Abstract: Certain systems can function well only if they recognize the sound environment as humans do. In this research, we focus on sound classification by adopting a convolutional neural network and aim to develop a method that automatically classifies various environmental sounds. Although the neural network is a powerful technique, the performance depends on the type of input data. Therefore, we propose an approach via a slice bispectrogram, which is a third-order spectrogram and is a slice version of the amplitude for the short-time bispectrum. This paper explains the slice bispectrogram and discusses the effectiveness of the derived method by evaluating the experimental results using the ESC‑50 sound dataset. As a result, the proposed scheme gives high accuracy and stability. Furthermore, some relationship between the accuracy and non-Gaussianity of sound signals was confirmed.
Abstract: In more complex systems, such as automotive
gearbox, a rigorous treatment of the data is necessary because there
are several moving parts (gears, bearings, shafts, etc.), and in this
way, there are several possible sources of errors and also noise. The
basic objective of this work is the detection of damage in automotive
gearbox. The detection methods used are the wavelet method, the
bispectrum; advanced filtering techniques (selective filtering) of
vibrational signals and mathematical morphology. Gearbox vibration
tests were performed (gearboxes in good condition and with defects)
of a production line of a large vehicle assembler. The vibration
signals are obtained using five accelerometers in different positions
of the sample. The results obtained using the kurtosis, bispectrum,
wavelet and mathematical morphology showed that it is possible to
identify the existence of defects in automotive gearboxes.