A Novel Method of Temporomandibular Joint Hypermobility Diagnosis Based on Signal Analysis

Despite the temporomandibular joint (TMJ) being a well-known anatomical structure its diagnosis may become difficult because physiological sounds accompanying joint movement can falsely indicate pathological symptoms. One example of such a situation is temporomandibular joint hypermobility (TMJH), which still requires comprehensive study. The commonly used official research diagnostic criteria for temporomandibular disorders (RDC/TMD) does not support the recognition of TMJH. Therefore, in this paper the authors propose a novel diagnostic method of TMJH based on the digital time–frequency analysis of sounds generated by TMJ. Forty-seven volunteers were diagnosed using the RDC/TMD questionnaire and auscultated with the Littmann 3200 electronic stethoscope on both sides of the head simultaneously. Recorded TMJ sounds were transferred to the computer via Bluetooth® for numerical analysis. The representation of the signals in the time–frequency domain was computed with the use of the Python Numpy and Matplotlib libraries and short-time Fourier transform. The research reveals characteristic time–frequency features in acoustic signals which can be used to detect TMJH. It is also proved that TMJH is a rare disorder; however, its prevalence at the level of around 4% is still significant.

Download Full-text

Temporomandibular Joint Hypermobility - Diagnosis Based on Auscultation and Signals Analysis

10.21203/rs.3.rs-41127/v1 ◽

2020 ◽

Author(s):

Justyna Agnieszka Lemejda ◽

Marcin Kajor ◽

Dominik Grochala ◽

Marek Iwaniec ◽

Joanna Iwaniec ◽

...

Keyword(s):

Temporomandibular Joint ◽

Myofascial Pain ◽

Good Clinical Practice ◽

Joint Hypermobility ◽

Joint Movement ◽

Second Person ◽

Electronic Stethoscope ◽

Time Frequency ◽

First Case ◽

Frequency Features

Abstract BackgroundThe temporomandibular joint is a well-known anatomical structure a vast majority of dentists doesn’t know how to treat patients with temporomandibular disorders. What is more, even physiological sounds accompanying joint movement can deceitfully indicate pathological features. An example of TMD is temporomandibular joint hypermobility, a disorder which still requires comprehensive study and analysis.MethodsForty seven volunteers were diagnosed with the RDC/TMD questionnaire and auscultated with electronic stethoscope Littmann 3200 on both sides simultaneously. Recorded TMJ sounds were sent to the computer via Bluetooth for further numerical analysis.ResultsTwo patients with TMJH were diagnosed. In the first case the RDC/TMD based diagnosis were discovered as Ia (myofascial pain) and IIIa (arthralgia). The second person was diagnosed with no disorder according to RDC/TMD questionnaire. However the RDC/TMD examination does not support recognition of TMJH. Therefore in this paper it was proved that such recognition can be performed based on the digital time-frequency analysis of the TMJ sound.ConclusionsTMJH is rare case, at ours research 4% patients. The recognition of dysfunction can be based on the characteristic time-frequency features presented in the spectrogram representation of TMJ sound.Trial registrationThe Jagiellonian University Bioethics Committee gave consent for examination, number 1072.6120.71.2019 from the 24th of April 2019 year. All participants were informed about the objectives of the study. Each of them expressed their written consent to participate in the examination and signed the consent form before the study. During the procedures, the rules of Good Clinical Practice were applied and the Helsinki Declaration was followed.

Download Full-text

Variable Speed Estimation for Wheel-Bearings with STFT and BP Neural Network

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.945-949.1112 ◽

2014 ◽

Vol 945-949 ◽

pp. 1112-1115

Author(s):

Yuan Zhou ◽

Bin Chen ◽

Bao Cheng Gao ◽

Si Jie Zhang

Keyword(s):

Neural Network ◽

Bp Neural Network ◽

Background Noise ◽

Speed Estimation ◽

Variable Speed ◽

Short Time Fourier Transform ◽

Time Frequency ◽

Novel Method ◽

Instantaneous Frequencies ◽

Short Time

For the variable speed estimation of wheel-bearings in strong background noise, a novel method with the short-time Fourier transform and BP neural network (STFT-BPNN) is proposed. In the method, it calculates the time-frequency spectrum with STFT technique. Then the instantaneous frequency is estimated by peak detection. Taking the instantaneous frequencies as the input vectors, the BP neural network is trained to fit the discrete instantaneous frequencies. The effectiveness of proposed method is demonstrated by simulation. Experimental results show that proposed method provides better performance on variable speed estimation for wheel-bearings.

