Kelp Fucoidans Facilitate Vascular Recanalization via Inhibiting Excessive Activation of Platelet in Deep Venous Thrombosis Model of Mouse

This study was carried out explore the mechanism underlying the inhibition of platelet activation by kelp fucoidans in deep venous thrombosis(DVT)mouse.In the control and sham mice,the walls of deep vein were regular and smooth with intact intima,myometrium and adventitia.The blood vessel was wrapped with the tissue and there was no thrombosis in the lumen.In the DVT model,the wall was uneven with thicken intima,myometrium and adventitia.After treated with fucoidans LF1 and LF2,the thrombus was dissolved and the blood vessel was recanalized.Compared with the control group,the ROS content,ET-1 and VWF content and the expression of PKC-βand NF-κB in the model were significantly higher(P<0.05);these levels were significantly reduced following treatments with LF2 and LF1.Compared with H_(2)O_(2)treated-HUVECs,combined LF1 and LF2 treatment resulted in significant decrease in the expression of PKC-β,NF-κB,VWF and TM protein(P<0.05).It is clear that LF1 and LF2 reduces DVT-induced ET-1,VWF and TM expressions and production of ROS,thus inhibiting the activation of PKC-β/NF-κB signal pathway and the activation of coagulation system and ultimately reducing the formation of venous thrombus.

Olive Leaf Disease Detection via Wavelet Transform and Feature Fusion of Pre-Trained Deep Learning Models

Olive trees are susceptible to a variety of diseases that can cause significant crop damage and economic losses.Early detection of these diseases is essential for effective management.We propose a novel transformed wavelet,feature-fused,pre-trained deep learning model for detecting olive leaf diseases.The proposed model combines wavelet transforms with pre-trained deep-learning models to extract discriminative features from olive leaf images.The model has four main phases:preprocessing using data augmentation,three-level wavelet transformation,learning using pre-trained deep learning models,and a fused deep learning model.In the preprocessing phase,the image dataset is augmented using techniques such as resizing,rescaling,flipping,rotation,zooming,and contrasting.In wavelet transformation,the augmented images are decomposed into three frequency levels.Three pre-trained deep learning models,EfficientNet-B7,DenseNet-201,and ResNet-152-V2,are used in the learning phase.The models were trained using the approximate images of the third-level sub-band of the wavelet transform.In the fused phase,the fused model consists of a merge layer,three dense layers,and two dropout layers.The proposed model was evaluated using a dataset of images of healthy and infected olive leaves.It achieved an accuracy of 99.72%in the diagnosis of olive leaf diseases,which exceeds the accuracy of other methods reported in the literature.This finding suggests that our proposed method is a promising tool for the early detection of olive leaf diseases.

Weakly supervised point cloud segmentation via deep morphological semantic information embedding

Segmenting the semantic regions of point clouds is a crucial step for intelligent agents to understand 3D scenes.Weakly supervised point cloud segmentation is highly desirable because entirely labelling point clouds is highly time-consuming and costly.For the low-costing labelling of 3D point clouds,the scene-level label is one of the most effortless label strategies.However,due to the limitation of classifier discriminative capability and the orderless and structurless nature of the point cloud data,existing scene-level method is hard to transfer the semantic information,which usually leads to the under-activated or over-activated issues.To this end,a local semantic embedding network is introduced to learn local structural patterns and semantic propagation.Specifically,the proposed network contains graph convolution-based dilation and erosion embedding modules to implement‘inside-out’and‘outside-in’semantic information dissemination pathways.Therefore,the proposed weakly supervised learning framework could achieve the mutual propagation of semantic information in the foreground and background.Comprehensive experiments on the widely used ScanNet benchmark demonstrate the superior capacity of the proposed approach when compared to the current alternatives and baseline models.

Early identification of stroke through deep learning with multi-modal human speech and movement data

Early identification and treatment of stroke can greatly improve patient outcomes and quality of life.Although clinical tests such as the Cincinnati Pre-hospital Stroke Scale(CPSS)and the Face Arm Speech Test(FAST)are commonly used for stroke screening,accurate administration is dependent on specialized training.In this study,we proposed a novel multimodal deep learning approach,based on the FAST,for assessing suspected stroke patients exhibiting symptoms such as limb weakness,facial paresis,and speech disorders in acute settings.We collected a dataset comprising videos and audio recordings of emergency room patients performing designated limb movements,facial expressions,and speech tests based on the FAST.We compared the constructed deep learning model,which was designed to process multi-modal datasets,with six prior models that achieved good action classification performance,including the I3D,SlowFast,X3D,TPN,TimeSformer,and MViT.We found that the findings of our deep learning model had a higher clinical value compared with the other approaches.Moreover,the multi-modal model outperformed its single-module variants,highlighting the benefit of utilizing multiple types of patient data,such as action videos and speech audio.These results indicate that a multi-modal deep learning model combined with the FAST could greatly improve the accuracy and sensitivity of early stroke identification of stroke,thus providing a practical and powerful tool for assessing stroke patients in an emergency clinical setting.

