Search

Collaboration between Light Detection and Ranging (LiDAR) point clouds and deep learning has been proven to be an effective approach for vegetation mapping. Current studies have predominantly focused on 2D vegetation mapping, whereas 3D mapping, which directly classifies point clouds at point level, offers a more comprehensive understanding of the stratified structural information of vegetation. However, there is a lack of research on 3D vegetation species mapping, and the disparities between 2D and 3D mapping in natural scenarios remain unclear. To resolve these issues, we compared the deep learning performance of 2D and 3D vegetation species mapping across three distinct natural scenes: karst wetland, mangrove forest, and hill forest. In addition, the 2D and 3D mapping in natural scenes are adversely affected by the elevated channel count of LiDAR-derived features and the extreme category imbalance in point cloud. To mitigate these challenges, we propose a novel Multi-resolution Feature Selection Network (MrFSNet) to select optimal feature combinations at different scales for better 2D mapping performance. Additionally, we introduce a novel Dynamic Weighted Sampling (DWS) strategy, which is combined with KPConv to address the extreme category imbalance present in 3D mapping. Results indicate that: (1) 3D vegetation species mapping exhibited the highest performance, achieving an mF1 of 89.78% for karst wetland, 92.25% for mangrove forest, and 92.05% for hill forest. (2) 3D mapping outperformed 2D mapping, improving mF1 by 3.43% to 27.08%. (3) MrFSNet adaptively extracted optimal features at various scales and performed well with the limited training data in 2D vegetation mapping, resulting in a 1.66%–18.46% higher mF1 than that of Swin Transformer. (4) DWS effectively resolved the extreme category imbalance problem and produced 1.28%–2.80% higher mF1 than the non-DWS version in 3D vegetation mapping.

In recent years, minimally invasive surgery has developed rapidly in the clinical practice of surgery and has gradually become one of the critical surgical techniques. Compared with traditional surgery, the advantages of minimally invasive surgery include small incisions and less pain during the operation, and the patients recover faster after surgery. With the expansion of minimally invasive surgery in several medical fields, traditional minimally invasive techniques have bottlenecks in clinical practice, such as the inability of the endoscope to determine the depth information of the lesion area from the two-dimensional images obtained, the difficulty in locating the endoscopic position information and the inability to get a complete view of the overall situation in the cavity. This paper uses a visual simultaneous localization and mapping (SLAM) approach to achieve endoscope localization and reconstruction of the surgical region in a minimally invasive surgical environment. Firstly, the K-Means algorithm combined with the Super point algorithm is used to extract the feature information of the image in the lumen environment. Compared with Super points, the logarithm of successful matching points increased by 32.69%, the proportion of effective points increased by 25.28%, the error matching rate decreased by 0.64%, and the extraction time decreased by 1.98%. Then the iterative closest point method is used to estimate the position and attitude information of the endoscope. Finally, the disparity map is obtained by the stereo matching method, and the point cloud image of the surgical area is finally recovered.

In order to enhance cone-beam computed tomography (CBCT) image information and improve the registration accuracy for image-guided radiation therapy, we propose a super-resolution (SR) image enhancement method. This method uses super-resolution techniques to pre-process the CBCT prior to registration. Three rigid registration methods (rigid transformation, affine transformation, and similarity transformation) and a deep learning deformed registration (DLDR) method with and without SR were compared. The five evaluation indices, the mean squared error (MSE), mutual information, Pearson correlation coefficient (PCC), structural similarity index (SSIM), and PCC + SSIM, were used to validate the results of registration with SR. Moreover, the proposed method SR-DLDR was also compared with the VoxelMorph (VM) method. In rigid registration with SR, the registration accuracy improved by up to 6% in the PCC metric. In DLDR with SR, the registration accuracy was improved by up to 5% in PCC + SSIM. When taking the MSE as the loss function, the accuracy of SR-DLDR is equivalent to that of the VM method. In addition, when taking the SSIM as the loss function, the registration accuracy of SR-DLDR is 6% higher than that of VM. SR is a feasible method to be used in medical image registration for planning CT (pCT) and CBCT. The experimental results show that the SR algorithm can improve the accuracy and efficiency of CBCT image alignment regardless of which alignment algorithm is used.

