Machine learning prediction model for gray-level co-occurrence matrix features of synchronous liver metastasis in colorectal cancer

BACKGROUND Synchronous liver metastasis(SLM)is a significant contributor to morbidity in colorectal cancer(CRC).There are no effective predictive device integration algorithms to predict adverse SLM events during the diagnosis of CRC.AIM To explore the risk factors for SLM in CRC and construct a visual prediction model based on gray-level co-occurrence matrix(GLCM)features collected from magnetic resonance imaging(MRI).METHODS Our study retrospectively enrolled 392 patients with CRC from Yichang Central People’s Hospital from January 2015 to May 2023.Patients were randomly divided into a training and validation group(3:7).The clinical parameters and GLCM features extracted from MRI were included as candidate variables.The prediction model was constructed using a generalized linear regression model,random forest model(RFM),and artificial neural network model.Receiver operating characteristic curves and decision curves were used to evaluate the prediction model.RESULTS Among the 392 patients,48 had SLM(12.24%).We obtained fourteen GLCM imaging data for variable screening of SLM prediction models.Inverse difference,mean sum,sum entropy,sum variance,sum of squares,energy,and difference variance were listed as candidate variables,and the prediction efficiency(area under the curve)of the subsequent RFM in the training set and internal validation set was 0.917[95%confidence interval(95%CI):0.866-0.968]and 0.09(95%CI:0.858-0.960),respectively.CONCLUSION A predictive model combining GLCM image features with machine learning can predict SLM in CRC.This model can assist clinicians in making timely and personalized clinical decisions.

基于改进Frequency-Bessel变换法的主动源Love波频散分析

近年来,Love波多道分析技术在浅地表结构探测中受到越来越广泛的应用.与Rayleigh波相比,Love波相速度不受纵波速度影响,其反演参数较少,可使反演过程更加稳定、求解的横波速度模型更加可靠.高分辨率和多模式面波频散分析是面波多道分析技术中至关重要的一环.本文利用改进Frequency-Bessel变换法对主动源Love波进行频散分析.通过改进的0阶Frequency-Bessel变换,将时间-空间域多道Love波记录变换到频率-波数域,获得其频散能量谱.通过公式推导和数值模拟,验证了该方法的有效性.实例测试表明,该方法具有较高的分辨率和多模式分辨能力,为多分量面波勘探提供了一种有效的频散分析手段.

Artificial intelligence on diabetic retinopathy diagnosis: an automatic classification method based on grey level co-occurrence matrix and naive Bayesian model

AIM: To develop an automatic tool on screening diabetic retinopathy(DR) from diabetic patients.METHODS: We extracted textures from eye fundus images of each diabetes subject using grey level co-occurrence matrix method and trained a Bayesian model based on these textures. The receiver operating characteristic(ROC) curve was used to estimate the sensitivity and specificity of the Bayesian model.RESULTS: A total of 1000 eyes fundus images from diabetic patients in which 298 eyes were diagnosed as DR by two ophthalmologists. The Bayesian model was trained using four extracted textures including contrast, entropy, angular second moment and correlation using a training dataset. The Bayesian model achieved a sensitivity of 0.949 and a specificity of 0.928 in the validation dataset. The area under the ROC curve was 0.938, and the 10-fold cross validation method showed that the average accuracy rate is 93.5%.CONCLUSION: Textures extracted by grey level cooccurrence can be useful information for DR diagnosis, and a trained Bayesian model based on these textures can be an effective tool for DR screening among diabetic patients.

Binary Image Steganalysis Based on Distortion Level Co-Occurrence Matrix

In recent years,binary image steganography has developed so rapidly that the research of binary image steganalysis becomes more important for information security.In most state-of-the-art binary image steganographic schemes,they always find out the flippable pixels to minimize the embedding distortions.For this reason,the stego images generated by the previous schemes maintain visual quality and it is hard for steganalyzer to capture the embedding trace in spacial domain.However,the distortion maps can be calculated for cover and stego images and the difference between them is significant.In this paper,a novel binary image steganalytic scheme is proposed,which is based on distortion level co-occurrence matrix.The proposed scheme first generates the corresponding distortion maps for cover and stego images.Then the co-occurrence matrix is constructed on the distortion level maps to represent the features of cover and stego images.Finally,support vector machine,based on the gaussian kernel,is used to classify the features.Compared with the prior steganalytic methods,experimental results demonstrate that the proposed scheme can effectively detect stego images.