Deep eutectic solvents for separation and purification applications in critical metal metallurgy:Recent advances and perspectives

Solvent extraction,a separation and purification technology,is crucial in critical metal metallurgy.Organic solvents commonly used in solvent extraction exhibit disadvantages,such as high volatility,high toxicity,and flammability,causing a spectrum of hazards to human health and environmental safety.Neoteric solvents have been recognized as potential alternatives to these harmful organic solvents.In the past two decades,several neoteric solvents have been proposed,including ionic liquids(ILs)and deep eutectic solvents(DESs).DESs have gradually become the focus of green solvents owing to several advantages,namely,low toxicity,degradability,and low cost.In this critical review,their classification,formation mechanisms,preparation methods,characterization technologies,and special physicochemical properties based on the most recent advancements in research have been systematically described.Subsequently,the major separation and purification applications of DESs in critical metal metallurgy were comprehensively summarized.Finally,future opportunities and challenges of DESs were explored in the current research area.In conclusion,this review provides valuable insights for improving our overall understanding of DESs,and it holds important potential for expanding separation and purification applications in critical metal metallurgy.

基于Deep Forest算法的对虾急性肝胰腺坏死病(AHPND)预警数学模型构建

为预报池塘养殖凡纳对虾(Penaeus vannamei)急性肝胰腺坏死病(AHPND)的发生,自2020年开始,笔者对凡纳对虾养殖区开展了连续监测工作,包括与疾病发生相关的环境理化因子、微生物因子、虾体自身健康状况等18个候选预警因子指标,通过数据标准化处理后分析病原、宿主与环境之间的相关性,对候选预警因子进行筛选,基于Python语言编程结合Deep Forest、Light GBM、XGBoost算法进行数据建模和预测性能评判,仿真环境为Python2.7,以预警因子指标作为输入样本(即警兆),以对虾是否发病指标作为输出结果(即警情),根据输入样本和输出结果各自建立输入数据矩阵和目标数据矩阵,利用原始数据矩阵对输入样本进行初始化,结合函数方程进行拟合,拟合的源代码能利用已知环境、病原及对虾免疫指标数据对目标警情进行预测。最终建立了基于Deep Forest算法的虾体(肝胰腺内)细菌总数、虾体弧菌(Vibrio)占比、水体细菌总数和盐度的4维向量预警预报模型,准确率达89.00%。本研究将人工智能算法应用到对虾AHPND发生的预测预报,相关研究结果为对虾AHPND疾病预警预报建立了预警数学模型,并为对虾健康养殖和疾病防控提供了技术支撑和有力保障。

MmNet:Identifying Mikania micrantha Kunth in the wild via a deep Convolutional Neural Network

Mikania micrantha Kunth is an invasive alien weed and known as a plant killer around the world.Accurately and rapidly identifying M.micrantha in the wild is important for monitoring its growth status,as this helps management officials to take the necessary steps to devise a comprehensive strategy to control the invasive weed in the identified area.However,this approach still mainly depends on satellite remote sensing and manual inspection.The cost is high and the accuracy rate and efficiency are low.We acquired color images of the monitoring area in the wild environment using an Unmanned Aerial Vehicle(UAV)and proposed a novel network-MmNet-based on a deep Convolutional Neural Network(CNN)to identify M.micrantha in the images.The network consists of AlexNet Local Response Normalization(LRN),along with the GoogLeNet and continuous convolution of VGG inception models.After training and testing,the identification of 400 testing samples by MmNet is very good,with accuracy of 94.50%and time cost of 10.369 s.Moreover,in quantitative comparative analysis,the proposed MmNet not only has high accuracy and efficiency but also simple construction and outstanding repeatability.Compared with recently popular CNNs,MmNet is more suitable for the identification of M.micrantha in the wild.However,to meet the challenge of wild environments,more M.micrantha images need to be acquired for MmNet training.In addition,the classification labels need to be sorted in more detail.Altogether,this research provides some theoretical and scientific basis for the development of intelligent monitoring and early warning systems for M.micrantha and other invasive species.

COVID-19 Detection via a 6-Layer Deep Convolutional Neural Network

Many people around the world have lost their lives due to COVID-19.The symptoms of most COVID-19 patients are fever,tiredness and dry cough,and the disease can easily spread to those around them.If the infected people can be detected early,this will help local authorities control the speed of the virus,and the infected can also be treated in time.We proposed a six-layer convolutional neural network combined with max pooling,batch normalization and Adam algorithm to improve the detection effect of COVID-19 patients.In the 10-fold cross-validation methods,our method is superior to several state-of-the-art methods.In addition,we use Grad-CAM technology to realize heat map visualization to observe the process of model training and detection.

Collaborative Pushing and Grasping of Tightly Stacked Objects via Deep Reinforcement Learning

Directly grasping the tightly stacked objects may cause collisions and result in failures,degenerating the functionality of robotic arms.Inspired by the observation that first pushing objects to a state of mutual separation and then grasping them individually can effectively increase the success rate,we devise a novel deep Q-learning framework to achieve collaborative pushing and grasping.Specifically,an efficient non-maximum suppression policy(PolicyNMS)is proposed to dynamically evaluate pushing and grasping actions by enforcing a suppression constraint on unreasonable actions.Moreover,a novel data-driven pushing reward network called PR-Net is designed to effectively assess the degree of separation or aggregation between objects.To benchmark the proposed method,we establish a dataset containing common household items dataset(CHID)in both simulation and real scenarios.Although trained using simulation data only,experiment results validate that our method generalizes well to real scenarios and achieves a 97%grasp success rate at a fast speed for object separation in the real-world environment.

Analysis of community question-answering issues via machine learning and deep learning:State-of-the-art review

Over the last couple of decades,community question-answering sites(CQAs)have been a topic of much academic interest.Scholars have often leveraged traditional machine learning(ML)and deep learning(DL)to explore the ever-growing volume of content that CQAs engender.To clarify the current state of the CQA literature that has used ML and DL,this paper reports a systematic literature review.The goal is to summarise and synthesise the major themes of CQA research related to(i)questions,(ii)answers and(iii)users.The final review included 133 articles.Dominant research themes include question quality,answer quality,and expert identification.In terms of dataset,some of the most widely studied platforms include Yahoo!Answers,Stack Exchange and Stack Overflow.The scope of most articles was confined to just one platform with few cross-platform investigations.Articles with ML outnumber those with DL.Nonetheless,the use of DL in CQA research is on an upward trajectory.A number of research directions are proposed.

ReLFA:Resist Link Flooding Attacks via Renyi Entropy and Deep Reinforcement Learning in SDN-IoT

Link flooding attack(LFA)is a fresh distributed denial of service attack(DDoS).Attackers can cut off the critical links,making the services in the target area unavailable.LFA manipulates legal lowspeed flow to flood critical links,so traditional technologies are difficult to resist such attack.Meanwhile,LFA is also one of the most important threats to Internet of things(IoT)devices.The introduction of software defined network(SDN)effectively solves the security problem of the IoT.Aiming at the LFA in the software defined Internet of things(SDN-IoT),this paper proposes a new LFA mitigation scheme ReLFA.Renyi entropy is to locate the congested link in the data plane in our scheme,and determines the target links according to the alarm threshold.When LFA is detected on the target links,the control plane uses the method based on deep reinforcement learning(DRL)to carry out traffic engineering.Simulation results show that ReLFA can effectively alleviate the impact of LFA in SDN IoT.In addition,the rerouting time of ReLFA is superior to other latest schemes.

Simultaneous Denoising and Interpolation of Seismic Data via the Deep Learning Method

Utilizing data from controlled seismic sources to image the subsurface structures and invert the physical properties of the subsurface media is a major effort in exploration geophysics. Dense seismic records with high signal-to-noise ratio(SNR) and high fidelity helps in producing high quality imaging results. Therefore, seismic data denoising and missing traces reconstruction are significant for seismic data processing. Traditional denoising and interpolation methods rarely occasioned rely on noise level estimations, thus requiring heavy manual work to deal with records and the selection of optimal parameters. We propose a simultaneous denoising and interpolation method based on deep learning. For noisy records with missing traces, we adopt an iterative alternating optimization strategy and separate the objective function of the data restoring problem into two sub-problems. The seismic records can be reconstructed by solving a least-square problem and applying a set of pre-trained denoising models alternatively and iteratively.We demonstrate this method with synthetic and field data.

