Global Correlation Research Articles

Multispectral and hyperspectral images fusion based on subspace representation and nonlocal low-rank regularization

ABSTRACT Multispectral image (MSI) and hyperspectral image (HSI) fusion is a popular method for HSI super-resolution reconstruction (HSI-SR). MSI-HSI fusion problem is ill-posed and demands several image priors or regularization terms to solve accurately, which is a challenging issue. In this paper, we propose an MSI-HSI fusion model via subspace representation and nonlocal low-rank regularization (SRNLRR). SRNLRR model incorporates the global spectral correlations and spatial nonlocal similarities of HSI to improve the fusion results, where the priors complement each other. First, we use the mode-n tensor-matrix product to project latent high spatial resolution HSI (HR-HSI) into spectral subspace, which can capture spectral low-rankness and reduce computational complexity. Then, based on low-rank representation (LRR) and nonlocal processing strategy, we design a spatial nonlocal LRR regularization (spa-NLRR) and a spectral global LRR regularization (spe-GLRR). These two regularizations analyze the spatial nonlocal similarities and spectral global correlations from intermediate-level vision. Finally, we use the residual regularization program to obtain more image information and input it into the fusion model. We use alternate minimization (AM) methods to optimize the SRNLRR model and employ the alternating direction method (ADM) on spatial/spectral LRR learning. Comparison experiments between the SRNLRR method and six advanced methods on three HSI datasets indicate the superiority of our method.

Geochemistry, Monazite (U–Pb–Th) Geochronology, and P-T Pseudosection Modelling of Two-Pyroxene Mafic Granulite from Sonapahar, Shillong Meghalaya Gneissic Complex, India: Implication for Tectono-Metamorphic Evolution and Global Pan-African Correlation

Geochemistry, Monazite (U–Pb–Th) Geochronology, and P-T Pseudosection Modelling of Two-Pyroxene Mafic Granulite from Sonapahar, Shillong Meghalaya Gneissic Complex, India: Implication for Tectono-Metamorphic Evolution and Global Pan-African Correlation

GLIMS: Attention-guided lightweight multi-scale hybrid network for volumetric semantic segmentation

Convolutional Neural Networks (CNNs) have become widely adopted for medical image segmentation tasks, demonstrating promising performance. However, the inherent inductive biases in convolutional architectures limit their ability to model long-range dependencies and spatial correlations. While recent transformer-based architectures address these limitations by leveraging self-attention mechanisms to encode long-range dependencies and learn expressive representations, they often struggle to extract low-level features and are highly dependent on data availability. This motivated us for the development of GLIMS, a data-efficient attention-guided hybrid volumetric segmentation network. GLIMS utilizes Dilated Feature Aggregator Convolutional Blocks (DACB) to capture local–global feature correlations efficiently. Furthermore, the incorporated Swin Transformer-based bottleneck bridges the local and global features to improve the robustness of the model. Additionally, GLIMS employs an attention-guided segmentation approach through Channel and Spatial-Wise Attention Blocks (CSAB) to localize expressive features for fine-grained border segmentation. Quantitative and qualitative results on glioblastoma and multi-organ CT segmentation tasks demonstrate GLIMS’ effectiveness in terms of complexity and accuracy. GLIMS demonstrated outstanding performance on BraTS2021 and BTCV datasets, surpassing the performance of Swin UNETR. Notably, GLIMS achieved this high performance with a significantly reduced number of trainable parameters. Specifically, GLIMS has 47.16 M trainable parameters and 72.30G FLOPs, while Swin UNETR has 61.98 M trainable parameters and 394.84G FLOPs. The code is publicly available on https://github.com/yaziciz/GLIMS.

Pruning Self-Attentions Into Convolutional Layers in Single Path.

