scholarly journals Recovering Geometric Information with Learned Texture Perturbations

2021 ◽  
Vol 4 (3) ◽  
pp. 1-18
Author(s):  
Jane Wu ◽  
Yongxu Jin ◽  
Zhenglin Geng ◽  
Hui Zhou ◽  
Ronald Fedkiw
Keyword(s):  
Neural Network ◽  
High Frequency ◽  
Low Frequency ◽  
Level Of Detail ◽  
Training Data ◽  
General Strategy ◽  
Frequency Data ◽  
Geometric Information ◽  
Multiple Camera ◽  
Frequency Information

Regularization is used to avoid overfitting when training a neural network; unfortunately, this reduces the attainable level of detail hindering the ability to capture high-frequency information present in the training data. Even though various approaches may be used to re-introduce high-frequency detail, it typically does not match the training data and is often not time coherent. In the case of network inferred cloth, these sentiments manifest themselves via either a lack of detailed wrinkles or unnaturally appearing and/or time incoherent surrogate wrinkles. Thus, we propose a general strategy whereby high-frequency information is procedurally embedded into low-frequency data so that when the latter is smeared out by the network the former still retains its high-frequency detail. We illustrate this approach by learning texture coordinates which when smeared do not in turn smear out the high-frequency detail in the texture itself but merely smoothly distort it. Notably, we prescribe perturbed texture coordinates that are subsequently used to correct the over-smoothed appearance of inferred cloth, and correcting the appearance from multiple camera views naturally recovers lost geometric information.

scholarly journals A Novel Approach for Transmission Line Protection Using Wavelet Transform and Neural Network

2011 ◽  
pp. 121-126
Author(s):  
Mrunalini M. Rao ◽  
P.M. Deoghare
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Transmission Line ◽  
High Frequency ◽  
Low Frequency ◽  
Line Length ◽  
Frequency Information ◽  
Protection Scheme ◽  
Frequency Components ◽  
Transmission Line Protection

The two most important expected objectives of the transmission line protection are – 1) Differentiating the internal faults from external faults and 2) identifying exactly the fault type using one end data only. In conventional distance protection scheme only 80 percent of line length gets primary protection while for remaining 20 percent of line length a time delay is provided to avoid maloperation due to overreach in case of D.C. offset. In this new scheme a fault generated transients based protection method is introduced by which the whole line length gets primary protection by using the concept of bus capacitance. This scheme implements improved solution based on wavelet transform and self-organized neural network. The measured current and voltage signals are preprocessed first and then decomposed using wavelet multiresolution analysis to obtain the high frequency and low frequency information. The training patterns are formed based on high frequency signal components and the low frequency components of all three phase voltages and current. Zero sequence voltage and current are also used to identify faults involving grounds. The input sets formed based on the high frequency components are arranged as inputs of neural network-1, whose task is to indicate whether the fault is internal or external. The input sets formed based on the low frequency components are arranged as inputs of neural network- 2, whose task is indicate the type of fault. The new method uses both low and high frequency information of the fault signal to achieve an advanced transmission line protection scheme.

Research on Improvement Algorithm of Image Edge Detection

2014 ◽  
Vol 539 ◽  
pp. 141-145
Author(s):  
Shui Li Zhang
Keyword(s):  
Cognitive Psychology ◽  
Edge Detection ◽  
High Frequency ◽  
Detection Method ◽  
Low Frequency ◽  
Frequency Information ◽  
Image Edge Detection ◽  
Improvement Algorithm ◽  
Image Edge ◽  
Edge Detection Method

This paper presents new theorems Stevens edge detection method based on cognitive psychology on. Firstly, based on the number of the image is decomposed into high-frequency and low-frequency information, and the high-frequency information extracted by subtracting the maximum number of images to the image after the filter, then the amount of high frequency information into psychological cognitive psychology based on Stevenss theorem. The algorithm suppression refined edge after the non-minimum, applications Pillar K-means algorithm to extract image edge. Experimental results show that: the brightness of the image is converted to the amount of psychological edge can better unify under different brightness values.

