Search

Existing deep learning-based interactive image segmentation methods have significantly reduced the user’s interaction burden with simple click interactions. However, they still require excessive numbers of clicks to continuously correct the segmentation for satisfactory results. This article explores how to harvest accurate segmentation of interested targets while minimizing the user interaction cost. To achieve the above goal, we propose a one-click-based interactive segmentation approach in this work. For this particularly challenging problem in the interactive segmentation task, we build a top-down framework dividing the original problem into a one-click-based coarse localization followed by a fine segmentation. A two-stage interactive object localization network is first designed, which aims to completely enclose the target of interest based on the supervision of object integrity (OI). Click centrality (CC) is also utilized to overcome the overlapping problem between objects. This coarse localization helps to reduce the search space and increase the focus of the click at a higher resolution. A principled multilayer segmentation network is then designed by a progressive layer-by-layer structure, which aims to accurately perceive the target with extremely limited prior guidance. A diffusion module is also designed to enhance the information flow between layers. Besides, the proposed model can be naturally extended to multiobject segmentation task. Our method achieves the state-of-the-art performance under one-click interaction on several benchmarks.

A near-field integrated sensing, positioning, and communication (ISPAC) framework is proposed, where a base station (BS) simultaneously serves multiple communication users and carries out target sensing and positioning. A novel double-array structure is proposed to enable the near-field ISPAC at the BS. Specifically, a small-scale assisting transceiver (AT) is attached to the large-scale main transceiver (MT) to empower the communication system with the ability of sensing and positioning. Based on the proposed framework, the joint angle and distance Cramér-Rao bound (CRB) is first derived. Then, the CRB is minimized subject to the minimum communication rate requirement in both downlink and uplink ISPAC scenarios: 1) For downlink ISPAC, a downlink target positioning algorithm is proposed and a penalty dual decomposition (PDD)-based double-loop algorithm is developed to tackle the non-convex optimization problem. 2) For uplink ISPAC, an uplink target positioning algorithm is proposed and an efficient alternating optimization algorithm is conceived to solve the non-convex CRB minimization problem with coupled user communication and target probing design. Both proposed optimization algorithms can converge to a stationary point of the CRB minimization problem. Numerical results show that: 1) The proposed ISPAC system can locate the target in both angle and distance domains merely relying on single BS and limited bandwidths; and 2) the positioning performance achieved by the hybrid-analog-and-digital ISPAC approaches that achieved by fully digital ISPAC when the communication rate requirement is not stringent.

Complicated molecular alterations in tumors generate various mutant peptides. Some of these mutant peptides can be presented to the cell surface and then elicit immune responses, and such mutant peptides are called neoantigens. Accurate detection of neoantigens could help to design personalized cancer vaccines. Although some computational frameworks for neoantigen detection have been proposed, most of them can only detect SNV‐ and indel‐derived neoantigens. In addition, current frameworks adopt oversimplified neoantigen prioritization strategies. These factors hinder the comprehensive and effective detection of neoantigens. We developed NeoHunter, flexible software to systematically detect and prioritize neoantigens from sequencing data in different formats. NeoHunter can detect not only SNV‐ and indel‐derived neoantigens but also gene fusion‐ and aberrant splicing‐derived neoantigens. NeoHunter supports both direct and indirect immunogenicity evaluation strategies to prioritize candidate neoantigens. These strategies utilize binding characteristics, existing biological big data, and T‐cell receptor specificity to ensure accurate detection and prioritization. We applied NeoHunter to the TESLA dataset, cohorts of melanoma and non‐small cell lung cancer patients. NeoHunter achieved high performance across the TESLA cancer patients and detected 79% (27 out of 34) of validated neoantigens in total. SNV‐ and indel‐derived neoantigens accounted for 90% of the top 100 candidate neoantigens while neoantigens from aberrant splicing accounted for 9%. Gene fusion‐derived neoantigens were detected in one patient. NeoHunter is a powerful tool to ‘catch all’ neoantigens and is available for free academic use on Github (XuegongLab/NeoHunter).