Due to globalization, English has gradually become a lingua franca, leading to a rising demand for proficient English teachers all over the globe. In China, more EFL teachers are being recruited, particularly at the tertiary level, with a greater preference for so-called “native English speaking teachers (NESTs)” over “non-native English-speaking teachers (NNESTs)” due to the impacts of native-speakerism. Research has shown NESTs, NNESTs, and students are often misaligned in terms of beliefs about language learning and teaching which affect teaching effectiveness as well as student achievement. Recognizing this issue, this study investigated NESTs’, NNESTs’, and Chinese English-major students’ perceptions of characteristics of effective EFL teachers at four mid-tier universities across China. Findings from semi-structured interviews with 16 students suggest that NNESTs and Chinese English-major students had similar views on language learning and teaching. Both groups valued prerequisite qualities such as having expert knowledge, language skills, teaching skills, and professionalism. NESTs, however, valued qualities such as caring, patience, flexibility, engagement, and awareness of students’ learning needs. These differences are likely the result of these two groups of teachers’ linguistic, cultural, and educational background differences. The highly uniform views of the two groups of teachers suggest that they tended to emphasize certain qualities while disregarding others. These findings suggest the need to raise teachers’ and students’ awareness of the benefits of different types of teacher qualities so that curriculum design and lesson planning can be implemented for better instructional alignment to ultimately improve teaching effectiveness.

Abstract When a severe natural disaster occurs, the extraction of post-disaster building damage information is one of the methods to quickly obtain disaster information. The increasingly mature high-resolution remote sensing technology provides a solid foundation for obtaining information about building damage. To address the issues with inaccurate building positioning in existing building damage assessment methods, as well as poor classification due to similar minor and major damage characteristics in building damage classification. Based on U-Net, we designed a two-stage building damage assessment network. The first stage is an independent U-Net focused on building segmentation, followed by a Siamese U-Net focused on building damage classification. The Extra Skip Connection and Asymmetric Convolution Block were used for enhancing the network's ability to segment buildings on different scales; Shuffle Attention directed the network's attention to the correlation of buildings before and after the disaster. The xBD dataset was used for training and testing in the study, and the overall performance was evaluated using a balanced F-score (F1). The improved network had an F1 of 0.8741 for localization and F1 of 0.7536 for classification. When compared to other methods, it achieved better overall performance for building damage assessment and was able to generalize to multiple disasters.

Abstract The water shoreline is essential for unmanned surface vessels (USVs) to navigate autonomously. Many existing traditional water shoreline detections approaches not only fail to overcome the effects of water reflections, image inversions, and other factors but are also unsuitable for water shoreline detection in a variety of weather conditions and in complex inland river scenarios. Therefore, we propose a water shoreline detection approach based on an enhanced Pyramid Scene Parsing Network (PSPNet). We introduce a migration learning approach to the PSPNet feature backbone extraction network Resnet50 to improve training efficiency and add a Convolutional Block Attention Module (CBAM) attention mechanism module to improve the robustness of training. In addition, the pyramid pooling module adds the branch of the atrous convolution module. Finally, the waterfront segmentation map is processed by the Canny edge detection method, which detects the water shorelines. For the network's training and validation, we use the USVInland dataset, the world's first urban inland driverless dataset. The experimental results show that the segmentation accuracy MIou of this paper is 96.87% and Accuracy is 98.41, which are higher than some mainstream algorithms. It is capable of detecting water shorelines accurately in a variety of interior river situations.

Abstract Robust 3D lane detection is the key to advanced autonomous driving technologies. However, complex traffic scenes such as bad weather and variable terrain are the main factors affecting the robustness of lane detection algorithms. In this paper, a generalized two-stage network called Att-Gen-LaneNet was proposed to achieve robust 3D lane detection in complex traffic scenes. The Efficient Channel Attention (ECA) module and the Convolutional Block Attention Module (CBAM) were combined in this network. In the first stage of the network, we improved the semantic segmentation network ENet and proposed the weighted cross-entropy loss function to solve the problem of ambiguous distant lane segmentation. This method improved Pixel Accuracy to 99.7% and MIoU to 89.5%. In the second stage of the network, we introduced the interpolation loss function to achieve accurate lane fitting. This method outperformed existing detection methods by 6% in F-score and Average Precision on the Apollo Synthetic dataset. The proposed method achieved better overall performance in 3D lane detection and was applicable to broader and more complex traffic scenes.