Download Full-text

Multiclass Radio Frequency Interference Detection and Suppression for SAR Based on the Single Shot MultiBox Detector

Sensors ◽

10.3390/s18114034 ◽

2018 ◽

Vol 18 (11) ◽

pp. 4034 ◽

Cited By ~ 7

Author(s):

Junfei Yu ◽

Jingwen Li ◽

Bing Sun ◽

Jie Chen ◽

Chunsheng Li

Keyword(s):

Radio Frequency ◽

Pulse Compression ◽

Radio Frequency Interference ◽

Single Shot ◽

Separation Problem ◽

Underdetermined Blind Source Separation ◽

Time Frequency ◽

Interference Signals ◽

Novel Method ◽

Short Time

Radio frequency interference (RFI) is known to jam synthetic aperture radar (SAR) measurements, severely degrading the SAR imaging quality. The suppression of RFI in SAR echo signals is usually an underdetermined blind source separation problem. In this paper, we propose a novel method for multiclass RFI detection and suppression based on the single shot multibox detector (SSD). First, an echo-interference dataset is established by randomly combining the target signal with various types of RFI in a simulation, and the time–frequency form of the dataset is obtained by utilizing the short-time Fourier transform (STFT). Next, the time–frequency dataset acts as input data to train the SSD and obtain a network that is capable of detecting, identifying and estimating the interference. Finally, all of the interference signals are exactly reconstructed based on the prediction results of the SSD and mitigated by an adaptive filter. The proposed method can effectively increase the signal-to-interference-noise ratio (SINR) of RFI-contaminated SAR echoes and improve the peak sidelobe ratio (PSLR) after pulse compression. The simulated experimental results validate the effectiveness of the proposed method.

Download Full-text

The Gearbox Fault Detection of Machine Center by Using Time Frequency Order Spectrum

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.452-453.1329 ◽

2012 ◽

Vol 452-453 ◽

pp. 1329-1333 ◽

Cited By ~ 1

Author(s):

C.C. Wang ◽

Y. Kang ◽

Y.L. Chung

Keyword(s):

Fault Detection ◽

Back Propagation ◽

Machine Center ◽

Rotor Systems ◽

Time Frequency ◽

Order Spectrum ◽

Signal Features ◽

Stationary Signals ◽

Short Time ◽

Frequency Features

Previously, for the case of fixed or steady state rotation rate, spectrum analysis can be used to extract the frequency features as the basis for the gearbox fault detection of machine center. However, the gearbox of machine center for increasingly instant speed variations mostly generate non-stationary signals, and the signal features must be averaged with analysis time which makes it difficult to identify the causes of failures. This study proposes a time frequency order spectrum method combining the short-time Fourier transform (STFT) and speed frequency order method to capture the order features of non-stationary signals. Such signal features do not change with speed, and are thus effective in identifying faults in mechanical components under non-stationary conditions. In this study, back propagation neural networks (BPNN) and time frequency order spectrum methods were used to verify faults diagnosis and obtained superior diagnosis results in non-stationary signals of gear-rotor systems in machine center.

Download Full-text

Convolutional Neural Networks based OSA Event Prediction from ECG Scalograms and Spectrograms

10.21203/rs.3.rs-381294/v1 ◽

2021 ◽

Author(s):

Huseyin Nasifoglu ◽

Osman Erogul

Keyword(s):

Time Domain ◽

Continuous Wavelet ◽

Short Time Fourier Transform ◽

Time Frequency ◽

Ecg Signals ◽

Event Prediction ◽

Proposed Model ◽

Obstructive Sleep ◽

Short Time ◽

Frequency Features

Abstract In this study, we conducted a comparative analysis of deep convolutional neural network (CNN) models in predicting Obstructive Sleep Apnea (OSA) using electrocardiograms. Unlike other studies in the literature, this study automatically extracts time-frequency features by using CNNs instead of manual feature extraction from ECG recordings. For this purpose, the proposed model generates scalogram and spectrogram representations by transforming preprocessed 30-sec ECG segments from time domain to the frequency domain using Continuous Wavelet Transform (CWT) and Short Time Fourier transform (STFT), respectively. We examined AlexNet, GoogleNet and ResNet18 models in predicting OSA events. The effect of transfer learning on success is also investigated. Based on the observed results, we proposed a new model that is found more effective in estimation. In total, 152 ECG recordings were included in the study for training and evaluation of the models. The prediction using scalograms immediately 30 seconds before potential OSA onsets gave the best performance with 82.30% accuracy, 83.22% sensitivity, 82.27% specificity and 82.95% positive predictive value. On the other hand, the prediction using spectrograms also provided up to 80.13% accuracy and 81.99% sensitivity on prediction. The results show that the proposed CNN model can be used as a good indicator to accurately predict OSA events using ECG signals.