Vision Transformers (ViTs) have achieved impressive performance over various computer vision tasks. However, modeling global correlations with multi-head self-attention (MSA) layers leads to two widely recognized issues: the massive computational resource consumption and the lack of intrinsic inductive bias for modeling local visual patterns. To solve both issues, we devise a simple yet effective method named Single-Path Vision Transformer pruning (SPViT), to efficiently and automatically compress the pre-trained ViTs into compact models with proper locality added. Specifically, we first propose a novel weight-sharing scheme between MSA and convolutional operations, delivering a single-path space to encode all candidate operations. In this way, we cast the operation search problem as finding which subset of parameters to use in each MSA layer, which significantly reduces the computational cost and optimization difficulty, and the convolution kernels can be well initialized using pre-trained MSA parameters. Relying on the single-path space, we introduce learnable binary gates to encode the operation choices in MSA layers. Similarly, we further employ learnable gates to encode the fine-grained MLP expansion ratios of FFN layers. In this way, our SPViT optimizes the learnable gates to automatically explore from a vast and unified search space and flexibly adjust the MSA-FFN pruning proportions for each individual dense model. We conduct extensive experiments on two representative ViTs showing that our SPViT achieves a new SOTA for pruning on ImageNet-1 k. For example, our SPViT can trim 52.0% FLOPs for DeiT-B and get an impressive 0.6% top-1 accuracy gain simultaneously.

Broad-UNet-diff: Diffeomorphic Deformable Medical Image Registration based on Multi-scale Feature Learning

Introduction: To propose a medical image registration method with significant performance improvement. The spatial transformation obtained by the traditional deformable image registration technology is not smooth enough, and the calculation amount is too large to solve the optimization parameters. The network model proposed based on deep learning medical image registration technology has some limitations, which cannot guarantee the registration of topological structures, resulting in the loss of spatial features. It makes the model have topological conservation and transform reversibility, has the ability to learn more multi-scale features and complex image structures, and captures finer changes while clearly encoding global correlation. Method: Based on the core UNet model, a deformable image registration method with a new architecture Broad-UNet-diff is proposed. The model is equipped with asymmetric parallel convolution and uses diffeomorphism mapping. Result: Compared with the seven classical registration methods under the brain MRI datasets, the proposed method has significantly improved the registration performance. In particular, compared with the advanced TransMorph-diff registration method, the Dice score can be improved by 12 %, but only the 1/10 parameters are needed. Conclusion: This method confirms its convincing effectiveness and accuracy.

DepthGAN: GAN-based depth generation from semantic layouts

AbstractExisting GAN-based generative methods are typically used for semantic image synthesis. We pose the question of whether GAN-based architectures can generate plausible depth maps and find that existing methods have difficulty in generating depth maps which reasonably represent 3D scene structure due to the lack of global geometric correlations. Thus, we propose DepthGAN, a novel method of generating a depth map using a semantic layout as input to aid construction, and manipulation of well-structured 3D scene point clouds. Specifically, we first build a feature generation model with a cascade of semantically-aware transformer blocks to obtain depth features with global structural information. For our semantically aware transformer block, we propose a mixed attention module and a semantically aware layer normalization module to better exploit semantic consistency for depth features generation. Moreover, we present a novel semantically weighted depth synthesis module, which generates adaptive depth intervals for the current scene. We generate the final depth map by using a weighted combination of semantically aware depth weights for different depth ranges. In this manner, we obtain a more accurate depth map. Extensive experiments on indoor and outdoor datasets demonstrate that DepthGAN achieves superior results both quantitatively and visually for the depth generation task.

System-wide coordination and communication of lipid metabolism atlas revealed cytotoxicity of epoxy triglyceride in deep-frying oil

The epoxy triglycerides generated by oxidation, cyclization, and free radical chain reaction of unsaturated dietary oils during deep-frying are demonstrated to have cytotoxicity and can induce lipid metabolism related diseases. Metabolic diseases are usually characterized by metabolic abnormalities in different tissues, however, the relationship between changes in intratissue coordination and communication induced by epoxy triglycerides and specific pathogenic mechanisms remains largely unknown. We conducted lipid metabolomics analysis across six different tissues in C57BL/6J mice, including the medial prefrontal cortex, interscapular brown adipose tissue, epididymal white adipose tissue, liver, intestine, and heart. Normal diet intake demonstrated a high degree of association between lipid metabolites, indicative of cross-communication and cooperation among various tissues and organs, while, a global correlation that was disrupted and restructured by epoxy triglycerides intake. Examination of blood samples revealed that epoxy triglycerides enhanced bacterial translocation from the gut to the systemic circulation, consequently stimulating the TLR4/CD36/NF-κB pathway. In summary, this study found that epoxy triglyceride upsets the comprehensive coordination and information exchange of lipid metabolism, providing a fresh perspective for future research on the systemic metabolic network and identifying metabolic disease markers and associated mechanisms induced by deep-frying oil.

