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.
Abstract: –In this paper the damage in clamped-free, clampedclamped and free-free beam are analyzed considering samples
without and with structural modifications. The damage location is
investigated by the use of the bispectrum and wavelet analysis. The
mathematical models are obtained using 2D elasticity theory and the
Finite Element Method (FEM). The numerical and experimental data
are approximated using the Particle Swarm Optimizer (PSO) method
and this way is possible to adjust the localization and the severity of
the damage. The experimental data are obtained through
accelerometers placed along the sample. The system is excited using
impact hammer.
Abstract: The linear SEF (Spectral Edge Frequency) parameter
and spectrum analysis method can not reflect the non-linear of EEG.
This method can not contribute to acquire real time analysis and obtain
a high confidence in the clinic due to low discrimination. To solve the
problems, the development of a new index is carried out using the
bispectrum analyzing the EEG(electroencephalogram) including the
non-linear characteristic. After analyzing the bispectrum of the 2
dimension, the most significant power spectrum density peaks appeared abundantly at the specific area in awakening and anesthesia state. These points are utilized to create the new index since many
peaks appeared at the specific area in the frequency coordinate. The measured range of an index was 0-100. An index is 20-50 at an anesthesia, while the index is 90-60 at the awake. New index could afford to effectively discriminate the awake and anesthesia state.
Abstract: The measurement of anesthetic depth is necessary in
anesthesiology. NN10 is very simple method among the RR intervals
analysis methods. NN10 parameter means the numbers of above the 10
ms intervals of the normal to normal RR intervals.
Bispectrum analysis is defined as 2D FFT. EEG signal reflected the
non-linear peristalsis phenomena according to the change brain
function. After analyzing the bispectrum of the 2 dimension, the most
significant power spectrum density peaks appeared abundantly at the
specific area in awakening and anesthesia state. These points are
utilized to create the new index since many peaks appeared at the
specific area in the frequency coordinate. The measured range of an
index was 0-100. An index is 20-50 at an anesthesia, while the index is
90-60 at the awake.
In this paper, the relation between NN10 parameter using ECG and
bisepctrum index using EEG is observed to estimate the depth of
anesthesia during anesthesia and then we estimated the utility of the
anesthetic.
Abstract: One of the primary uses of higher order statistics in
signal processing has been for detecting and estimation of non-
Gaussian signals in Gaussian noise of unknown covariance. This is
motivated by the ability of higher order statistics to suppress additive
Gaussian noise. In this paper, several methods to test for non-
Gaussianity of a given process are presented. These methods include
histogram plot, kurtosis test, and hypothesis testing using cumulants
and bispectrum of the available sequence. The hypothesis testing is
performed by constructing a statistic to test whether the bispectrum
of the given signal is non-zero. A zero bispectrum is not a proof of
Gaussianity. Hence, other tests such as the kurtosis test should be
employed. Examples are given to demonstrate the performance of the
presented methods.