Search

This paper introduces a real-time GeoAI workflow for large-scale image analysis and the segmentation of Arctic permafrost features at a fine-granularity. Very high-resolution (0.5m) commercial imagery is used in this analysis. To achieve real-time prediction, our workflow employs a lightweight, deep learning-based instance segmentation model, SparseInst, which introduces and uses Instance Activation Maps to accurately locate the position of objects within the image scene. Experimental results show that the model can achieve better accuracy of prediction at a much faster inference speed than the popular Mask-RCNN model.

Additional file 1: Figure S1. Gut microbiota (GM) composition differences among healthy adolescent controls (HC), unmedicated depressive adolescents (DEP) and sertraline-treated adolescents. A Venn diagram of feature profiling among three groups. B Genus abundance of Roseburia in the HC, DEP, and DEP-sertraline treated groups. Data were displayed as Minimum to Maximum in B. Significant differences among the three groups were determined via Kruskal–Wallis test, Benjamini–Hochberg test was applied for multiple comparison. Figure S2. The detailed Trp-Kyn metabolic pathway and NAD+ concentration in serum. A Representation of Trp catabolism along 5-HT and Kyn branches. B NAD+ concentration in the serum of DEP and DEP-sertraline treated adolescents. C Correlation analysis between serum NAD+ level and RCADS. Data were represented as mean ± SEM. ****p < 0.0001 versus DEP group. Significant differences were determined via Student’s t-test and correlations between RCADS and NAD+ levels was shown in Pearson’s r value. Trp, tryptophan; 5-HT, 5-hydroxytryptamine; TDO: tryptophan 2,3-dioxygenase; IDO: indoleamine 2,3-dioxygenase; Kyn: Kynurenine; KATs: kynurenine aminotransferases; Kyna: kynurenic acid; KYNU: kynureninase; AA: anthranilic acid; KMO: kynurenine 3-monooxygenase; 3-HK: 3-hydroxycanuridine; XA: xanthurenic acid; 3-HAA: 3-hydroxyanthranilic acid; PA: picolinic acid; 3HAO: 3-hydroxyanthranilate 3,4-dioxygenase; Quin: quinolinic acid; QPRT: quinolinate phosphoribosyl transferase; NAM: nicotinamide; NAD/NADP: nicotinamide adenine dinucleotide/nicotinamide adenine dinucleotide phosphate. RCADS: the Revised Child Anxiety and Depression Scale. Figure S3. Trp-derived metabolites in the PFC and serum of FMT mice. A Other downstream products of kynurenine pathway (KP) and Trp-5-HT branch in PFC determined by UHPLC-MS/MS. B Levels of Trp-Kyn and Trp-5-HT pathway metabolites detected by UHPLC-MS/MS in mouse serum of GM transplantation model, and the levels of Kyna, Quin and NAD+ were measured by ELISA. Data were represented as mean ± SEM. *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001 versus CTR group; ##p < 0.01, ####p < 0.0001 versus CRS group; &&&p < 0.001, &&&&p < 0.0001 versus CRS + HC-tr group. All data here were analyzed by one-way ANOVA, Tukey’s multiple comparison test was applied for post hoc test. Figure S4. Concentrations of neurotransmitters along Trp-derived metabolic pathways in Ri. intervened mice. A Other downstream products of KP and Trp-5-HT branches in PFC. B Concentrations of neurotransmitters from Trp-Kyn and Trp-5-HT metabolic pathway in mouse serum. Data were represented as mean ± SEM. *p < 0.05, **p < 0.01, ***p < 0.001, ****p < 0.0001 versus CTR + PBS group; &p < 0.05, &&p < 0.01, &&&p < 0.001, &&&&p < 0.0001 versus CTR + Ri group; #p < 0.05, ##p < 0.01, ####p < 0.0001 versus CRS + PBS group. All data here were analyzed by two-way ANOVA, Tukey’s multiple comparison test was applied for post hoc test. Figure S5. Expression of large neutral amino acid transporter 1 (LAT1) in PFC and mucus changes in colon of each treatment group. A LAT1 expression in PFC of Ri. gavage mice. B Statistical graph of LAT1. Data were represented as mean ± SEM. *p < 0.05, versus the CTR + PBS group; #p < 0.05 versus the CRS + PBS group. Significant differences were determined via two-way ANOVA, Tukey’s multiple comparison test was applied for post hoc test. Table S1. Demographic characteristics of depressive and healthy control participants. Table S2. Specific primers sequences.

Additional file 1: Table A1. Odds ratio (95% CI) associated with HL and PMPU in male and female, and the gender comparison.

