Search

Recently, deep learning techniques have been used for low-dose CT (LDCT) reconstruction to reduce the radiation risk for patients. Despite the improvement in performance, the network models used for LDCT reconstruction are becoming increasingly complex and computationally expensive under the mantra of “deeper is better”. However, in clinical settings, lightweight models with a low computational cost and short reconstruction times are more popular. For this reason, this paper proposes a computationally efficient CNN model with a simple structure for sparse-view LDCT reconstruction. Inspired by super-resolution networks for natural images, the proposed model interpolates projection data directly in the sinogram domain with a fully convolutional neural network that consists of only four convolution layers. The proposed model can be used directly for sparse-view CT reconstruction by concatenating the classic filtered back-projection (FBP) module, or it can be incorporated into existing dual-domain reconstruction frameworks as a generic sinogram domain module. The proposed model is validated on both the 2016 NIH-AAPM-Mayo Clinic LDCT Grand Challenge dataset and The Lung Image Database Consortium dataset. It is shown that despite the computational simplicity of the proposed model, its reconstruction performance at lower sparsity levels (1/2 and 1/4 radiation dose) is comparable to that of the sophisticated baseline models and shows some advantages at higher sparsity levels (1/8 and 1/15 radiation dose). Compared to existing sinogram domain baseline models, the proposed model is computationally efficient and easy to train on small training datasets, and is thus well suited for clinical real-time reconstruction tasks.

The atmospheric density of the thermosphere is a fundamental parameter for spacecraft launch and orbit control. Under magnetic storm conditions, the thermospheric atmospheric density experiences significant fluctuations, which have a negative impact on spacecraft control. Exploring thermospheric density during geomagnetic storms can help to mitigate the effects of such events. Research on the inversion of accelerometer measurements for different satellites and the variations of atmospheric density under extreme conditions is still in its infancy. In this paper, the distribution of atmospheric density during three geomagnetic storms is investigated from the inversion results of the Swarm-C accelerometer. Three major geomagnetic storms and their recovery phases are selected as case studies. The thermospheric density obtained by Swarm-C is separated into day and night regions. The empirical orthogonal function analysis method is used to study the spatiotemporal distribution of thermospheric density during geomagnetic storms. The results indicate that storms have a more significant impact on nighttime thermospheric density. The impact of magnetic storms on the temporal distribution of thermospheric density is considerable. The first-order empirical orthogonal function (EOF) time coefficient value on the day after the storm is the largest, reaching 2–3 times that before the magnetic storm. The impact of magnetic storms on atmospheric density is mainly reflected in the time distribution. The spatial distribution of atmospheric density is less affected by magnetic storms and is relatively stable in the short term. The impact of magnetic storms on the spatial distribution of nighttime thermospheric density is more significant than that of daytime regions, and the response of daytime regions to magnetic storms is slower.

Recently, the Vision Transformer (ViT) model has been used for various computer vision tasks, due to its advantages to extracting long-range features. To better integrate the long-range features useful for classification, the standard ViT adds a class token, in addition to patch tokens. Despite state-of-the-art results on some traditional vision tasks, the ViT model typically requires large datasets for supervised training, and thus, it still face challenges in areas where it is difficult to build large datasets, such as medical image analysis. In the ViT model, only the output corresponding to the class token is fed to a Multi-Layer Perceptron (MLP) head for classification, and the outputs corresponding to the patch tokens are exposed. In this paper, we propose an improved ViT architecture (called ViT-Patch), which adds a shared MLP head to the output of each patch token to balance the feature learning on the class and patch tokens. In addition to the primary task, which uses the output of the class token to discriminate whether the image is malignant, a secondary task is introduced, which uses the output of each patch token to determine whether the patch overlaps with the tumor area. More interestingly, due to the correlation between the primary and secondary tasks, the supervisory information added to the patch tokens help with improving the performance of the primary task on the class token. The introduction of secondary supervision information also improves the attention interaction among the class and patch tokens. And by this way, ViT reduces the demand on dataset size. The proposed ViT-Patch is validated on a publicly available dataset, and the experimental results show its effectiveness for both malignant identification and tumor localization.

