Estimation of the anisotropy of hydraulic conductivity through 3D fracture networks using the directional geological entropy

With an extension of the geological entropy concept in porous media,the approach called directional entrogram is applied to link hydraulic behavior to the anisotropy of the 3D fracture networks.A metric called directional entropic scale is used to measure the anisotropy of spatial order in different directions.Compared with the traditional connectivity indexes based on the statistics of fracture geometry,the directional entropic scale is capable to quantify the anisotropy of connectivity and hydraulic conductivity in heterogeneous 3D fracture networks.According to the numerical analysis of directional entrogram and fluid flow in a number of the 3D fracture networks,the hydraulic conductivities and entropic scales in different directions both increase with spatial order(i.e.,trace length decreasing and spacing increasing)and are independent of the dip angle.As a result,the nonlinear correlation between the hydraulic conductivities and entropic scales from different directions can be unified as quadratic polynomial function,which can shed light on the anisotropic effect of spatial order and global entropy on the heterogeneous hydraulic behaviors.

Numerical Study of the Biomechanical Behavior of a 3D Printed Polymer Esophageal Stent in the Esophagus by BP Neural Network Algorithm

Esophageal disease is a common disorder of the digestive system that can severely affect the quality of life andprognosis of patients. Esophageal stenting is an effective treatment that has been widely used in clinical practice.However, esophageal stents of different types and parameters have varying adaptability and effectiveness forpatients, and they need to be individually selected according to the patient’s specific situation. The purposeof this study was to provide a reference for clinical doctors to choose suitable esophageal stents. We used 3Dprinting technology to fabricate esophageal stents with different ratios of thermoplastic polyurethane (TPU)/(Poly-ε-caprolactone) PCL polymer, and established an artificial neural network model that could predict the radial forceof esophageal stents based on the content of TPU, PCL and print parameter. We selected three optimal ratios formechanical performance tests and evaluated the biomechanical effects of different ratios of stents on esophagealimplantation, swallowing, and stent migration processes through finite element numerical simulation and in vitrosimulation tests. The results showed that different ratios of polymer stents had different mechanical properties,affecting the effectiveness of stent expansion treatment and the possibility of postoperative complications of stentimplantation.

Design,progress and challenges of 3D carbon-based thermally conductive networks

The advent of the 5G era has stimulated the rapid development of high power electronics with dense integration.Three-dimensional(3D)thermally conductive networks,possessing high thermal and electrical conductivities and many different structures,are regarded as key materials to improve the performance of electronic devices.We provide a critical overview of carbonbased 3D thermally conductive networks,emphasizing their preparation-structure-property relationships and their applications in different scenarios.A detailed discussion of the microscopic principles of thermal conductivity is provided,which is crucial for increasing it.This is followed by an in-depth account of the construction of 3D networks using different carbon materials,such as graphene,carbon foam,and carbon nanotubes.Techniques for the assembly of two-dimensional graphene into 3D networks and their effects on thermal conductivity are emphasized.Finally,the existing challenges and future prospects for 3D carbon-based thermally conductive networks are discussed.

3D Road Network Modeling and Road Structure Recognition in Internet of Vehicles

Internet of Vehicles (IoV) is a new system that enables individual vehicles to connect with nearby vehicles,people, transportation infrastructure, and networks, thereby realizing amore intelligent and efficient transportationsystem. The movement of vehicles and the three-dimensional (3D) nature of the road network cause the topologicalstructure of IoV to have the high space and time complexity.Network modeling and structure recognition for 3Droads can benefit the description of topological changes for IoV. This paper proposes a 3Dgeneral roadmodel basedon discrete points of roads obtained from GIS. First, the constraints imposed by 3D roads on moving vehicles areanalyzed. Then the effects of road curvature radius (Ra), longitudinal slope (Slo), and length (Len) on speed andacceleration are studied. Finally, a general 3D road network model based on road section features is established.This paper also presents intersection and road section recognition methods based on the structural features ofthe 3D road network model and the road features. Real GIS data from a specific region of Beijing is adopted tocreate the simulation scenario, and the simulation results validate the general 3D road network model and therecognitionmethod. Therefore, thiswork makes contributions to the field of intelligent transportation by providinga comprehensive approach tomodeling the 3Droad network and its topological changes in achieving efficient trafficflowand improved road safety.

