Search

Background and purposeClinical studies showed that prolonged infusion of methotrexate (MTX) leads to more severe adverse reactions than short infusion of MTX at the same dose. We hypothesized that it is the saturation of folate polyglutamate synthetase (FPGS) at high MTX concentration that limits the intracellular synthesis rate of methotrexate polyglutamate (MTX-PG). Due to a similar accumulation rate, a longer infusion duration may increase the concentration of MTX-PG and, result in more serious adverse reactions. In this study, we validated this hypothesis.Experimental approachA549, BEL-7402 and MHCC97H cell lines were treated with MTX at gradient concentrations. Liquid chromatograph-mass spectrometer (UPLC-MS/MS) was used to quantify the intracellular concentration of MTX-PG and the abundance of FPGS and γ-glutamyl hydrolase (GGH). High quality data were used to fit the cell pharmacokinetic model.Key resultsBoth cell growth inhibition rate and intracellular MTX-PG concentration showed a nonlinear relationship with MTX concentration. The parameter Vmax in the model, which represents the synthesis rate of MTX-PG, showed a strong correlation with the abundance of intracellular FPGS.Conclusion and implicationsAccording to the model fitting results, it was confirmed that the abundance of FPGS is a decisive factor limiting the synthesis rate of MTX-PG. The proposed hypothesis was verified in this study. In addition, based on the intracellular metabolism, a reasonable explanation was provided for the correlation between the severity of adverse reactions of MTX and infusion time. This study provides a new strategy for the individualized treatment and prediction of efficacy/side effects of MTX.

Substation equipment defects are important factors affecting the safe operation of power grids. However, many non-rigid defects have low detection accuracy and poor robustness,due to boundary ambiguity, irregular shape and tiny size. To address these problems,we propose a swin-transformer with recursive gated convolution framework for substation equipment non-rigid defect. Firstly, in order to effectively detect non-rigid defect objects to improve the discriminability of image features, we design the Swin-Transformer with Recursive Gated Convolution(Swin-RGC) framework to extract the interaction features between spaces in the deep model. Secondly, to avoid the loss of object location information, the Task-aligned One-stage Object Detection(TOOD) head is improved by fusing Coordinate Attention modules. Finally, a substation equipment defect detection dataset is established to provide a baseline for detecting non-rigid defects in substation power equipment. Experiment results on our dataset demonstrate that our proposed method achieves the performance of 69.9% Mean Average Precision (mAP) in the substation equipment non-rigid defect detection, which outweighs the state-of-the-art approaches.

In substation lightning rod meter reading data taking, the classical object detection model is not suitable for deployment in substation monitoring hardware devices due to its large size, large number of parameters, and slow detection speed, while is difficult to balance detection accuracy and real-time requirements with the existing lightweight object detection model. To address this problem, this paper constructs a lightweight object detection algorithm, YOLOv5-Meter Reading Lighting (YOLOv5-MRL), based on the improved YOLOv5 model’s speed while maintaining accuracy. Then, the YOLOv5s are pruned based on the convolutional kernel channel soft pruning algorithm, which greatly reduces the number of parameters in the YOLOv5-MRL model while maintaining a certain accuracy loss. Finally, in order to facilitate the dial reading, the dial external circle fitting method is proposed to calculate the dial reading using the circular angle algorithm. The experimental results on the self-built dataset show that the YOLOv5-MRL object detection model achieves a mean average precision of 96.9%, a detection speed of 5 ms/frame, and a model weight size of 5.5 MB, making it better than other advanced dial reading models.

Magnetar is proposed as one of the possible central engines for a gamma-ray burst (GRB). Recent studies show that if a magnetar has a rotational axis misaligned from the magnetic one, a periodic lightcurve pattern is expected with a period of seconds to minutes. Inspired by this unique feature, in this paper, we search for the quasiperiodic oscillation (QPO) signals in the Swift observations of GRBs. Using the Lomb–Scargle periodogram and the weighted wavelet Z-transform algorithms, we find that the Swift Burst Alert Telescope data of GRB 210514A has a QPO signal with a period ∼11 s. The estimated confidence level of the signal is over 3 σ . The global lightcurve of this GRB exhibits a double-plateau structure with a sharp decay segment between plateaus. The lightcurve feature resembles those of GRBs that were reported to have internal plateaus. We explain the observations of GRB 210514A with a supramassive magnetar (SMM) model, where the QPO signal in the first plateau is produced via the dipole radiation of the SMM experiencing a precession motion, the sharp decay is due to the collapse of the SMM into a black hole (BH), and the second plateau could be produced via the fallback accretion of the newborn BH. We fit the precession model to the observations using the Bayesian statistic and the best-fit magnetar parameters are discussed. Alternative models concerning a BH central engine may also provide reasonable explanations for this burst, only in this case the QPO signal could merely be a coincidence.

