scholarly journals Hydro-generators fault diagnosis with short-time-wavelet-entropy and variational auto-encoder

2021 ◽  
Vol 1207 (1) ◽  
pp. 012009
Author(s):  
Ryad Zemouri ◽  
Simon Bernier ◽  
Olivier Kokoko ◽  
Arezki Merkhouf
Keyword(s):  
Health Management ◽  
Flux Measurement ◽  
Discrete Wavelet ◽  
Wavelet Entropy ◽  
Non Invasive ◽  
Latent Space ◽  
Hydroelectric Plants ◽  
Reduced Space ◽  
Industrial Level ◽  
Short Time

Abstract The prognosis and health management (PHM) of hydroelectric plants are full of difficulties caused by the complexity of the hydro-generators where each machine is different and almost unique. At industrial level, several tools are used to monitor the generator condition. Among these tools, the measurement of magnetic stray flux is one which is gaining interest. This measurement is generally based on an inductive sensor and mainly mounted near the stator. The main advantages of the magnetic stray flux are the non-invasive nature and the simplicity of its implementation. In this work, the discrete wavelet transform (DWT) is used to decompose the stray flux signal. Short-Time-Wavelet-Entropy (STWE) is then applied to extract the features from the sub-bands. Finally, a variational auto-encoder (VAE) is used in an unsupervised learning process to structure the STWE signatures of more than 400 stray flux measurement collected on real hydroelectric plants. The obtained results show that the VAE has well captured the features from the wavelet entropy (WE) signatures. An analysis of the resulting latent space shows a strong correlation between a given trajectory in the reduced space and an increase of the WE.

A Harmonic Tracking Technique for Recovery of Gear Motion From Non-Stationary Vibration Signals

1995 ◽  
Author(s):  
Christopher A. Lerch ◽  
Richard H. Lyon
Keyword(s):  
Diagnostic System ◽  
Time Spectrum ◽  
Time Dependent ◽  
Invasive Technique ◽  
Signal Distortion ◽  
Vibration Signals ◽  
Tracking Method ◽  
Non Invasive ◽  
Stationary Vibration ◽  
Short Time

Abstract A method termed harmonic tracking is developed to recover time dependent gear motion from machine casing vibration. The harmonic tracking method uses short-time spectral generation and a subsequent set of algorithms to locate and track gear meshing frequencies as functions of time. The meshing frequencies are then integrated with respect to time to obtain the rotation of individual gears. More specifically, spectral generation is performed using the discrete Fourier transform, and the locating and tracking algorithms involve locating tones in each short-time spectrum and tracking them through successive spectra to recover gear meshing harmonics. The harmonic tracking method is found to be more robust than demodulation-based methods in the presence of measurement noise and signal distortion from the structural transfer function between gears and the casing. The harmonic tracking method is tested, both through simulation and experiments involving motor-operated valves (MOV’s) as part of the development of a diagnostic system for MOV’s. In all cases, the harmonic tracking method is found to recover gear motion with sufficient accuracy to perform diagnostics. The harmonic tracking method should be generally applicable to situations in which a non-invasive technique is required for determining the time-dependent angular speeds and displacements of gearbox input, intermediary, and output shafts.

Classification of Parkinson's Disease from Smartphone Recording Data using Time-Frequency Analysis and Convolutional Neural Network (Preprint)

2021 ◽  
Author(s):  
Denchai Worasawate ◽  
Warisara Asawaponwiput ◽  
Natsue Yoshimura ◽  
Apichart Intarapanich ◽  
Decho Surangsrirat
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Fourier Transform ◽  
Short Time Fourier Transform ◽  
Time Frequency ◽  
Non Invasive ◽  
The Central Nervous System ◽  
Short Time ◽  
The Voice

