Classification of sleep stages is an efficient way of diagnosing sleep problems based on processing the bio-signals (ECG, EEG, EOG, and PPG). The less complex this signal is, the better the detection and processing will be. Feature extraction methods that are done manually are tedious and time-consuming. On the contrary, those features with no hand intervention are called deep features that are usually extracted from images. Analysis of the time-frequency characteristics of non-static bio-signals is of importance since it can provide useful information. The current study aimed to extract the time-frequency image using ECG signal spectrogram as well as the deep features using the convolutional neural network. After extracting the deep features, sleep stages were classified based on deep transfer learning method. Network training was then performed using one of the ECG signals, and testing was done considering the other ECG signal channel. According to the findings, it is possible to detect sleep stages with acceptable accuracy and different amplitudes of signals. Finally, the accuracy and sensitivity values of the sleep stages were measured as 98. 92% and 96. 52%, respectively.

Degradation of rivers and the associated loss of biodiversity reduces ecosystem health and water quality. One of the best practical approaches to understand ecological status of a water body and determine impacts of human activities in reducing water quality is the use of benthic macroinvertebrates as evaluation tools for monitoring their biological integrity and health. The aim of this study was to evaluate the health of Zarin Gol River using signal index. Macroinvertebrate samples were taken using Surber sampler (an area of 900 cm2) with 3 replicates in 4 sampling sites (upstream, entrance of fish farm, forest area) in winter and spring seasons on Zarin Gol River. The total number of abundance of macroinvertebrate were counted 1971 belonging to 8 order, 19 families. The result showed that signal index among all stations are same and lies in quadrant a. but signal 2 score result indicates that station 3 lies in quadrant b. In general, based on the results of the distribution of macroinvertebrates and biotic index, the influence of these factors on Zarin Gol river is quite evidence and the stations that were affected by a variety of effluents (2, 4) had undesirable conditions in the studied river.

Objective: To obtain abnormalities in quantitative Electroencephalography (QEEG) and to observe connectivity between electrodes in children with Asperger disorder.Method: In this study, spectrogram criteria and coherence values are used as a tool for evaluating QEEG in 15 children with Asperger disorder (10 boys and 5 girls aged between 6 to 11 years old) and in 11 control children (7 boys and 4 girls with the same age range).Results: The evaluation of QEEG using statistical analysis and spectrogram criteria demonstrates that the relaxed eye-opened condition in gamma frequency band (34-44Hz) has the best distinction level of 96.2% using spectrogram. The children with Asperger disorder had significant lower spectrogram criteria values (p<0.01) at Fp1 electrode and lower values (p<0.05) at Fp2 and T6 electrodes. Coherence values at 171 pairs of EEG electrodes indicate that the connectivity at (T4, P4), (T4, Cz), (T4, C4) electrode pairs and (T4, O1) had significant differences (p<0.01) in the two groups in the gamma band.Conclusions: It is shown that gamma frequency band can discriminate 96.2% of the two groups using the spectrogram criteria. The results demonstrate that there are more abnormalities in the prefrontal and right temporal lobes using spectrogram criteria and there are more abnormalities in the connectivity of right temporal lobe with the other lobes in the gamma frequency band.

The abstract should include the One of the most exciting topics for researchers over the past few years is detecting underwater acoustic noises. Meanwhile, the complicated nature of the ocean makes this task very challenging. Also, making signals formatted data compatible with machine learning approaches needs much knowledge in signal processing for feature detection. This paper proposed a method to overcome these challenges, which extracts features with Convolutional Neural Network (CNN) and Mel-spectrogram (converting signal data to images). This method needless knowledge in signal processing and more knowledge in machine learning; because using CNNs find the hidden pattern and knowledge of the data automatically. The proposed approach detected the presence of the ships and categorized them into different kinds of them with 99% accuracy that is a noticeable improvement considering state of the art. The performed CNN models consist of 2 CNN layers for feature extraction and a Dense layer for classification the underwater ship noises.

Recently permutation multimedia ciphers were broken in a chosen-plaintext scenario. That attack models a very resourceful adversary which may not always be the case. To show insecurity of these ciphers, we present a cipher-text only attack on speech permutation ciphers. We show inherent redundancies of speech can pave the path for a successful cipher-text only attack. To that end, regularities of speech are extracted in time and frequency using short time Fourier transform. We show that spectrograms of cipher-texts are in fact scrambled puzzles. Then, different techniques including estimation, image processing, and graph theory are fused together in order to create and solve these puzzles. Conducted tests show that the proposed method achieves accuracy of 87: 8% and intelligibility of 92: 9%. These scores are 50: 9% and 34: 6%, respectively, higher than scores of previous method. Finally a novel method, based on moving spectrogram distance, is proposed that can give accurate estimation of segment length of the scrambler system.

Objective: to evaluate the brain signals in children with autism disorder in many different conditions of quantitative Electroencephalography (qEEG) recordings in order to highlight abnormalities and to characterize this group.Method: In this study, spectrogram was used as a tool for evaluating qEEG in 15 children with autism disorders (13 boys and 2 girls aged between 6 to 11 years old) and in 11 normal children (7 boys and 4 girts with the same age range). signals of the two groups were recorded in nine conditions. Results: The recorded signals with the relaxed eye-opened condition in alpha band, those recorded with looking at a stranger's picture condition in beta band, and the ones obtained with children looking at inverted stranger's picture in the same beta band show the best discrimination of 92.3%, 88,9% and 88.9%respectively using spectrogram. Conclusion: Among the several different EEG recordings, the relaxed eye-opened condition in alpha band had been the best condition for discriminating the two groups using spectrogram. More abnormalities were observed in the prefrontal lobe and the left brain hemisphere in children with autism disorders.