Gas mixtures analysis and concentration measurement is of great significance in the fields of environmental protection, industrial safety, life sciences, and so on, and the nondispersive infrared spectroscopy (NDIR) technique has emerged as a critical measurement method with its high accuracy, selectivity, stability, and fast response. Building upon a multipass optical NDIR measurement system, this article introduces a stepwise multilayer perceptron (SMLP) neural network algorithm for the rapid detection of gas mixtures. This algorithm addresses the limitations of traditional metrology methods that necessitate manual feature selection and extensive data modeling. Through the iterative application of the multilayer perceptron (MLP), this article first classifies gas mixtures and then selectively regresses them against known gas types, enabling the automatic extraction of effective features and simplification of the network structure. The results show that the multipass optical measurement data provide more environmental information, achieving higher classification accuracy and smaller regression root mean square error (RMSE). In addition, achieving the same accuracy and RMSE with fewer training samples is possible. The classification and concentration regression for CO2 and CH4 can be achieved using only 0.5 s of data, with a classification accuracy of 98.21% and normalized RMSE estimates of 0.42% and 0.45%, respectively. In contrast to commonly employed classical machine learning algorithms, the SMLP algorithm demonstrates enhanced classification and regression capabilities, offering the potential to streamline network complexity and simplify the parameterization process.

Ultrathin superconducting films are the basis of superconductor devices. van der Waals (vdW) NbSe2with noncentrosymmetry exhibits exotic superconductivity and shows promise in superconductor electronic devices. However, the growth of inch-scale NbSe2films with layer regulation remains a challenge because vdW structural material growth is strongly dependent on the epitaxial guidance of the substrate. Herein, a vdW self-epitaxy strategy is developed to eliminate the substrate driving force in film growth and realize inch-sized NbSe2film growth with thicknesses from 2.1 to 12.1 nm on arbitrary substrates. The superconducting transition temperature of 5.1 K and superconducting transition width of 0.30 K prove the top homogeneity and quality of superconductivity among all of the synthetic NbSe2films. Coupled with a large area and substrate compatibility, this work paves the way for developing NbSe2superconductor electronics.

To sequester particulate matter (PM) and chemical loads, stormwater basins are a common infrastructure component of transportation land use systems in a planning/design or a retrofit phase. Basin design relies on residence time (RT), capacity–inflow ratio (CIR), and continuous stirred-tank reactor (CSTR) concepts to provide presumptive guidance for load reduction. For example, 14-day (or 21-day) RT is presumed to provide load reduction for total suspended solids (TSS) (e.g., commonly 80%), and for total phosphorus (TP) (e.g., commonly 60%). Despite such guidance, most existing basins are impaired—not meeting presumptive guidance, whether for TSS, nutrients, or chemicals (e.g., metals). RT guidance results in high initial basin design costs (land and construction). For impaired basin retrofit, RT guidance generates a significantly higher cost (area/volume increase), if such a retrofit is even feasible considering proximate infrastructure constraints. This study presents a computational fluid dynamics (CFD)-machine learning (ML) augmented web application, DeepXtorm, for cost–benefit optimization of basin design and retrofit. DeepXtorm is examined against basin costs from as-built data, RT, CIR, and CSTR (deployed in the Storm Water Management Model [SWMM]) over a range of load reduction levels of TSS (60%–90%) and TP (40%–60%). For a given load reduction requirement, DeepXtorm demonstrates up to an order of magnitude (or more) lower basin cost compared with RT, CIR, and CSTR models, and greater than an order of magnitude compared with as-built cost data. DeepXtorm represents a more robust and cost-effective tool for stormwater basin design and retrofit.

