrid encasement. To analyze the bearing behavior of GEAC, indoor compression tests were conducted on GEAC with different aggregate sizes, aspect ratios, and encasement layers, using digital image measurement and other techniques. The effects of these parameters on the failure mode, load capacity, and aggregate displacement of GEAC were investigated. The results indicate that: among the aspect ratio, encasement layer, and aggregate size, the encasement layer is the most influential factor on the bearing performance of GEAC, and increasing the number of encasement layers can significantly enhance the load capacity of GEAC; the failure mode of GEAC is buckling when the aspect ratio exceeds 5.33, and is bulging when the aspect ratio is equal to or less than 5.33; in the local region of GEAC, the remarkable horizontal relative displacement of the aggregates is the main cause of the shear band formation; under unconfined compression, the “net pocket effect” of the multi-layer geogrid encasement layer prevents the local stress concentration in GEAC, which helps to resist local failure and delay the yielding and failure of GEAC. Under confined compression, the overlapping part of the multi-layer encasement also increases the lateral contact area between GEAC and the surrounding soil, enhances the radial confinement and the lateral friction of the soil on GEAC, effectively improves the ultimate load capacity, and reduces the compression of GEAC.

Cathodoluminescence spectroscopy of monolayer hexagonal boron nitride

Cathodoluminescence (CL) spectroscopy is a suitable technique for studying the luminescent properties of optoelectronic materials because CL has no limitation on the excitable bandgap energy and eliminates ambiguous signals due to simple light scattering and resonant Raman scattering potentially involved in the photoluminescence spectra. However, direct CL measurements of atomically thin two-dimensional materials have been difficult due to the small excitation volume that interacts with high-energy electron beams. Herein, distinct CL signals from a monolayer hexagonal BN (hBN), namely mBN, epitaxial film grown on a graphite substrate are shown by using a CL system capable of large-area and surface-sensitive excitation. Spatially resolved CL spectra at 13 K exhibited a predominant 5.5-eV emission band, which has been ascribed to originate from multilayered aggregates of hBN, markedly at thicker areas formed on the step edges of the substrate. Conversely, a faint peak at 6.04 ± 0.01 eV was routinely observed from atomically flat areas, which is assigned as being due to the recombination of phonon-assisted direct excitons of mBN. The CL results support the transition from indirect bandgap in bulk hBN to direct bandgap in mBN. The results also encourage one to elucidate emission properties of other low-dimensional materials by using the present CL configuration.

Deep matched filtering for retinal vessel segmentation

The structure of the retinal vascular tree can reflect many indicators of ophthalmic health status. Retinal vessel segmentation, an important basis for the quantitative analysis of vascular structure, has been developed over decades. However, in the areas of imaging quality and contrast, there are still vascular ruptures and missed detection by existing methods. Moreover, the problem of false positives caused by existing lesions has not been properly addressed. Inspired by the primary visual cortex of the biological visual system, this paper proposes Anisotropic Perceptive Convolution (APC) and Anisotropic Enhancement Module (AEM) to model visual cortex cells and their orientation selection mechanism, respectively, as well as a novel network named W-shaped Deep Matched Filtering (WS-DMF) having a W-shaped overall framework. In the feature extraction backbone, a DMF based on a multilayer aggregation of APC is designed to enhance vascular features and inhibit the expression of pathological features. In addition, AEMs are embedded into DMF to enhance the orientation and position information of high-dimensional features. Furthermore, in order to enhance the ability of APC for perceiving linear textures (such as blood vessels), an Orientation Anisotropic Loss (OAL) is introduced. Based on experiments on several widely used datasets and several professional vessel segmentation metrics, the proposed method exhibits strong abilities of vessel extraction and lesion inhibition, surpassing many state-of-the-art algorithms. The results indicate the potential value of WS-DMF in clinical practice. The source code is available at https://www.github.com/tyb311/WS-DMF.