BACKGROUND Parkinson’s disease (PD) is a long-term neurodegenerative disease of the central nervous system. The current diagnosis is dependent on clinical observation and the abilities and experience of a trained specialist. One of the symptoms that affect most patients over the course of their illness is voice impairment. OBJECTIVE Voice is one of the non-invasive data that can be collected remotely for diagnosis and disease progression monitoring. In this study, we analyzed voice recording data from a smartphone as a possible disease biomarker. The dataset is from one of the largest mobile PD studies, the mPower study. METHODS A total of 29,798 audio clips from 4,051 participants were used for the analysis. The voice recordings were from sustained phonation by the participant saying /aa/ for ten seconds into the iPhone microphone. The audio samples were converted to a spectrogram using a short-time Fourier transform. CNN models were then applied to classify the samples. RESULTS A total of 29,798 audio clips from 4,051 participants were used for the analysis. The voice recordings were from sustained phonation by the participant saying /aa/ for ten seconds into the iPhone microphone. The audio samples were converted to a spectrogram using a short-time Fourier transform. CNN models were then applied to classify the samples. CONCLUSIONS Classification accuracies of the proposed method with LeNet-5, ResNet-50, and VGGNet-16 are 97.7 ± 0.1%, 98.6 ± 0.2%, and 99.3 ± 0.1%, respectively. CLINICALTRIAL ClinicalTrials.gov NCT02696603; https://www.clinicaltrials.gov/ct2/show/NCT02696603

scholarly journals Effects of Olfactory and Auditory Enrichment on the Behaviour of Shelter Dogs

Animals ◽  
2020 ◽  
Vol 10 (4) ◽  
pp. 581 ◽  
Author(s):  
Veronica Amaya ◽  
Mandy B.A. Paterson ◽  
Clive J.C. Phillips
Keyword(s):  
Environmental Enrichment ◽  
Control Group ◽  
Physiological Effects ◽  
Non Invasive ◽  
Human Animal Bond ◽  
Exit Door ◽  
Shelter Dogs ◽  
Human Animal ◽  
Short Time ◽  
Increased Activity

Shelter environments are stressful for dogs, as they must cope with many stimuli over which they have little control. This can lead to behavioural changes, negatively affect their welfare and downgrade the human‐animal bond, affecting re-homing success. Arousal is evident in their behaviour, particularly increased activity and frequent vocalisation. Environmental enrichment plays an important role in reducing arousal behaviour, either through direct physiological effects or by masking stressful stimuli. The present study focused on sensory environmental enrichment, using olfactory and auditory stimuli under shelter conditions. Sixty dogs were allocated to one of four treatments: three types of enrichment, Lavender, Dog appeasing pheromone (DAP) and Music, and a Control group. Stimuli were applied for 3 h/d on five consecutive days. Dogs exposed to DAP lay down more, and those exposed to Music lay down more with their head down, compared to the Control. Those in the Control stood more on their hind legs with their front legs on the exit door, compared to those exposed to Music and DAP, particularly if they had only been in the shelter for a short time. They also panted and vocalised much more than dogs in the three enrichment treatments, which tended to persist during the 4 h period post treatment, and in the case of vocalisation into the subsequent night. The study suggests that all three enrichments had some positive benefits for dogs in shelters, as well as being non-invasive and easy to apply in the shelter environment.

scholarly journals A Non-Invasive Medical Device for Parkinson’s Patients with Episodes of Freezing of Gait

Sensors ◽  
2019 ◽  
Vol 19 (3) ◽  
pp. 737 ◽  
Author(s):  
Catalina Punin ◽  
Boris Barzallo ◽  
Roger Clotet ◽  
Alexander Bermeo ◽  
Marco Bravo ◽  
...  
Keyword(s):  
Wavelet Transform ◽  
Mobile Application ◽  
Low Cost ◽  
Freezing Of Gait ◽  
Discrete Wavelet ◽  
Vibratory Stimulation ◽  
Non Invasive ◽  
Sensitivity Specificity ◽  
Gait Monitoring ◽  
Stimulation Of

A critical symptom of Parkinson’s disease (PD) is the occurrence of Freezing of Gait (FOG), an episodic disorder that causes frequent falls and consequential injuries in PD patients. There are various auditory, visual, tactile, and other types of stimulation interventions that can be used to induce PD patients to escape FOG episodes. In this article, we describe a low cost wearable system for non-invasive gait monitoring and external delivery of superficial vibratory stimulation to the lower extremities triggered by FOG episodes. The intended purpose is to reduce the duration of the FOG episode, thus allowing prompt resumption of gait to prevent major injuries. The system, based on an Android mobile application, uses a tri-axial accelerometer device for gait data acquisition. Gathered data is processed via a discrete wavelet transform-based algorithm that precisely detects FOG episodes in real time. Detection activates external vibratory stimulation of the legs to reduce FOG time. The integration of detection and stimulation in one low cost device is the chief novel contribution of this work. We present analyses of sensitivity, specificity and effectiveness of the proposed system to validate its usefulness.