Human voice contains characteristics such as: ethnicity, gender, feelings, age and other information, and speaker recognition identifies people based on their voice. Although researchers have worked in this area over the years and provide methods to improve the speaker recognition accuracy, there are still challenges. In this paper, a new speaker recognition method is proposed based on Gabor filter bank and convolutional neural networks. At first, spectrogram of the speech signal is formed and then, effective Gabor filter bank is designed so that these filters are suitable for extracting effective features of the speech signal. In the next step, spectrogram of the signal is passed through the Gabor filter bank to extract the speech signal features. Finally, speaker recognition is done using a convolutional neural network. Two datasets Aurora2 and TIMIT are used to evaluate the proposed method. Results show that the accuracy of the proposed method is competitive with the state-of-the-art methods.

Time representation was the first way to describe a signal, and later on the frequency representation was introduced as another important way to describe a signal for its physical significance. Due to the non-stationary property of seismic data, time-frequency transform has to be used to analyze it. During the last decade, spectral decomposition techniques have proven to be an excellent tool to describe thin beds associated with channel sands, alluvial fans, and the like. However, with the traditional spectral decomposition method based on the short time Fourier Transform, it is difficult to acquire the accurate time-frequency spectrum for non-stationary seismic signals. Recently, the emergence of seismic attribute co-rendering, principal component analysis, cluster analysis, and neural networks has partially solved the problem, but the extraction of spectral attributes from spectral-decomposition tightly linked to the geology has more advantages over other approaches. Popular time–frequency methods have some disadvantages.A good time resolution requires a short window and a good frequency resolution require a narrow-band filter, i.e. a long window, but unfortunately, these two cannot be simultaneously realized. The Wigner-Ville Distribution (WVD) of a signal is the Fourier Transform of the signal’s time-dependent auto-correlation function, a quadratic expression which is bilinear in the signal. As a result, the cross-terms appear in the locations of the resulting time-frequency spectra that either interfere with the interpretation of auto-terms or for which we can provide no physical interpretation. Due to the existence of cross-terms, WVD is not often used. Reduction of the cross-terms is achieved by manipulating the ambiguity function as a mask that reduces the cross-terms while preserving the time and frequency resolution of WVD.The short-time Fourier Transform (STFT) spectrogram, which is the squared modulus of the STFT, is a smoothed version of WVD. An STFT spectrogram is a 2-D convolution of the signal WVD and the utilized window function. In this paper, we introduce a Deconvolutive Short-Time Fourier Transform (DSTFT) spectrogram method, which improves the time-frequency resolution and reduces the cross-terms simultaneously by applying a 2-D deconvolution operation on the STFT spectrogram. Compared to the STFT spectrogram, the spectrogram obtained by this method shows a significant improvement in the time-frequency resolution. In this study, we extract two attributes namely the peak frequency and the peak amplitude, based on the Deconvolutive Short-Time Fourier Transform. The maximum frequency attribute is directly related to the thickness of the thin-bed, like channel, and the maximum amplitude attribute also responds to the thin-bed.We use instantaneous seismic attributes: maximum instantaneous frequencies and their associated amplitudes, as a tool to detect seismic geomorphologic bodies and to identify thin layers. Then we use attributes extracted by Deconvolutive Short Time Fourier Transform to detect the burial channel in both synthetic and real 3D seismic data. Usually, the center of the channel is recognized by the lower maximum frequency and when the thickness of the channel gets thinner away from the center of the channel, the maximum frequency increases correspondingly. Therefore, this attribute could clearly describe the distribution of channel both vertically and horizontally. Results of this study on the synthetic and real seismic data examples illustrate the good performance of the DSTFT spectrogram compared with other traditional time-frequency representations.

Automatic Speaker Verification (ASV) systems have proven to bevulnerable to various types of presentation attacks, among whichLogical Access attacks are manufactured using voiceconversion and text-to-speech methods. In recent years, there has beenloads of work concentrating on synthetic speech detection, and with the arrival of deep learning-based methods and their success in various computer science fields, they have been a prevailing tool for this very task too. Most of the deep neural network-based techniques forsynthetic speech detection have employed the acoustic features basedon Short-Term Fourier Transform (STFT), which are extracted from theraw audio signal. However, lately, it has been discovered that the usageof Constant Q Transform's (CQT) spectrogram can be a beneficialasset both for performance improvement and processing power andtime reduction of a deep learning-based synthetic speech detection. In this work, we compare the usage of the CQT spectrogram and some most utilized STFT-based acoustic features. As lateral objectives, we consider improving the model's performance as much as we can using methods such as self-attention and one-class learning. Also, short-duration synthetic speech detection has been one of the lateral goals too. Finally, we see that the CQT spectrogram-based model not only outperforms the STFT-based acoustic feature extraction methods but also reduces the processing time and resources for detecting genuine speech from fake. Also, the CQT spectrogram-based model places wellamong the best works done on the LA subset of the ASVspoof 2019 dataset, especially in terms of Equal Error Rate.