To explore the potential protective effect of resveratrol (RES) on cold-exposed broilers, 360 21-day-old broilers were equally divided into 5 groups with 6 replicates. A control (CON) group was reared at the normal feeding temperature and received a basal diet, and 4 cold exposure (8 ± 1°C for 10 h/d from d 29 to 42) groups were fed the basal diet with 0 (CE), 250 (CE + RES250), 500 (CE + RES500), and 750 (CE + RES750) mg/kg RES from d 22 to 42. Broilers were slaughtered on d 42 and heart tissues were collected to measure the relevant indexes. The results showed that heart tissues of all CE-broilers had inflammatory cell infiltrations, and dietary RES supplementation reduced this phenomenon. Compared to CON group, the concentrations of MDA and H2O2were increased and activities of SOD and CAT were decreased in all CE-broilers (P< 0.05). mRNA expression of genes related to endoplasmic reticulum (ER) stress (GRP78, IRE1, PERK, EIF-2α, ATF4, ATF6, and CHOP), pyroptosis (NLRP3, ASC, Caspase1, GSDME, IL-18, and IL-1β), and proinflammation (TNF-α, IFN-γ, IL-2, and IL-6) was upregulated and that of ant-inflammatory cytokines (IL-4 and IL-10) was downregulated in CE and all CE + RES groups compared to CON group (P< 0.05). Compared to CE group, the activities of SOD and CAT and mRNA expression of anti-inflammatory genes were increased (P< 0.05), and concentrations of MDA and H2O2and mRNA expression of ER stress, pyroptosis and proinflammatory genes were reduced (P< 0.05) in 3 CE + RES groups. Additionally, protein levels of PERK, ATF4, CHOP, NLRP3, Caspase1, GSDMD, IL-18, IL-1β, TNF-α, and IL-10 were similar in their mRNA expression. Overall, cold exposure caused oxidative stress and ER stress, and induced pyroptosis and inflammatory response, resulting in heart injury in broilers, and dietary RES addition reduced heart damage by enhancing antioxidant defense function. This study indicates that RES can be a feed additive to alleviate cold exposure-induced heart injury in broilers, and a 500 mg RES/kg diet is the optimal supplemental level.

We propose a novel machine learning approach to reconstruct meshless surface wind speed fields, i.e., to reconstruct the surface wind speed at any location, based on meteorological background fields and geographical information. The random forest method is selected to develop the machine learning data reconstruction model (MLDRM-RF) for wind speeds over Beijing from 2015–19. We use temporal, geospatial attribute and meteorological background field features as inputs. The wind speed field can be reconstructed at any station in the region not used in the training process to cross-validate model performance. The evaluation considers the spatial distribution of and seasonal variations in the root mean squared error (RMSE) of the reconstructed wind speed field across Beijing. The average RMSE is 1.09 m s−1, considerably smaller than the result (1.29 m s−1) obtained with inverse distance weighting (IDW) interpolation. Finally, we extract the important feature permutations by the method of mean decrease in impurity (MDI) and discuss the reasonableness of the model prediction results. MLDRM-RF is a reasonable approach with excellent potential for the improved reconstruction of historical surface wind speed fields with arbitrary grid resolutions. Such a model is needed in many wind applications, such as wind energy and aviation safety assessments.

•We propose a novel method for the robust identification of parsimonious and accurate PDEs with no prior knowledge in a noisy environment.•The knowledge discovery and embedding are jointly achieved by the structural identification with the evolutionary neural network algorithm and the metadata optimization with the PINN training.•The present method actively creates candidate expressions based on a basic set of symbols using genetic operators, with no need to predefine a library of functions.•The candidate PDEs are also expressed in the form of neural networks, which are not only efficiently optimized with the data gradients information, but also embedded as physical constraints in the PINN training, embedding the discovered PDEs to further optimize the metadata used for iterative PDE identification.

Reduction of mercury(II) to elemental mercury was easily achieved using carbon dots (r-CDs) synthesized from sucrose. This reduction was accomplished with the large numbers of electrons contained in r-CDs rather than the oxidation of its functional groups.

The scale of expressway information networking is constantly expanding. Currently the existing analysis system is still built on the relational database. Traffic data produced by the system has reached a data volume of 3 million items monthly. The performance requirements, including high concurrency, massive throughput, visualisation and scalability, are difficult to be satisfied. The expressway traffic data analysis system (ETDAS) is designed to meet the needs of the collection, analysis and visualisation of increasing expressway traffic data by means of the distributed frameworks. The new system is expected to help regulate the road network traffic flow, reduce traffic congestion, and provide analytical support for the optimisation strategy of road network. ETDAS has been deployed online.

