The identification of Wiener systems is very difficult because of the output nonlinearity and the parameter product term. To identify the Wiener system, a novel stochastic gradient algorithm based on the multierror and the key term separation is proposed. Firstly, the Wiener system is parameterized as a pseudo-linear model to avoid the products of the parameters. Secondly, a parzen window is used to estimate the probability density function of the error. Thirdly, a stochastic information gradient algorithm with the multierror is adopted to estimate the parameters. The multierror takes the place of the scalar error by the stacked error, which accelerates the algorithm greatly. Fourthly, a variable forgetting factor considering errors is integrated to further speed the algorithm up. Finally, the proposed algorithm is validated by a numerical example and an industrial case. The estimation results indicate that the proposed algorithm can obtain accurate estimates with fast convergence speed.
In this article, a stochastic gradient algorithm based on the minimum Shannon entropy is proposed to identify a type of Hammerstein system with random noise. Firstly, the probability density function is estimated by a parzen window based on the Gaussian kernel. Then, the traditional stochastic gradient algorithm is adopted to estimate the parameters. However, the traditional stochastic gradient algorithm converges quite slowly. To fasten the algorithm, a multierror method is integrated into the algorithm. In this multierror gradient algorithm, the scalar error is replaced by a vector error. This vector error can accelerate the algorithm greatly and give a more accurate estimate by using the same data set. Finally, the proposed algorithm is validated by a numerical example and an industrial process. The estimation results indicate that the proposed algorithm can obtain more accurate estimates than the traditional gradient algorithm and has a faster convergence speed.
ARX model is an autoregressive model with exogenous terms. Because of its simplicity and easy parameterization, the ARX model has been widely used in various applications. However, most reports on ARX identification are about Gaussian noise or white noise environment. In many practical industrial applications, impulse noise widely exists. For systems contaminated by this noise, the performance of the mean square error algorithm will deteriorate. To get more accurate results, a variable step size stochastic information gradient algorithm is proposed. The algorithm is based on the Renyi square error entropy and introduces a fourth-order statistic of the error-kurtosis-into the variable step size, which not only effectively suppresses the impulse noise, but also accelerates the convergence speed. At the same time, a simple method of determining the maximum step size is given. The computational cost and the convergence are also analyzed. Numerical experiments and case study show that for the ARX model disturbed by impulse noise, the proposed algorithm can obtain high-precision parameter estimates with fast convergence speed.
Because of the unstructured characteristics of natural orchards, the efficient detection and segmentation applications of green fruits remain an essential challenge for intelligent agriculture. Therefore, an innovative fruit segmentation method based on deep learning, termed SE-COTR (segmentation based on coordinate transformer), is proposed to achieve accurate and real-time segmentation of green apples. The lightweight network MobileNetV2 is used as the backbone, combined with the constructed coordinate attention-based coordinate transformer module to enhance the focus on effective features. In addition, joint pyramid upsampling module is optimized for integrating multiscale features, making the model suitable for the detection and segmentation of target fruits with different sizes. Finally, in combination with the outputs of the function heads, the dynamic convolution operation is applied to predict the instance mask. In complex orchard environment with variable conditions, SE-COTR achieves a mean average precision of 61.6% with low complexity for green apple fruit segmentation at severe occlusion and different fruit scales. Especially, the segmentation accuracy for small target fruits reaches 43.3%, which is obviously better than other advanced segmentation models and realizes good recognition results. The proposed method effectively solves the problem of low accuracy and overly complex fruit segmentation models with the same color as the background and can be built in portable mobile devices to undertake accurate and efficient agricultural works in complex orchard.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.