Search

Abstract S-nitrosoglutathione reductase (GSNOR) is involved in the response to cadmium (Cd) exposure. In this study, the plants of mutant (gsnor1-3) with lossing-function of- and over-expression (GSNOR OE 5) of GSNOR were used to clear the role of GSNOR in Cd tolerance. GSNOR activity increased through upregulating the expression of the AtGSNOR gene and protein in Arabidopsis thaliana under Cd stress, which attenuated Cd tolerance. Oxidative damage was more serious in GSNOR OE 5 and was alleviated in gsnor1-3 under Cd stress, compared with Col-0. Induction of GSNOR facilitated H2O2 accumulation but inhibited catalase (CAT) activity in shoots under Cd stress. This phenotype was eliminated by 3-amino-1,2,4-triazole (3-AT), a CAT inhibitor. In addition, the expressions of AtCAT1 and AtCAT2 were down-regulated with increasing GSNOR activity under Cd stress. This suggested that GSNOR was involved in the accumulation of hydrogen peroxide (H2O2) through regulating CAT expression and activity under Cd exposure. Furthermore, Cd tolerance and CAT activity were improved by spraying S-nitrosoglutathione (GSNO) onto the surface of the leaves. The in vitro activity of CAT increased with GSNO concentration until a GSNO/CAT ratio of 2 was reached. Thus, CAT activity was relative to GSNOR through regulating the expression and S-nitrosylation level of proteins. In summary, the Cd-induced promotion of GSNOR activity aggravated Cd toxicity in plants by mediating H2O2 accumulation controlled by CAT.

Abstract Purpose The essence of this scholarly work was to carefully outline the key factors intensifying the virulence and protracted contagion of COVID-19, particularly among individuals afflicted with hematologic malignancies (HM), in an epoch predominantly governed by the Omicron variant. Methods Adults with HM diagnosed with COVID-19 from November 2022 to February 2023 were monitored in this retrospective study. Patient blood samples yielded biochemical data, and COVID-19 was confirmed through RNA or antigen testing. The factors affecting severity and infection duration were examined using both univariate and multivariate logistic regression analyses. For calculating the overall survival probabilities, the Kaplan–Meier product limit approach was employed. Results In the examined cohort, 133 individuals diagnosed with HM and concomitantly infected with COVID-19 were scrutinized. Of the participants, 29.3% (39 patients) were classified as Severe/Critical, while the other 70.7% (94 patients) were categorized as Non-severe. A significant difference was observed in vaccination status: 61.7% of patients in the Non-severe group had received at least a two-dose vaccine regimen, whereas 61.5% of the Severe/Critical group had either minimal or only one dose of vaccination. The data analysis revealed that elevated C-reactive protein levels (≥ 100 mg/L) significantly raised the risk of severe/critical conditions in HM patients with COVID-19, as determined by advanced multivariate logistic regression. The odds ratio was 3.415 with a 95% confidence interval of 1.294–9.012 (p = 0.013). Patients who continued to have positive nucleic acid tests and ongoing symptoms beyond 30 days were categorized as having a persistent infection, whereas those who achieved infection control within this timeframe were categorized as having infection recovery. Of the HM cohort, 11 did not survive beyond 30 days after diagnosis. The results from a competing risk model revealed that increased interleukin-6 levels (HR: 2.626, 95% CI: 1.361–5.075; p = 0.004) was significantly associated with persistent infection. Conversely, receiving more than two vaccine doses (HR: 0.366, 95% CI: 0.158–0.846; p = 0.019), and having high IgG levels (≥ 1000 mg/dl) (HR: 0.364, 95% CI: 0.167–0.791; p = 0.011), were associated with infection recovery. There was a notable disparity in survival rates between patients with persistent infections and infection recovery, with those in the non-persistent group demonstrating superior survival outcomes (P

Accurate diagnosis of kidney disease is crucial, as it is a significant health concern that demands precise identification for effective and appropriate treatment. Deep learning methods are increasingly recognized as valuable tools for disease diagnosis in the biomedical field. However, current models utilizing deep networks often encounter challenges of overfitting and low accuracy, necessitating further refinement for optimal performance. To overcome these challenges, this paper proposes the introduction of two ensemble models designed for kidney stone detection in CT images. The first model, called StackedEnsembleNet, is a two-level deep stack ensemble model that effectively integrates the predictions from four base models: InceptionV3, InceptionResNetV2, MobileNet, and Xception. By leveraging the collective knowledge of these models, StackedEnsembleNet improves the accuracy and reliability of kidney stone detection. The second model PSOWeightedAvgNet, leverages the Particle Swarm Optimization (PSO) algorithm to determine the optimal weights for the weighted average ensemble. Through PSO, this ensemble approach assigns optimized weights to each model during the ensembling process, effectively enhancing the performance by optimizing the combination of their predictions. Experimental results conducted on a large dataset of 1799 CT images demonstrate that both StackedEnsembleNet and PSOWeightedAvgNet outperform the individual base models, achieving high accuracy rates in kidney stone detection. Furthermore, additional experiments on an unseen dataset validate the models’ ability to generalize. The comparison with previous methods confirms the superior performance of the proposed ensemble models. The paper also presents Grad-CAM visualizations and error case analysis to provide insights into the decision-making processes of the models. By overcoming the limitations of existing deep learning models, StackedEnsembleNet and PSOWeightedAvgNet offer a promising approach for accurate kidney stone detection, contributing to improved diagnosis and treatment outcomes in the field of nephrology.

Poyang Lake is the largest freshwater lake in China and plays a significant ecological role. Deep-learning-based video surveillance can effectively monitor bird species on the lake, contributing to the local biodiversity preservation. To address the challenges of multi-scale object detection against complex backgrounds, such as a high density and severe occlusion, we propose a new model known as the YOLOv8-bird model. First, we use Receptive-Field Attention convolution, which improves the model’s ability to capture and utilize image information. Second, we redesign a feature fusion network, termed the DyASF-P2, which enhances the network’s ability to capture small object features and reduces the target information loss. Third, a lightweight detection head is designed to effectively reduce the model’s size without sacrificing the precision. Last, the Inner-ShapeIoU loss function is proposed to address the multi-scale bird localization challenge. Experimental results on the PYL-5-2023 dataset demonstrate that the YOLOv8-bird model achieves precision, recall, mAP@0.5, and mAP@0.5:0.95 scores of 94.6%, 89.4%, 94.8%, and 70.4%, respectively. Additionally, the model outperforms other mainstream object detection models in terms of accuracy. These results indicate that the proposed YOLOv8-bird model is well-suited for bird detection and counting tasks, which enable it to support biodiversity monitoring in the complex environment of Poyang Lake.

This study introduces a novel approach for enhancing robotic path planning and navigation by optimizing point configuration through convolutional neural networks (CNNs). Faced with the challenge of precise area coverage and the inefficiency of traditional traversal and intelligent algorithms (e.g., genetic algorithms, particle swarm optimization) in point layout, we proposed a CNN-based optimization model. This model not only tackles the issues of speed and accuracy in point configuration with Gaussian distribution characteristics but also significantly improves the robot's capability to efficiently navigate and cover designated areas with high precision. Our methodology begins with defining a coverage index, followed by an optimization model that integrates polygon image features with the variability of Gaussian distribution. The proposed CNN model is trained with datasets generated from systematic point configurations, which then predicts optimal layouts for enhanced navigation. Our method achieves an experimental result error of

Background Acute myeloid leukemia (AML) with t(8;21) is generally associated with a favorable clinical course. Loss of sex chromosome (LOS) are frequently observed in t (8;21) AML, but the prognostic value of LOS remains uncertain.Methods A total of 73 patients with AML with t(8;21) were studied and divided into t(8;21) with LOS group (n = 36) and t(8;21) alone group (n = 37). The patients with t(8;21) AML with ACAs other than LOS were excluded. The clinical characteristics of these two groups were compared, and the prognostic value of LOS was evaluated based on disease-free survival (DFS) and overall survival (OS).Results The clinical characteristics (except for gender) were found to have no significant difference between these two groups, and the male patients tended to account for a larger proportion in the former group (P = .001). The OS of the t(8;21) AML with LOS group was significantly longer than that of the t(8;21) AML alone group (P = .005). While not obvious, the patients with LOS seemed to have longer DFS (P = .061). The multivariable analysis also showed LOS to be an independent favorable prognostic factor of t(8;21) AML (P = .022).Conclusions Our results suggested that LOS could be associated with a favorable prognosis in t(8;21) AML patients without other ACAs, and for this subtype of AML, longer DFS and a satisfactory and stable survival can be achieved with high-dose cytarabine (HDAC) consolidation treatment.

Coronary perforation (CP) is a rare complication of percutaneous coronary intervention (PCI) and can lead to pericardial tamponade. Prolonged balloon inflation is a reasonable treatment for CP, but there is no standard recommendation on the preferable choice between the balloon site for prolonged balloon inflation (ie, proximal and in situ of the perforation). We present a rare case of successful prolonged balloon inflation at the proximal site of the CP after the failure of balloon inflation at the site of perforation. The patient developed CP during balloon inflation post-stent, rapidly progressing to cardiac tamponade. In situ prolonged balloon inflation (3 times) failed to close the CP, but proximal inflation could manage the CP. The take-home message from this case is that balloon expansion at the proximal site could be better than in situ of perforation in patients with CP after PCI.

The unprecedented prosperity of the industrial internet of things (IIoT) has opened up a new path for the traditional industrial manufacturing model.Intelligent shop scheduling is one of the key technologies to achieve the overall control and flexible production of the whole production process.It requires an effective plan with a minimum makespan to allocate multiple processes and multiple machines for production scheduling.Firstly, the shop scheduling problem was defined as a Markov decision process (MDP), and a shop scheduling model based on the pointer network was established.Secondly, the job scheduling process was regarded as a mapping from one sequence to another, and a new shop scheduling algorithm based on deep reinforcement learning (DRL) was proposed.By analyzing the convergence of the model under different parameter settings, the optimal parameters were determined.Experimental results on different scales of public data sets and actual production data sets show that the proposed DRL algorithm can obtain better performances.

With the application and development of UAV technology and navigation and positioning technology, higher requirements are put forward for UAV maneuvering obstacle avoidance ability and real-time route planning. In this paper, for the problem of real-time UAV route planning in the unknown environment, we combine the ideas of artificial potential field method to modify the state observation and reward function, which solves the problem of sparse rewards of reinforcement learning algorithm, improves the convergence speed of the algorithm, and improves the generalization of the algorithm by step-by-step training based on the ideas of curriculum learning and transfer learning according to the difficulty of the task. The simulation results show that the improved SAC algorithm has fast convergence speed, good timeliness and strong generalization, and can better complete the UAV route planning task.

Abstract Peripheral T-cell lymphoma(PTCL) is a group of lymphoproliferative tumors originated from post-thymic T cells or mature natural killer (NK) cells. It shows highly aggressive clinical behaviour, resistance to conventional chemotherapy, and a poor prognosis. Although a few prognostic models of PTCL have been established in retrospective studies, some high-risk patients still can not be screened out. Therefor we retrospectively studied 347 newly diagnosed PTCL patients and assessed the prognostic role of lymphocyte-monocyte ratio (LMR) and platelet-monocyte ratio (PMR) in the complete response (CR) and survival of PTCL patients. Patients with LMR ≤ 1.68 and PMR ≤ 300 achieved a lower CR rate and a poor survival. In multivariate analysis, LMR ≤ 1.68 (HR = 1.751, 95% CI 1.158–2.647, p