We used the Swarm-C accelerometer data to invert the orbital atmospheric density in this study. First, the Swarm-C satellite mission data were obtained from the ESA’s public data platform, and preliminary data error correction was performed. This paper refers to the calibration method of GRACE-A satellite accelerometer data. It adds linear temperature correction on the original basis. Moreover, this study’s accelerometer data correction results were compared with the data correction results published by the ESA. In order to explore the influence of light radiation on the accelerometer, we established a geometric model of Swarm-C to simulate the physical shape of the satellite surface. The light radiation pressure model and the shadow area judgment model were established, the change in the light radiation acceleration during the transition process of the satellite from the umbra area to the penumbra area and then to the shadowless area was studied, and the state transition during the transition process was analyzed. Finally, the atmospheric drag coefficient was calculated based on the Sentman model. Atmospheric density inversion calculations were performed using the above data. We show the spatial distribution of atmospheric density at a fixed latitude, testing our results during geomagnetic storms. We compared the density results with existing research data, demonstrating the effectiveness of our approach.

The attitude closed-loop control of the parallel platform in the working space needs to determine the relationship between the pose of the top moving platform and the length of each mechanical arm, that is, the kinematics problem of the parallel platform. In this study, the kinematics model of the six-degree-of-freedom parallel platform was established. The kinematics forward solution algorithm based on Newton–Raphson iteration was studied. The kinematics forward solution method usually adopts a numerical solution, which often needs multiple iterations, and the algorithm has a poor real-time performance. In order to improve the real-time performance of the parallel platform control system, a multivariate polynomial regression kinematics forward solution algorithm is proposed in this paper. Moreover, by combining the multivariate polynomial regression with the Newton iterative method, we obtained an efficient solution algorithm with controllable solution accuracy. The effectiveness of the proposed method was verified by simulation tests and physical tests.

The modeling and simulation of biological tissue is the core part of a virtual surgery system. In this study, the geometric and physical methods related to soft tissue modeling were investigated. Regarding geometric modeling, the problem of repeated inverse calculations of control points in the Bezier method was solved via re-parameterization, which improved the calculation speed. The base surface superposition method based on prior information was proposed to make the deformation model not only have the advantages of the Bezier method but also have the ability to fit local irregular deformation surfaces. Regarding physical modeling, the fitting ability of the particle spring model to the anisotropy of soft tissue was improved by optimizing the topological structure of the particle spring model. Then, the particle spring model had a more extensive nonlinear fitting ability through the dynamic elastic coefficient parameter. Finally, the secondary modeling of the elastic coefficient based on the virtual body spring enabled the model to fit the creep and relaxation characteristics of biological tissue according to the elongation of the virtual body spring.

Stereo matching is the operation of obtaining the parallax value between two images by matching all the corresponding image points in the two images, thus obtaining the dense parallax image between the two images. How to obtain accurate disparity images has always been a key point in the field of stereo vision. Presently, in the research of 3D reconstruction technology based on binocular stereo vision, the main research direction of domestic and foreign scholars is to improve the efficiency and accuracy of stereo matching, and there is research literature on soft tissues. This paper proposes an improved stereo matching algorithm based on joint similarity measures and adaptive weights. The algorithm improves the matching cost calculation based on the joint similarity measure to fit the color image of the heart soft tissue. At the same time, the algorithm uses the idea of graph cutting to improve the adaptive weight. The experimental results show that both the improved joint similarity measure and the improved adaptive weight can effectively reduce the mismatch rate. In addition, the corresponding matching effect is better than using only one of the improved joint similarity measures.

At present, machine sense of smell has shown its important role and advantages in many scenarios. The development of machine sense of smell is inseparable from the support of corresponding data and algorithms. However, the process of olfactory data collection is relatively cumbersome, and it is more difficult to collect labeled data. However, in many scenarios, to use a small amount of labeled data to train a good-performing classifier, it is not feasible to rely only on supervised learning algorithms, but semi-supervised learning algorithms can better cope with only a small amount of labeled data and a large amount of unlabeled data. This study combines the new weighted kernel with SKELM and proposes a semi-supervised extreme learning machine algorithm based on the weighted kernel, SELMWK. The experimental results show that the proposed SELMWK algorithm has good classification performance and can solve the semi-supervised gas classification task of the same domain data well on the used dataset.

This research mainly studies the semi-supervised learning algorithm of different domain data in machine olfaction, also known as sensor drift compensation algorithm. Usually for this kind of problem, it is difficult to obtain better recognition results by directly using the semi-supervised learning algorithm. For this reason, we propose a domain transformation semi-supervised weighted kernel extreme learning machine (DTSWKELM) algorithm, which converts the data through the domain and uses SWKELM algorithmic classification to transform the semi-supervised classification problem of different domain data into a semi-supervised classification problem of the same domain data.