Abstract Background Different methods of acetabular reconstruction with total hip arthroplasty (THA) for Crowe II and III of adult developmental dysplasia of the hip (DDH) acetabular bone defect have been implemented clinically. However, the biomechanical effect of different augmented materials for acetabular reconstruction in THA on shell stability has never been discussed. Methods In the present study, autologous bone graft (BG)and metal (Ti6Al4V) augment (MA) were simulated with several acetabular bone defect models of DDH in THA. The contact pressure and micromotion between the shell and host bone were measured for evaluating the shell stability using a finite element method. Results The peak contact stress between shell and host bone was higher in the MA situation (12.45 vs 8.71 MPa). And the load transfer path was different, for BG models, the high local contact stresses were found at the junction of bone graft and host bone while for MA models the concentrated contact stresses were at the surface of MA. The peak relative micromotion between shell and host bone was higher in the MA situation (12.61 vs 11.13 µm). However, the peak micromotion decreased in the contact interface of MA and cup compared to the BG models. Conclusions The higher micromotion was found in MA models, however, enough for bone ingrowth, and direct stronger fixation was achieved in the MA-cup interface. Thus, we recommended the MA can be used as an option, even for Crowe III, however, the decision should be made from clinical follow-up results.

In recent years, with the development of modern technology and industrialization, the shipbuilding industry has become an essential field in a country. Offshore operations, such as helicopter take-off and landing, and ship-to-ship cargo replenishment, need an accurate prediction of ship motion attitude, not only to improve efficiency but also to protect crew members’ lives. However, using the single model has limited influence on prediction. Therefore, this paper proposed a Cross-Parallel optimization algorithm framework, which made full use of the development ability of the Harris Hawk Optimization algorithm (HHO) and the searching ability of the Sine-Cosine Algorithm (SCA). In this paper, we use Rosenbrock and Rastrigin functions for testing. The results show that the Cross-Parallel optimization algorithm has faster search speed and stronger optimization capability. The optimization algorithm is used to optimize the hyperparameters of Long Short-Term Memory (LSTM) neural networks. It improves the network’s training ability to predict the ship’s attitude. The proposed method in this paper is compared with 9 models such as BP, LSTM, GRU, BILSTM and TCN. It is tested with three degrees of freedom under different sea states. MAE and RMSE are used as the evaluation indexes of this paper. In the six sets of experimental results, compared with the other nine models, the method in this paper can reduce the MAE by up to 9.2%, 7.2%, 4.7%, 5.4%, 6.4%, and 6.8%, respectively. When using RMSE as the evaluation index, the decrease was at most 10.1%, 8.7%, 5.6%, 7.1%, 7.5%, and 8.2%. The experimental results show that the method in this paper has the highest prediction accuracy.

The insulation performance of the core transformer is determined by the winding quality of the insulation layer between the coils. It is necessary to assure uniform winding tension in order to ensure the insulation performance of the transformer and improve production efficiency. Thus, in this article, the dynamic characteristics of the transformer insulation winding process are analyzed, and the insulation winding tension control system is designed to decrease the tension fluctuation caused by the alternating change of the elliptical core radius in the winding process. Firstly, the time-varying characteristics of roll radius and inertia are analyzed, the mechanical structure and dynamic models of unwinding and rewinding are established, and the effects of upstream and downstream span length and dancer inertia on the resonant frequency and response performance of the system are revealed. Later, the influence factors of tension fluctuation and disturbance propagation frequency are investigated, and the tension control model of Hybrid dancer position feedback is established. The variable universe fuzzy PI controller is designed by setting fuzzy rules and universe adjustment factors. Finally, the stability of the controller and the weakening effect on the tension disturbance are verified by simulation, and the performance and application value of the automatic winding tension control system are tested by a series of experiments.