Denoising for full-waveform inversion with expanded prediction-error filters

Geophysics ◽  
2021 ◽  
pp. 1-54
Author(s):  
Milad Bader ◽  
Robert G. Clapp ◽  
Biondo Biondi
Keyword(s):  
High Frequency ◽  
Prediction Error ◽  
Signal To Noise Ratio ◽  
Waveform Inversion ◽  
Low Frequency ◽  
Full Waveform Inversion ◽  
Frequency Data ◽  
Signal To Noise ◽  
Frequency Signal ◽  
Full Waveform

Low-frequency data below 5 Hz are essential to the convergence of full-waveform inversion towards a useful solution. They help build the velocity model low wavenumbers and reduce the risk of cycle-skipping. In marine environments, low-frequency data are characterized by a low signal-to-noise ratio and can lead to erroneous models when inverted, especially if the noise contains coherent components. Often field data are high-pass filtered before any processing step, sacrificing weak but essential signal for full-waveform inversion. We propose to denoise the low-frequency data using prediction-error filters that we estimate from a high-frequency component with a high signal-to-noise ratio. The constructed filter captures the multi-dimensional spectrum of the high-frequency signal. We expand the filter's axes in the time-space domain to compress its spectrum towards the low frequencies and wavenumbers. The expanded filter becomes a predictor of the target low-frequency signal, and we incorporate it in a minimization scheme to attenuate noise. To account for data non-stationarity while retaining the simplicity of stationary filters, we divide the data into non-overlapping patches and linearly interpolate stationary filters at each data sample. We apply our method to synthetic stationary and non-stationary data, and we show it improves the full-waveform inversion results initialized at 2.5 Hz using the Marmousi model. We also demonstrate that the denoising attenuates non-stationary shear energy recorded by the vertical component of ocean-bottom nodes.

Acquisition/Processing: Machine learning-based deblending: Dispersed source array data example

2021 ◽  
Vol 40 (10) ◽  
pp. 759-767
Author(s):  
Rolf H. Baardman ◽  
Rob F. Hegge
Keyword(s):  
Machine Learning ◽  
High Frequency ◽  
Low Frequency ◽  
Seismic Interpretation ◽  
Salt Dome ◽  
Training Data ◽  
Array Data ◽  
Seismic Processing ◽  
Processing Machine ◽  
Source Array

Machine learning (ML) has proven its value in the seismic industry with successful implementations in areas of seismic interpretation such as fault and salt dome detection and velocity picking. The field of seismic processing research also is shifting toward ML applications in areas such as tomography, demultiple, and interpolation. Here, a supervised ML deblending algorithm is illustrated on a dispersed source array (DSA) data example in which both high- and low-frequency vibrators were deployed simultaneously. Training data pairs of blended and corresponding unblended data were constructed from conventional (unblended) data from another survey. From this training data, the method can automatically learn a deblending operator that is used to deblend for both the low- and the high-frequency vibrators of the DSA data. The results obtained on the DSA data are encouraging and show that the ML deblending method can offer a good performing, less user-intensive alternative to existing deblending methods.

scholarly journals Driving Simulators for Human Vehicle Interaction Design

2015 ◽  
Vol 1 (1) ◽  
pp. 297-306
Author(s):  
Alexandra Tucă ◽  
Valerian Croitorescu ◽  
Mircea Oprean ◽  
Thomas Brandemeir
Keyword(s):  
Real World ◽  
Input Signal ◽  
Interaction Design ◽  
High Frequency ◽  
Driver Behavior ◽  
Low Frequency ◽  
Driving Simulators ◽  
Sensory Inputs ◽  
Frequency Information ◽  
Busy Road

AbstractThe interaction human-vehicle, as well as driver’s behavior are subject long debated in the automotive engineering domain. Driving simulators have an extraordinary important role allowing research that would not be possible to study in real world scenarios.A driver uses his sensory inputs to obtain the required input to base his decision on. The bandwidth of the required input signal should be in accordance to the driver’s task. For simple tasks, like turning on the screen wipers or direction indicator, low frequency information is sufficient. High frequency information is required when cornering on a busy road or when driving in relatively limit situations.The optimal configuration of each sub-system remains a significant cause for debate and still poses a major challenge when considering the ability of simulators to extract realistic driver behavior. If a difference is observed between real and virtual conditions, the factors specifically cause these differences are very difficult to be explained.

scholarly journals Postoperative seizure outcome-guided machine learning for interictal electrocorticography in neocortical epilepsy

2018 ◽  
Vol 119 (6) ◽  
pp. 2265-2275 ◽  
Author(s):  
Seong-Cheol Park ◽  
Chun Kee Chung
Keyword(s):  
Machine Learning ◽  
Free Group ◽  
High Frequency ◽  
Low Frequency ◽  
Outcome Data ◽  
Training Data ◽  
Seizure Outcome ◽  
Data Set ◽  
Neocortical Epilepsy ◽  
Postoperative Seizure

The objective of this study was to introduce a new machine learning guided by outcome of resective epilepsy surgery defined as the presence/absence of seizures to improve data mining for interictal pathological activities in neocortical epilepsy. Electrocorticographies for 39 patients with medically intractable neocortical epilepsy were analyzed. We separately analyzed 38 frequencies from 0.9 to 800 Hz including both high-frequency activities and low-frequency activities to select bands related to seizure outcome. An automatic detector using amplitude-duration-number thresholds was used. Interictal electrocorticography data sets of 8 min for each patient were selected. In the first training data set of 20 patients, the automatic detector was optimized to best differentiate the seizure-free group from not-seizure-free-group based on ranks of resection percentages of activities detected using a genetic algorithm. The optimization was validated in a different data set of 19 patients. There were 16 (41%) seizure-free patients. The mean follow-up duration was 21 ± 11 mo (range, 13–44 mo). After validation, frequencies significantly related to seizure outcome were 5.8, 8.4–25, 30, 36, 52, and 75 among low-frequency activities and 108 and 800 Hz among high-frequency activities. Resection for 5.8, 8.4–25, 108, and 800 Hz activities consistently improved seizure outcome. Resection effects of 17–36, 52, and 75 Hz activities on seizure outcome were variable according to thresholds. We developed and validated an automated detector for monitoring interictal pathological and inhibitory/physiological activities in neocortical epilepsy using a data-driven approach through outcome-guided machine learning. NEW & NOTEWORTHY Outcome-guided machine learning based on seizure outcome was used to improve detections for interictal electrocorticographic low- and high-frequency activities. This method resulted in better separation of seizure outcome groups than others reported in the literature. The automatic detector can be trained without human intervention and no prior information. It is based only on objective seizure outcome data without relying on an expert’s manual annotations. Using the method, we could find and characterize pathological and inhibitory activities.

Multisource Image Fusion Based on DWT and Simplified Pulse Coupled Neural Network

2013 ◽  
Vol 457-458 ◽  
pp. 736-740 ◽  
Author(s):  
Nian Yi Wang ◽  
Wei Lan Wang ◽  
Xiao Ran Guo
Keyword(s):  
Neural Network ◽  
Image Fusion ◽  
High Frequency ◽  
Low Frequency ◽  
Discrete Wavelet ◽  
Cortical Model ◽  
Fusion Algorithm ◽  
Global Coupling ◽  
Maximum Selection ◽  
Pulse Synchronization

In this paper, a new image fusion algorithm based on discrete wavelet transform (DWT) and spiking cortical model (SCM) is proposed. The multiscale decomposition and multi-resolution representation characteristics of DWT are associated with global coupling and pulse synchronization features of SCM. Two different fusion rules are used to fuse the low and high frequency sub-bands respectively. Maximum selection rule (MSR) is used to fuse low frequency coefficients. As to high frequency subband coefficients, spatial frequency (SF) is calculated and then imputed into SCM to motivate neural network. Experimental results demonstrate the effectiveness of the proposed fusion method.

Sign in / Sign up

Export Citation Format

Share Document