The accurate and efficient detection of defective insulators is an essential prerequisite for ensuring the safety of the power grid in the new generation of intelligent electrical system inspections. Currently, traditional object detection algorithms for detecting defective insulators in images face issues such as excessive parameter size, low accuracy, and slow detection speed. To address the aforementioned issues, this article proposes an insulator defect detection model based on the lightweight Faster R-CNN (Faster Region-based Convolutional Network) model (Faster R-CNN-tiny). First, the Faster R-CNN model’s backbone network is turned into a lightweight version of it by substituting EfficientNet for ResNet (Residual Network), greatly decreasing the model parameters while increasing its detection accuracy. The second step is to employ a feature pyramid to build feature maps with various resolutions for feature fusion, which enables the detection of objects at various scales. In addition, replacing ordinary convolutions in the network model with more efficient depth-wise separable convolutions increases detection speed while slightly reducing network detection accuracy. Transfer learning is introduced, and a training method involving freezing and unfreezing the model is employed to enhance the network’s ability to detect small target defects. The proposed model is validated using the insulator self-exploding defect dataset. The experimental results show that Faster R-CNN-tiny significantly outperforms the Faster R-CNN (ResNet) model in terms of mean average precision (mAP), frames per second (FPS), and number of parameters.

The field of computer vision has shown great potential for the identification of crops at large scales based on multispectral images. However, the challenge in designing crop identification networks lies in striking a balance between accuracy and a lightweight framework. Furthermore, there is a lack of accurate recognition methods for non-large-scale crops. In this paper, we propose an improved encoder-decoder framework based on DeepLab v3+ to accurately identify crops with different planting patterns. The network employs ShuffleNet v2 as the backbone to extract features at multiple levels. The decoder module integrates a convolutional block attention mechanism that combines both channel and spatial attention mechanisms to fuse attention features across the channel and spatial dimensions. We establish two datasets, DS1 and DS2, where DS1 is obtained from areas with large-scale crop planting, and DS2 is obtained from areas with scattered crop planting. On DS1, the improved network achieves a mean intersection over union (mIoU) of 0.972, overall accuracy (OA) of 0.981, and recall of 0.980, indicating a significant improvement of 7.0%, 5.0%, and 5.7%, respectively, compared to the original DeepLab v3+. On DS2, the improved network improves the mIoU, OA, and recall by 5.4%, 3.9%, and 4.4%, respectively. Notably, the number of parameters and giga floating-point operations (GFLOPs) required by the proposed Deep-agriNet is significantly smaller than that of DeepLab v3+ and other classic networks. Our findings demonstrate that Deep-agriNet performs better in identifying crops with different planting scales, and can serve as an effective tool for crop identification in various regions and countries.

Motion estimation is a major issue in applications of Unmanned Aerial Vehicles (UAVs). This paper proposes an entire solution to solve this issue using information from an Inertial Measurement Unit (IMU) and a monocular camera. The solution includes two steps: visual location and multisensory data fusion. In this paper, attitude information provided by the IMU is used as parameters in Kalman equations, which are different from pure visual location methods. Then, the location of the system is obtained, and it will be utilized as the observation in data fusion. Considering the multiple updating frequencies of sensors and the delay of visual observation, a multi-rate delay-compensated optimal estimator based on the Kalman filter is presented, which could fuse the information and obtain the estimation of 3D positions as well as translational speed. Additionally, the estimator was modified to minimize the computational burden, so that it could run onboard in real time. The performance of the overall solution was assessed using field experiments on a quadrotor system, compared with the estimation results of some other methods as well as the ground truth data. The results illustrate the effectiveness of the proposed method.

Cortical vein thrombosis (CVT) is a rare subtype of cerebral venous thrombosis. Because CVT is rare and its clinical and imaging findings are atypical, the misdiagnosis of CVT may be extremely high. We report a case of cortical venous infarction (CVI) secondary to CVT. Due to the atypical symptoms, we were perplexed about confirming the diagnosis between CVI and glioma hemorrhage. Eventually, CVT was confirmed by pathology combined with imaging.