The key to image-guided surgery (IGS) technology is to find the transformation relationship between preoperative 3D images and intraoperative 2D images, namely, 2D/3D image registration. A feature-based 2D/3D medical image registration algorithm is investigated in this study. We use a two-dimensional weighted spatial histogram of gradient directions to extract statistical features, overcome the algorithm’s limitations, and expand the applicable scenarios under the premise of ensuring accuracy. The proposed algorithm was tested on CT and synthetic X-ray images, and compared with existing algorithms. The results show that the proposed algorithm can improve accuracy and efficiency, and reduce the initial value’s sensitivity.

Learning information from a single or a few samples is called few-shot learning. This learning method will solve deep learning’s dependence on a large sample. Deep learning achieves few-shot learning through meta-learning: “how to learn by using previous experience”. Therefore, this paper considers how the deep learning method uses meta-learning to learn and generalize from a small sample size in image classification. The main contents are as follows. Practicing learning in a wide range of tasks enables deep learning methods to use previous empirical knowledge. However, this method is subject to the quality of feature extraction and the selection of measurement methods supports set and the target set. Therefore, this paper designs a multi-scale relational network (MSRN) aiming at the above problems. The experimental results show that the simple design of the MSRN can achieve higher performance. Furthermore, it improves the accuracy of the datasets within fewer samples and alleviates the overfitting situation. However, to ensure that uniform measurement applies to all tasks, the few-shot classification based on metric learning must ensure the task set’s homologous distribution.

Image-guided surgery (IGS) can reduce the risk of tissue damage and improve the accuracy and targeting of lesions by increasing the surgery’s visual field. Three-dimensional (3D) medical images can provide spatial location information to determine the location of lesions and plan the operation process. For real-time tracking and adjusting the spatial position of surgical instruments, two-dimensional (2D) images provide real-time intraoperative information. In this experiment, 2D/3D medical image registration algorithm based on the gray level is studied, and the registration based on normalized cross-correlation is realized. The Gaussian Laplacian second-order differential operator is introduced as a new similarity measure to increase edge information and internal detail information to solve single information and small convergence regions of the normalized cross-correlation algorithm. The multiresolution strategy improves the registration accuracy and efficiency to solve the low efficiency of the normalized cross-correlation algorithm.

As the vital technology of natural language understanding, sentence representation reasoning technology mainly focuses on sentence representation methods and reasoning models. Although the performance has been improved, there are still some problems, such as incomplete sentence semantic expression, lack of depth of reasoning model, and lack of interpretability of the reasoning process. Given the reasoning model’s lack of reasoning depth and interpretability, a deep fusion matching network is designed in this paper, which mainly includes a coding layer, matching layer, dependency convolution layer, information aggregation layer, and inference prediction layer. Based on a deep matching network, the matching layer is improved. Furthermore, the heuristic matching algorithm replaces the bidirectional long-short memory neural network to simplify the interactive fusion. As a result, it improves the reasoning depth and reduces the complexity of the model; the dependency convolution layer uses the tree-type convolution network to extract the sentence structure information along with the sentence dependency tree structure, which improves the interpretability of the reasoning process. Finally, the performance of the model is verified on several datasets. The results show that the reasoning effect of the model is better than that of the shallow reasoning model, and the accuracy rate on the SNLI test set reaches 89.0%. At the same time, the semantic correlation analysis results show that the dependency convolution layer is beneficial in improving the interpretability of the reasoning process.

With the development of artificial intelligence, more and more people hope that computers can understand human language through natural language technology, learn to think like human beings, and finally replace human beings to complete the highly difficult tasks with cognitive ability. As the key technology of natural language understanding, sentence representation reasoning technology mainly focuses on the sentence representation method and the reasoning model. Although the performance has been improved, there are still some problems such as incomplete sentence semantic expression, lack of depth of reasoning model, and lack of interpretability of the reasoning process. In this paper, a multi-layer semantic representation network is designed for sentence representation. The multi-attention mechanism obtains the semantic information of different levels of a sentence. The word order information of the sentence is also integrated by adding the relative position mask between words to reduce the uncertainty caused by word order. Finally, the method is verified on the task of text implication recognition and emotion classification. The experimental results show that the multi-layer semantic representation network can promote sentence representation’s accuracy and comprehensiveness.