Global Strong Winds Occurrence Characteristics and Climate Index Correlation

Guided by entering the deep sea and achieving deep marine development in marine construction, the factors hindering marine construction cannot be ignored. Strong ocean winds have a devastating impact on tasks such as ship navigation, carrier aircraft take-off and landing, naval operations and military exercises, and affect the planning of sea routes and the development of the long-distance sea. This paper uses ERA5 wind field data and key climate indices to conduct a systematic analysis of catastrophic winds in the global ocean using methods such as climate statistical analysis, the Theil–Sen trend method, Pearson correlation and contribution rate calculation. It points out the spatiotemporal distribution, variation trend, climate index correlation and contribution rate characteristics of strong winds occurrence (SWO) and hopes that the results of this study can serve as a guide for maritime route planning and provide technical assistance and decision-making support for marine development and other needs. The results show the following: The high global SWO occurs in the Southern Ocean, the North Atlantic, the North Pacific, near Taiwan, China, the Arabian Sea and other locations, with the strongest SWO in summer. The growth trend of SWO in the Southern Ocean is strongest, with decreasing regions near the Arabian Sea and the Bay of Bengal, and the growth trend is reflected in all four seasons. The climate indices with the strongest correlation and highest contribution to the global SWO are AAO (Antarctic Oscillation) and EP–NP (East Pacific–North Pacific pattern) with a correlation between −0.5 and 0.5 and a contribution rate of up to −50%~50%.

A New Sparse Collaborative Low-Rank Prior Knowledge Representation for Thick Cloud Removal in Remote Sensing Images

Efficiently removing clouds from remote sensing imagery presents a significant challenge, yet it is crucial for a variety of applications. This paper introduces a novel sparse function, named the tri-fiber-wise sparse function, meticulously engineered for the targeted tasks of cloud detection and removal. This function is adept at capturing cloud characteristics across three dimensions, leveraging the sparsity of mode-1, -2, and -3 fibers simultaneously to achieve precise cloud detection. By incorporating the concept of tensor multi-rank, which describes the global correlation, we have developed a tri-fiber-wise sparse-based model that excels in both detecting and eliminating clouds from images. Furthermore, to ensure that the cloud-free information accurately matches the corresponding areas in the observed data, we have enhanced our model with an extended box-constraint strategy. The experiments showcase the notable success of the proposed method in cloud removal. This highlights its potential and utility in enhancing the accuracy of remote sensing imagery.

AES-Net: An adapter and enhanced self-attention guided network for multi-stage glaucoma classification using fundus images

Glaucoma is a progressive eye condition that can lead to permanent vision loss. Therefore, on-time detection of glaucoma is critical for making an effective treatment plan. In recent years, enormous attempts have been made to develop automated glaucoma classification systems using CNNs through images. In contrast, limited methods have been proposed for diagnosing different glaucoma stages. It is mainly owing to the lack of large publicly available labeled datasets. Also, fundus images exhibit a high inter-stage resemblance, redundant features and minute size variations of lesions, making the conventional CNNs difficult to classify multiple stages of glaucoma accurately. To address these challenges, this paper proposes a novel adapter and enhanced self-attention based CNN framework named AES-Net for effective classification of glaucoma stages. In particular, we propose a spatial adapter module on top of the backbone network for learning better feature representations and an enhanced self-attention module (ESAM) to capture global feature correlations among the relevant channels and spatial positions. The ESAM assists in capturing stage-specific and detailed-lesion features from the fundus images. Extensive experiments on two multi-stage glaucoma datasets indicate that our AES-Net surpasses CNN-based existing approaches. The Grad-CAM++ visualization maps further confirm the effectiveness of our AES-Net.