SFA-guided mosaic transformer for tracking small objects in snapshot spectral imaging

This paper presents an end-to-end solution, the Spectral Filter Array (SFA)-guided Mosaic Transformer (SMT), designed for tracking small objects within mosaic spectral videos captured by snapshot spectral cameras. Tracking small objects amidst complex scenes poses greater challenges due to their variable appearances and limited feature representation. Spectral imaging, leveraging spectral and spatial information to characterize the material properties of objects, offers enhanced object feature discrimination compared to conventional visual imaging, making it an ideal choice for this task. Existing spectral tracking techniques, however, fall short in delivering satisfactory results for small objects due to their disruption of spatial-spectral aliasing correlations or disregard for small object characteristics. Hence, the proposed SMT leverages SFA guidance to model and aggregate multi-layer features effectively. Comprising the SFA-guided mosaic backbone (SMB), Multi-layer Feature Aggregation (MFA), and Prediction Head, SMT extracts hierarchical features directly from mosaic spectral images, amalgamates interdependencies between shallow-layer detail and deep-layer semantic information, and precisely locates small objects. Experiment results on our curated fully-annotated mosaic spectral small object tracking dataset, alongside a public normal-sized object tracking dataset, showcase SMT’s prowess in adeptly tracking small objects amidst challenging scenarios such as occlusion and drift. Specifically, our SMT achieves gains ranging from 0.3% to 5.3% in average precision rate and from 2.0% to 5.1% in average success rate over the second-ranked trackers across various challenging attributes. The dataset and code are available at: https://github.com/Chenlulu1993/SMT.

Heterogeneous aggregation between microplastics and microalgae: May provide new insights for microplastics removal

Existing studies have shown that microplastics (MPs) as artificial surfaces can be colonized by plankton microorganisms. However, systematic research on exploring the aggregation formation process of MPs and microalgae is still lacking and particularly the influencing factors of aggregation remain to be elucidated. Therefore, this study investigated the heterogeneous aggregation process between various microalgal species (i.e., Chlorella vulgaris, Scenedesmus obliquus, Tetraselmis subcordiformis, Chaetoceros müelleri and Streptococcus westermani) and MPs (i.e., mPS and mPLA) with different sizes (i.e., 74 μm and 613 μm), concentrations (i.e., 0.1 g/L, 1 g/L and 2 g/L) and shapes (i.e., the particle and sheet). The results showed that microalgae can first attach to the holes or protrusions of MPs and highly accumulate in the local region, and then multi-layer aggregation can be formed subsequently. The aggregation degree between MPs and microalgae was closely related to the MPs shape and size, and was less related to the MPs concentration. The aggregation speed of small-sized MPs (e.g., 74 μm) was faster than the large-sized ones (e.g., 613 μm). The MPs in a shape of sheet were more obvious than those in particle on their aggregation with microalgae. The density of aggregates was increased compared with pristine MPs, which is related to the cell density and cell number of attached microalgae. For the same type of MPs, the aggregation degree for the tested microalgae was as follows: Scenedesmus obliquus > C. vulgaris > T. subcordiformis > C. müelleri > S. westermani. Meanwhile, MPs inhibited cell growth of microalgae, particularly under the circumstance of their aggregation, by limiting the gas and mass transfer between microalgal cells and the extracellular environment. The heterogeneous aggregation of MPs and microalgae may provide new ideas for treatment and controlling of MPs in the environment.

Multi-layer and Multi-scale feature aggregation for DIBR-Synthesized image quality assessment

Depth-Image-Based Rendering (DIBR) is one of the main fundamental techniques for generating new viewpoints in 3D video applications such as multi-viewpoint video (MVV), free viewpoint video (FVV) and virtual reality (VR). Due to the imperfections of color images, depth maps or texture restoration techniques, several types of distortions occur in synthesized views. However, most of related works evaluated the quality of DIBR-synthesized views by only detecting a specific type of distortion, such as stretching, black holes, blurring, etc., which were unable to accurately evaluate the quality of DIBR-synthesized views. In this paper, a new no-reference image quality assessment method is proposed to evaluate the quality of DIBR-synthesized images by combining multi-layer and multi-scale features of images. To be specific, the distortions introduced by different stages of virtual viewpoint synthesis are first analyzed, and then multi-layer and multi-scale features are extracted to estimate the degree of texture and structure distortions. As a result, individual quality scores associated with two types of distortions (e.g., structural distortion and texture distortion) are aggregated to an overall image quality. Experimental results on two publicly available DIBR datasets show that the method has better performance than the state-of-the-art models.Index Terms: image quality assessment, DIBR-synthesized image, distortion correction, BIQA.