Highway Lane Change Decision-Making via Attention-Based Deep Reinforcement Learning

Dear editor,Deep reinforcement learning(DRL),combining the perception capability of deep learning(DL)and the decision-making capability of reinforcement learning(RL)[1],has been widely investigated for autonomous driving decision-making tasks.In this letter,Fund:supported in part by the National Natural Science Foundation of China(NSFC)(62173325);the Beijing Municipal Natural Science Foundation(L191002).

Accurate and generalizable quantitative scoring of liver steatosis from ultrasound images via scalable deep learning

BACKGROUND Hepatic steatosis is a major cause of chronic liver disease.Two-dimensional(2D)ultrasound is the most widely used non-invasive tool for screening and monitoring,but associated diagnoses are highly subjective.AIM To develop a scalable deep learning(DL)algorithm for quantitative scoring of liver steatosis from 2D ultrasound images.METHODS Using multi-view ultrasound data from 3310 patients,19513 studies,and 228075 images from a retrospective cohort of patients received elastography,we trained a DL algorithm to diagnose steatosis stages(healthy,mild,moderate,or severe)from clinical ultrasound diagnoses.Performance was validated on two multiscanner unblinded and blinded(initially to DL developer)histology-proven cohorts(147 and 112 patients)with histopathology fatty cell percentage diagnoses and a subset with FibroScan diagnoses.We also quantified reliability across scanners and viewpoints.Results were evaluated using Bland-Altman and receiver operating characteristic(ROC)analysis.RESULTS The DL algorithm demonstrated repeatable measurements with a moderate number of images(three for each viewpoint)and high agreement across three premium ultrasound scanners.High diagnostic performance was observed across all viewpoints:Areas under the curve of the ROC to classify mild,moderate,and severe steatosis grades were 0.85,0.91,and 0.93,respectively.The DL algorithm outperformed or performed at least comparably to FibroScan control attenuation parameter(CAP)with statistically significant improvements for all levels on the unblinded histology-proven cohort and for“=severe”steatosis on the blinded histology-proven cohort.CONCLUSION The DL algorithm provides a reliable quantitative steatosis assessment across view and scanners on two multi-scanner cohorts.Diagnostic performance was high with comparable or better performance than the CAP.

Underdetermined DOA estimation via multiple time-delay covariance matrices and deep residual network

Higher-order statistics based approaches and signal sparseness based approaches have emerged in recent decades to resolve the underdetermined direction-of-arrival(DOA)estimation problem.These model-based methods face great challenges in practical applications due to high computational complexity and dependence on ideal assumptions.This paper presents an effective DOA estimation approach based on a deep residual network(DRN)for the underdetermined case.We first extract an input feature from a new matrix calculated by stacking several covariance matrices corresponding to different time delays.We then provide the input feature to the trained DRN to construct the super resolution spectrum.The DRN learns the mapping relationship between the input feature and the spatial spectrum by training.The proposed approach is superior to existing model-based estimation methods in terms of calculation efficiency,independence of source sparseness and adaptive capacity to non-ideal conditions(e.g.,low signal to noise ratio,short bit sequence).Simulations demonstrate the validity and strong performance of the proposed algorithm on both overdetermined and underdetermined cases.

Toward Coordination Control of Multiple Fish-Like Robots:Real-Time Vision-Based Pose Estimation and Tracking via Deep Neural Networks

Controlling multiple multi-joint fish-like robots has long captivated the attention of engineers and biologists,for which a fundamental but challenging topic is to robustly track the postures of the individuals in real time.This requires detecting multiple robots,estimating multi-joint postures,and tracking identities,as well as processing fast in real time.To the best of our knowledge,this challenge has not been tackled in the previous studies.In this paper,to precisely track the planar postures of multiple swimming multi-joint fish-like robots in real time,we propose a novel deep neural network-based method,named TAB-IOL.Its TAB part fuses the top-down and bottom-up approaches for vision-based pose estimation,while the IOL part with long short-term memory considers the motion constraints among joints for precise pose tracking.The satisfying performance of our TAB-IOL is verified by testing on a group of freely swimming fish-like robots in various scenarios with strong disturbances and by a deed comparison of accuracy,speed,and robustness with most state-of-the-art algorithms.Further,based on the precise pose estimation and tracking realized by our TAB-IOL,several formation control experiments are conducted for the group of fish-like robots.The results clearly demonstrate that our TAB-IOL lays a solid foundation for the coordination control of multiple fish-like robots in a real working environment.We believe our proposed method will facilitate the growth and development of related fields.