Knowledge graphs are a key technique for linking and integrating cross-domain data, concepts, tools, and knowledge to enable data-driven analytics. As much of the worlds data have become massive in size, visualizing graph entities and their interrelationships intuitively and interactively has become a crucial task for ingesting and better utilizing graph content to support semantic reasoning, discovering hidden knowledge discovering, and better scientific understanding of geophysical and social phenomena. Despite the fact that many such phenomena (e.g., disasters) have clear spatial footprints and geographical properties, their location information is considered only as a textual label in existing graph visualization tools, limiting their capability to reveal the geospatial distribution patterns of the graph nodes. In addition, most graph visualization techniques rely on 2D graph visualization, which constraints the dimensions of information that can be presented and lacks support for graph structure examination from multiple angles. To tackle the above challenges, we developed a novel 3D map-based graph visualization algorithm to enable interactive exploration of graph content and patterns in a spatially explicit manner. The algorithm extends a 3D force directed graph by integrating a web map, an additional geolocational force, and a force balancing variable that allows for the dynamic adjustment of the 3D graph structure and layout. This mechanism helps create a balanced graph view between the semantic forces among the graph nodes and the attractive force from a geolocation to a graph node. Our solution offers a new perspective in visualizing and understanding spatial entities and events in a knowledge graph.

This article investigates the challenge of achieving functional tool-use grasping with high-DoF anthropomorphic hands, with the aim of enabling anthropomorphic hands to perform tasks that require human-like manipulation and tool-use. However, accomplishing human-like grasping in real robots present many challenges, including obtaining diverse functional grasps for a wide variety of objects, handling generalization ability for kinematically diverse robot hands and precisely completing object shapes from a single-view perception. To tackle these challenges, we propose a six-step grasp synthesis algorithm based on fine-grained contact modeling that generates physically plausible and human-like functional grasps for category-level objects with minimal human demonstrations. With the contact-based optimization and learned dense shape correspondence, the proposed algorithm is adaptable to various objects in same category and a board range of robot hand models. To further demonstrate the robustness of the framework, over 10K functional grasps are synthesized to train our neural network, named DexFG-Net, which generates diverse sets of human-like functional grasps based on the reconstructed object model produced by a shape completion module. The proposed framework is extensively validated in simulation and on a real robot platform. Simulation experiments demonstrate that our method outperforms baseline methods by a large margin in terms of grasp functionality and success rate. Real robot experiments show that our method achieved an overall success rate of 79\% and 68\% for tool-use grasp on 3-D printed and real test objects, respectively, using a 5-Finger Schunk Hand. The experimental results indicate a step towards human-like grasping with anthropomorphic hands., Comment: 20 pages, 23 figures and 7 tables

Light field (LF) images captured by LF cameras can store the intensity and direction information of light rays in the scene, which have advantages in many computer vision tasks, such as 3D reconstruction, target tracking and so on. But there is a trade-off between the spatial and angular resolution of LF images due to the fixed resolution of sensor in LF cameras. So LF image super-resolution (SR) is widely explored. Most of the existing methods do not consider the different degree of importance of spatial and angular information provided by other views in LF. So we propose a LF spatial-angular attention module (LFSAA) to adjust the weights of spatial and angular information in spatial and angular domain respectively. Based on this module, a LF image SR network is designed to super-resolve all views in LF simultaneously. And we further combine the LF image SR network with single image SR network to improve the ability to explore spatial information of a single image in LF. Experiments on both synthetic and real-world LF datasets have demonstrated the performance of our method.

Dual-energy CT is an FDA approved CT technique introduced into fast clinical scanners 10 years ago. It may be obtained in multiple ways, such as switching the tube voltages of the X-ray source rapidly during the scan (usually between 80 kVp and 140 kVp) to generate images with different energy levels. Different materials including soft tissues, bone, and contrast agent, have different CT number attenuation ratios at low- versus high-energy, where CT number is a quantitative scale for describing radio-density. Based on this property, different materials can be separated. Currently there are very limited numbers of contrast agents designed for dual-energy CT, and the long-term goal of our research is to develop a silicon-based novel enteric contrast agent for dual-energy CT.In order to get FDA approval for initial human testing, it is important to collect in vivo bio-elimination and impurity data for the novel contrast agent. The main purpose of my research is to access the safety of the novel contrast agent, including: 1) Quantification of bio-eliminated contrast agent in mice; 2) Semi-quantification of bio-eliminated contrast agent in phantoms and rats; 3) Heavy metal quantification for fumed silica beads.Based on our in vivo DECT imaging tests, most of the novel contrast agent will be eliminated out of rats in approximately 2 days, but further quantitative verification is still needed. In addition, although the amounts of most heavy metals are below the daily allowable threshold limit, undesirably high amounts of barium and lead are seen in this novel contrast agent. Further tests and modifications are necessary to better quantify and improve the contrast agent before it will be ready for human testing.

The vibration based signal processing technique is one of the principal tools for diagnosing faults of rotating machinery. Empirical mode decomposition (EMD), as a time-frequency analysis technique, has been widely used to process vibration signals of rotating machinery. But it has the shortcoming of mode mixing in decomposing signals. To overcome this shortcoming, ensemble empirical mode decomposition (EEMD) was proposed accordingly. EEMD is able to reduce the mode mixing to some extent. The performance of EEMD, however, depends on the parameters adopted in the EEMD algorithms. In most of the studies on EEMD, the parameters were selected artificially and subjectively. To solve the problem, a new adaptive ensemble empirical mode decomposition method is proposed in this paper. In the method, the sifting number is adaptively selected, and the amplitude of the added noise changes with the signal frequency components during the decomposition process. The simulation, the experimental and the application results demonstrate that the adaptive EEMD provides the improved results compared with the original EEMD in diagnosing rotating machinery.