Frequency Domain Filtering SAR Interferometric Phase Noise Using the Amended Matrix Pencil Model

Interferometric phase filtering is one of the key steps in interferometricsynthetic aperture radar (InSAR/SAR). However, the ideal filtering results are difficult toobtain due to dense fringe and low coherence regions. Moreover, the InSAR/SAR datarange is relatively large, so the efficiency of interferential phase filtering is one of themajor problems. In this letter, we proposed an interferometric phase filtering methodbased on an amended matrix pencil and linear window mean filter. The combination ofthe matrix pencil and the linear mean filter are introduced to the interferometric phasefiltering for the first time. First, the interferometric signal is analyzed, and theinterferometric phase filtering is transformed into a local frequency estimation problem.Then, the local frequency is estimated using an amended matrix pencil at a window. Thelocal frequency can represent terrain changes, thus suggesting that the frequency can beaccurately estimated even in dense fringe regions. Finally, the local frequency is filteredby using a linear window mean filter, and the filtered phase is recovered. The proposedmethod is calculated by some matrices. Therefore, the computational complexity isreduced, and the efficiency of the interferometric phase filtering is improved.Experiments are conducted with simulated and real InSAR data. The proposed methodexhibits a better filtering effect and an ideal efficiency as compared with the traditionalfiltering method.

3D Gray Level Co-Occurrence Matrix Based Classification of Favor Benign and Borderline Types in Follicular Neoplasm Images

Since the efficiency of treatment of thyroid disorder depends on the risk of malignancy, indeterminate follicular neoplasm (FN) images should be classified. The diagnosis process has been done by visual interpretation of experienced pathologists. However, it is difficult to separate the favor benign from borderline types. Thus, this paper presents a classification approach based on 3D nuclei model to classify favor benign and borderline types of follicular thyroid adenoma (FTA) in cytological specimens. The proposed method utilized 3D gray level co-occurrence matrix (GLCM) and random forest classifier. It was applied to 22 data sets of FN images. Furthermore, the use of 3D GLCM was compared with 2D GLCM to evaluate the classification results. From experimental results, the proposed system achieved 95.45% of the classification. The use of 3D GLCM was better than 2D GLCM according to the accuracy of classification. Consequently, the proposed method probably helps a pathologist as a prescreening tool.

Efficient solution of large-scale matrix of acoustic wave equations in 3D frequency domain

In 3D frequency domain seismic forward and inversion calculation,the huge amount of calculation and storage is one of the main factors that restrict the processing speed and calculation efficiency.The frequency domain finite-difference forward simulation algorithm based on the acoustic wave equation establishes a large bandwidth complex matrix according to the discretized acoustic wave equation,and then the frequency domain wave field value is obtained by solving the matrix equation.In this study,the predecessor's optimized five-point method is extended to a 3D seven-point finite-difference scheme,and then a perfectly matched layer absorbing boundary condition(PML)is added to establish the corresponding matrix equation.In order to solve the complex matrix,we transform it to the equivalent real number domain to expand the solvable range of the matrix,and establish two objective functions to transform the matrix solving problem into an optimization problem that can be solved using gradient methods,and then use conjugate gradient algorithm to solve the problem.Previous studies have shown that in the conjugate gradient algorithm,the product of the matrix and the vector is the main factor that affects the calculation efficiency.Therefore,this study proposes a method that transform bandwidth matrix and vector product problem into some equivalent vector and vector product algorithm,thereby reducing the amount of calculation and storage.

A Combination of Feature Selection and Co-occurrence Matrix Methods for Leukocyte Recognition System

A leukocyte recognition system, as part of a differential blood counter system, is very important in hematology field. In this paper, the propose system aims to automatically classify the white blood cells (leukocytes) on a given microscopic image. The classifications of leukocytes are performed based on the combination of color and texture features of the blood cell images. The developed system classifies the leukocytes in one of the five categories (neutrophils, eosinophils, basophils, lymphocytes, and monocytes). In the preprocessing stage, the system starts with converting the microscopic images from Red Green Blue (RGB) color space to Hue Saturation Value (HSV) color space. Next, the system splits the Hue and Saturation features from the Value feature. For both Hue and Saturation features, the system processes their color information using the Feature Selection method and the Window Cropping method;while the Value feature is processed by its texture information using the Co-occurrence matrix method. The final recognition stage is performed using the Euclidean distance method. The combination of the Feature Selection and Co-occurrence Matrix methods gives the best overall recognition accuracies for classifying leukocyte images.