Unsupervised multi-level spatio-spectral fusion transformer for hyperspectral image super-resolution

Fusing a low spatial resolution hyperspectral image (LR-HSI) with a high spatial resolution multispectral image (HR-MSI) is widely used for HSI super-resolution. Recent works still face problems in exploring global spatio-spectral correlation and lack effective utilization of multi-level features of the inputs (i.e., HR-MSI and LR-HSI), which results in a lack of similarity between the reconstruction and the inputs, ultimately causing significant spatio-spectral distortion. To solve these problems, we design an Unsupervised Multi-level Spatio-spectral Fusion Transformer (UMSFT). In UMSFT, a novel multi-level features fusion strategy is constructed, which fuses the hierarchy features of the inputs via proposed Spatio-spectral Feature Fusion Attention Blocks (S2F-FAB) in a level-by-level manner, thereby fully exploring the interaction between the hierarchical features. The S2F-FAB is specially designed for HSI-MSI fusion consisting of two components: (1) a spatial fusion module (Spa-FM) is designed for spatial domain fusion, and its output is set as Values (V) of a transformer; (2) a novel spectral feature cross attention (Spe- FCA) formulates the features of LR-HSI and HR-MSI as Queries (Q) and Keys (K), respectively, and achieves spectral domain fusion by applying attention mechanism along the spectral dimension. Incorporating spatial detail reconstruction and spectral feature integration into the attention mechanism, the S2F-FAB efficiently exploits the spatio-spectral correlation between target HR-HSI and inputs. Experimental results on three public datasets and our real-world images show the superiority of our method as compared with eleven state-of-the-art methods. Codes will be available at https://github.com/Caoxuheng/HIFtool.

Paleomagnetic investigation of the basal Maieberg Formation (Namibia) cap carbonate sequence (635 Ma): Implications for Snowball Earth postglacial dynamics

In this study, we investigate the paleomagnetism of the basal Maieberg Formation (Namibia) cap carbonate sequence to elucidate its magnetic properties and paleolatitude of deposition, establish global correlations, and contribute to the understanding of Snowball Earth postglacial dynamics. Two distinct magnetization components, C1 and C2, were identified. C1 is interpreted as a depositional or post-depositional remanent magnetization carried by detrital pseudo-single domain (PSD) magnetite, while the C2 component is a thermochemical remanent magnetization carried by fine authigenic single domain (SD)−PSD magnetite. The deposition paleolatitude provided by C1 is 33.3° ± 3.2°, which gives an initial quantitative approximation of the paleolatitude for the underlying Marinoan Ghaub diamictites. The thickness of the Keilberg Member cap dolostone is anomalously high for the paleolatitude calculated with C1, which suggests that other factors besides the influence of the paleolatitude on carbonate oversaturation may have influenced the sedimentary production of cap dolostones and the overall thickness of the flooding cap carbonate sequence. Possible explanations could include the influence of alkalinity input combined with local tectonic subsidence during a long glacial period with unusually low sedimentation rates, which appear to be in a favorable configuration for the substantial thickness of the Keilberg Member. Paleomagnetic field reversals at the Keilberg cap dolostone and analogous units globally suggest a longer duration of marine transgression than energy-balance deglaciation models and sedimentological-geochemical observations have constrained. Factors such as ocean warming, thermal expansion, and local glacio-isostatic adjustments imply extended marine transgressions beyond the deglaciation period. Still, magnetostratigraphic estimates for postglacial transgressive sequences require longer time scales by a factor of five or more. Thus, the conflict arising between estimates derived from paleomagnetic data and the constraints imposed by climate physics underscores uncertainties regarding an unconventional field state or a remanence acquisition mechanism within these cap carbonates that is not fully understood. Importantly, if such a phenomenon proves to be primary and global, the widespread occurrence of these stratigraphically compressed reversals would support the precise temporal correlation between Marinoan cap dolostones. The C2 pole correlates with Cambrian remagnetization poles observed in carbonates from West Gondwana, which now extend to the Congo craton. The remanence acquisition of C2 likely stems from diagenesis-related low-temperature authigenic magnetite formation after the conversion of iron-rich smectite to iron-poor illite. Cooling associated with the Kaoko orogen’s exhumation and tectonic uplift possibly locked the magnetic system at ca. 520 Ma, supported by the C2 pole position on the West Gondwana apparent polar wander path, although other explanations remain valid.

