Intelligent diagnosis of retinal vein occlusion based on color fundus photographs

AIM:To develop an artificial intelligence(AI)diagnosis model based on deep learning(DL)algorithm to diagnose different types of retinal vein occlusion(RVO)by recognizing color fundus photographs(CFPs).METHODS:Totally 914 CFPs of healthy people and patients with RVO were collected as experimental data sets,and used to train,verify and test the diagnostic model of RVO.All the images were divided into four categories[normal,central retinal vein occlusion(CRVO),branch retinal vein occlusion(BRVO),and macular retinal vein occlusion(MRVO)]by three fundus disease experts.Swin Transformer was used to build the RVO diagnosis model,and different types of RVO diagnosis experiments were conducted.The model’s performance was compared to that of the experts.RESULTS:The accuracy of the model in the diagnosis of normal,CRVO,BRVO,and MRVO reached 1.000,0.978,0.957,and 0.978;the specificity reached 1.000,0.986,0.982,and 0.976;the sensitivity reached 1.000,0.955,0.917,and 1.000;the F1-Sore reached 1.000,0.9550.943,and 0.887 respectively.In addition,the area under curve of normal,CRVO,BRVO,and MRVO diagnosed by the diagnostic model were 1.000,0.900,0.959 and 0.970,respectively.The diagnostic results were highly consistent with those of fundus disease experts,and the diagnostic performance was superior.CONCLUSION:The diagnostic model developed in this study can well diagnose different types of RVO,effectively relieve the work pressure of clinicians,and provide help for the follow-up clinical diagnosis and treatment of RVO patients.

Dynamic properties of rumor propagation model induced by L´evy noise on social networks

Social networks are inevitably subject to disruptions from the physical world,such as sudden internet outages that sever local connections and impede information flow.While Gaussian white noise,commonly used to simulate stochastic disruptions,only fluctuates within a narrow range around its mean and fails to capture large-scale variations,L´evy noise can effectively compensate for this limitation.Therefore,a susceptible–infected–removed rumor propagation model with L´evy noise is constructed on homogeneous and heterogeneous networks,respectively.Then,the existence of a global positive solution and the asymptotic path-wise of the solution are derived on heterogeneous networks,and the sufficient conditions of rumor extinction and persistence are investigated.Subsequently,theoretical results are verified through numerical calculations and the sensitivity analysis related to the threshold is conducted on the model parameters.Through simulation experiments on Watts–Strogatz(WS)and Barab´asi–Albert networks,it is found that the addition of noise can inhibit the spread of rumors,resulting in a stochastic resonance phenomenon,and the optimal noise intensity is obtained on the WS network.The validity of the model is verified on three real datasets by particle swarm optimization algorithm.

OptoGPT: A foundation model for inverse design in optical multilayer thin film structures

Optical multilayer thin film structures have been widely used in numerous photonic applications.However,existing inverse design methods have many drawbacks because they either fail to quickly adapt to different design targets,or are difficult to suit for different types of structures,e.g.,designing for different materials at each layer.These methods also cannot accommodate versatile design situations under different angles and polarizations.In addition,how to benefit practical fabrications and manufacturing has not been extensively considered yet.In this work,we introduce OptoGPT(Opto Generative Pretrained Transformer),a decoder-only transformer,to solve all these drawbacks and issues simultaneously.

Political Optimizer with Deep Learning-Enabled Tongue Color Image Analysis Model

Biomedical image processing is widely utilized for disease detection and classification of biomedical images.Tongue color image analysis is an effective and non-invasive tool for carrying out secondary detection at anytime and anywhere.For removing the qualitative aspect,tongue images are quantitatively inspected,proposing a novel disease classification model in an automated way is preferable.This article introduces a novel political optimizer with deep learning enabled tongue color image analysis(PODL-TCIA)technique.The presented PODL-TCIA model purposes to detect the occurrence of the disease by examining the color of the tongue.To attain this,the PODL-TCIA model initially performs image pre-processing to enhance medical image quality.Followed by,Inception with ResNet-v2 model is employed for feature extraction.Besides,political optimizer(PO)with twin support vector machine(TSVM)model is exploited for image classification process,shows the novelty of the work.The design of PO algorithm assists in the optimal parameter selection of the TSVM model.For ensuring the enhanced outcomes of the PODL-TCIA model,a wide-ranging experimental analysis was applied and the outcomes reported the betterment of the PODL-TCIA model over the recent approaches.