Scene text recognition is a crucial area of research in computer vision. However, current mainstream scene text recognition models suffer from incomplete feature extraction due to the small downsampling scale used to extract features and obtain more features. This limitation hampers their ability to extract complete features of each character in the image, resulting in lower accuracy in the text recognition process. To address this issue, a novel text recognition model based on multi-scale fusion and the convolutional recurrent neural network (CRNN) has been proposed in this paper. The proposed model has a convolutional layer, a feature fusion layer, a recurrent layer, and a transcription layer. The convolutional layer uses two scales of feature extraction, which enables it to derive two distinct outputs for the input text image. The feature fusion layer fuses the different scales of features and forms a new feature. The recurrent layer learns contextual features from the input sequence of features. The transcription layer outputs the final result. The proposed model not only expands the recognition field but also learns more image features at different scales; thus, it extracts a more complete set of features and achieving better recognition of text. The results of experiments are then presented to demonstrate that the proposed model outperforms the CRNN model on text datasets, such as Street View Text, IIIT-5K, ICDAR2003, and ICDAR2013 scenes, in terms of text recognition accuracy.

Meter reading is an important part of intelligent inspection, and the current meter reading method based on target detection has problems of low accuracy and large error. In order to improve the accuracy of automatic meter reading, this paper proposes an automatic reading method for pointer-type meters based on the YOLOv5-Meter Reading (YOLOv5-MR) model. Firstly, in order to improve the detection performance of small targets in YOLOv5 framework, a multi-scale target detection layer is added to the YOLOv5 framework, and a set of Anchors is designed based on the lightning rod dial data set; secondly, the loss function and up-sampling method are improved to enhance the model training convergence speed and obtain the optimal up-sampling parameters; Finally, a new external circle fitting method of the dial is proposed, and the dial reading is calculated by the center angle algorithm. The experimental results on the self-built dataset show that the Mean Average Precision (mAP) of the YOLOv5-MR target detection model reaches 79%, which is 3% better than the YOLOv5 model, and outperforms other advanced pointer-type meter reading models.

Adding an attention module to the deep convolution semantic segmentation network has significantly enhanced the network performance. However, the existing channel attention module focusing on the channel dimension neglects the spatial relationship, causing location noise to transmit to the decoder. In addition, the spatial attention module exemplified by self-attention has a high training cost and challenges in execution efficiency, making it unsuitable to handle large-scale remote sensing data. We propose an efficient vector pooling attention (VPA) module for building the channel and spatial location relationship. The module can locate spatial information better by performing a unique vector average pooling in the vertical and horizontal dimensions of the feature maps. Furthermore, it can also learn the weights directly by using the adaptive local cross-channel interaction. Multiple weight learning ablation studies and comparison experiments with the classical attention modules were conducted by connecting the VPA module to a modified DeepLabV3 network using ResNet50 as the encoder. The results show that the mIoU of our network with the addition of an adaptive local cross-channel interaction VPA module increases by 3% compared to the standard network on the MO-CSSSD. The VPA-based semantic segmentation network can significantly improve precision efficiency compared with other conventional attention networks. Furthermore, the results on the WHU Building dataset present an improvement in IoU and F1-score by 1.69% and 0.97%, respectively. Our network raises the mIoU by 1.24% on the ISPRS Vaihingen dataset. The VPA module can also significantly improve the network’s performance on small target segmentation.

Microstrip series-fed weighted arrays have widespread applications in millimeter wave (MMW) radar due to their low profile and light weight. Our study proposes a novel Ka-band compact monopulse radar antenna design with a highly directional 2D series-fed microstrip array antenna. The structure is composed of a symmetrical four quadrant radiation array and an innovative stripline monopulse comparator with two segments. Our novel design applies the stripline in the back-end which considerably reduces the antenna’s backward radiation. The shaped patterns in the E and H planes are achieved by tapering patch widths and adjusting the impedance transformer of each subarray. Four half power quadrature hybrids are combined to form 2D monopulse feeding in the back-end. Both parts adopt a simple symmetrical layout that simplifies the design process. The measured reflection coefficients of each port are lower than −10 dB across 34.5 GHz to 35.5 GHz working band meanwhile isolation between these ports are better than 25 dB. Furthermore, the first side lobe level (FSLL) in the sum beam, which is remarkably suppressed by Taylor synthesis design method, achieves about −24 dB both in E and H planes. The measured gain of the sum pattern achieves 25.3 dBi at 35 GHz center frequency, while the nulling depth of the difference patterns in both planes are lower than −30 dB.

