This paper presents the evaluation of 36 convolutional neural network (CNN) models, which were trained on the same dataset (ImageNet). The aim of this research was to evaluate the performance of pre-trained models on the binary classification of images in a “real-world” application. The classification of wildlife images was the use case, in particular, those of the Eurasian lynx (lat. “Lynx lynx”), which were collected by camera traps in various locations in Croatia. The collected images varied greatly in terms of image quality, while the dataset itself was highly imbalanced in terms of the percentage of images that depicted lynxes.

Design and measurement results of the signal converter with three-phase and quadrature outputs are presented in this paper. Input to the converter is a sinusoidal reference signal and the outputs are the quadrature and symmetrical three-phase sinusoidal signals of the same frequency as the reference. The output amplitudes are proportional to the reference amplitude. The quadrature output is generated in the novel phase-shift controlled all-pass filter, while the three-phase outputs are generated from the quadrature and reference signals in the electronic implementation of the Scott-T transformer. The converter is of all-analog design and is intended for driving receiver (Rx) type synchros and resolvers during testing and students hands-on laboratory experiments in the frequency range 50 Hz–5 kHz.