Abstract Background Fatal hemorrhagic pneumonia is one of the most severe manifestations of Stenotrophomonas maltophilia (SM) infections. Here, we aimed to investigate the clinical characteristics of SM bacteremia and to identify the risk factors of hemorrhagic pneumonia caused by SM in patients with hematologic diseases. Methods The clinical records of 55 patients diagnosed with hematologic diseases and SM bacteremia were retrospectively reviewed. We compared patients’ clinical characteristics and outcomes between the hemorrhagic pneumonia group and non-hemorrhagic pneumonia group. Results Twenty-seven (49.1%) patients developed hemorrhagic pneumonia. The overall mortality rate of SM bacteremia was 67.3%. Hemorrhagic pneumonia (adjusted HR 2.316, 95% CI 1.140–4.705; P = 0.020) was an independent risk factor of 30-day mortality in hematological patients with SM bacteremia. Compared with the non-hemorrhagic pneumonia group, patients in the hemorrhagic pneumonia group were older and showed clinical manifestations as higher proportions of isolated SM in sputum culture, neutropenia and elevated procalcitonin (PCT). Multivariate analysis showed that neutropenia, high levels of PCT, prior tigecycline therapy within 1 month were independent risk factors associated with hemorrhagic pneumonia. Conclusions Neutropenia, high level of PCT and prior tigecycline therapy within 1 month were significant independent predictors of hemorrhagic pneumonia in hematologic patients with SM bacteremia. Due to no effective antibiotics to prevent hemorrhagic pneumonia, prophylaxis of SM infection and its progression to hemorrhagic pneumonia is particularly important.

Edge detection for PolSAR images has demonstrated its importance in various applications such as segmentation and classification. Although there are many edge detectors which have demonstrated an impressive ability to achieve accurate edge detection results, these methods only focus on edge detection in a single-date PolSAR image. However, a single-date PolSAR image cannot fully characterize the changes in scattering mechanisms of land cover in different growth cycles, resulting in some omissions of the true edges. In this paper, we propose a novel edge detection method for multi-temporal PolSAR images based on the SIRV model and an SDAN-based 3D Gaussian-like kernel. The spherically invariant random vector (SIRV) and span-driven adaptive neighborhood (SDAN) improve the estimation accuracy of the average covariance matrix (ACM) in terms of data representation and spatial support, respectively. We propose an SDAN-based 2D Gaussian kernel to accurately extract the edge strength of single-date PolSAR images. Then, we design a 1D convolution kernel in the temporal dimension to smooth fluctuations in the edge strength of multi-temporal PolSAR images. The SDAN-based 2D Gaussian kernels in the X- and Y-directions are combined with the 1D convolution kernel in the Z-direction to form an SDAN-based 3D Gaussian-like kernel. In addition, we design an adaptive hysteresis threshold method to optimize the edge map. The performance of our proposed method is presented and analyzed on two real multi-temporal PolSAR datasets, and the results demonstrate that the proposed edge detector achieves a better performance than other edge detectors, particularly for crop regions with time-varying scattering mechanisms.

Abstract Mixed phenotype acute leukemia (MPAL) is an uncommon type of leukemia. It is one kind of malignant clonal diseases that expresses more than one genealogical specific antigen simultaneously. Most MPAL patients are associated with clonal chromosomal abnormalities and molecular genetic changes, such as t(9;22) (q34;q11) and KMT2A (MLL) rearrangement. These specific abnormalities usually have important guiding significance in MPAL diagnosis, targeted therapy and prognosis judgment. In this paper, we reported a case of MPAL, T/myeloid (M5) with an unfrequent combination of PML-RARα positivity and t(15;17). The treatment was successful with chemotherapy for both AML and ALL with daunorubicin, cytarabine (DA) and vincristine, prednisone (VP). We reported here this suggestive MPAL case of rare disease condition and effective treatment, in order to provide experience for the early diagnosis and treatment of similar patients.

In view of the complex and severe challenges faced by financial technology regulation and the lag behind situation of the existing regulatory sandbox which is highly dependent on manual operation,the important feature and development trend of the Chinese “innovative regulatory tools on financial technology” lie in “intelligence” were pointed out.A systematic platform framework of “intelligent innovative regulatory tools on financial technology” was proposed,that is,use modern means of science and technology to realize the full life cycle supervision of financial technology innovative applications.The elements of innovative regulatory tools were elaborated,including the underlying blockchain,public opinion monitoring platform,explainable artificial intelligence based on knowledge graphs,and presented the key technologies involved.The new iterative methodology used in the development of the innovative regulatory tools platform was introduced,i.e.,the spiral development model and iterative design driven by the hierarchy of needs.Towards the end,some thoughts and prospects on the proposed innovative regulatory tools were put forward,and the regulatory tools are expected to create a set of regulatory technology infrastructure to serve regulatory authorities and financial institutions were pointed out.