The scientific research strength in the aerospace field has become an essential criterion for measuring a country’s scientific and technological level and comprehensive national power, but in the grand scheme, many factors are beyond human control. As is known, the difficulty with non-cooperative target intersection docking is its failure to provide attitude information autonomously. The existing non-cooperative target poses estimation methods with low accuracy and high resource consumption. This paper proposes a deep-learning-based pose estimation method for solving these problems. The proposed pose estimation method consists of two distinctly innovative works. You Only Look Once v5 (YOLOv5) is an innovative and lightweight network that is used to pre-recognize non-cooperative targets. Another part introduces concurrent space and channel compressor theory modules in a lightweight High-Resolution Network (HRNet) to extend its advantages in real-time, and hence proposes a spatial and channel Squeeze and Excitation—Lightweight High-Resolution Network (scSE-LHRNet) network for pose estimation. To verify the superiority of the proposed network, experiments were conducted on a publicly available dataset with multiple evaluation metrics to compare and analyze existing methods. The experimental results show that the proposed pose estimation method dramatically reduces the complexity of the model, effectively decreases the amount of computation, and achieves significant pose estimation results.

Objectives: We aimed to conduct a comprehensive evaluation of the population impact of methadone maintenance treatment (MMT) for its future program planning.Methods: We conducted a literature review of the effects of MMT in China on HIV and HCV disease burden, injecting, and sexual behaviors and drug-related harm during 2004–2015. Data synthesis and analysis were conducted to obtain the pooled estimates of parameters for a mathematical model which was constructed to evaluate the effectiveness and cost-effectiveness of the program.Results: Based on a review of 134 articles, this study demonstrated that MMT is highly effective in reducing crime-related, high risk sexual, and injecting behaviors. The model estimated US$1,037 m which was invested in MMT from 2004 to 2015 has prevented 29,463 (15,325–43,600) new HIV infections, 130,563 (91,580–169,546) new HCV infections, 10,783 (10,380–11,187) deaths related to HIV, HCV and drug-related harm, and 338,920.0 (334,596.2–343,243.7) disability-adjusted life years (DALYs). The costs for each prevented HIV infection, HCV infection, death, and DALY were $35,206.8 (33,594.8–36,981.4), $7,944.7 ($7,714.4–8,189.2), $96,193.4 (92,726.0–99,930.2), and $3,060.6 ($3,022.0–3,100.1) respectively.Conclusion: The Chinese MMT program has been effective and cost-effective in reducing injecting, injecting-related risk behaviors and adversities due to HIV/HCV infection and drug-related harm among drug users.

The early diagnosis of retinopathy is crucial to the prevention and treatment of diabetic retinopathy. The low proportion of positive cases in the asymmetric microaneurysm detection problem causes preprocessing to treat microaneurysms as noise to be eliminated. To obtain a binary image containing microaneurysms, the object was segmented by a symmetry algorithm, which is a combination of the connected components and SSA methods. Next, a candidate microaneurysm set was extracted by multifeature clustering of binary images. Finally, the candidate microaneurysms were mapped to the Radon frequency domain to achieve microaneurysm detection. In order to verify the feasibility of the algorithm, a comparative experiment was conducted on the combination of the connected components and SSA methods. In addition, PSNR, FSIM, SSIM, fitness value, average CPU time and other indicators were used as evaluation standards. The results showed that the overall performance of the binary image obtained by the algorithm was the best. Last but not least, the accuracy of the detection method for microaneurysms in this paper reached up to 93.24%, which was better than that of several classic microaneurysm detection methods in the same period.

With the rapid development of science and technology as well as the comprehensive societal progress, the demand for electricity in all walks of life is also increasing. As is known to all, the mechanical structure and tension control of a transformer winding machine is the key to improving the quality of coil winding, due to coil winding being generally considered the core technology of transformer manufacturing. Aiming at the synchronous winding control problem of the conductor and insulating layer of the transformer winding machine, this paper presents a mechanical structure and tension control scheme of a new type of transformer winding machine. Based on the dynamic analysis and modeling of the mechanical structure of the winding machine, the speed control of the main speed roller by the fuzzy PID control rate is implemented initially. Combined with the actual demand of the project, the feasibility and effectiveness of the control target with different tension are verified by the simulation experiment and further compared with the traditional PID control method. The simulation results show that the proposed fuzzy PID control rate can realize the automatic and efficient winding of the transformer winding machine, showing that it is superior to the traditional PID control rate in overcoming the disturbance and controlling effect.