Calculation of the Standard Model Parameters and Particles Based on a SU(4) Preon Model

This paper describes an extension and a new foundation of the Standard Model of particle physics based on a SU(4)-force called hyper-color, and on preon subparticles. The hyper-color force is a generalization of the SU(2)-based weak interaction and the SU(1)-based right-chiral self-interaction, in which the W-and the Z-bosons are Yukawa residual-field-carriers of the hyper-color force, in the same sense as the pions are the residual-field-carriers of the color SU(3) interaction. Using the method of numerical minimization of the SU(4)-action based on this model, the masses and the inner structure of leptons, quarks and weak bosons are calculated: the mass results are very close to the experimental values. We calculate also precisely the value of the Cabibbo angle, so the mixing matrices of the Standard model, CKM matrix for quarks and PMNS matrix for neutrinos can also be calculated. In total, we reduce the 29 parameters of the Standard Model to a total of 7 parameters.

Visualization of uncertainty associated with spatial prediction of continuous variables using HSI color model:a case study of prediction of pH for topsoil in peri-urban Beijing,China

Hue-Saturation-Intensity （HSI） color model, a psychologically appealing color model, was employed to visualize uncertainty represented by relative prediction error based on the case of spatial prediction of pH of topsoil in the peri-urban Beijing. A two-dimensional legend was designed to accompany the visualization-vertical axis （hues） for visualizing the predicted values and horizontal axis （whiteness） for visualizing the prediction error. Moreover, different ways of visualizing uncertainty were briefly reviewed in this paper. This case study indicated that visualization of both predictions and prediction uncertainty offered a possibility to enhance visual exploration of the data uncertainty and to compare different prediction methods or predictions of totally different variables. The whitish region of the visualization map can be simply interpreted as unsatisfactory prediction results, where may need additional samples or more suitable prediction models for a better prediction results.

基于R-L分数阶定义的CCM Flyback变换器建模与分析

针对电容电感都为分数阶这一事实,利用分数阶微积分R-L定义和状态空间平均法,对工作在电感电流连续模式(CCM)下的分数阶Flyback变换器进行建模与分析。推导CCM分数阶Flyback变换器的静态工作点和小信号传递函数以及变换器工作在CCM模式下的条件。其次,讨论Caputo模型与R-L导数模型的区别,得出在R-L分数阶定义下直流静态工作点不仅与占空比相关,而且还与电感和电容的阶数以及负载有关。最后,在PSIM中搭建R-L分数阶CCM Flyback变换器电路模型,得到不同分数阶电感电容阶数下分数阶Flyback变换器输出电压和电感电流的仿真波形,通过仿真结果与理论计算结果对比,验证所建模型的正确性,得出分数阶电感电容的阶数会影响闭环控制器的设计和分数阶模型能更加精确地描述Flyback变换器的工作特性。

盐湖大气环境下316 L仪表管点蚀深度预测研究

为提高316 L仪表管在盐湖大气环境下点蚀深度的预测精度,采用变阶平均弱化缓冲算子、积分背景值和新陈代谢对分数阶累加灰色模型FGM(1,1,r)进行改进,首先通过改进Tent混沌映射、莱维飞行和区间自适应反向学习策略提高黏菌算法(SMA)的寻优能力和收敛速度,随后利用改进黏菌算法(ISMA)对FGM(1,1,r,ρ)中的参数r和ρ进行寻优,最后构建仪表管ISMA-FGM(1,1,r,ρ)点蚀深度预测模型。研究结果表明:经优化的新模型比原模型误差更小、拟合度更高,在仪表管点蚀深度预测方面具有更好的性能。研究结果可为仪表管道系统的完整性评价和风险预警提供参考。

Modeling Method of Automotive Body CAN/LIN Nets Application Protocol Based on Object-oriented Colored Petri Net

Recently automotive nets are adopted to solve increasing problems in automotive electronic systems.Technologies of automotive local area network from CAN and LIN can solve the problems of the increasing of wire bunch weight and lack in module installation space.However,the multilayer automotive nets software becomes more and more complex,and the development expense is difficult to predict and to keep in check.In this paper,the modeling method of hierarchical automotive nets and the substitution operation based on object-oriented colored Petri net(OOCPN) are proposed.The OOCPN model which analyzes the software structure and validates the collision mechanism of CAN/LIN bus can speed the automobile system development.First,the subsystems are divided and modeled by object-oriented Petri net(OOPN).According to the sets of message sharing relations,the message ports among them are set and the communication gate transitions are defined.Second,the OOPN model is substituted step by step until the inner objects in the automotive body control modules(BCM) are indivisible and colored by colored Petri net(CPN).And the color subsets mark the node messages for the collision mechanism.Third,the OOCPN model of the automotive body CAN/LIN nets is assembled,which keeps the message sets and the system can be expanded.The proposed model is used to analyze features of information sharing among the objects,and it is also used to describe each subsystem real-time behavior of processing messages and implemental device controllers operating,and puts forward a reasonable software framework for the automotive body control subsystem.The research can help to design the communication model in the automotive body system effectively and provide a convenient and rapid way for developing the logical hierarchy software.

Color Image Segmentation Based on HSI Model

he objective of the research is to develop a fast procedure for segmenting typical videophone images. In this paper, a new approach to color image segmentation based on HSI(Hue, Saturation, Intensity) color model is reported. It is in contrast to the conventional approaches by using the three components of HSI color model in succession. This strategy makes the segmentation procedure much fast and effective. Experimental results with typical “headandshoulders” real images taken from videophone sequences show that the new appproach can fulfill the application requirements.

Color-texture segmentation using JSEG based on Gaussian mixture modeling

An improved approach for J-value segmentation （JSEG） is presented for unsupervised color image segmentation. Instead of color quantization algorithm, an automatic classification method based on adaptive mean shift （AMS） based clustering is used for nonparametric clustering of image data set. The clustering results are used to construct Gaussian mixture modelling （GMM） of image data for the calculation of soft J value. The region growing algorithm used in JSEG is then applied in segmenting the image based on the multiscale soft J-images. Experiments show that the synergism of JSEG and the soft classification based on AMS based clustering and GMM overcomes the limitations of JSEG successfully and is more robust.

A Real-Time Photo-Realistic Rendering Algorithm of Ocean Color Based on Bio-Optical Model

Abstract A real-time photo-realistic rendering algorithm of ocean color is introduced in the paper, which considers the impact of ocean bio-optical model. The ocean bio-optical model mainly involves the phytoplankton, colored dissolved organic material （CDOM）, inorganic suspended particle, etc., which have different contributionsto absorption and scattering of light. We decompose the emergent light of the ocean surface into the reflected light from the sun and the sky, and the subsurface scattering light. We estab- lish an ocean surface transmission model based on ocean bidirectional reflectance distribution function （BRDF） and the Fresnel law, and this model＇s outputs would be the incident light parameters of subsurface scattering. Using ocean subsurface scattering algorithm combined with bio-optical model, we compute the scattering light emergent radiation in different directions. Then, we blend the re- flection of sunlight and sky light to implement the real-time ocean color rendering in graphics processing unit （GPU）. Finally, we use two kinds of radiance reflectance calculated by Hydrolight radiative transfer model and our algorithm to validate the physical reality of our method, and the results show that our algorithm can achieve real-time highly realistic ocean color scenes.

Spatiotemporal characteristics and remote sensing estimation of colored dissolved organic matter around the Leizhou Peninsula

Colored dissolved organic matter(CDOM)is an important optically active substance in marine environment.Its biochemical conservatism makes it an important indicator to offshore pollution process.Monitoring the content,composition,and diffusion process of CDOM is a good approach to analyze the terrestrial input,optical properties,and ecological environment of offshore areas.The spatiotemporal characteristics of CDOM around the Leizhou Peninsula were analyzed based on field observation data collected in the autumn 2020 and spring 2021,and an empirical inversion model of the ag(355)(absorption coefficient at 355 nm)and spectral slope(Sg)(g stands for gelbstoff/gilvin,which is called CDOM)based on Sentinel-3A ocean and land color instrument(OLCI)images was constructed.The results show(1)the order of average ag(355)value around the Leizhou Peninsula was east coast(0.503/m)>Qiongzhou Strait(0.502/m)>west coast(0.365/m);(2)the best band combinations of CDOM inversion in spring and autumn were(B4+B11)/B3 and(B7-B1)/B6(B stands for the band of spectral images),and the final inversion results are close to the measured results,indicating that the model has good accuracy;(3)the S_(g)value of the CDOM absorption spectrum was fitted to the hyperbolicexponential model.The fitting accuracy of the model was higher than those of the exponential model and the hyperbolic model,and the best S_(g)inversion model was constructed by selecting Sg(275-295)and Sg(250-295)in spring and autumn;(4)the spatial distributions of ag(355)and S_(g)were inverted,and CDOM in the waters around the Leizhou Peninsula originated from terrestrial organic matter carried by coastal aquaculture zones and runoff in the northeast Zhanjiang and the northern Beibu Gulf.

