基于多光谱成像和卷积神经网络的玉米作物营养状况识别方法研究

水肥一体化自动装备的使用能够有效提高水肥资源利用率,但需要在作业前获知作物的营养状况及水肥需求量,而通过人工手持测量仪器来获取这些信息,存在着时效性差和劳动强度大等缺点。针对以上问题,本研究以常见的作物玉米为研究对象,使用大疆精灵Ⅲ无人机携带RedEdge-M多光谱相机在田间上空采集玉米多光谱图像,同时使用YLS-D系列植株营养测定仪测量玉米植株的氮素和水分含量等营养信息,根据这些信息将采集的图像分为3个等级(每个等级共包含530幅五通道图像,其中480幅作为训练集,50幅作为验证集),提出了一种基于卷积神经网络的玉米作物营养状况识别方法。并基于TensorFlow深度学习框架搭建了ResNet18卷积神经网络模型,通过向模型输入彩色图像数据和五通道多光谱图像数据,分别训练出适合于彩色图像和多光谱图像的玉米植株营养状况等级识别模型。试验结果表明:训练后的模型能够识别玉米作物的彩色图像和多光谱图像,能够输出玉米的营养状况等级和GPS信息,识别彩色图像模型在验证集的正确率为84.7%,识别多光谱图像模型在验证集的正确率为90.5%,模型训练平均时间为4.5h,五通道图像识别平均用时为3.56s。该识别方法可快速无损地获取玉米作物的营养状况,为有效提高水肥资源利用率提供了方法和依据。

Deep Transcranial Magnetic Stimulation as a Potential Approach for Digital Pain Management in Patients with Psychotic Disorder

Dear Editor,Pain is a common and complex clinical problem which affects 28%-50%of the general population and is responsible for large health-related costs.People with chronic pain often develop nociceptive sensitization,having mood and anxiety disorders as comorbidities.Sustained pain may alter the processing of affective information in the brain,thereby inducing anxio-depressive disorders.

Exosomes derived from human amniotic epithelial cells accelerate diabetic wound healing via PI3K-AKT-mTOR-mediated promotion in angiogenesis and fibroblast function

Background:Diabetic wounds are one of the most common and serious complications of diabetes mellitus,characterized by the dysfunction of wound-healing-related cells in quantity and quality.Our previous studies revealed that human amniotic epithelial cells(hAECs)could promote diabetic wound healing by paracrine action.Interestingly,numerous studies demonstrated that exosomes derived from stem cells are the critical paracrine vehicles for stem cell therapy.However,whether exosomes derived from hAECs(hAECs-Exos)mediate the effects of hAECs on diabetic wound healing remains unclear.This study aimed to investigate the biological effects of hAECs-Exos on diabetic wound healing and preliminarily elucidate the underlying mechanism.Methods:hAECs-Exos were isolated by ultracentrifugation and identified by transmission electron microscopy,dynamic light scattering and flow cytometry.A series of in vitro functional analyses were performed to assess the regulatory effects of hAECs-Exos on human fibroblasts(HFBs)and human umbilical vein endothelial cells(HUVECs)in a high-glycemic microenvironment.Highthroughput sequencing and bioinformatics analyses were conducted to speculate the related mechanisms of actions of hAECs-Exos on HFBs and HUVECs.Subsequently,the role of the candidate signaling pathway of hAECs-Exos in regulating the function of HUVECs and HFBs,as well as in diabetic wound healing,was assessed.Results:hAECs-Exos presented a cup-or sphere-shaped morphology with a mean diameter of 105.89±10.36 nm,were positive for CD63 and TSG101 and could be internalized by HFBs and HUVECs.After that,hAECs-Exos not only significantly promoted the proliferation and migration of HFBs,but also facilitated the angiogenic activity of HUVECs in vitro.High-throughput sequencing revealed enriched miRNAs of hAECs-Exos involved in wound healing.Kyoto Encyclopedia of Genes and Genomes and Gene Ontology analyses have shown that the target genes of the top 15 miRNAs were highly enriched in the PI3K-AKT pathway.Further functional studies demonstrated that the PI3K-AKT-mTOR pathway was necessary for the induced biological effects of hAECs-Exos on HFBs and HUVECs,as well as on wound healing,in diabetic mice.Conclusions:Our findings demonstrated that hAECs-Exos represent a promising,novel strategy for diabetic wound healing by promoting angiogenesis and fibroblast function via activation of the PI3K-AKT-mTOR pathway.