Manifold regularized deep canonical variate analysis with interpretable attribute guidance for three-phase flow process monitoring

Oil–gas–water three-phase flow has multiple flow states, exhibiting dynamic, nonlinear, and instantaneous behaviors. Monitoring and analysis of flow state are crucial for ensuring safe operation of industrial processes. However, the absence of a universal definition for three-phase flow states, owing to the complex flow characteristics and structures, leads to that labeling three-phase flow states by categories is impractical. For comprehensive monitoring and analysis, the flow states should be described from both global (e.g., the dominant phase) and local (e.g., the interphase structure) aspects. Given the aforementioned challenges, the work aims to address the accurate identification of typical three-phase flow states and to meticulously monitor and analyze the continuous evolutionary process of three-phase flow. To achieve it, the manifold regularized deep canonical variate analysis with attribute guidance (Ag-MRDCVA) is proposed, which not only introduces an innovative monitoring paradigm that designs state attributes for process description but also facilitates knowledge transfer from typical flow states to transition states. For enhancing the model’s feature embedding capabilities, an attribute guidance module is introduced to increase supervision information at both class and attribute levels. Then, convolutional neural network (CNN) backbones are developed with a dual objective of global serial correlation and local manifold regularization, which capture spatiotemporal information at both global and local scales, facilitating effective attribute encoding and characterization of flow states. Finally, the attribute evolution heat map and a monitoring metric (MM) collectively offer a compelling and comprehensive analysis of the three-phase flow process. Extensive experiments demonstrate that Ag-MRDCVA surpasses existing methods, showcasing its ability to minutely monitor the process while providing reasonable explanations.

GSGSL: Gravity-driven self-supervised graph structure learning

The existing graph structure learning methods heavily rely on the original graph structure and often fail to capture potential high-level abstract features and global correlations within the graph. To address these issues, this paper proposes a Universal Gravitational-driven Self-supervised Graph Structure Learning method (GSGSL), overcoming the limitations of current graph structure learning methods in advanced feature extraction. GSGSL models the graph structure using the universal force of gravity in a dynamic, globally adaptive manner. Additionally, it employs a multi-perspective contrastive learning approach to eliminate the need for external labels, jointly optimizing graph structure learning with downstream tasks. Extensive experimental results on public datasets demonstrate that, in comparative experiments without considering the original adjacency matrix, the GSGSL method outperforms baseline models by 0.5% to 17.3%. In comparative experiments optimizing the original adjacency matrix, the GSGSL method exhibits improvements ranging from 0.9% to 12%, validating that the GSGSL approach to simulating gravitational fields has better dynamic characteristics. It effectively captures advanced abstract features and global characteristics of graph data, surpassing the limitations of baseline methods in graph structure learning.

Transient hygro- and hydro-expansion of freely and restrained dried paper: the fiber-network coupling

AbstractThe transient dimensional changes during hygro-expansion and hydro-expansion of freely and restrained dried, softwood and hardwood sheets and fibers is monitored, to unravel the governing micro-mechanisms occurring during gradual water saturation. The response of individual fibers is measured using a full-field global digital height correlation method, which has been extended to monitor the transient hydro-expansion of fibers from dry to fully saturated. The hygro- and hydro-expansion is larger for freely versus restrained dried and softwood versus hardwood handsheets. The transient sheet-scale hydro-expansion reveals a sudden strain and moisture content step. It is postulated that the driving mechanism is the moisture-induced softening of the so-called ”dislocated regions” in the fiber’s cellulose micro-fibrils, unlocking further fiber swelling. The strain step is negligible for restrained dried handsheets, which is attributed to the ”dislocated cellulose regions” being locked in their stretched configuration during restrained drying, which is supported by the single fiber hydro-expansion measurements. Finally, an inter-fiber bond model is exploited and adapted to predict the sheet-scale hygro-expansion from the fiber level characteristics. The model correctly predicts the qualitative differences between freely versus restrained dried and softwood versus hardwood handsheets, yet, its simplified geometry does not allow for more quantitative predictions of the sheet-scale hydro-expansion.

Full waveform inversion using frequency shift envelope-based global correlation norm for ultrasound computed tomography.