Noncentrosymmetry (NCS) is essential for a second-harmonic nonlinear-optical (NLO) crystal; however, the tailored synthesis of NCS materials has historically posed significant challenges because the adjacent dipole moments of constituted NLO-active units in the structure tend to align in opposite directions, resulting in the NLO effect being canceled as in a centrosymmetric (CS) crystal. In this work, we propose a polar-layer-driven strategy, wherein a polarization-layered framework is constructed to constrain the dipole moment to align in the same direction, thereby facilitating the formation of the NCS structure. Taking the layered structure CS K2ZnV2O7as a prototype compound, a novel vandate K4ZnV5O15Br (KZVB) was rationally synthesized via a multiple sites-oriented cosubstition method. KZVB containing two types of NLO-active units of V5+d0and Zn2+d10cations can be utilized as a mid-infrared NLO crystal with a remarkable NLO response comparable to that of nonoxide AgGaS2. This work not only broadens the effective strategy for designing novel NCS compounds but also provides a progressive development of NLO materials.

Improving immune function is an important indicator for establishing cold adaptation in broilers. In the study, to explore the effects and molecular mechanisms of intermittent and mild cold stimulation (IMCS) on the immune function of broilers, CIRP and TRPM8, induced by cold stimulation, as well as the NF-κB and MAPK pathways which play an important role in immune response, were selected to investigate. A total of 192 one-day-old broilers (Ross 308) were selected and randomly divided into the control group (CC) and the cold stimulation group (CS). The broilers in CC were raised at normal feeding temperature from d 1 to 43, while the broilers in CS were subjected to cold stimulation from day 15 to 35, with a temperature 3 °C below that of the CC group for 5 h, at 1 d intervals. The results showed that IMCS had little effect on the broiler hearts, and the myocardial structure was not damaged. On d 22, IMCS significantly increased the mRNA levels of CIRP, TRPM8, P65, P38, COX-2, TNF-α, IFN- γ, IL-6, IL-10, and the protein levels of CIRP, P65, P38, IL-1β and iNOS in the hearts, and the levels of CIRP and all cytokines in the serum (P≤ 0.05). The mRNA and protein levels of IκB-α were significantly reduced (P≤ 0.05). On d 36, the mRNA levels of TRPM8, P65, ERK,and IL-10in the hearts and the content of COX-2 in the serum in CS were increased significantly (P≤ 0.05), while the mRNA levels of IκB-α, P38,and IL-1βwere decreased significantly (P≤ 0.05). On d 43, IMCS significantly upregulated the mRNA levels of TRPM8, IFN- γ, IL-4, IL-6, IL-10, and the protein levels of IκB-α, P38, and the levels of iNOS, TNF-α, IL6 and IL10 in the serum (P≤ 0.05); whereas it significantly downregulated CIRP, JNK, P38, iNOS, TNF-αmRNA levels, and CIRP, P65, ERK, JNK, IL1β and iNOS protein levels (P≤ 0.05). Therefore, IMCS can enhance broiler immune function through co-regulation of CIRP and TRPM8 on the NF-κB and MAPK pathways, which facilitate the cold adaptation in broilers.