Download Full-text

Strain Sensitivity Enhancement of Broadband Ultrasonic Signals in Plates Using Spectral Phase Filtering

Applied Sciences ◽

10.3390/app11062582 ◽

2021 ◽

Vol 11 (6) ◽

pp. 2582

Author(s):

Lucas M. Martinho ◽

Alan C. Kubrusly ◽

Nicolás Pérez ◽

Jean Pierre von der Weid

Keyword(s):

Fourier Transform ◽

Guided Waves ◽

Strain Level ◽

Energy Concentration ◽

Short Time Fourier Transform ◽

Time Frequency ◽

Frequency Representation ◽

The Fourier Transform ◽

Short Time ◽

Sensitivity Gain

The focused signal obtained by the time-reversal or the cross-correlation techniques of ultrasonic guided waves in plates changes when the medium is subject to strain, which can be used to monitor the medium strain level. In this paper, the sensitivity to strain of cross-correlated signals is enhanced by a post-processing filtering procedure aiming to preserve only strain-sensitive spectrum components. Two different strategies were adopted, based on the phase of either the Fourier transform or the short-time Fourier transform. Both use prior knowledge of the system impulse response at some strain level. The technique was evaluated in an aluminum plate, effectively providing up to twice higher sensitivity to strain. The sensitivity increase depends on a phase threshold parameter used in the filtering process. Its performance was assessed based on the sensitivity gain, the loss of energy concentration capability, and the value of the foreknown strain. Signals synthesized with the time–frequency representation, through the short-time Fourier transform, provided a better tradeoff between sensitivity gain and loss of energy concentration.

Download Full-text

Deep Learning Approach for Vibration Signals Applications

Sensors ◽

10.3390/s21113929 ◽

2021 ◽

Vol 21 (11) ◽

pp. 3929

Author(s):

Han-Yun Chen ◽

Ching-Hung Lee

Keyword(s):

Surface Roughness ◽

Tool Wear ◽

Parameters Optimization ◽

Frequency Spectra ◽

Vibration Signals ◽

Bearing Faults ◽

Time Frequency ◽

And Performance ◽

The One ◽

Short Time

This study discusses convolutional neural networks (CNNs) for vibration signals analysis, including applications in machining surface roughness estimation, bearing faults diagnosis, and tool wear detection. The one-dimensional CNNs (1DCNN) and two-dimensional CNNs (2DCNN) are applied for regression and classification applications using different types of inputs, e.g., raw signals, and time-frequency spectra images by short time Fourier transform. In the application of regression and the estimation of machining surface roughness, the 1DCNN is utilized and the corresponding CNN structure (hyper parameters) optimization is proposed by using uniform experimental design (UED), neural network, multiple regression, and particle swarm optimization. It demonstrates the effectiveness of the proposed approach to obtain a structure with better performance. In applications of classification, bearing faults and tool wear classification are carried out by vibration signals analysis and CNN. Finally, the experimental results are shown to demonstrate the effectiveness and performance of our approach.

Download Full-text

Ultrasonic Assessment of Thickness and Bonding Quality of Coating Layer Based on Short-Time Fourier Transform and Convolutional Neural Networks

Coatings ◽

10.3390/coatings11080909 ◽

2021 ◽

Vol 11 (8) ◽

pp. 909

Author(s):

Azamatjon Kakhramon ugli Malikov ◽

Younho Cho ◽

Young H. Kim ◽

Jeongnam Kim ◽

Junpil Park ◽

...