SAR image registration is the basis for applications such as change detection, image fusion, and three-dimensional reconstruction. Although CNN-based SAR image registration methods have achieved competitive results, they are insensitive to small displacement errors in matched point pairs and do not provide a comprehensive description of keypoint information in complex scenes. In addition, existing keypoint detectors are unable to obtain a uniform distribution of keypoints in SAR images with complex scenes. In this paper, we propose a texture constraint-based phase congruency (TCPC) keypoint detector that uses a rotation-invariant local binary pattern operator (RI-LBP) to remove keypoints that may be located at overlay or shadow locations. Then, we propose a Siamese dense capsule network (SD-CapsNet) to extract more accurate feature descriptors. Then, we define and verify that the feature descriptors in capsule form contain intensity, texture, orientation, and structure information that is useful for SAR image registration. In addition, we define a novel distance metric for the feature descriptors in capsule form and feed it into the Hard L2 loss function for model training. Experimental results for six pairs of SAR images demonstrate that, compared to other state-of-the-art methods, our proposed method achieves more robust results in complex scenes, with the number of correctly matched keypoint pairs (NCM) at least 2 to 3 times higher than the comparison methods, a root mean square error (RMSE) at most 0.27 lower than the compared methods.

Change detection (CD) is an important research topic in remote sensing, which has been applied in many fields. In the paper, we focus on the post-processing of difference images (DIs), i.e., how to further improve the quality of a DI after the initial DI is obtained. The importance of DIs for CD problems cannot be overstated, however few methods have been investigated so far for re-processing DIs after their acquisition. In order to improve the DI quality, we propose a global and local graph-based DI-enhancement method (GLGDE) specifically for CD problems; this is a plug-and-play method that can be applied to both homogeneous and heterogeneous CD. GLGDE first segments the multi-temporal images and DIs into superpixels with the same boundaries and then constructs two graphs for the DI with superpixels as vertices: one is the global feature graph that characterizes the association between the similarity relationships of connected vertices in the multi-temporal images and their changing states in a DI, the other is the local spatial graph that exploits the change information and contextual information of the DI. Based on these two graphs, a DI-enhancement model is built, which constrains the enhanced DI to be smooth on both graphs. Therefore, the proposed GLGDE can not only smooth the DI but also correct the it. By solving the minimization model, we can obtain an improved DI. The experimental results and comparisons on different CD tasks with six real datasets demonstrate the effectiveness of the proposed method.

The residual levels of 25 monitored pesticides in 6,229 brown rice samples obtained from the 17 provinces of the three main rice-growing regions in China during 2016–2020 were analyzed, and the cumulative risks of chronic and acute exposure to pesticides for the Chinese population were assessed. The QuEChERS extraction coupled with liquid chromatography-mass spectrometry for simultaneous determination of 25 pesticide residues in brown rice was developed and validated with good accuracy and precision (recoveries of 70%–120% and RSD ≤20%). The overall detection rate and over the maximum residue limit (MRL) rate of pesticides in brown rice decreased from 39.15% and 3.59% in 2016 to 34.11% and 1.53% in 2020, respectively. The Yangtze River basin had a higher detection rate and over MRL rate (43.14% and 2.88%, respectively) compared with the Southeast Coastal region (37.28% and 2.77%) and the Northeast Plain (11.28% and 0.17%). Isoprothiolane (13.57%) and carbendazim (8.32%) were the most frequently detected in rice samples. Pesticide residues exceeding the MRLs were found most often in triazophos (0.75%) and isocarbophos (0.51%). The risk ranking of pesticide residues based on the ranking matrix showed that carbofuran, methamidophos, and isocarbophos had the highest residual risk scores of 25.09, 25.01, and 25.00, respectively. 17.7% of rice samples contained two or more pesticide residues. The cumulative risk assessments based on the relative potency factor (RPF) approach revealed that the cumulative risks of chronic and acute dietary exposure to organophosphorus, neonicotinoid insecticides, and triazole fungicides from rice ranged from 7.43 × 10−4 to 3.36 × 10−2, which were not considered of health concern. The study provides national-scale information on the contamination levels and health risks of pesticide residues in rice, which can help develop continuous monitoring programs for pesticide residue contamination in rice in China.