Luminescence regulation of Sb^(3+)in 0D hybrid metal halides by hydrogen bond network for optical anti-counterfeiting

The Sb^(3+) doping strategy has been proven to be an effective way to regulate the band gap and improve the photophysical properties of organic-inorganic hybrid metal halides(OIHMHs).However,the emission of Sb^(3+) ions in OIHMHs is primarily confined to the low energy region,resulting in yellow or red emissions.To date,there are few reports about green emission of Sb^(3+)-doped OIHMHs.Here,we present a novel approach for regulating the luminescence of Sb^(3+) ions in 0D C_(10)H_(2)_(2)N_(6)InCl_(7)·H_(2)O via hydrogen bond network,in which water molecules act as agents for hydrogen bonding.Sb^(3+)-doped C_(10)H_(2)2N_(6)InCl_(7)·H_(2)O shows a broadband green emission peaking at 540 nm and a high photoluminescence quantum yield(PLQY)of 80%.It is found that the intense green emission stems from the radiative recombination of the self-trapped excitons(STEs).Upon removal of water molecules with heat,C_(10)H_(2)_(2)N_(6)In_(1-x)Sb_(x)Cl_(7) generates yellow emis-sion,attributed to the breaking of the hydrogen bond network and large structural distortions of excited state.Once water molecules are adsorbed by C_(10)H_(2)_(2)N_(6)In_(1-x)Sb_(x)Cl_(7),it can subsequently emit green light.This water-induced reversible emission switching is successfully used for optical security and information encryption.Our findings expand the under-standing of how the local coordination structure influences the photophysical mechanism in Sb^(3+)-doped metal halides and provide a novel method to control the STEs emission.

SGT-Net: A Transformer-Based Stratified Graph Convolutional Network for 3D Point Cloud Semantic Segmentation

In recent years,semantic segmentation on 3D point cloud data has attracted much attention.Unlike 2D images where pixels distribute regularly in the image domain,3D point clouds in non-Euclidean space are irregular and inherently sparse.Therefore,it is very difficult to extract long-range contexts and effectively aggregate local features for semantic segmentation in 3D point cloud space.Most current methods either focus on local feature aggregation or long-range context dependency,but fail to directly establish a global-local feature extractor to complete the point cloud semantic segmentation tasks.In this paper,we propose a Transformer-based stratified graph convolutional network(SGT-Net),which enlarges the effective receptive field and builds direct long-range dependency.Specifically,we first propose a novel dense-sparse sampling strategy that provides dense local vertices and sparse long-distance vertices for subsequent graph convolutional network(GCN).Secondly,we propose a multi-key self-attention mechanism based on the Transformer to further weight augmentation for crucial neighboring relationships and enlarge the effective receptive field.In addition,to further improve the efficiency of the network,we propose a similarity measurement module to determine whether the neighborhood near the center point is effective.We demonstrate the validity and superiority of our method on the S3DIS and ShapeNet datasets.Through ablation experiments and segmentation visualization,we verify that the SGT model can improve the performance of the point cloud semantic segmentation.

3D Ice Shape Description Method Based on BLSOM Neural Network

When checking the ice shape calculation software,its accuracy is judged based on the proximity between the calculated ice shape and the typical test ice shape.Therefore,determining the typical test ice shape becomes the key task of the icing wind tunnel tests.In the icing wind tunnel test of the tail wing model of a large amphibious aircraft,in order to obtain accurate typical test ice shape,the Romer Absolute Scanner is used to obtain the 3D point cloud data of the ice shape on the tail wing model.Then,the batch-learning self-organizing map(BLSOM)neural network is used to obtain the 2D average ice shape along the model direction based on the 3D point cloud data of the ice shape,while its tolerance band is calculated using the probabilistic statistical method.The results show that the combination of 2D average ice shape and its tolerance band can represent the 3D characteristics of the test ice shape effectively,which can be used as the typical test ice shape for comparative analysis with the calculated ice shape.

Review of Artificial Intelligence for Oil and Gas Exploration: Convolutional Neural Network Approaches and the U-Net 3D Model

Deep learning, especially through convolutional neural networks (CNN) such as the U-Net 3D model, has revolutionized fault identification from seismic data, representing a significant leap over traditional methods. Our review traces the evolution of CNN, emphasizing the adaptation and capabilities of the U-Net 3D model in automating seismic fault delineation with unprecedented accuracy. We find: 1) The transition from basic neural networks to sophisticated CNN has enabled remarkable advancements in image recognition, which are directly applicable to analyzing seismic data. The U-Net 3D model, with its innovative architecture, exemplifies this progress by providing a method for detailed and accurate fault detection with reduced manual interpretation bias. 2) The U-Net 3D model has demonstrated its superiority over traditional fault identification methods in several key areas: it has enhanced interpretation accuracy, increased operational efficiency, and reduced the subjectivity of manual methods. 3) Despite these achievements, challenges such as the need for effective data preprocessing, acquisition of high-quality annotated datasets, and achieving model generalization across different geological conditions remain. Future research should therefore focus on developing more complex network architectures and innovative training strategies to refine fault identification performance further. Our findings confirm the transformative potential of deep learning, particularly CNN like the U-Net 3D model, in geosciences, advocating for its broader integration to revolutionize geological exploration and seismic analysis.

