Artificial Intelligence-based quantitative evaluation of retinal vascular parameters in thyroid-associated ophthalmopathy.

Purpose: Thyroid-associated ophthalmopathy (TAO) may result in increased metabolism and abnormalities in microcirculation. The fractal dimension (Df) of retinal vessels has been shown to be related to the pathology of a number of ophthalmic disorders, but it hasn't been investigated in TAO.

Methods: We analyzed 1078 participants aged 18 to 72 (548 healthy volunteers and 530 TAO).

A health status estimation method based on interpretable neural network observer for HVs.

Estimating the health status is a crucial step in learning about the health of hypersonic vehicles beforehand. The estimation results can be used to detect abnormal states and provide data reference for fault diagnosis. However, certain conventional neural network-based estimate techniques rely heavily on data and have limited model interpretability, which challenges the accuracy of the estimation results.

Periodic analysis on gas path fault diagnosis of gas turbines.

The gas path fault diagnosis is considered widely to ensure the economy, safety and practicability of gas turbines. Traditional gas path diagnosis methods are vulnerable to various uncertainties, resulting in a deviation between the diagnostic results and the real states, which brings huge potential safety hazard to industrial production. Periodic analysis can suppress the uncertainty interference and extract accurately the features of performance parameters to improve the accuracy of health evaluation.

Adaptive stochastic resonance in bistable system driven by noisy NLFM signal: phenomenon and application.

The stochastic resonance (SR) in a bistable system driven by nonlinear frequency modulation (NLFM) signal and strong noise is studied. Combined with empirical mode decomposition (EMD) and piecewise idea, an adaptive piecewise re-scaled SR method based on the optimal intrinsic mode function (IMF), is proposed to enhance the weak NLFM signal. At first, considering the advantages of EMD for dealing with non-stationary signals, the segmented NLFM signal is processed by EMD.

Robust Building Extraction for High Spatial Resolution Remote Sensing Images with Self-Attention Network.

Building extraction from high spatial resolution remote sensing images is a hot spot in the field of remote sensing applications and computer vision. This paper presents a semantic segmentation model, which is a supervised method, named Pyramid Self-Attention Network (PISANet). Its structure is simple, because it contains only two parts: one is the backbone of the network, which is used to learn the local features (short distance context information around the pixel) of buildings from the image; the other part is the pyramid self-attention module, which is used to obtain the global features (long distance context information with other pixels in the image) and the comprehensive features (includes color, texture, geometric and high-level semantic feature) of the building.