The traditional sensorless control system of permanent magnet synchronous motor (PMSM) has the problems of low estimation accuracy and poor anti-interference ability. Moreover, the position estimation performance is subjected to position harmonic ripples caused by inverter nonlinearities and flux spatial harmonics. To optimize the dynamic performance of the PMSM sensorless control system, this paper proposes a sensorless control scheme that combines integral backstepping control with enhanced linear extended state observer (ELESO). The ELESO consists of two linear extended state observers (LESOs), which estimate the internal and external disturbances of the system, to improve the estimation accuracy of rotor position. Then, the integral backstepping controller processes the estimated rotor position and speed information to obtain d and q-axis voltages. The sensorless control scheme is implemented in the Matlab/Simulink and verified by experiments. The simulation and experiment show that the scheme can effectively suppress load interference and improve control accuracy.

Summary: Fluorescent anti-counterfeiting technology has been widely reported for its advantages, such as easy identification and multiple anti-counterfeiting functions. Most of the current fluorescent anti-counterfeiting materials focus on the innovation of anti-counterfeiting mode. However, stability is a prerequisite for applying anti-counterfeiting materials and determining whether a material can be widely used. Inspired by water stains, we report fluorescent nanoparticles that are easily prepared and inkjet printable and have multiple anti-counterfeiting functions and high stability. They are applied successfully to fluorescent anti-counterfeiting. 3D printed microreactors prepared the fluorescent nanoparticles with different emission wavelengths. The nanoparticles adhere firmly to the fibers of paper or cloth under the combined effect of hydrogen bonding and van der Waals forces. The sample paper exhibits good tolerance to extreme environments, such as boiling water, liquid nitrogen, photobleaching, and strong acid. Finally, multiple anti-counterfeiting functions are realized by mobile phones and clustering algorithms.

Spinal cord injury (SCI) is a devastating condition that results in severe motor, sensory, and autonomic dysfunction. The L-/T-type calcium channel blocker nimodipine (NMD) exerts a protective effect on neuronal injury; however, the protective effects of long-term administration of NMD in subjects with SCI remain unknown. Thus, the aim of this study was to evaluate the role of long-term treatment with NMD on a clinically relevant SCI model. Female rats with SCI induced by 25 mm contusion were subcutaneously injected with vehicle or 10 mg/kg NMD daily for six consecutive weeks. We monitored the motor score, hind limb grip strength, pain-related behaviors, and bladder function in this study to assess the efficacy of NMD in rats with SCI. Rats treated with NMD showed improvements in locomotion, pain-related behaviors, and spasticity-like symptoms, but not in open-field spontaneous activity, hind limb grip strength or bladder function. SCI lesion areas and perilesional neuronal numbers, gliosis and calcitonin gene-related peptide (CGRP+) fiber sprouting in the lumbar spinal cord and the expression of K+–Cl− cotransporter 2 (KCC2) on lumbar motor neurons were also observed to further explore the possible protective mechanisms of NMD. NMD-treated rats showed greater tissue preservation with reduced lesion areas and increased perilesional neuronal sparing. NMD-treated rats also showed improvements in gliosis, CGRP+ fiber sprouting in the lumbar spinal cord, and KCC2 expression in lumbar motor neurons. Together, these results indicate that long-term treatment with NMD improves functional recovery after SCI, which may provide a potential therapeutic strategy for the treatment of SCI.

Summary: Spinal cord injury (SCI) often results in spasticity. There is currently no effective therapy for spasticity. Here, we describe a method to efficiently differentiate human pluripotent stem cells from spinal GABA neurons. After transplantation into the injured rat spinal cord, the DREADD (designer receptors exclusively activated by designer drug)-expressing spinal progenitors differentiate into GABA neurons, mitigating spasticity-like response of the rat hindlimbs and locomotion deficits in 3 months. Administering clozapine-N-oxide, which activates the grafted GABA neurons, further alleviates spasticity-like response, suggesting an integration of grafted GABA neurons into the local neural circuit. These results highlight the therapeutic potential of the spinal GABA neurons for SCI.