Resilient Fixed-Order Distributed Dynamic Output Feedback Load Frequency Control Design for Interconnected Multi-Area Power Systems

The paper proposes a novel H∞ load frequency control(LFC) design method for multi-area power systems based on an integral-based non-fragile distributed fixed-order dynamic output feedback(DOF) tracking-regulator control scheme. To this end, we consider a nonlinear interconnected model for multiarea power systems which also include uncertainties and timevarying communication delays. The design procedure is formulated using semi-definite programming and linear matrix inequality(LMI) method. The solution of the proposed LMIs returns necessary parameters for the tracking controllers such that the impact of model uncertainty and load disturbances are minimized. The proposed controllers are capable of receiving all or part of subsystems information, whereas the outputs of each controller are local. These controllers are designed such that the resilient stability of the overall closed-loop system is guaranteed. Simulation results are provided to verify the effectiveness of the proposed scheme. Simulation results quantify that the distributed(and decentralized) controlled system behaves well in presence of large parameter perturbations and random disturbances on the power system.

Controlling the light wavefront through a scattering medium based on direct digital frequency synthesis technology

Phase modulation is a crucial step when the frequency-based wavefront optimization technique is exploited to measure the optical transmission matrix(TM) of a scattering medium. We report a simple but powerful method, direct digital frequency synthesis(DDS) technology to modulate the phase front of the laser and measure the TM. By judiciously modulating the phase front of a He–Ne laser beam, we experimentally generate a high quality focus at any targeted location through a 2 mm thick 120 grit ground glass diffuser, which is commercially used in laser display and laser holographic display for improving brightness uniformity and reducing speckle. The signal to noise ratio(SNR) of the clear round focus is 50 and the size is about 44 μm. Our study will open up new avenues for enhancing light energy delivery to the optical engine in laser TV to lower the power consumption, phase compensation to reduce the speckle noise, and controlling the lasing threshold in random lasers.

Material microstructures analyzed by using gray level Co-occurrence matrices

The mechanical properties of materials greatly depend on the microstructure morphology. The quantitative characterization of material microstructures is essential for the performance prediction and hence the material design. At present,the quantitative characterization methods mainly rely on the microstructure characterization of shape, size, distribution,and volume fraction, which related to the mechanical properties. These traditional methods have been applied for several decades and the subjectivity of human factors induces unavoidable errors. In this paper, we try to bypass the traditional operations and identify the relationship between the microstructures and the material properties by the texture of image itself directly. The statistical approach is based on gray level Co-occurrence matrix（GLCM）, allowing an objective and repeatable study on material microstructures. We first present how to identify GLCM with the optimal parameters, and then apply the method on three systems with different microstructures. The results show that GLCM can reveal the interface information and microstructures complexity with less human impact. Naturally, there is a good correlation between GLCM and the mechanical properties.

Detection of fabric defects based on frequency-tuned salient algorithm

The correct rate of detection for fabric defect is affected by low contrast of images. Aiming at the problem,frequencytuned salient map is used to detect the fabric defect. Firstly,the images of fabric defect are divided into blocks. Then,the blocks are highlighted by frequency-tuned salient algorithm. Simultaneously,gray-level co-occurrence matrix is used to extract the characteristic value of each rectangular patch. Finally,PNN is used to detect the defect on the fabric image. The performance of proposed algorithm is estimated off-line by two sets of fabric defect images. The theoretical argument is supported by experimental results.

Dual Treatment Strategy by Venous Ulcers: Pilot Study to Dual-Frequency Ultrasound Application

We propose a new dual treatment strategy by venous ulcer, consisting in simultaneous modulation of matrix metalloproteinases (MMPs) and heat shock proteins (HSPs) in the wound. One treatment method which can efficiently modulate both these substances is based on the application of dual-frequency ultrasound (LDM). This strategy was checked in a pilot study on 10 patients with chronic venous ulcers and demonstrated excellent healing rate.