Many studies have been carried out on ultrasound computed tomography (USCT) for its ability to offer quantitative measurements of tissue sound speed. Full waveform inversion (FWI) is a technique for reconstructing high-resolution sound speed images by iteratively minimizing the difference between the observed ultrasound data and the synthetic data based on the waveform equation. However, FWI suffers from cycle-skipping, which usually causes FWI convergence at a local minimum. Cycle-skipping occurs when the phase difference between the observed data and the synthetic data exceeds half a cycle. The simplest way to avoid cycle-skipping is to use low-frequency information for reconstruction. Nevertheless, in imaging systems, the response bandwidth of the probe is limited, and reliable low-frequency information often exceeds the response band. Therefore, it is a challenge to perform FWI imaging and avoid cycle-skipping problems without low-frequency information. In this paper, we propose a frequency shift envelope-based global correlation norm (FSEGCN), where an artificial source wavelet with a lower frequency is adopted to calculate synthetic data. FSEGCN compared with FWI, envelope inversion (EI), global correlation norm (GCN), envelope-based global correlation norm (EGCN) through concentric circle phantom without low-frequency information. The experimental results demonstrated the capability of the proposed method to recover the sound speed close to the exact model in the absence of low-frequency information, whereas FWI, EI, GCN, and
EGCN cannot. Experiments on phantoms of the human head and calf show that artificial source wavelets can reduce image artifacts and enhance reconstruction robustness, when original low-frequency information is absent.

Characterizing the polygenic overlap and shared loci between rheumatoid arthritis and cardiovascular diseases

BackgroundDespite substantial research revealing that patients with rheumatoid arthritis (RA) have excessive morbidity and mortality of cardiovascular disease (CVD), the mechanism underlying this association has not been fully known. This study aims to systematically investigate the phenotypic and genetic correlation between RA and CVD.MethodsBased on UK Biobank, we conducted two cohort studies to evaluate the phenotypic relationships between RA and CVD, including atrial fibrillation (AF), coronary artery disease (CAD), heart failure (HF), and stroke. Next, we used linkage disequilibrium score regression, Local Analysis of [co]Variant Association, and bivariate causal mixture model (MiXeR) methods to examine the genetic correlation and polygenic overlap between RA and CVD, using genome-wide association summary statistics. Furthermore, we explored specific shared genetic loci by conjunctional false discovery rate analysis and association analysis based on subsets.ResultsCompared with the general population, RA patients showed a higher incidence of CVD (hazard ratio [HR] = 1.21, 95% confidence interval [CI]: 1.15–1.28). We observed positive genetic correlations of RA with AF and stroke, and a mixture of negative and positive local genetic correlations underlying the global genetic correlation for CAD and HF, with 13 ~ 33% of shared genetic variants for these trait pairs. We further identified 23 pleiotropic loci associated with RA and at least one CVD, including one novel locus (rs7098414, TSPAN14, 10q23.1). Genes mapped to these shared loci were enriched in immune and inflammatory-related pathways, and modifiable risk factors, such as high diastolic blood pressure.ConclusionsThis study revealed the shared genetic architecture of RA and CVD, which may facilitate drug target identification and improved clinical management.

Genetic influences and causal pathways shared between cannabis use disorder and other substance use traits.

Cannabis use disorder (CanUD) has increased with the legalization of the use of cannabis. Around 20% of individuals using cannabis develop CanUD, and the number of users has grown with increasing ease of access. CanUD and other substance use disorders (SUDs) are associated phenotypically and genetically. We leveraged new CanUD genomics data to undertake genetically-informed analyses with unprecedented power, to investigate the genetic architecture and causal relationships between CanUD and lifetime cannabis use with risk for developing SUDs and substance use traits. Analyses included calculating local and global genetic correlations, genomic structural equation modeling (genomicSEM), and Mendelian Randomization (MR). Results from the genetic correlation and genomicSEM analyses demonstrated that CanUD and cannabis use differ in their relationships with SUDs and substance use traits. We found significant causal effects of CanUD influencing all the analyzed traits: opioid use disorder (OUD) (Inverse variant weighted, IVW β = 0.925 ± 0.082), problematic alcohol use (PAU) (IVW β = 0.443 ± 0.030), drinks per week (DPW) (IVW β = 0.182 ± 0.025), Fagerström Test for Nicotine Dependence (FTND) (IVW β = 0.183 ± 0.052), cigarettes per day (IVW β = 0.150 ± 0.045), current versus former smokers (IVW β = 0.178 ± 0.052), and smoking initiation (IVW β = 0.405 ± 0.042). We also found evidence of bidirectionality showing that OUD, PAU, smoking initiation, smoking cessation, and DPW all increase risk of developing CanUD. For cannabis use, bidirectional relationships were inferred with PAU, smoking initiation, and DPW; cannabis use was also associated with a higher risk of developing OUD (IVW β = 0.785 ± 0.266). GenomicSEM confirmed that CanUD and cannabis use load onto different genetic factors. We conclude that CanUD and cannabis use can increase the risk of developing other SUDs. This has substantial public health implications; the move towards legalization of cannabis use may be expected to increase other kinds of problematic substance use. These harmful outcomes are in addition to the medical harms associated directly with CanUD.