Alloy gene Gibbs energy partition function and equilibrium holographic network phase diagrams of AuCu_3-type sublattice system

Taking AuCu3-type sublattice system as an example, three discoveries have been presented: First, the third barrier hindering the progress in metal materials science is that researchers have got used to recognizing experimental phenomena of alloy phase transitions during extremely slow variation in temperature by equilibrium thinking mode and then taking erroneous knowledge of experimental phenomena as selected information for establishing Gibbs energy function and so-called equilibrium phase diagram. Second, the equilibrium holographic network phase diagrams of AuCu3-type sublattice system may be used to describe systematic correlativity of the composition?temperature-dependent alloy gene arranging structures and complete thermodynamic properties, and to be a standard for studying experimental subequilibrium order-disorder transition. Third, the equilibrium transition of each alloy is a homogeneous single-phase rather than a heterogeneous two-phase, and there exists a single-phase boundary curve without two-phase region of the ordered and disordered phases; the composition and temperature of the top point on the phase-boundary curve are far away from the ones of the critical point of the AuCu3 compound.

Alloy gene Gibbs energy partition function and equilibrium holographic network phase diagrams of Au_3Cu-type sublattice system

Taking Au3Cu-type sublattice system as an example, three discoveries have been presented. First, the fourth barrier to hinder the progress of metal materials science is that today’s researchers do not understand that the Gibbs energy function of an alloy phase should be derived from Gibbs energy partition function constructed of alloy gene sequence and their Gibbs energy sequence. Second, the six rules for establishing alloy gene Gibbs energy partition function have been discovered, and it has been specially proved that the probabilities of structure units occupied at the Gibbs energy levels in the degeneracy factor for calculating configuration entropy should be degenerated as ones of component atoms occupied at the lattice points. Third, the main characteristics unexpected by today’s researchers are as follows. There exists a single-phase boundary curve without two-phase region coexisting by the ordered and disordered phases. The composition and temperature of the top point on the phase-boundary curve are far away from those of the critical point of the Au3Cu compound; At 0 K, the composition of the lowest point on the composition-dependent Gibbs energy curve is notably deviated from that of the Au3Cu compounds. The theoretical limit composition range of long range ordered Au3Cu-type alloys is determined by the first jumping order degree.

Performance analysis in 3G/ad hoc integrated network

An analytical approach to evaluate the performance of the 3G/ad hoc integrated network is presented. A channel model capturing both path loss and shadowing is applied to the analysis so as to characterize power falloff vs. distance. The 3G/ad hoc integrated network scenario model is introduced briefly. Based on this model, several performances of the 3G/ ad hoc integrated network in terms of outage probability, call dropping probability and new call blocking probability are evaluated. The corresponding performance formulae are deduced in accordance with the analytical models. Meanwhile, the formula of the 3G/ad hoc integrated network capacity is deduced on the basis of the formula of the outage probability. It is observed from extensive simulation and numerical analysis that the 3G/ad hoc integrated network remarkably outperforms the 3G network with regards to the network performance. This derived evaluation approach can be applied into planning and optimization of the 3G/ad hoc network.

Array Networks为3G清除安全障碍

刚刚上市的Array Networks在金融危机中将位于北京的Array Networks（北京）公司搬人了CBD核心区，做好了新一轮扩张的准备，同时该公司CEO赵耀对外宣布的新产品计划锁定了中国3G市场，可见，这家全球领先的SSLVPN以及负载均衡解决方案提供商的3G准备已经完成。

Prediction of flow stress of Ti-15-3 alloy with artificial neural network

Hot compression experiments were conducted on Ti 15 3 alloy specimens using Gleeble 1500 Thermal Simulator.These tests were focused to obtain the flow stress data under various conditions of strain,strain rate and temperature. On the basis of these data, the predicting model for the nonlinear relation between flow stress and deformation strain,strain rate and temperature for Ti 15 3 alloy was developed with a back propagation artificial neural network method. Results show that the neural network can reproduce the flow stress in the sampled data and predict the nonsampled data well. Thus the neural network method has been verified to be used to tackle hot deformation problems of Ti 15 3 alloy. [