六自由度运动模拟平台设计与分析

针对实际道路测试周期长、成本高、容易受到恶劣天气影响等问题,设计一种能够用于车载光电跟踪系统进行模拟试验的六自由度摇摆台。模拟扰动测试,通过六自由度摇摆台提供扰动;对六自由度摇摆台进行结构设计、运动及频率特性分析。结果表明,该摇摆台能够推导其固有频率与机构刚度矩阵和质量矩阵的关系。

模块化多电平矩阵换流器接入下的工频故障特性分析

基于模块化多电平矩阵换流器(M3C)的柔性低频输电系统在中远海风电外送、异步电网互联等方面优势突出。然而,有别于模块化多电平换流器(MMC)等其他电力电子换流设备,M3C的控制策略将导致系统故障特性发生显著变化。现有将电力电子设备负序部分等效为开路的故障等值与响应特性计算方法无法适用。文中计及M3C正序定电容电压总平均值控制、负序电流注入控制以及环流控制分层构成的桥臂电容电压均衡策略,推导了工频侧线路故障以后,M3C输入输出功率均衡、桥臂功率均衡(电容电压均衡的必要条件)与正负序电压电流间的映射关系,由此构建了工频侧线路故障(不对称、对称)后的M3C输出电压电流响应特性的等效模型。在此基础上,提出了M3C接入下工频侧线路故障后电压电流响应特性的精确计算方法。最后,基于PSCAD/EMTDC仿真平台,搭建了海上风电柔性低频送出系统仿真模型,通过大量仿真算例充分验证了所提故障特性分析方法的正确性和精确性。

埃尔米特梁单元的分块对角与高阶质量矩阵

埃尔米特梁单元常用的集中质量矩阵,是由挠度自由度对应的一致质量矩阵元素通过行求和或节点积分构造.然而,数值结果表明该集中质量矩阵在求解包含自由端的梁振动问题时,会出现频率精度掉阶现象.本文首先从保障质量矩阵最优收敛性的数值积分精度出发,分别针对三次和五次梁单元,发展了质量矩阵的梯度增强节点积分方案.利用梯度增强节点积分方案,可以得到具有分块对角形式的单元质量矩阵,而其组装的整体质量矩阵除边界节点外仍然呈现对角形式.对于两种单元,其分块对角质量矩阵分别具有4阶最优精度和6阶次优精度.再者,将标准一致质量矩阵和具有同阶精度的梯度增强节点积分质量矩阵进行优化组合,建立了具有超收敛特性的高阶质量矩阵.最后,通过数值算例系统验证了三次和五次单元的分块对角与高阶质量矩阵的频率计算精度.

协方差驱动随机子空间辨识的参数敏感性分析

协方差驱动随机子空间辨识(Covariance-driven Stochastic Subspace Identification,SSI-cov)是近年来发展较为成熟的工作模态分析方法。针对其识别精度和效率对参数设置具有较高敏感性的问题,基于敏感性分析方法,利用奇异熵增量跳跃点明显程度、频率平均识别误差、阻尼比总变异系数、振型平均模态置信因子、运行时间5种评价指标以及稳定图,通过一经典五自由度层模型仿真算例,研究Toeplitz矩阵行块数、采样频率、数据长度对SSI-cov识别结果的影响规律。并给出既能满足精度要求又可控制程序运行时间的参数建议取值范围。最后,通过一缩尺三层框架模型在白噪声激励下实测数据对提出的根据SSI-cov改进参数设置进行验证,结果表明提出的各参数建议取值范围均较为合理。

远距离风电分频送出方式及大功率变频装置的研发

分频输电作为一种新型输电方式,在风电远距离送出场景下极具优势。为了给远距离风电经分频输电系统送出场景下的关键变频设备——模块化多电平矩阵式换流器(modular multilevel matrix converter,M3C)在工程上的实机研制与生产运行提供参考,首先介绍了分频输电的特性、风电经分频输电送出的系统方案与拓扑以及分频输电系统的关键变频设备。在此基础上,研制了分频输电系统中工/分频能量变换的关键设备——35 kV/3 MVA M3C变频器,并进行了性能试验。试验结果表明:分频变频器工程样机满载情况下的效率、模块电压不均衡度、电压/电流谐波畸变率、分频侧频率调节偏差以及功率阶跃响应时间等关键性能指标均符合设计要求。最后对分频输电系统的发展前景以及效益进行了分析,同时也指出了目前分频输电系统发展所面临的技术挑战。