In this paper, the model output machine learning (MOML) method is proposed for simulating weather consultation, which can improve the forecast results of numerical weather prediction (NWP). During weather consultation, the forecasters obtain the final results by combining the observations with the NWP results and giving opinions based on their experience. It is obvious that using a suitable post-processing algorithm for simulating weather consultation is an interesting and important topic. MOML is a post-processing method based on machine learning, which matches NWP forecasts against observations through a regression function. By adopting different feature engineering of datasets and training periods, the observational and model data can be processed into the corresponding training set and test set. The MOML regression function uses an existing machine learning algorithm with the processed dataset to revise the output of NWP models combined with the observations, so as to improve the results of weather forecasts. To test the new approach for grid temperature forecasts, the 2-m surface air temperature in the Beijing area from the ECMWF model is used. MOML with different feature engineering is compared against the ECMWF model and modified model output statistics (MOS) method. MOML shows a better numerical performance than the ECMWF model and MOS, especially for winter. The results of MOML with a linear algorithm, running training period, and dataset using spatial interpolation ideas, are better than others when the forecast time is within a few days. The results of MOML with the Random Forest algorithm, year-round training period, and dataset containing surrounding gridpoint information, are better when the forecast time is longer. 数值天气预报的预报结果可以通过天气会商来进行提高, 本文提出了模式输出机器学习(MOML)方法对天气会商过程进行模拟, 从而提高数值预报结果. 通过天气会商, 预报员利用预报经验知识结合数值预报结果和观测数据得到最终的天气预报结果. 显然, 利用合适的模式后处理算法模拟预报员天气会商的过程是一个有趣和重要的课题. MOML方法是一个基于机器学习的模式后处理方法, 它通过一个回归函数将数值预报结果跟观测数据进行配置. 对数据集和训练期采用不同的特征工程技术, 我们把观测数据和模式数据处理为不同的训练集和测试集, 之后再将已有的机器学习回归算法应用到处理后的数据集中, 从而提高模式结果. 我们把这个方法应用到北京地区2米格点地表气温的ECMWF模式后处理中来进行检验. 我们设计了各种特征工程方案, 得到了不同的MOML算法模型, 并和ECMWF模式结果以及模式输出统计(MOS)方法进行比较. 数值结果表明, MOML方法的结果比ECMWF模式结果和MOS方法更好, 尤其是冬季更明显. 其中最好的MOML特征工程混合方案是短期预报用线性回归, 滑动训练器和基于空间插值思想的数据集的组合, 中期预报用随机森林, 全年训练器和包含周围格点的数据集的组合.

With the rapid development of Additive Manufacturing (AM) technology, the demand for batch printing is increasing, whose central issue is the printing layout. In order to solve the problem of insufficient utilization of space under self-supporting parts by existing nesting algorithms and reduce time spent searching for the placement position and rotation angle, a new 3D layout method is proposed based on the Convex-concave Coding Similarity of the Voxelized model (VCCCS) for AM. The voxelization method is innovatively used to generally show and standardize the geometric convexity and concavity of part surface and layout space. The Orthogonal Convex-concave Surface (OCCS) coding method is proposed to digitize the convexity and concavity of the voxelized model and layout space for the first time. Through finding Convex-concave Similarity Coding Sub-blocks (CCSCSBs), the positions in the similar geometric characteristics between the part and space can be obtained to guide the placement. The VCCCS placement method can make use of the placeable space generated by the self-supporting property of the materials, which avoids the loss of surface accuracy by stacking the parts at the same time. Experiments and corresponding analyses verify the effectiveness of the proposed algorithm and its industrial values.

In general knowledge base question answering (KBQA) models, subject recognition (SR) is usually a precondition of finding an answer, and it is a common way to employ a general named entity recognition (NER) model such as BERT-CRF to recognize the subject. However, in previous researches, the difference between a NER task and a SR task is usually ignored, and a wrong entity recognized by the NER model will certainly lead to a wrong answer in the KBQA task, which is one bottleneck for KBQA performance. In this paper, a multigranularity pruning model (MGPM) is proposed to answer a question when general models fail to recognize a subject. In MGPM, the set of all possible subjects in the Knowledge Base (KB) is pruned by 4 multigranularity pruning submodels successively based on the constraint of relation (domain and tuple), string similarity, and semantic similarity. Experimental results show that our model is compatible with various KBQA models for both single-relation and complex questions answering. The integrated MGPM model (with the BERT-CRF model) achieves a SR accuracy of 94.4% on the SimpleQuestions dataset, 68.6% on the WebQuestionsSP dataset, and 63.7% on the WebQuestions dataset, which outperforms the original model by a margin of 3.6%, 8.6%, and 5.3%, respectively.

Unfolding the “black-box” associations between genotype and phenotype is essential for understanding the molecular mechanisms of complex human diseases. Here, we describe the use of GRPath to uncover putative causal paths (pcPaths) from genetic variants to disease phenotypes. GRPath takes multiple omics data and summary statistics as input and identifies pcPaths that link the putative causal region (pcRegion), putative causal variant (pcVariant), putative causal gene (pcGene), noteworthy cell type, and disease phenotype.