Point cloud registration for agriculture and forestry crops based on calibration balls using Kinect V2

For the process of point cloud registration,and the problem of inaccurate registration due to errors in correspondence between keypoints.In this paper,a registration method based on calibration balls was proposed,the trunk,branch,and crown were selected as experimental objects,and three calibration balls were randomly placed around the experimental objects to ensure different distances between two ball centers.Using the Kinect V2 depth camera to collect the point cloud of the experimental scene from four different viewpoints,the PassThrough filter algorithm was used for point cloud filtering in each view of the experimental scenes.The Euclidean cluster extraction algorithm was employed for point cloud clustering and segmentation to extract the experimental object and the calibration ball.The random sample consensus(RANSAC)algorithm was applied to fit the point cloud of a ball and calculate the coordinates of the ball center so that the distance between two ball centers under different viewpoints can be obtained by using the coordinates of the ball center.Comparing the distance between the ball centers from different viewpoints to determine the corresponding relationship between the ball centers from different viewpoints,and then using the singular value decomposition(SVD)method,the initial registration matrix was obtained.Finally,Iterative Closest Point(ICP)and its improved algorithm were used for accurate registration.The experimental results showed that the method of point cloud registration based on calibration balls can solve the problem of corresponding error of keypoints,and can register point clouds from different viewpoints of the same object.The registration method was evaluated by using the registration running time and the fitness score.The final registration running time of different experimental objects was not more than 6.5 s.The minimum fitness score of the trunk was approximately 0.0001,the minimum fitness score of the branch was approximately 0.0001,and the minimum fitness score of the crown was approximately 0.0006.

The computational fluid dynamic modeling of downwash flow field for a six-rotor UAV

The downwash flow field of the multi-rotor unmanned aerial vehicle(UAV), formed by propellers during operation, has a significant influence on the deposition, drift and distribution of droplets as well as the spray width of the UAV for plant protection. To study the general characteristics of the distribution of the downwash airflow and simulate the static wind field of multi-rotor UAVs in hovering state, a 3 D full-size physical model of JF01-10 six-rotor plant protection UAV was constructed using Solid Works. The entire flow field surrounding the UAV and the rotation flow fields around the six rotors were established in UG software. The physical model and flow fields were meshed using unstructured tetrahedral elements in ANSYS software.Finally, the downwash flow field of UAV was simulated.With an increased hovering height, the ground effect was reduced and the minimum current velocity increased initially and then decreased. In addition, the spatial proportion of the turbulence occupied decreased. Furthermore, the appropriate operational hovering height for the JF01-10 is considered to be 3 m. These results can be applied to six-rotor plant protection UAVs employed in pesticide spraying and spray width detection.

Model migration for CFD and verification of a six-rotor UAV downwash

Currently,Computational Fluid Dynamics(CFD)has been used to investigate agricultural UAV downwash.However,the validations of CFD models are difficult to deal with.Current verification methods are to use either water-sensitive papers or wind-speed arrays,which could get wind distribution or speed only.In this study,model migration was used to develop and verify downwash CFD models.The basic idea is to try to use the results of a scaled-down drone to represent that of a real-used UAV.The CFD models of both a real-used six-rotor UAV,JF01-10,and a 1:10 scaled-down small drone were developed by ANSYS.Then,the scaled-down drone was utilized to conduct trials by particle image velocimetry(PIV),so that not only distribution and speed but also flowing direction of downwash could be obtained.Results indicated the relative error between the PIV tests and the CFD models of the small UAV was less than 12%,while that between the tests and the CFD models of JF01-10 was less than 34%.It could be indicated that model migration could reflect multiple downwash characteristics but should be optimized in some complex details.This study was a preliminary but fundamental attempt to investigate CFD modelling and validation of agricultural UAVs and provided a novel thinking of downwash verification.