基于改进MobileNetV2的棉花颜色分级检测

针对棉花颜色级检验中感官检验容易受到主观因素影响、仪器检验不稳定的问题,提出一种使用改进MobileNetV2神经网络实现棉花颜色级检测的方法。通过自主设计的图像采集装置,收集白棉一级到白棉五级5种棉花颜色级样品,制作数据集。将MobileNetV2网络后三层进行特征融合,并嵌入CBAM注意力机制,同时与GhostNet、ShuffleNetV2和原始MobileNetV2模型进行对比,预测棉花颜色分级。结果表明:改进后的MobileNetV2在测试集的准确率达到92.10%,相对于GhostNet、ShuffleNetV2和原始MobileNetV2分别提高了3.01个百分点、4.61个百分点、1.24个百分点,具有较好的检测效果。

Modelling the impacts of cover crop management strategies on the water use,carbon exchange and yield of olive orchards

Cover crops have long been proposed as an alternative soil management for minimizing erosion rates in olive stands while providing additional ecosystem services.However,the trade-off between these benefits and the competition for water with the trees makes the definition of optimal management practices a challenging task in semiarid climates.This work presents an improved version of OliveCan,a process-based simulation model of olive orchards that now can simulate the main impacts of cover crops on the water and carbon balances of olive orchards.Albeit simple in its formulation,the new model components were developed to deal with different cover crop management strategies.Examples are presented for simulation runs of a traditional olive orchard in the conditions of southern Spain,evaluating the effects of different widths for the strip occupied by the cover crop(Fcc)and two contrasting mowing dates.Results revealed that high Fccresulted in lower olive yields,but only when mowing was applied at the end of spring.In this regard,late mowing and high Fccwas associated with lower soil water content from spring to summer,coinciding with olive flowering and the earlier stages of fruit growth.Fccwas also negatively correlated with surface runoff irrespective of the mowing date.On the other hand,net ecosystem productivity(NEP)was substantially affected by both Fccand mowing date.Further simulations under future climate scenarios comparing the same management alternatives are also presented,showing substantial yield reductions by the end of the century and minor or negligible changes in NEP and seasonal runoff.

GLOBAL SOLUTIONS TO A HYDRODYNAMIC MODEL FOR SEMICONDUCTORS WITH VELOCITY RELAXATION

In this paper,we apply the method given in the paper“Zero relaxation time limits to a hydrodynamic model of two carrier types for semiconductors”(Mathematische Annalen,2022,382:1031–1046)to study the Cauchy problem for a one dimensional inhomogeneous hydrodynamic model of two-carrier types for semiconductors with the velocity relaxation.

A Parametric Colored Petri Net Model of a Switched Network

A parametric Colored Petri net model of the switched Ethernet network with the tree-like topology is developed. The model’s structure is the same for any given network and contains fixed number of nodes. The tree-like topology of a definite network is given as the marking of dedicated places. The model represents a network containing workstations, servers, switches, and provides the evaluation of the network response time. Besides topology, the parameters of the model are performances of hardware and software used within the network. Performance evaluation for the network of the railway dispatcher center is implemented. Topics of the steady-stable condition and the optimal choice of hardware are discussed.

MODELING RADIO RESOURCE MANAGEMENT IN COGNITIVE RADIO SYSTEM BASED ON OFDMA USING COLORED PETRI NET

Cognitive Radio(CR) system based on Orthogonal Frequency Division Multiple Access(OFDMA),such as Wireless Regional Area Networks(WRAN) and Worldwide Interoperability for Microwave Access(WiMAX),often attempt to improve performance via dynamic radio resource management,which is characterized as concurrent processing of different traffic and nondeterministic system capacity.It is essential to design and evaluate such complex system using proper modeling and analysis tools.In the previous work,most of the communication systems were modeled as Markov Chain(MC) and Stochastic Petri Nets(SPN),which have the explicit limitation in evaluating adaptive OFDMA CR system with wide area traffic.In this paper,we develop an executable top-down hier-archical Colored Petri Net(CPN) model for adaptive OFDMA CR system,and analyze its performance using CPN tools.The results demonstrate that the CPN can model different radio resource manage-ment algorithms in CR Systems,and the CPN tools require less computational effort than Markov model using Matlab,with its flexibility and adaptability to the traffics which arrival interval and processing time are not exponentially distributed.

Transitions in a Logistic Growth Model Induced by Noise Coupling and Noise Color

With unified colored noise approximation, the logistic growth model is used to analyze cancer cell population when colored noise is included. It is found that both the coupling between noise terms and the noise color can induce continuous first-order-like and re-entrance-like phase transitions in the system. The coupling and the noise color can also increase tumor cell growth for small number of cell mass and repress tumor cell growth for large number of cell mass. It is shown that the approximate analytic expressions are consistent with the numerical simulations.

A colored Petri net-based model for web service composition

In this paper, a model based colored Petri net （CPN） to provide semantic support for web service composition is proposed, and the reliability and maintainability of composite services are improved. The composite constructs in the model are sequence, concurrent, choice, loop and replace. The web service is formally defined by a CPN. A closed composing algebra is defined to obtain a framework which enables declarative composition of web services. Availability, confidentiality, and integrity of composite service are analyzed within the framework of the model based CPN.