Image retrieval is becoming more and more important due to the rapid increase of the number of images on the web. To improve the efficiency of computing the similarity of images, hashing has moved into the focus of research. This paper proposes a Deep Attention-based Hash (DAH) retrieval model, which combines an attention module and a convolutional neural network to obtain hash codes with strong representability. Our DAH has the following features: The Hamming distance between the hash codes generated by similar images is small and the Hamming distance of hash codes of dissimilar images has a larger constant value. The quantitative loss from Euclidean distance to Hamming distance is minimized. DAH has a high image retrieval precision: We thoroughly compare it with ten state-of-the-art approaches on the CIFAR-10 dataset. The results show that the Mean Average Precision (MAP) of DAH reaches more than 92% in terms of 12, 24, 36 and 48 bit hash codes on CIFAR-10, which is better than what the state-of- art methods used for comparison can deliver.

DNA-binding proteins (DBPs) play pivotal roles in many biological functions such as alternative splicing, RNA editing, and methylation. Many traditional machine learning (ML) methods and deep learning (DL) methods have been proposed to predict DBPs. However, these methods either rely on manual feature extraction or fail to capture long-term dependencies in the DNA sequence. In this paper, we propose a method, called PDBP-Fusion, to identify DBPs based on the fusion of local features and long-term dependencies only from primary sequences. We utilize convolutional neural network (CNN) to learn local features and use bi-directional long-short term memory network (Bi-LSTM) to capture critical long-term dependencies in context. Besides, we perform feature extraction, model training, and model prediction simultaneously. The PDBP-Fusion approach can predict DBPs with 86.45% sensitivity, 79.13% specificity, 82.81% accuracy, and 0.661 MCC on the PDB14189 benchmark dataset. The MCC of our proposed methods has been increased by at least 9.1% compared to other advanced prediction models. Moreover, the PDBP-Fusion also gets superior performance and model robustness on the PDB2272 independent dataset. It demonstrates that the PDBP-Fusion can be used to predict DBPs from sequences accurately and effectively; the online server is at http://119.45.144.26:8080/PDBP-Fusion/.

Background Several studies have investigated the effect of non–vitamin K antagonist oral anticoagulants (NOACs) in atrial fibrillation (AF) patients with cancer, but the results remain controversial. Therefore, we conducted a meta‐analysis to compare the efficacy and safety of NOACs versus warfarin in this population. Methods and Results We systematically searched the PubMed and Embase databases until February 16, 2019 for studies comparing the effect of NOACs with warfarin in AF patients with cancer. Risk ratios (RRs) with 95% CIs were extracted and pooled by a random‐effects model. Five studies involving 8908 NOACs and 12 440 warfarin users were included. There were no significant associations between cancer status and risks of stroke or systemic embolism, major bleeding, or death in AF patients. Compared with warfarin, NOACs were associated with decreased risks of stroke or systemic embolism (RR, 0.52; 95% CI, 0.28–0.99), venous thromboembolism (RR, 0.37, 95% CI, 0.22–0.63), and intracranial or gastrointestinal bleeding (RR, 0.65; 95% CI, 0.42–0.98) and with borderline significant reductions in ischemic stroke (RR, 0.63; 95% CI, 0.40–1.00) and major bleeding (RR, 0.73; 95% CI, 0.53–1.00). In addition, risks of efficacy and safety outcomes of NOACs versus warfarin were similar between AF patients with and without cancer. Conclusions In patients with AF and cancer, compared with warfarin, NOACs had lower or similar rates of thromboembolic and bleeding events and posed a reduced risk of venous thromboembolism.

OBJECTIVES:The primary objective of this study was to establish a novel method to assess the effect of imipenem/cilastatin (IMP) on liver function laboratory indexes in Chinese underage inpatients (inpatients aged

The interpolation of Thiele-type continued fractions is thought of as the traditional rational interpolation and plays a significant role in numerical analysis and image interpolation. Different to the classical method, a novel type of bivariate Thiele-like rational interpolation continued fractions with parameters is proposed to efficiently address the interpolation problem. Firstly, the multiplicity of the points is adjusted strategically. Secondly, bivariate Thiele-like rational interpolation continued fractions with parameters is developed. We also discuss the interpolant algorithm, theorem, and dual interpolation of the proposed interpolation method. Many interpolation functions can be gained through adjusting the parameter, which is flexible and convenient. We also demonstrate that the novel interpolation function can deal with the interpolation problems that inverse differences do not exist or that there are unattainable points appearing in classical Thiele-type continued fractions interpolation. Through the selection of proper parameters, the value of the interpolation function can be changed at any point in the interpolant region under unaltered interpolant data. Numerical examples are given to show that the developed methods achieve state-of-the-art performance.

