Single plane wave (PW) imaging produces ultrasound images of poor quality at high frame rates (ultrafast). High-quality PW imaging usually relies on the coherent compounding of several successive steered emissions (typically more than ten), which in turn results in a decreased frame rate. We propose a new strategy to reduce the number of emitted PWs by learning a compounding operation from data, i.e., by training a convolutional neural network to reconstruct high-quality images using a small number of transmissions. We present experimental evidence that this approach is promising, as we were able to produce high-quality images from only three PWs, competing in terms of contrast ratio and lateral resolution with the standard compounding of 31 PWs ( 10× speedup factor).

Condition monitoring of machines working under non-stationary operations is one of the most challenging problems in maintenance. A wind turbine is an example of such class of machines. One of effective approaches may be to identify operating conditions and investigate their influence on used diagnostic features. Commonly used methods based on measurement of electric current, rotational speed, power and other process variables require additional equipment (sensors, acquisition cards) and software. It is proposed to use advanced signal processing techniques for instantaneous shaft speed recovery from a vibration signal. It may be used instead of extra channels or in parallel as signal verification.

This paper investigates the circularity of Short Time Fourier Transform (STFT) coefficients noise only, and proposes a modified STFT such that all coefficients coming from white Gaussian noise are circular. In order to use the spectral kurtosis (SK) as a Gaussianity test to check if signal points are present in a set of STFT points, we consider the SK of complex circular random variables, and its link with the kurtosis of the real and imaginary parts. We show that the variance of the SK is smaller than the variance of the kurtosis estimated from both real and imaginary parts. The effect of the noncircularity of Gaussian variables upon the spectral kurtosis of STFT coefficients is studied, as well as the effect of signal presence. Finally, a time-frequency segmentation algorithm based on successive iterations of noise variance estimation and timefrequency coefficients detection is proposed. The iterations are stopped when the spectral kurtosis on non-detected points reaches zero. Examples of segmented time-frequency space are presented on a dolphin whistle and on a simulated signal in non-white and non-stationary Gaussian noise.