Imbalanced data classification is an inevitable problem in medical intelligent diagnosis. Most of real-world biomedical datasets are usually along with limited samples and high-dimensional feature. This seriously affects the classification performance of the model and causes erroneous guidance for the diagnosis of diseases. Exploring an effective classification method for imbalanced and limited biomedical dataset is a challenging task. In this paper, we propose a novel multilayer extreme learning machine (ELM) classification model combined with dynamic generative adversarial net (GAN) to tackle limited and imbalanced biomedical data. Firstly, principal component analysis is utilized to remove irrelevant and redundant features. Meanwhile, more meaningful pathological features are extracted. After that, dynamic GAN is designed to generate the realistic-looking minority class samples, thereby balancing the class distribution and avoiding overfitting effectively. Finally, a self-adaptive multilayer ELM is proposed to classify the balanced dataset. The analytic expression for the numbers of hidden layer and node is determined by quantitatively establishing the relationship between the change of imbalance ratio and the hyper-parameters of the model. Reducing interactive parameters adjustment makes the classification model more robust. To evaluate the classification performance of the proposed method, numerical experiments are conducted on four real-world biomedical datasets. The proposed method can generate authentic minority class samples and self-adaptively select the optimal parameters of learning model. By comparing with W-ELM, SMOTE-ELM, and H-ELM methods, the quantitative experimental results demonstrate that our method can achieve better classification performance and higher computational efficiency in terms of ROC, AUC, G-mean, and F-measure metrics. Our study provides an effective solution for imbalanced biomedical data classification under the condition of limited samples and high-dimensional feature. The proposed method could offer a theoretical basis for computer-aided diagnosis. It has the potential to be applied in biomedical clinical practice.

The X-ray radiation from computed tomography (CT) brought us the potential risk. Simply decreasing the dose makes the CT images noisy and diagnostic performance compromised. Here, we develop a novel denoising low-dose CT image method. Our framework is based on an improved generative adversarial network coupling with the hybrid loss function, including the adversarial loss, perceptual loss, sharpness loss, and structural similarity loss. Among the loss function terms, perceptual loss and structural similarity loss are made use of to preserve textural details, and sharpness loss can make reconstruction images clear. The adversarial loss can sharp the boundary regions. The results of experiments show the proposed method can effectively remove noise and artifacts better than the state-of-the-art methods in the aspects of the visual effect, the quantitative measurements, and the texture details.

The reliable circulation of automotive supply chain data is crucial for automotive manufacturers and related enterprises as it promotes efficient supply chain operations and enhances their competitiveness and sustainability. However, with the increasing prominence of privacy protection and information security issues, traditional data sharing solutions are no longer able to meet the requirements for highly reliable secure storage and flexible access control. In response to this demand, we propose a secure data storage and access control scheme for the supply chain ecosystem based on the enterprise-level blockchain platform Hyperledger Fabric. The design incorporates a dual-layer attribute-based auditable access control model for access control, with four smart contracts aimed at coordinating and implementing access policies. The experimental results demonstrate that the proposed approach exhibits significant advantages under large-scale data and multi-attribute conditions. It enables fine-grained, dynamic access control under ciphertext and maintains high throughput and security in simulated real-world operational scenarios.

The on-axis two-frequency mutual coherence function (MCF) for beam waves propagating along a horizontal path in strong anisotropic atmospheric turbulence is theoretically formulated by making use of the extended Huygens-Fresnel principle. Based on this formulation, a new closed-form expression for the mean square temporal width of Gaussian-beam-wave pulses passing horizontally through strong anisotropic atmospheric turbulence is developed. With the help of this expression, the increments of mean square temporal pulse width due to strong anisotropic atmospheric turbulence under various conditions are further calculated. Results show that the increment of mean square temporal pulse width due to strong anisotropic atmospheric turbulence is basically proportional to the effective anisotropic factor in most situations of interest, with the possible exception of cases in which both the Fresnel ratio and spectral index become relatively small; increasing the effective anisotropic factor can reduce the number of the said exceptions; the turbulence-induced increment of mean square temporal pulse width enlarges as the spectral index increases with a fixed value of the nondimensional turbulence-strength parameter. It is also illustrated that a significant enlargement in the turbulence-induced increment of mean square temporal pulse width occurs by changing the Fresnel ratio from a large to a tiny value if both the effective anisotropic factor and spectral index are relatively small.

The efficiency of coupling a plane wave into a single-mode fiber can be reduced by both the aperture obstruction of receivers and the turbulence-induced degradation of optical coherence. Using the Gaussian approximation to the mutual coherence function of the incident optical field, we derived an analytical solution for the fiber-coupling efficiency when a plane wave, propagating through atmospheric turbulence, is received by an annular-aperture receiver and coupled into a single-mode fiber. It is a function of the coupling geometry, the aperture-radius-to-coherence-radius ratio (ARCRR), and the aperture-obstruction parameter. It is found by the numerical optimization method that the optimal coupling geometry depends on both the ARCRR and the aperture-obstruction parameter. The results obtained are useful for analyzing and designing a fiber-coupling system influenced by atmospheric turbulence.