For ocean-going vessels sailing in different areas on the sea, the change of external environment factors will cause frequent changes in load, traditional ship air-conditioning system is usually designed with a fixed cooling capacity, this design method causes serious waste of resources. A new type of sea-based air conditioning system is proposed in this paper, which uses the sea-based source heat pump system, combined with variable air volume, variable water technology. The multifunctional cabins’ dynamic loads for a ship navigating in a typical Eurasian route were calculated based on Simulink. The model can predict changes in full voyage load. Based on the simulation model, the effects of variable air volume and variable water volume on the energy consumption of the air-conditioning system are analyzed. The results show that: When the VAV is coupled with the VWV, the energy saving rate is 23.2%. Therefore, the application of variable air volume and variable water technology to marine air conditioning systems can achieve economical and energy saving advantages.

General interpolation formulae for bivariate interpolation are established by introducing multiple parameters, which are extensions and improvements of those studied by Tan and Fang. The general interpolation formulae include general interpolation formulae of symmetric branched continued fraction, general interpolation formulae of univariate and bivariate interpolation, univariate block based blending rational interpolation, bivariate block based blending rational interpolation and their dual schemes, and some interpolation form studied by many scholars in recent years. We discuss the interpolation theorem, algorithms, dual interpolation, and special cases and give many kinds of interpolation scheme. Numerical examples are given to show the effectiveness of the method.

Depth estimation is an important task in computer vision. Collecting data at scale for monocular depth estimation is challenging, as this task requires simultaneously capturing RGB images and depth information. Therefore, data augmentation is crucial for this task. Existing data augmentationmethods often employ pixel-wise transformations, whichmay inadvertently disrupt edge features. In this paper, we propose a data augmentationmethod formonocular depth estimation, which we refer to as the Perpendicular-Cutdepth method. This method involves cutting realworld depth maps along perpendicular directions and pasting them onto input images, thereby diversifying the data without compromising edge features. To validate the effectiveness of the algorithm, we compared it with existing convolutional neural network (CNN) against the current mainstream data augmentation algorithms. Additionally, to verify the algorithm's applicability to Transformer networks, we designed an encoder-decoder network structure based on Transformer to assess the generalization of our proposed algorithm. Experimental results demonstrate that, in the field of monocular depth estimation, our proposed method, Perpendicular-Cutdepth, outperforms traditional data augmentationmethods. On the indoor dataset NYU, our method increases accuracy from0.900 to 0.907 and reduces the error rate from0.357 to 0.351. On the outdoor dataset KITTI, our method improves accuracy from 0.9638 to 0.9642 and decreases the error rate from 0.060 to 0.0598. [ABSTRACT FROM AUTHOR]

Species distribution models have been widely used to explore suitable habitats of species, the impact of climate change on the distribution of suitable habitats of species, and the construction of ecological reserves. This paper introduced species distribution models commonly used in biodiversity analysis, as well as model performance evaluation indexes, challenges in the application of species distribution models, and finally prospected the development trend of research on species distribution models. [ABSTRACT FROM AUTHOR]

The field of computer vision has shown great potential for the identification of crops at large scales based on multispectral images. However, the challenge in designing crop identification networks lies in striking a balance between accuracy and a lightweight framework. Furthermore, there is a lack of accurate recognition methods for non-large-scale crops. In this paper, we propose an improved encoder-decoder framework based on DeepLab v3+ to accurately identify crops with different planting patterns. The network employs ShuffleNet v2 as the backbone to extract features at multiple levels. The decoder module integrates a convolutional block attention mechanism that combines both channel and spatial attention mechanisms to fuse attention features across the channel and spatial dimensions. We establish two datasets, DS1 and DS2, where DS1 is obtained from areas with large-scale crop planting, and DS2 is obtained from areas with scattered crop planting. On DS1, the improved network achieves a mean intersection over union (mIoU) of 0.972, overall accuracy (OA) of 0.981, and recall of 0.980, indicating a significant improvement of 7.0%, 5.0%, and 5.7%, respectively, compared to the original DeepLab v3+. On DS2, the improved network improves the mIoU, OA, and recall by 5.4%, 3.9%, and 4.4%, respectively. Notably, the number of parameters and giga floating-point operations (GFLOPs) required by the proposed Deep-agriNet is significantly smaller than that of DeepLab v3+ and other classic networks. Our findings demonstrate that DeepagriNet performs better in identifying crops with different planting scales, and can serve as an effective tool for crop identification in various regions and countries. [ABSTRACT FROM AUTHOR]