Dynamic Task Offloading for Digital Twin-Empowered Mobile Edge Computing via Deep Reinforcement Learning

Limited by battery and computing re-sources,the computing-intensive tasks generated by Internet of Things(IoT)devices cannot be processed all by themselves.Mobile edge computing(MEC)is a suitable solution for this problem,and the gener-ated tasks can be offloaded from IoT devices to MEC.In this paper,we study the problem of dynamic task offloading for digital twin-empowered MEC.Digital twin techniques are applied to provide information of environment and share the training data of agent de-ployed on IoT devices.We formulate the task offload-ing problem with the goal of maximizing the energy efficiency and the workload balance among the ESs.Then,we reformulate the problem as an MDP problem and design DRL-based energy efficient task offloading(DEETO)algorithm to solve it.Comparative experi-ments are carried out which show the superiority of our DEETO algorithm in improving energy efficiency and balancing the workload.

Mitigating Deep Dielectric Charging Effects at the Orbits of Jovian Planets

Deep dielectric charging/discharging,caused by high energy electrons,is an important consideration in electronic devices used in space environments because it can lead to spacecraft anomalies and failures.The Jovian planets,including Saturn,Uranus,Neptune and Jupiter’s moons,are believed to have robust electron radiation belts at relativistic energies.In particular,Jupiter is thought to have caused at least 42 internal electrostatic discharge events during the Voyager 1 flyby.With the development of deep space exploration,there is an increased focus on the deep dielectric charging effects in the orbits of Jovian planets.In this paper,GEANT4,a Monte Carlo toolkit,and radiation-induced conductivity(RIC)are used to calculate deep dielectric charging effects for Jovian planets.The results are compared with the criteria for preventing deep dielectric charging effects in Earth orbit.The findings show that effective criteria used in Earth orbit are not always appropriate for preventing deep dielectric charging effects in Jovian orbits.Generally,Io,Europa,Saturn(R_S=6),Uranus(L=4.73)and Ganymede missions should have a thicker shield or higher dielectric conductivity,while Neptune(L=7.4)and Callisto missions can have a thinner shield thickness or a lower dielectric conductivity.Moreover,dielectrics grounded with double metal layers and thinner dielectrics can also decrease the likelihood of discharges.

Bridge the Gap Between Full-Reference and No-Reference:A Totally Full-Reference Induced Blind Image Quality Assessment via Deep Neural Networks

Blind image quality assessment(BIQA)is of fundamental importance in low-level computer vision community.Increasing interest has been drawn in exploiting deep neural networks for BIQA.Despite of the notable success achieved,there is a broad consensus that training deep convolutional neural networks(DCNN)heavily relies on massive annotated data.Unfortunately,BIQA is typically a small sample problem,resulting the generalization ability of BIQA severely restricted.In order to improve the accuracy and generalization ability of BIQA metrics,this work proposed a totally opinion-unaware BIQA in which no subjective annotations are involved in the training stage.Multiple full-reference image quality assessment(FR-IQA)metrics are employed to label the distorted image as a substitution of subjective quality annotation.A deep neural network(DNN)is trained to blindly predict the multiple FR-IQA score in absence of corresponding pristine image.In the end,a selfsupervised FR-IQA score aggregator implemented by adversarial auto-encoder pools the predictions of multiple FR-IQA scores into the final quality predicting score.Even though none of subjective scores are involved in the training stage,experimental results indicate that our proposed full reference induced BIQA framework is as competitive as state-of-the-art BIQA metrics.

Deep density estimation via invertible block-triangular mapping

In this work,we develop an invertible transport map,called KRnet,for density estimation by coupling the Knothe–Rosenblatt(KR)rearrangement and the flow-based generative model,which generalizes the real-valued non-volume preserving(real NVP)model(arX-iv:1605.08803v3).The triangular structure of the KR rearrangement breaks the symmetry of the real NVP in terms of the exchange of information between dimensions,which not only accelerates the training process but also improves the accuracy significantly.We have also introduced several new layers into the generative model to improve both robustness and effectiveness,including a reformulated affine coupling layer,a rotation layer and a component-wise nonlinear invertible layer.The KRnet can be used for both density estimation and sample generation especially when the dimensionality is relatively high.Numerical experiments have been presented to demonstrate the performance of KRnet.