scholarly journals Efficient Multi-Objective Molecular Optimization in a Continuous Latent Space

2019 ◽  
Author(s):  
Robin Winter ◽  
Floriane Montanari ◽  
Andreas Steffen ◽  
Hans Briem ◽  
Frank Noé ◽  
...  
Keyword(s):  
Objective Function ◽  
In Silico ◽  
Prediction Models ◽  
Chemical Space ◽  
In Silico Prediction ◽  
Swarm Optimization ◽  
Starting Compound ◽  
Latent Space ◽  
Novel Method ◽  
Short Time

In this work, we propose a novel method that combines in silico prediction of molecular properties such as biological activity or pharmacokinetics with an in silico optimization algorithm, namely Particle Swarm Optimization. Our method takes a starting compound as input and proposes new molecules with more desirable (predicted) properties. It navigates a machine-learned continuous representation of a drug-like chemical space guided by a de fined objective function. The objective function combines multiple in silico prediction models, de fined desirability ranges and substructure constraints. We demonstrate that our proposed method is able to consistently fi nd more desirable molecules for the studied tasks in relatively short time.<br>

scholarly journals Biospeckle Optical Coherence Tomography (bOCT) in the Speedy Assessment of the Responses of the Seeds of Raphanus sativus L. (Kaiware Daikon) to Acid Mine Drainage (AMD)

2021 ◽  
Vol 12 (1) ◽  
pp. 355
Author(s):  
Danyang Li ◽  
Uma Maheswari Rajagopalan ◽  
Y. Sanath K. De Silva ◽  
Fenwu Liu ◽  
Hirofumi Kadono
Keyword(s):  
Optical Coherence Tomography ◽  
Acid Mine Drainage ◽  
Mine Drainage ◽  
Mineral Resources ◽  
Vital Role ◽  
Invasive Technique ◽  
Optical Coherence ◽  
Non Invasive ◽  
Acid Mine ◽  
Short Time

The extraction of mineral resources from mines plays a vital role in global socio-economic development. However, acid mine drainage (AMD) has been one of the major pollutants, and a vast area of the agricultural fields has been polluted. Therefore, techniques for monitoring the response of plants to AMD that arise during mineral extraction are necessary. In addition, such a technique becomes especially valuable to understand how the plants could play a role in the phytoremediation of AMD. We propose the use of biospeckle Optical Coherence Tomography (bOCT) to investigate the response of Kaiware daikon seeds under the exposure to simulated AMD at two different concentrations of 40 mL/L and 80 mL/L. OCT images of the Kaiware daikon seed were obtained at a speed of 10 frames per second (1 frame: 512 × 2048 pixels) for a few tens of seconds. For each pixel of the OCT structural images, the contrast across the temporal axis was calculated to give biospeckle contrast OCT images (bOCT images). It was found that bOCT images clearly distinguished the changes due to 40 mL/L and 80 mL/L of AMD treatments from the control within a short time of around an hour, compared to the conventional OCT images that failed to show any changes. This variation was found to be statistically significant and could reflect the internal activity of the seeds. The proposed bOCT method could be a rapid, non-invasive technique for screening suitable plants in AMD phytoremediation applications.

Assessing the archaeological sites’ cultural layer preservation by the methods of multi-zone aerial photography, ground-based sounding and cartography

2020 ◽  
Vol 960 (6) ◽  
pp. 45-55
Author(s):  
I.V. Zhurbin ◽  
A.I. Bazhenova ◽  
V.N. Milich ◽  
A.G. Zlobina
Keyword(s):  
Aerial Photography ◽  
Wavelet Function ◽  
Processing Method ◽  
Archaeological Sites ◽  
Discrete Wavelet ◽  
Cultural Layer ◽  
Multispectral Data ◽  
Cultural Heritage Objects ◽  
Short Time ◽  
Successive Method

Arranging effective state protection of historical and cultural heritage objects requires developing modern methods of identifying archaeological sites and determining their boundaries. To solve this task, an algorithm of interdisciplinary research based on the analysis of multispectral data obtained with unmanned aerial vehicles is proposed. To search for areas of the surface-transformed and substituted cultural layer, it is proposed to use a processing method based on the two-dimensional discrete wavelet transform. Using the Shannon–Kotelnikov wavelet function to study the medieval Kushman settlement of Uchkakar enabled assessing the preservation of the cultural layer in various parts of the settlement. The correctness of the proposed interpretation is confirmed by the data of geophysical studies, soil drilling and materials of archaeological excavations. Complex application of multispectral aerial photography, geophysics and soil investigation made it possible to obtain reliable cartographic information on the boundaries of the archaeological sites and the preservation of their cultural layer in a short time. The effectiveness of the algorithm is that each successive method verifies the previously obtained data and at the same time supplements the information on the archaeological sites.

Abstract 281: Is Cerebral Regional Oxygen Saturation (rSO 2 ) Useful as a Physiological Monitoring Tool During CPR in Pre-Hospital Settings? An Analysis of 72 Cases in Osaka, Japan

Circulation ◽  
2018 ◽  
Vol 138 (Suppl_2) ◽  
Author(s):  
Tomohiko Sakai ◽  
Tadahiko Shiozaki ◽  
Mitsuo Ohnishi ◽  
Ryosuke Takegawa ◽  
Jotaro Tachino ◽  
...  
Keyword(s):  
Oxygen Saturation ◽  
Monitoring System ◽  
Cerebral Perfusion ◽  
Medical Service ◽  
Regional Cerebral Oxygen Saturation ◽  
Monitoring Tool ◽  
Non Invasive ◽  
Short Time

Introduction: Simplified monitoring system of regional cerebral oxygen saturation (rSO 2 ) is a non-invasive technology for cerebral perfusion, but continuous changes of cerebral rSO 2 values among OHCA patients in pre-hospital settings have been insufficiently investigated. Methods: We recently developed a portable rSO 2 monitoring system that is very small (170х100х50mm in size and 600g in weight) and can use in pre-hospital settings. The sensor pad is attached to the patient’s forehead by the emergency-medical-service (EMS) personnel, and it can monitor cerebral rSO 2 immediately and continuously during CPR, from June 2013 through May 2018 in Osaka City, Japan. Results: We collected continuous changes in cerebral rSO 2 values for 72 OHCA patients during CPR by EMS personnel. Sixty-six cases were measured rSO 2 before ROSC and 6 cases were measured after ROSC. According to the analyses of continuous changes in rSO 2 values of 66 cases, two patterns of changes in cerebral rSO 2 values were found as follows; Type 1: Increasing rSO 2 type (n=30). Measured rSO 2 increased gradually during CPR or after ROSC. Type 2: Not increasing rSO 2 type (n=36) Measured rSO 2 did not increase during CPR. And we found out two phenomena of changes in cerebral rSO 2 values were found as follows; Phenomenon 1: Dropping rSO 2 type (n=3). Measured rSO 2 dropped after confirmation of ROSC or before arrest, which suggests that the re-arrest or arrest occurred during monitoring. Phenomenon 2: Initially decreasing rSO 2 type (n=6). Measured rSO 2 decreased gradually despite performing CPR by EMS personnel, which suggests that short time has passed after arrest. Conclusion: We measured continuous changes in cerebral rSO 2 values among 72 patients with OHCA pre-hospital settings and found the 2 patterns and 2-specific phenomena regarding continuous changes in rSO 2 values. Furthermore, it is needed to collect many cases to establish resuscitation strategies for OHCA by using cerebral rSO 2 monitoring.

REDUNDANT MORPHOLOGICAL WAVELET AND LOCAL PATTERN SPECTRUM

2013 ◽  
Vol 11 (04) ◽  
pp. 1360001
Author(s):  
TOMONARI YAMAGUCHI ◽  
MITSUHIKO FUJIO ◽  
KATSUHIRO INOUE
Keyword(s):  
Wavelet Analysis ◽  
Discrete Wavelet ◽  
Short Time Fourier Transform ◽  
Shape Information ◽  
Local Pattern ◽  
Pattern Spectrum ◽  
Time Frequency ◽  
Stationary Signals ◽  
Shift Invariance ◽  
Short Time

Time-frequency analysis methods such as wavelet analysis are applied to investigate characteristic from non-stationary signals. In this study, we proposed redundant morphological wavelet analysis that was a kind of nonlinear discrete wavelet and redundant wavelet. This method analyzes a transition of shape information from signals in detail since this method keeps property of shift invariance though information of decomposition includes redundancy. Local pattern spectrum which corresponds to nonlinear short time Fourier transform is derived from this nonlinear wavelet. The characteristics of these methods were confirmed by applying to simulation data and actual data.

Sign in / Sign up

Export Citation Format

Share Document