Mikhail Ronkin's repositories
dsatools
Digital signal analysis library for python. The library includes such methods of the signal analysis, signal processing and signal parameter estimation as ARMA-based techniques; subspace-based techniques; matrix-pencil-based methods; singular-spectrum analysis (SSA); dynamic-mode decomposition (DMD); empirical mode decomposition; variational mode decomposition (EMD); empirical wavelet transform (EWT); Hilbert vibration decomposition (HVD) and many others.
Passive-Fingerprinting-of-Same-Model-Electrical-Devices-by-Current-Consumption
One of the possible device authentication methods is based on device fingerprints, such as software- or hardware-based unique characteristics. In this paper, we propose a fingerprinting technique based on passive externally measured information, i.e. current consumption from the electrical network. The key insight is that small hardware discrepancies naturally exist even between same-electrical-circuit devices, making it feasible to identify small variations in the consumed current. An experimental database of current consumption signals was collected. The resulting signals we classified within several modern time series classification methods, including \texttt{tsfel}, deep neural network (DNN), ROCKET and empirical wavelet decomposition-based manual feature extraction technique. We have successfully identified 40 similar (same-model) electrical devices with about 94\% precision.
arch_comp_sys
lec, workshops, questions
cd-diagram
Critical difference diagram with Wilcoxon-Holm post-hoc analysis.
Basic_ML_Alg
Supplementary repository for Basic Algorithms of ML in Python
Computer-Vision-Course_lec-practice
Курс Компьютерное зрение (глубокое обучение в компьютерном зрении) для баколавров 09.03.04 Программная инженерия
CvPytorch
CvPytorch is an open source COMPUTER VISION toolbox based on PyTorch.
gost732
Преамбула и другие части LaTeX-документа для соответствия ГОСТ 7.32-2017
stylegan2-pytorch
Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement