Publications
Semblance or slowness time coherence (STC) is the main tool for estimating the interval times (velocities) of the wave packet components when using multielement acoustic logging. The idea of semblance in the (τ-p)-domain is that visualization of matrices of its values assumes spots of bursts of coherent energy of a finite number of constituent waves (P, S, St, casing, and collar) located in the vicinity of the tool line. The semblance analysis can be complicated for several reasons. The first is the need to select the value of the mandatory time window (half-window) of averaging, which, in fact, coarsens the distribution of coherent energy. The identification and localization of the spots of the semblance image can be hampered by interference and quantization noise (time step and distance between receivers). Also, in standard processing, it is not always possible to perform a clear tracing of the interval timelines for the components of the waves in depth. Here, we present two new semblance matrices filtering methods that partially address some of the disadvantages of traditional semblance.
Nine machine learning methods (ANN, ANFIS, ELM, FM, SVM, GPR, RF, RT, k-NN) are compared using the example of predicting acoustic logging data. With machine learning, the solution to the regression problem can be used not only for predicting geophysical fields, but also for filing in missing data. The constructed curve T(Р) of the P-wave interval time can be considered as a forecasted result, if acoustic logging is expected later; if additional acoustic logging is not possible, then the synthetic curve T(Р) replaces the log-derived one for further interpretation. The RF method is shown to provide the best test results.
The Alford method is a modern tool for estimating anisotropy from cross-dipole acoustic logging records. The azimuthal angle of the acoustic anisotropy direction is estimated by the minimum cross energy of the converted records. The interval times (speeds) of the fast and slow bending wave pfast, pslow in the forward and reverse directions of anisotropy are estimated using the corresponding transfor-mations. Practical implementation of the method is considered, using the analytical solution of the min-imization problem.
The problem regarding the use of machine learning in cybersecurity is difficult to solve because the advances in the field offer many opportunities that it is challenging to find exceptional and beneficial use cases for implementation and decision making. Moreover, such technologies can be used by intruders to attack computer systems. The goal of this paper to explore machine learning usage in cybersecurity and cyberattack and provide a model of machine learning-powered attack.
Semblance or slowness time coherence is a measure of the coherence of energy distribution be-tween recorded signals at antenna array receivers of acoustic wave logging probe in the coordinates "the reduced time of the wave path from the middle of the antenna array” — “interval time". Several semblance filtering methods are proposed to allow for elimination of the effect of aliasing and to separate the wave packet components.