Ternary Metal–Organic Framework Derived 2D Fe_(2)O_(3)/Co_(3)O_(4)/NiO/NC Heterostructured Nanosheets for Super Lithium Storage

Fe_(2)O_(3)/Co_(3)O_(4)/NiO/NC nanosheets have been successfully prepared via a two-step annealing process of ternary metal coordination polymer. Attributing to the synergistic effects of the multiple metal oxides and the unique 2D nanosheet structure, the improved electrical conductivity and effective electron/ion transfer enables Fe_(2)O_(3)/Co_(3)O_(4)/NiO/NC electrode to exhibit excellent electrochemical properties with outstanding rate capacity and cycling stability. This work may pave the way to construct ternary metal oxide electrode material with an excellent electrochemical performance by introducing multiple metal oxides.

Finite element modal analysis and experiment of rice transplanter chassis

The vibration problem during the operation of rice transplanters is the most common phenomenon.In order that the static and dynamic characteristics of the rice transplanter chassis can meet the requirements of more stable operation,the research took the 2ZG-6DK rice transplanter as the research object to carry out a vibration reduction optimization study.In the research,the Pro/Engineer 5.0 software was first used to model the chassis of the rice transplanter.The constructed finite element model was revised by using the structural parameter revision method and the mixed penalty function method.The model was imported into ANSYS Workbench to solve the modal frequency and vibration shape of the rice transplanter chassis.Based on the MAC(modal assurance criterion)criterion,modal tests were carried out to verify the accuracy of the finite element theoretical analysis.Through the analysis of the characteristics of the external excitation frequency,the chassis is structurally optimized to avoid resonance caused by the natural frequency of the chassis falling within the road excitation frequency range.The final optimization results showed that the first four orders of modal frequencies of the chassis were adjusted to 32.083 Hz,33.751 Hz,42.517 Hz,and 50.362 Hz,respectively,in the case that the chassis mass was increased by 6.714 kg(8.8%).They all avoid the range of road excitation frequency(10-30 Hz)so that the rice transplanter can effectively avoid the resonance phenomenon during operation.This study can provide a reference for the design and optimization of the chassis structure of transplanter.

Redox-responsive self-assembly polymeric micelles based on mPEG-β-cyclodextrin and a camptothecin prodrug as drug release carriers

Stimuli-responsive drug delivery systems based on polymeric micelles can achieve controlled drug release to improve the therapeutic outcome and reduce unwanted systematic toxicity and side effects of the cytotoxic drug in chemotherapy but often face challenging synthesis and purification of functionalized biocompatible polymer materials and low drug loading efficiency. In the present study, we reported a novel redox-responsive self-assembly polymeric micelle system, mPEG-β-CD/Ad-SS-CPT, to achieve high loading efficiency and selective delivery of camptothecin(CPT) in a reductive environment inside cancer cells. The host-guest supramolecular micelles utilized a simple β-CD modified PEG, mPEG-β-cyclodextrin(mPEG-β-CD), as the polymeric host with the ease of synthesis and purification. The guest prodrug Ad-SS-CPT contained the disulfide bond as the redox sensitivity group. The selective cleavage of disulfide bond and subsequent drug release in a reductive environment could potentially reduce system toxicity and improve the therapeutic outcome of CPT. In vitro studies showed that the micelles exhibited excellent cytotoxicity against He La cells comparable to the free drug. The host-guest polymeric micelles also showed great potentials for multi-drug co-delivery. Collectively, our current findings provided a general and convenient approach to design drug delivery systems based on stimuli-responsive polymeric micelles for disease treatment.