Although the deep neural network (DNN) has shown a powerful ability in hyperspectral image (HSI) classification, its learning requires a large number of labeled training samples; otherwise, it is prone to over-fitting and has a poor classification performance. However, this requirement is impractical for HSIs due to the difficulty in obtaining class labels. To make DNNs suitable for HSI classification with few labeled samples, we propose a graph-based deep multitask few-shot learning (GDMFSL) framework that learns the intrinsic relationships among all samples (labeled and unlabeled) of HSIs with the assistance of graph information to alleviate the over-fitting caused by few labeled training samples. Firstly, a semi-supervised graph is constructed to generate graph information. Secondly, a deep multitask network (DMN) is designed, which contains two subnetworks (tasks): a classifier subnetwork for learning class information from labeled samples and a Siamese subnetwork for learning sample relationships from the semi-supervised graph. To effectively learn graph information, a loss function suitable for the Siamese subnetwork is designed that shortens (and expands) the distance between the target sample and its nearest (and farthest) neighbors. Finally, since the number of training samples of the two subnetworks is severely imbalanced, a multitask few-shot learning strategy is designed to make two subnetworks converge simultaneously. Experimental results on the Indian Pines, University of Pavia and Salinas datasets demonstrate that GDMFSL achieves a better classification performance relative to existing competitors in few-shot settings. In particular, when only five labels per class are involved in training, the classification accuracy of GDMFSL on the three datasets reaches 87.58%, 86.42% and 98.85%, respectively.

This is the first time that the landscape footpath is realized on the suspension monorail system. To study the comfort of pedestrians on the landscape footpath when the vehicle passes, the dynamic responses of the track beam and the landscape footpath at different speeds were analyzed using the established vehicle-bridge dynamic analysis model. To evaluate the comfort of pedestrians on the landscape footpath, two indexes, Root Mean Square (RMS) value of acceleration (ISO 10137) and peak value of acceleration (EN 03), were adopted. Results show that the displacement and acceleration responses of landscape footpath and track beam are obviously different. Vertical displacement of the track beam is much larger than that of the landscape footpath due to the eccentric load of vehicles. Due to the displacement and rotation of the structural components which support the landscape footpath, the lateral response transferred to the landscape footpath would be slightly weakened. Maximum RMS values of the lateral and vertical acceleration of landscape footpath are 0.162 m/s2 and 0.169 m/s2, respectively, which meet the requirements of ISO 10137. Peak lateral acceleration is 0.546 m/s2, which reaches CL3 standard, and the peak vertical acceleration is 0.548 m/s2, which reaches CL2 standard. Lateral comfort is slightly worse than vertical comfort.

The controller design of hypersonic flight vehicles is a challenging task, especially when its flexible states are immeasurable. Unfortunately, the flexible states are difficult to measure directly. In this paper, an angular-accelerometer-based method for the estimation of flexible states is proposed. By adding a pitch angel angular accelerometer and designing an Extended Kalman Filter-based online estimation method, the flexible states could be obtained in real time. Then, based on the estimated flexible states, a stable inversion-based controller-design method was utilized, and a robust tracking controller was designed for hypersonic flight vehicles. The proposed method provides an effective means of estimating flexible states and conducting the observer-based controller design of hypersonic flight vehicles. Finally, a numeral simulation is given to show the effectiveness of the proposed control method.

Population based search techniques have been developed and applied to wide applications for their good performance, such as the optimization of the unmanned aerial vehicle (UAV) path planning problems. However, the search for optimal solutions for an optimization problem is usually expensive. For example, the UAV problem is a large-scale optimization problem with many constraints, which makes it hard to get exact solutions. Especially, it will be time-consuming when multiple UAV problems are waiting to be optimized at the same time. Evolutionary multi-task optimization (EMTO) studies the problem of utilizing the population-based characteristics of evolutionary computation techniques to optimize multiple optimization problems simultaneously, for the purpose of further improving the overall performance of resolving all these problems. EMTO has great potential in solving real-world problems more efficiently. Therefore, in this paper, we develop a novel EMTO algorithm using a classical PSO algorithm, in which the developed knowledge transfer strategy achieves knowledge transfer between task by synthesizing the transferred knowledges from a selected set of component tasks during the updating of the velocities of population. Two knowledge transfer strategies are developed along with two versions of the proposed algorithm. The proposed algorithm is compared with the multifactorial PSO algorithm, the SREMTO algorithm, the popular multifactorial evolutionary algorithm and a classical PSO algorithm on nine popular single-objective MTO problems and six five-task MTO problems, which demonstrates its superiority.