Keyword(s):

Fourier Transform ◽

Coating Layer ◽

Ultrasonic Pulse ◽

Short Time Fourier Transform ◽

Coating Materials ◽

Time Frequency ◽

High Attenuation ◽

Bonding State ◽

The Time Domain ◽

Short Time

Ultrasonic non-destructive analysis is a promising and effective method for the inspection of protective coating materials. Offshore coating exhibits a high attenuation rate of ultrasonic energy due to the absorption and ultrasonic pulse echo testing becomes difficult due to the small amplitude of the second echo from the back wall of the coating layer. In order to address these problems, an advanced ultrasonic signal analysis has been proposed. An ultrasonic delay line was applied due to the high attenuation of the coating layer. A short-time Fourier transform (STFT) of the waveform was implemented to measure the thickness and state of bonding of coating materials. The thickness of the coating material was estimated by the projection of the STFT into the time-domain. The bonding and debonding of the coating layers were distinguished using the ratio of the STFT magnitude peaks of the two subsequent wave echoes. In addition, the advantage of the STFT-based approach is that it can accurately and quickly estimate the time of flight (TOF) of a signal even at low signal-to-noise ratios. Finally, a convolutional neural network (CNN) was applied to automatically determine the bonding state of the coatings. The time–frequency representation of the waveform was used as the input to the CNN. The experimental results demonstrated that the proposed method automatically determines the bonding state of the coatings with high accuracy. The present approach is more efficient compared to the method of estimating bonding state using attenuation.

Download Full-text

Time–frequency analysis of serum with proton nuclear magnetic resonance for diagnosis of pancreatic cancer

Scientific Reports ◽

10.1038/s41598-020-79087-3 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Asahi Sato ◽

Toshihiko Masui ◽

Akitada Yogo ◽

Takashi Ito ◽

Keiko Hirakawa ◽

...

Keyword(s):

Pancreatic Cancer ◽

Carbohydrate Antigen ◽

Serum Markers ◽

Proton Nuclear Magnetic Resonance ◽

Serum Samples ◽

Time Frequency ◽

H Nmr ◽

Free Induction ◽

Short Time ◽

Long Term Survivors

AbstractAlthough serum markers such as carcinoembryonic antigen (CEA) and carbohydrate antigen (CA19-9) have been widely used in screening for pancreatic cancer (PC), their sensitivity and specificity are unsatisfactory. Recently, a novel tool of analyzing serum using the short-time Fourier transform (STFT) of free induction decays (FIDs) obtained by 1H-NMR has been introduced. We for the first time evaluated the utility of this technology as a diagnostic tool for PC. Serum was obtained from PC patients before starting any treatments. Samples taken from individuals with benign diseases or donors for liver transplantation were obtained as controls. Serum samples from both groups underwent 1H-NMR and STFT of FIDs. STFT data were analyzed by partial least squares discriminant analysis (PLS-DA) to clarify whether differences were apparent between groups. As a result, PLS-DA score plots indicated that STFT of FIDs enabled effective classification of groups with and without PC. Additionally, in a subgroup of PC, long-term survivors (≥ 2 years) could be discriminated from short-term survivors (< 2 years), regardless of pathologic stage or CEA or CA19-9 levels. In conclusion, STFT of FIDs obtained from 1H-NMR have a potential to be a diagnostic and prognostic tool of PC.

Download Full-text

A combined generalized Warblet transform and second order synchroextracting transform for analyzing nonstationary signals of rotating machinery

Scientific Reports ◽

10.1038/s41598-021-96343-2 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Kai Wei ◽

Xuwen Jing ◽

Bingqiang Li ◽

Chao Kang ◽

Zhenhuan Dou ◽

...

Keyword(s):

Vibration Signal ◽

Rotating Machinery ◽

Second Order ◽

Variable Speed ◽

Short Time Fourier Transform ◽

Stationary Characteristic ◽

Nonstationary Signals ◽

Time Frequency ◽

Effective Technology ◽

Short Time

AbstractIn recent years, considerable attention has been paid in time–frequency analysis (TFA) methods, which is an effective technology in processing the vibration signal of rotating machinery. However, TFA techniques are not sufficient to handle signals having a strong non-stationary characteristic. To overcome this drawback, taking short-time Fourier transform as a link, a TFA methods that using the generalized Warblet transform (GWT) in combination with the second order synchroextracting transform (SSET) is proposed in this study. Firstly, based on the GWT and SSET theories, this paper proposes a method combining the two TFA methods to improve the TFA concentration, named GWT–SSET. Secondly, the method is verified numerically with single-component and multi-component signals, respectively. Quantized indicators, Rényi entropy and mean relative error (MRE) are used to analyze the concentration of TFA and accuracy of instantly frequency (IF) estimation, respectively. Finally, the proposed method is applied to analyze nonstationary signals in variable speed. The numerical and experimental results illustrate the effectiveness of the GWT–SSET method.

Download Full-text