Phenotypic and genetic effect of carotid intima-media thickness on the risk of stroke.

While carotid intima-media thickness (cIMT) as a noninvasive surrogate measure of atherosclerosis is widely considered a risk factor for stroke, the intrinsic link underlying cIMT and stroke has not been fully understood. We aimed to evaluate the clinical value of cIMT in stroke through the investigation of phenotypic and genetic relationships between cIMT and stroke. We evaluated phenotypic associations using observational data from UK Biobank (N = 21,526). We then investigated genetic relationships leveraging genomic data conducted in predominantly European ancestry for cIMT (N = 45,185) and any stroke (AS, Ncase/Ncontrol=40,585/406,111). Observational analyses suggested an increased hazard of stroke per one standard deviation increase in cIMT (cIMTmax-AS: hazard ratio (HR) = 1.39, 95%CI = 1.09-1.79; cIMTmean-AS: HR = 1.39, 95%CI = 1.09-1.78; cIMTmin-AS: HR = 1.32, 95%CI = 1.04-1.68). A positive global genetic correlation was observed (cIMTmax-AS: [Formula: see text]=0.23, P=9.44 × 10-5; cIMTmean-AS: [Formula: see text]=0.21, P=3.00 × 10-4; cIMTmin-AS: [Formula: see text]=0.16, P=6.30 × 10-3). This was further substantiated by five shared independent loci and 15 shared expression-trait associations. Mendelian randomization analyses suggested no causal effect of cIMT on stroke (cIMTmax-AS: odds ratio (OR)=1.12, 95%CI=0.97-1.28; cIMTmean-AS: OR=1.09, 95%CI=0.93-1.26; cIMTmin-AS: OR=1.03, 95%CI = 0.90-1.17). A putative association was observed for genetically predicted stroke on cIMT (AS-cIMTmax: beta=0.07, 95%CI = 0.01-0.13; AS-cIMTmean: beta=0.08, 95%CI = 0.01-0.15; AS-cIMTmin: beta = 0.08, 95%CI = 0.01-0.16) in the reverse direction MR, which attenuated to non-significant in sensitivity analysis. Our work does not find evidence supporting causal associations between cIMT and stroke. The pronounced cIMT-stroke association is intrinsic, and mostly attributed to shared genetic components. The clinical value of cIMT as a surrogate marker for stroke risk in the general population is likely limited.

Micro-Doppler based Human Activity Recognition using ABOA based Dual Spatial Convolution with Gated Recurrent Unit

The through-wall capability, device-free detection of radar-based human activity recognition are drawing a lot of interest from both academics and industry. The majority of radar-based systems do not yet combine signal analysis and feature extraction in the frequency domain and the time domain. Applications like smart homes, assisted living, and monitoring rely on human identification and activity recognition (HIAR). Radar has a number of advantages over other sensing modalities, such as the ability to shield users' privacy and conduct contactless sensing. The article introduces a new human tracking system that uses radar and a classifier called Dual Spatial Convolution Gated Recurrent Unit (DSC-GRU) to identify the subject and their behavior. The system follows the person and identifies the type of motion whenever it detects movement. One important feature is the integration of the GRU with the DSC unit, which allows the model to simultaneously capture the spatiotemporal dependence. Present prediction models just take into account spatial features that are immediately adjacent to each other, disregarding or just superimposing global spatial features when taking spatial correlation into account. A new dependency graph is created by calculating the correlation among nodes using the correlation coefficient; this graph represents the global spatial dependence, while the classic static graph represents the neighboring spatial dependence in the DSC unit. The DSC unit goes a step further by using a modified gated mechanism to quantify the various contributions of both local and global spatial correlation. While previous models performed worse, the suggested model outperformed them with an accuracy of 99.45 percent and a precision of 97.15 percent.