Deep neural networks have achieved significant development and wide applications for their amazing performance. However, their complex structure, high computation and storage resource limit their applications in mobile or embedding devices such as sensor platforms. Neural network pruning is an efficient way to design a lightweight model from a well-trained complex deep neural network. In this paper, we propose an evolutionary multi-objective one-shot filter pruning method for designing a lightweight convolutional neural network. Firstly, unlike some famous iterative pruning methods, a one-shot pruning framework only needs to perform filter pruning and model fine-tuning once. Moreover, we built a constraint multi-objective filter pruning problem in which two objectives represent the filter pruning ratio and the accuracy of the pruned convolutional neural network, respectively. A non-dominated sorting-based evolutionary multi-objective algorithm was used to solve the filter pruning problem, and it provides a set of Pareto solutions which consists of a series of different trade-off pruned models. Finally, some models are uniformly selected from the set of Pareto solutions to be fine-tuned as the output of our method. The effectiveness of our method was demonstrated in experimental studies on four designed models, LeNet and AlexNet. Our method can prune over 85%, 82%, 75%, 65%, 91% and 68% filters with little accuracy loss on four designed models, LeNet and AlexNet, respectively.

This Special Issue is focused on breakthrough developments in the field of Wireless Systems and Networks in the IoT. The selected contributions report current scientific progress in a wide range of topics covering clock error compensation in sensor networks, backscatter communication networks, Radio-Frequency Identification (RFID)-based inventory management, resource allocation in Long-Term Evolution (LTE)/LTE-A, (Long Range Wide-Area Network (LoRaWAN) modeling and key generation for the IoT.

Emotion entrainment, which is generally defined as the synchronous convergence of human emotions, performs many important social functions. However, what the specific mechanisms of emotion entrainment are beyond in-person interactions, and how human emotions evolve under different entrainment patterns in large-scale social communities, are still unknown. In this paper, we aim to examine the massive emotion entrainment patterns and understand the underlying mechanisms in the context of social media. As modeling emotion dynamics on a large scale is often challenging, we elaborate a pragmatic framework to characterize and quantify the entrainment phenomenon. By applying this framework on the datasets from two large-scale social media platforms, we find that the emotions of online users entrain through social networks. We further uncover that online users often form their relations via dual entrainment, while maintain it through single entrainment. Remarkably, the emotions of online users are more convergent in nonreciprocal entrainment. Building on these findings, we develop an entrainment augmented model for emotion prediction. Experimental results suggest that entrainment patterns inform emotion proximity in dyads, and encoding their associations promotes emotion prediction. This work can further help us to understand the underlying dynamic process of large-scale online interactions and make more reasonable decisions regarding emergency situations, epidemic diseases, and political campaigns in cyberspace.

This paper conducted one of the first comprehensive international Internet analyses of seasonal patterns in information seeking concerning tobacco and lung cancer. Search query data for the terms "tobacco" and "lung cancer" from January 2004 to January 2014 was collected from Google Trends. The relevant countries included the USA, Canada, the UK, Australia, and China. Two statistical approaches including periodogram and cross-correlation were applied to analyze seasonal patterns in the collected search trends and their associations. For these countries except China, four out of six cross-correlations of seasonal components of the search trends regarding tobacco were above 0.600. For these English-speaking countries, similar patterns existed in the data concerning lung cancer, and all cross-correlations between seasonal components of the search trends regarding tobacco and that regarding lung cancer were also above 0.700. Seasonal patterns widely exist in information seeking concerning tobacco and lung cancer on an international scale. The findings provide a piece of novel Internet-based evidence for the seasonality and health effects of tobacco use.