Dynamic Hand Gesture Recognition Using 3D-CNN and LSTM Networks

Recognition of dynamic hand gestures in real-time is a difficult task because the system can never know when or from where the gesture starts and ends in a video stream.Many researchers have been working on visionbased gesture recognition due to its various applications.This paper proposes a deep learning architecture based on the combination of a 3D Convolutional Neural Network(3D-CNN)and a Long Short-Term Memory(LSTM)network.The proposed architecture extracts spatial-temporal information from video sequences input while avoiding extensive computation.The 3D-CNN is used for the extraction of spectral and spatial features which are then given to the LSTM network through which classification is carried out.The proposed model is a light-weight architecture with only 3.7 million training parameters.The model has been evaluated on 15 classes from the 20BN-jester dataset available publicly.The model was trained on 2000 video-clips per class which were separated into 80%training and 20%validation sets.An accuracy of 99%and 97%was achieved on training and testing data,respectively.We further show that the combination of 3D-CNN with LSTM gives superior results as compared to MobileNetv2+LSTM.

CurveNet:Curvature-Based Multitask Learning Deep Networks for 3D Object Recognition

In computer vision fields,3D object recognition is one of the most important tasks for many real-world applications.Three-dimensional convolutional neural networks(CNNs)have demonstrated their advantages in 3D object recognition.In this paper,we propose to use the principal curvature directions of 3D objects(using a CAD model)to represent the geometric features as inputs for the 3D CNN.Our framework,namely CurveNet,learns perceptually relevant salient features and predicts object class labels.Curvature directions incorporate complex surface information of a 3D object,which helps our framework to produce more precise and discriminative features for object recognition.Multitask learning is inspired by sharing features between two related tasks,where we consider pose classification as an auxiliary task to enable our CurveNet to better generalize object label classification.Experimental results show that our proposed framework using curvature vectors performs better than voxels as an input for 3D object classification.We further improved the performance of CurveNet by combining two networks with both curvature direction and voxels of a 3D object as the inputs.A Cross-Stitch module was adopted to learn effective shared features across multiple representations.We evaluated our methods using three publicly available datasets and achieved competitive performance in the 3D object recognition task.

Sacrificial microgel‑laden bioink‑enabled 3D bioprinting of mesoscale pore networks

Three-dimensional(3D)bioprinting is a powerful approach that enables the fabrication of 3D tissue constructs that retain complex biological functions.However,the dense hydrogel networks that form after the gelation of bioinks often restrict the migration and proliferation of encapsulated cells.Herein,a sacrificial microgel-laden bioink strategy was designed for directly bioprinting constructs with mesoscale pore networks(MPNs)for enhancing nutrient delivery and cell growth.The sacrificial microgel-laden bioink,which contains cell/gelatin methacryloyl(GelMA)mixture and gelled gelatin microgel,is first thermo-crosslinked to fabricate temporary predesigned cell-laden constructs by extrusion bioprinting onto a cold platform.Then,the construct is permanently stabilized through photo-crosslinking of GelMA.The MPNs inside the printed constructs are formed after subsequent dissolution of the gelatin microgel.These MPNs allowed for effective oxygen/nutrient diffusion,facilitating the generation of bioactive tissues.Specifically,osteoblast and human umbilical vein endothelial cells encapsulated in the bioprinted large-scale constructs(≥1 cm)with MPNs showed enhanced bioactivity during culture.The 3D bioprinting strategy based on the sacrificial microgel-laden bioink provided a facile method to facilitate formation of complex tissue constructs with MPNs and set a foundation for future optimization of MPN-based tissue constructs with applications in diverse areas of tissue engineering.

Behavior recognition based on the fusion of 3D-BN-VGG and LSTM network

In order to effectively solve the problems of low accuracy,large amount of computation and complex logic of deep learning algorithms in behavior recognition,a kind of behavior recognition based on the fusion of 3 dimensional batch normalization visual geometry group(3D-BN-VGG)and long short-term memory(LSTM)network is designed.In this network,3D convolutional layer is used to extract the spatial domain features and time domain features of video sequence at the same time,multiple small convolution kernels are stacked to replace large convolution kernels,thus the depth of neural network is deepened and the number of network parameters is reduced.In addition,the latest batch normalization algorithm is added to the 3-dimensional convolutional network to improve the training speed.Then the output of the full connection layer is sent to LSTM network as the feature vectors to extract the sequence information.This method,which directly uses the output of the whole base level without passing through the full connection layer,reduces the parameters of the whole fusion network to 15324485,nearly twice as much as those of 3D-BN-VGG.Finally,it reveals that the proposed network achieves 96.5%and 74.9%accuracy in the UCF-101 and HMDB-51 respectively,and the algorithm has a calculation speed of 1066 fps and an acceleration ratio of 1,which has a significant predominance in velocity.

