Search Results (6,853)

Background: Gastrointestinal cancer cells display both morphology and physiology diversity, thus posing a significant challenge for precise representation by a single data model. We conducted an in-depth study of gastrointestinal cancer heterogeneity by integrating and analyzing data from multiple modalities. Methods: We used a modified Canny algorithm to identify edges from tumor images, capturing intricate nonlinear interactions between pixels. These edge features were then combined with differentially expressed mRNA, miRNA, and immune cell data. Before data integration, we used the K-medoids algorithm to pre-cluster individual data types. The results of pre-clustering were used to construct the kernel matrix. Finally, we applied spectral clustering to the fusion matrix to identify different tumor subtypes. Furthermore, we identified hub genes linked to these subtypes and their biological roles through the application of Weighted Gene Co-expression Network Analysis (WGCNA) and Gene Ontology (GO) enrichment analysis. Results: Our investigation categorized patients into three distinct tumor subtypes and pinpointed hub genes associated with each. Genes MAGI2-AS3, MALAT1, and SPARC were identified as having a differential impact on the metastatic and invasive capabilities of cancer cells. Conclusion: By harnessing multimodal features, our study enhances the understanding of gastrointestinal tumor heterogeneity and identifies biomarkers for personalized medicine and targeted treatments. Full article

Advanced video codecs such as High Efficiency Video Coding/H.265 (HEVC) and Versatile Video Coding/H.266 (VVC) are vital for streaming high-quality online video content, as they compress and transmit data efficiently. However, these codecs can occasionally degrade video quality by adding undesirable artifacts such as blockiness, blurriness, and ringing, which can detract from the viewer’s experience. To ensure a seamless and engaging video experience, it is essential to remove these artifacts, which improves viewer comfort and engagement. In this paper, we propose a deep feature fusion based convolutional neural network (CNN) architecture (VVC-PPFF) for post-processing approach to further enhance the performance of VVC. The proposed network, VVC-PPFF, harnesses the power of CNNs to enhance decoded frames, significantly improving the coding efficiency of the state-of-the-art VVC video coding standard. By combining deep features from early and later convolution layers, the network learns to extract both low-level and high-level features, resulting in more generalized outputs that adapt to different quantization parameter (QP) values. The proposed VVC-PPFF network achieves outstanding performance, with Bjøntegaard Delta Rate (BD-Rate) improvements of 5.81% and 6.98% for luma components in random access (RA) and low-delay (LD) configurations, respectively, while also boosting peak signal-to-noise ratio (PSNR). Full article

As the preferred technology in the current energy storage field, lithium-ion batteries cannot completely eliminate the occurrence of thermal runaway (TR) accidents. It is of significant importance to employ real-time monitoring and warning methods to perceive the battery’s safety status promptly and address potential safety hazards. Currently, the monitoring and warning of lithium-ion battery TR heavily rely on the judgment of single parameters, leading to a high false alarm rate. The application of multi-parameter early warning methods based on data fusion remains underutilized. To address this issue, the evaluation of lithium-ion battery safety status was conducted using the cloud model to characterize fuzziness and Dempster–Shafer (DS) evidence theory for evidence fusion, comprehensively assessing the TR risk level. The research determined warning threshold ranges and risk levels by monitoring voltage, temperature, and gas indicators during lithium-ion battery overcharge TR experiments. Subsequently, a multi-parameter fusion approach combining cloud model and DS evidence theory was utilized to confirm the risk status of the battery at any given moment. This method takes into account the fuzziness and uncertainty among multiple parameters, enabling an objective assessment of the TR risk level of lithium-ion batteries. Full article

Selective laser sintering (SLS) is a bed fusion additive manufacturing technology that facilitates rapid, versatile, intricate, and cost-effective prototype production across various applications. It supports a wide array of thermoplastics, such as polyamides, ABS, polycarbonates, and nylons. However, manufacturing plastic components using SLS poses significant challenges due to issues like low strength, dimensional inaccuracies, and rough surface finishes. The operational principle of SLS involves utilizing a high-power-density laser to fuse polymer or metallic powder surfaces. This paper presents a comprehensive analysis of the SLS process, emphasizing the impact of different processing variables on material properties and the quality of fabricated parts. Additionally, the study explores the application of machine learning (ML) techniques—supervised, unsupervised, and reinforcement learning—in optimizing processes, detecting defects, and ensuring quality control within SLS. The review addresses key challenges associated with integrating ML in SLS, including data availability, model interpretability, and leveraging domain knowledge. It underscores the potential benefits of coupling ML with in situ monitoring systems and closed-loop control strategies to enable real-time adjustments and defect mitigation during manufacturing. Finally, the review outlines future research directions, advocating for collaborative efforts among researchers, industry professionals, and domain experts to unlock ML’s full potential in SLS. This review provides valuable insights and guidance for researchers in regard to 3D printing, highlighting advanced techniques and charting the course for future investigations. Full article