Ni–Fe/Cu/Co/Cu multilayered nanowire arrays were electrodeposited into anodic aluminum oxide template by using dual-bath method at room temperature. Scanning electron microscopy and transmission electron microscopy were used to characterize the morphology and structure of the multilayered nanowire arrays. Vibrating sample magnetometer and physical property measurement system were used to measure their magnetic and giant magnetoresistance (GMR) properties. The effect of sub-layer thickness on the magnetic and GMR properties was investigated. The results indicate that magnetic properties of electrodeposited nanowires are not affected obviously by Cu layer thickness, while magnetic layers (Ni–Fe and Co layers) have significant influence. In addition, GMR ratio presents an oscillatory behavior as Cu layer thickness changes. The magnetic and GMR properties of the multilayered nanowire arrays are optimum at room temperature for the material structure of Ni–Fe (25nm)/Cu (15nm)/Co (25nm)/Cu (15nm) with 30 deposition cycles.

Type 2 corticotropin-releasing factor receptor (CRFR2) is expressed in skeletal muscle and stimulation of the receptor has been shown to inhibit the effect of insulin on glucose uptake in muscle cells. Currently, little is known about the mechanisms underlying this process. In this study, we first showed that both in vivo and in vitro CRFR2 expression in muscle was closely correlated with insulin sensitivity, with elevated receptor levels observed in insulin resistant muscle cells. Stimulation of CRFR2 by urocortin 2 (Ucn 2), a CRFR2-selective ligand, in C2C12 myotubes greatly attenuated insulin-induced glucose uptake. The inhibitory effect of CRFR2 signaling required cAMP production and is involved the mammalian target of rapamycine pathway, as rapamycin reversed the inhibitory effect of CRFR2 stimulation on insulin-induced glucose uptake. Moreover, stimulation of CRFR2 failed to inhibit glucose uptake in muscle cells induced by platelet-derived growth factor, which, similar to insulin, signals through Akt-mediated pathway but is independently of insulin receptor substrate (IRS) proteins to promote glucose uptake. This result argues that CRFR2 signaling modulates insulin's action likely at the levels of IRS. Consistent with this notion, Ucn 2 reduced insulin-induced tyrosine phosphorylation of IRS-1, and treatment with rapamycin reversed the inhibitory effect of Ucn 2 on IRS-1 and Akt phosphorylation. In conclusion, the inhibitory effect of CRFR2 signaling on insulin action is mediated by cAMP in a mammalian target of rapamycine-dependent manner, and IRS-1 is a key nodal point where CRFR2 signaling modulates insulin-stimulated glucose uptake in muscle cells.

Ni-Fe/Cu/Co/Cu multilayer nanowire arrays were electrodeposited into the pores of AAO template by using dual-bath method. The morphology and structure of the nanowire arrays were characterized by scanning electron microscopy and transmission electron microscopy. Vibrating sample magnetometer and physical property measurement system revealed that the magnetic properties and current perpendicular to the plane-giant magnetoresistance (CPP-GMR) of Ni-Fe/Cu/Co/Cu nanowire arrays were affected by the changes of nanowire diameter and period number. Along with the increase of the diameter, the coercivity and remanence ratio increased first, and then decreased. The properties of nanowire arrays were optimum and the maximum room temperature CPP-GMR ratio of 45.24% was achieved when the nanowire diameter was 80 nm and the period number was 300.

Abstract: We propose a new scheme for the generalized Kadomtsev–Petviashvili (KP) equation. The multi-symplectic conservation property of the new scheme is proved. Back error analysis shows that the new multi-symplectic scheme has second order accuracy in space and time. Numerical application on studying the KPI equation and the KPII equation are presented in detail. [Copyright &y& Elsevier]

Cancer is the main chronic disease that affects the health of Chinese residents; however, there have been few systematic studies on cancer-free life expectancy in China. We aimed to explore age-specific cancer mortality and changes in population lifespan after accounting for the removal of the burden of cancer to provide important insights and a basic reference on the development of relevant health policies, such as cancer control or elderly care.