The compressibility of the spinel solid solutions, (Mg1−xMnx)Cr2O4 with x = 0.00 (0), 0.20 (0), 0.44 (2), 0.61 (2), 0.77 (2) and 1.00 (0), has been investigated by using a diamond-anvil cell coupled with synchrotron X-ray radiation up to ∼10 GPa (ambient T). The second-order Birch–Murnaghan equation of state was used to fit the PV data, yielding the following values for the isothermal bulk moduli (KT), 198.2 (36), 187.8 (87), 176.1 (32), 168.7 (52), 192.9 (61) and 199.2 (61) GPa, for the spinel solid solutions with x = 0.00 (0), 0.20 (0), 0.44 (2), 0.61 (2), 0.77 (2) and 1.00 (0), respectively (KT′ fixed as 4). The KT value of the MgCr2O4 spinel is in good agreement with existing experimental determinations and theoretical calculations. The correlation between the KT and x is not monotonic, with the KT values similar at both ends of the binary MgCr2O4MnCr2O4, but decreasing towards the middle. This non-monotonic correlation can be described by two equations, KT = −49.2 (11)x + 198.0 (4) (x ≤ ∼0.6) and KT = 92 (41)x + 115 (30) (x ≥ ∼0.6), and can be explained by the evolution of the average bond lengths of the tetrahedra and octahedra of the spinel solid solutions. Additionally, the relationship between the thermal expansion coefficient and composition is correspondingly reinterpreted, the continuous deformation of the oxygen array is demonstrated, and the evolution of the component polyhedra is discussed for this series of spinel solid solutions. Our results suggest that the correlation between the KT and composition of a solid solution series may be complicated, and great care should be paid while estimating the KT of some intermediate compositions from the KT of the end-members.

This manuscript addresses a new multivariate generalized predictive control strategy using the least squares support vector machine for parabolic distributed parameter systems. First, a set of proper orthogonal decomposition-based spatial basis functions constructed from a carefully selected set of data is used in a Galerkin projection for the building of an approximate low-dimensional lumped parameter systems. Then, the temporal autoregressive exogenous model obtained by the least squares support vector machine is applied in the design of a multivariate generalized predictive control strategy. Finally, the effectiveness of the proposed multivariate generalized predictive control strategy is verified through a numerical simulation study on a typical diffusion-reaction process in radical symmetry.

The thermal equation of state of a natural kyanite has been investigated with a DIA-type, cubic-anvil apparatus (SAM85) combined with an energy-dispersive synchrotron X-ray radiation technique up to 8.55 GPa and 1273 K. No phase transition was observed in the studied pressure-temperature (P-T) range. The Le Bail full profile refinement technique was used to derive the unit-cell parameters. By fixing the bulk modulus K0 as 196 GPa and its pressure derivative K0′ as 4, our P-V (volume)-T data were fitted to the high temperature Birch–Murnaghan equation of state. The obtained parameters for the kyanite are: V0 = 294.05(9) Å3, α = 2.53(11) × 10−5 K−1 and (∂K/∂T)P = −0.021(8) GPa∙K−1. These parameters have been combined with other experimentally-measured thermodynamic data for the relevant phases to calculate the P-T locus of the reaction kyanite = stishovite + corundum. With this thermodynamically constrained phase boundary, previous high-pressure phase equilibrium experimental studies with the multi-anvil press have been evaluated.

Next generation sequencing (NGS) has revolutionized life sciences research. However, GC bias and costly, time-intensive library preparation make NGS an ill fit for increasing sequencing demands in the clinic. A new class of third-generation sequencing platforms has arrived to meet this need, capable of directly measuring DNA and RNA sequences at the single-molecule level without amplification. Here, we use the new GenoCare single-molecule sequencing platform from Direct Genomics to sequence the genome of the M13 virus. Our platform detects single-molecule fluorescence by total internal reflection microscopy, with sequencing-by-synthesis chemistry. We sequenced the genome of M13 to a depth of 316x, with 100% coverage. We determined a consensus sequence accuracy of 100%. In contrast to GC bias inherent to NGS results, we demonstrated that our single-molecule sequencing method yields minimal GC bias.