To optimally preserve and manage our civil structures, we need to have accurate information about their (1) geometry and dimensions, (2) boundary conditions, (3) material properties, and (4) structural conditions. The objective of this article is to show how imaging and image fusion using non-destructive testing (NDT) measurements can support structural engineers in performing accurate structural evaluations. The proposed methodology involves imaging using synthetic aperture focusing technique (SAFT)-based image reconstruction from ground penetrating radar (GPR) as well as ultrasonic echo array (UEA) measurements taken on multiple surfaces of a structural member. The created images can be combined using image fusion to produce a digital cross-section of the member. The feasibility of this approach is demonstrated using a case study of a prestressed concrete bridge that required a bridge load rating (BLR) but where no as-built plans were available. Imaging and image fusion enabled the creation of a detailed cross-section, allowing for confirmation of the number and location of prestressing strands and the location and size of internal voids. This information allowed the structural engineer of record (SER) to perform a traditional bridge load rating (BLR), ultimately avoiding load restrictions being imposed on the bridge. The proposed methodology not only provides useful information for structural evaluations, but also represents a basis upon which the digitalization of our infrastructure can be achieved. Full article

The COVID-19 pandemic, caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has filled a gap in our knowledge regarding the prevention of CoVs. Swine coronavirus (CoV) is a significant pathogen that causes huge economic losses to the global swine industry. Until now, anti-CoV prevention and control have been challenging due to the rapidly generated variants. Silver nanoparticles (AgNPs) with excellent antimicrobial activity have attracted great interest for biosafety prevention and control applications. In this study, we synthesized chitosan-modified AgNPs (Chi-AgNPs) with good biocompatibility to investigate their antiviral effects on swine CoVs. In vitro assays showed that Chi-AgNPs could significantly impaired viral entry. The direct interaction between Chi-AgNPs and CoVs can destroy the viral surface spike (S) protein secondary structure associated with viral membrane fusion, which is caused by the cleavage of disulfide bonds in the S protein. Moreover, the mechanism showed that Chi-AgNPs reduced the virus-induced apoptosis of Vero cells via the ROS/p53 signaling activation pathway. Our data suggest that Chi-AgNPs can serve as a preventive strategy for CoVs infection and provide a molecular basis for the viricidal effect of Chi-AgNPs on CoVs. Full article

The existing collaborative channel perception suffers from unreasonable data fusion weight allocation, which mismatches the channel perception capability of the node devices. This often leads to significant deviations between the channel perception results and the actual channel state. To solve this issue, this paper integrates the data fusion algorithm from evidence fusion theory with data link channel state perception. It applies the data fusion advantages of evidence fusion theory to evaluate the traffic pulse statistical capability of network node devices. Specifically, the typical characteristic parameters describing the channel perception capability of node devices are regarded as evidence parameter sets under the recognition framework. By calculating the credibility and falsity of the characteristic parameters, the differences and conflicts between nodes are measured to achieve a comprehensive evaluation of the traffic pulse statistical capabilities of node devices. Based on this evaluation, the geometric mean method is adopted to calculate channel state perception weights for each node within a single-hop range, and a weight allocation strategy is formulated to improve the accuracy of channel state perception. Full article

Through hydrocarbon explorations, deep carbonate reservoirs within a craton were determined to be influenced by deep strike-slip faults, which exhibit small displacements and are challenging to identify. Previous research has established a correlation between seismic attributes and deep geological information, wherein large-scale faults can cause abrupt waveform discontinuities. However, due to the inherent limitations of seismic datasets, such as low signal-to-noise ratios and resolutions, accurately characterizing complex strike-slip faults remains difficult, resulting in increased uncertainties in fault characterization and reservoir prediction. In this study, we integrate advanced techniques such as principal component analysis and structure-oriented filtering with a fault-centric imaging approach to refine the resolution of seismic data from the Tarim craton. Our detailed evaluation encompassed 12 distinct seismic attributes, culminating in the creation of a sophisticated model for identifying strike-slip faults. This model incorporates select seismic attributes and leverages fusion algorithms like K-means, ellipsoid growth, and wavelet transformations. Through the technical approach introduced in this study, we have achieved multi-scale characterization of complex strike-slip faults with throws of less than 10 m. This workflow has the potential to be extended to other complex reservoirs governed by strike-slip faults in cratonic basins, thus offering valuable insights for hydrocarbon exploration and reservoir characterization in similar geological settings. Full article