Quantification of 3D macropore networks in forest soils in Touzhai valley(Yunnan,China)using X-ray computed tomography and image analysis

The three dimensional （3D） geometry of soil macropores largely controls preferential flow, which is a significant infiltrating mechanism for rainfall in forest soils and affects slope stability. However, detailed studies on the 3D geometry of macropore networks in forest soils are rare. The intense rainfall-triggered potentially unstable slopes were threatening the villages at the downstream of Touzhai valley （Yunnan, China）. We visualized and quantified the 3D macropore networks in undisturbed soil columns （Histosols） taken from a forest hillslope in Touzhai valley, and compared them with those in agricultural soils （corn and soybean in USA; barley, fodder beet and red fescue in Denmark） and grassland soils in USA. We took two large undisturbed soil columns （250 mm^25o mmxsoo mm）, and scanned the soil columns at in-situ soil water content conditions using X-ray computed tomography at a voxel resolution of 0.945 × 0.945 × 1.500o mm^3. After reconstruction and visualization, we quantified the characteristics of macropore networks. In the studied forest soils, the main types of maeropores were root channels, inter-aggregate voids, maeropores without knowing origin, root-soil interfaee and stone-soil interface. While maeropore networks tend to be more eomplex, larger, deeper and longer. The forest soils have high maeroporosity, total maeropore wall area density, node density, and large maeropore volume, hydraulie radius, mean maeropore length, angle, and low tortuosity. The findings suggest that maeropore networks in the forest soils have high inter- connectivity, vertical continuity, linearity and less vertically oriented.

基于改进DeepLabv3+算法的起重机锈迹检测

室外工作的起重机金属结构易产生锈蚀现象,严重的锈蚀会导致结构承载能力显著降低,从而引发灾难性事故。文中针对当前起重机人工锈迹巡检中存在的漏检、误检和费时等问题,提出一种基于改进DeepLabv3+算法的自动化锈迹检测方法。该方法依托于机器视觉,将原始DeepLabv3+的骨干网络替换为幽灵网络(GhostNet)以提升网络的轻量化程度;使用特征金字塔网络(FPN)进行特征提取,用于抑制噪声和背景对锈迹提取的不良干扰;引入空间感知独立自注意机制(SSA)来提高网络区域感知性能;最后使用特征融合(Add)代替原始网络的特征堆叠来降低算法参数量。将所提方法应用于室外起重机锈迹检测,结果表明所提算法的检测性能优于原始算法和其他经典语义分割算法,具有重要的工程应用价值。

Ex vivo 3D osteocyte network construction with primary murine bone cells

Osteocytes reside as three-dimensionally（3D） networked cells in the lacunocanalicular structure of bones and regulate bone and mineral homeostasis. Despite of their important regulatory roles, in vitro studies of osteocytes have been challenging because：（1） current cell lines do not sufficiently represent the phenotypic features of mature osteocytes and（2） primary cells rapidly differentiate to osteoblasts upon isolation. In this study, we used a 3D perfusion culture approach to：（1） construct the 3D cellular network of primary murine osteocytes by biomimetic assembly with microbeads and（2） reproduce ex vivo the phenotype of primary murine osteocytes, for the first time to our best knowledge. In order to enable 3D construction with a sufficient number of viable cells, we used a proliferated osteoblastic population of healthy cells outgrown from digested bone chips. The diameter of microbeads was controlled to：（1） distribute and entrap cells within the interstitial spaces between the microbeads and（2） maintain average cell-to-cell distance to be about 19 mm. The entrapped cells formed a 3D cellular network by extending and connecting their processes through openings between the microbeads. Also, with increasing culture time, the entrapped cells exhibited the characteristic gene expressions（SOST and FGF23） and nonproliferative behavior of mature osteocytes. In contrast, 2D-cultured cells continued their osteoblastic differentiation and proliferation. This 3D biomimetic approach is expected to provide a new means of：（1） studying flow-induced shear stress on the mechanotransduction function of primary osteocytes,（2） studying physiological functions of 3D-networked osteocytes with in vitro convenience,and（3） developing clinically relevant human bone disease models.