Autonomous decision-making is a hallmark of intelligent mobile robots and an essential element of autonomous navigation. The challenge is to enable mobile robots to complete autonomous navigation tasks in environments with mapless or low-precision maps, relying solely on low-precision sensors. To address this, we have proposed an innovative autonomous navigation algorithm called PEEMEF-DARC. This algorithm consists of three parts: Double Actors Regularized Critics (DARC), a priority-based excellence experience data collection mechanism, and a multi-source experience fusion strategy mechanism. The algorithm is capable of performing autonomous navigation tasks in unmapped and unknown environments without maps or prior knowledge. This algorithm enables autonomous navigation in unmapped and unknown environments without the need for maps or prior knowledge. Our enhanced algorithm improves the agent’s exploration capabilities and utilizes regularization to mitigate the overestimation of state-action values. Additionally, the priority-based excellence experience data collection module and the multi-source experience fusion strategy module significantly reduce training time. Experimental results demonstrate that the proposed method excels in navigating the unmapped and unknown, achieving effective navigation without relying on maps or precise localization. Full article

Airport noise prediction models are divided into physics-guided methods and data-driven methods. The prediction results of physics-guided methods are relatively stable, but their overall prediction accuracy is lower than that of data-driven methods. However, machine learning methods have a relatively high prediction accuracy, but their prediction stability is inferior to physics-guided methods. Therefore, this article integrates the ECAC model, driven by aerodynamics and acoustics principles under the framework of deep neural networks, and establishes a physically guided neural network noise prediction model. This model inherits the stability of physics-guided methods and the high accuracy of data-driven methods. The proposed model outperformed physics-driven and data-driven models regarding prediction accuracy and generalization ability, achieving an average absolute error of 0.98 dBA in predicting the sound exposure level. This success was due to the fusion of physics-based principles with data-driven approaches, providing a more comprehensive understanding of aviation noise prediction. Full article

The Biome-BGC model is a classic forest ecosystem carbon cycle model driven by remote sensing and plant trait data, and it has been widely applied in various regions of China over the years. However, does the Biome-BGC model have good applicability in all regions of China? This question implies that the rationality of some applications of the Biome-BGC model in China might be questionable. To quantitatively assess the overall spatial applicability of the Biome-BGC model in China’s vegetation ecosystems, this study selected ten representative forest and grassland ecosystem sites, all of which have publicly available carbon flux data. In this study, we first used the EFAST method to identify the sensitive ecophysiological parameters of the Biome-BGC model at these sites. Subsequently, we calibrated the optimal values of these sensitive parameters through a literature review and the PEST method and then used these to drive the Biome-BGC model to simulate the productivity (including GPP and NEP) of these ten forest and grassland ecosystems in China. Finally, we compared the simulation accuracy of the Biome-BGC model at these ten sites in detail and established the spatial pattern of the model’s applicability across China. The results show that the sensitive ecophysiological parameters of the Biome-BGC model vary with spatial distribution, plant functional types, and model output variables. After conducting parameter sensitivity analysis and optimization, the simulation accuracy of the Biome-BGC model can be significantly improved. Additionally, for forest ecosystems in China, the model’s simulation accuracy decreases from north to south, while for grassland ecosystems, the accuracy increases from north to south. This study provides a set of localized ecophysiological parameters and advocates that the use of the Biome-BGC model should be based on parameter sensitivity analysis and optimization. Full article

In the rapidly advancing domain of Intelligent Connected Vehicles (ICVs), multimodal Federated Learning (FL) presents a powerful methodology to harness diverse data sources, such as sensors, cameras, and Vehicle-to-Everything (V2X) communications, without compromising data privacy. Despite its potential, the presence of Byzantine adversaries–malicious participants who contribute incorrect or misleading updates–poses a significant challenge to the robustness and reliability of the FL process. This paper proposes a Byzantine-robust multimodal FL framework specifically designed for ICVs. Our framework integrates a robust aggregation mechanism to mitigate the influence of adversarial updates, a multimodal fusion strategy to effectively manage and combine heterogeneous input data, and a global optimization objective that accommodates the presence of Byzantine clients. The theoretical foundation of the framework is established through formal definitions and equations, demonstrating its ability to maintain reliable and accurate learning outcomes despite adversarial disruptions. Extensive experiments highlight the framework’s efficacy in preserving model performance and resilience in real-world ICV environments. Full article

Source camera identification can verify whether two videos were shot by the same device, which is of great significance in multimedia forensics. Most existing identification methods use convolutional neural networks to learn sensor noise patterns to identify the source camera in closed forensic scenarios. While these methodologies have achieved remarkable results, they are nonetheless constrained by two primary challenges: (1) the interference of semantic information and (2) the incongruity in feature distributions across different datasets. The former will interfere with the extraction of effective features of the model. The latter will cause the model to fit the characteristic distribution of the training data and be sensitive to unseen data features. To address these challenges, we propose a novel source camera identification framework that determines whether a video was shot by the same device by obtaining similarities between source camera features. Firstly, we extract video key frames and use the integral image to optimize the smoothing blocks selection algorithm of inter-pixel variance to remove the interference of video semantic information. Secondly, we design a residual neural network fused with a constraint layer to adaptively learn video source features. Thirdly, we introduce a triplet loss metric learning strategy to optimize the network model to improve the discriminability of the model. Finally, we design a multi-dimensional feature vector similarity fusion strategy to achieve highly generalized source camera recognition. Extensive experiments show that our method achieved an AUC value of up to 0.9714 in closed-set forensic scenarios and an AUC value of 0.882 in open-set scenarios, representing an improvement of 5% compared to the best baseline method. Furthermore, our method demonstrates effectiveness in the task of deepfake detection. Full article

To address the problem that conventional neural networks trained on radar echo data cannot handle the phase of the echoes, resulting in insufficient information utilization and limited performance in detection and classification, we extend neural networks from the real-valued neural networks to the complex-valued neural networks, presenting a novel algorithm for classifying small sea surface targets. The proposed algorithm leverages an improved residual fusion network and complex time–frequency spectra. Specifically, we augment the Deep Residual Network-50 (ResNet50) with a spatial pyramid pooling (SPP) module to fuse feature maps from different receptive fields. Additionally, we enhance the feature extraction and fusion capabilities by replacing the conventional residual block layer with a multi-branch residual fusion (MBRF) module. Furthermore, we construct a complex time–frequency spectrum dataset based on radar echo data from four different types of sea surface targets. We employ a complex-valued improved residual fusion network for learning and training, ultimately yielding the result of small target classification. By incorporating both the real and imaginary parts of the echoes, the proposed complex-valued improved residual fusion network has the potential to extract more comprehensive features and enhance classification performance. Experimental results demonstrate that the proposed method achieves superior classification performance across various evaluation metrics. Full article

The geological environment damage caused by coal mining subsidence has become an important factor affecting the sustainable development of mining areas. Reconstruction of the Coal Mining Subsidence Field (CMSF) is the key to preventing geological disasters, and the needs of CMSF reconstruction cannot be met by solely relying on a single remote sensing technology. The combination of Unmanned Aerial Vehicle (UAV) and Synthetic Aperture Radar (SAR) has complementary advantages; however, the data fusion strategy by refining the SAR deformation field through UAV still needs to be updated constantly. This paper proposed a Prior Weighting (PW) method based on Satellite Aerial (SA) heterogeneous remote sensing. The method can be used to fuse SAR and UAV Light Detection and Ranging (LiDAR) data for ground subsidence parameter inversion. Firstly, the subsidence boundary of Differential Interferometric SAR (DInSAR) combined with the large gradient subsidence of Pixel Offset Tracking (POT) was developed to initialize the SAR preliminary CMSF. Secondly, the SAR preliminary CMSF was refined by UAV LiDAR data; the weights of SAR and UAV LiDAR data are 0.4 and 0.6 iteratively. After the data fusion, the subsidence field was reconstructed. The results showed that the overall CMSF accuracy improved from ±144 mm to ±51 mm. The relative errors of the surface subsidence factor and main influence angle tangent calculated by the physical model and in situ measured data are 1.3% and 1.7%. It shows that the proposed SAR/UAV fusion method has significant advantages in the reconstruction of CMSF, and the PW method contributes to the prevention and control of mining subsidence. Full article