Questions tagged [signal-processing]
Numerical analysis of a digitized signal
279
questions
2
votes
1answer
45 views
ML model for Signal Decomposition
So recently I got a task which can be summarized as follows:
Suppose we have 3 functions f1, f2, f3 and a certain combination of the functions gives us ...
1
vote
0answers
23 views
How to identify the frequencies of periodic peak signals in a noisy time series? (with R)
Suppose to have two time series with peak signals at different frequencies, like these two:
...
0
votes
1answer
28 views
How should I approach (in Python) to detect the change points in following time-series signal? [closed]
I want to extract different signals present in this image. To do so, I want to find the boundaries of change point at 2.429 GHz, 2.444 GHz, and so on. Note: These numbers are observed visually and ...
0
votes
0answers
14 views
Similarity index between 2 unevenly sampled time series
Say I have 2 time series $s_1$ and $s_2$ with independent variable $x_1$, and dependent value $y$. These 2 series are not evenly sampled across $x_1$, or even sampled at the same rate.
Now, I have ...
0
votes
0answers
25 views
Why do AR(1) times series generated by two methods look similar but have different variance estimate in Python
I come across one question when I use two ways to generate AR(1) sequences.
By definition, AR(1) sequence is
$x_t = \phi_1 x_{t-1} + \varepsilon_t,\quad \varepsilon_t\sim N(0, \sigma^2)$
I found ...
0
votes
0answers
12 views
Representing a time-series smoothed curve as a sinsoidal?
So attaches is an example of the kind of time series data I am working with. So far I have used Gaussian filters with sigma=3 and 6 to smooth the data, which has worked very well (especially sigma=3).
...
0
votes
0answers
8 views
Fourier transforms for noise reduction
Given a signal, which is regularly sampled over time and is noisy. The standard method is with a Fourier transform to reduce the noise and minimise the change to the signal.
...
1
vote
1answer
22 views
Periodogram explained
If I plot a periodogram of let's say sin(20x) + 2sin(80x) and it looks like this:
What does it say, i.e., how do I interpret this periodogram? How could I compute ...
0
votes
0answers
16 views
speaker verification model trained on one dataset does not perform well on another
I am quite new to audio signal processing, more specifically speaking speaker verification. I have trained a CNN-based Siamese network to do speaker verification. The whole thing is trained with one ...
0
votes
0answers
13 views
Resampling Ground Truth - Manipulation?
A validation task requires comparing a timebound-signal (out of a system under test) of length $1\times m$ to be compared against a ground truth (GT; reference) timebound-signal of length $1\times n$, ...
0
votes
0answers
20 views
Is resampling multi-variate time series data a useful practice in increasing binary classifier accuracy?
Let $x$ be defined as a multi-variate time series with length 30 seconds a sampling frequency $F_s = 60\text{ Hz}$ columns $\{C_1, C_2, C_3\}$
My first question is, in general, would resampling $x$ ...
0
votes
0answers
7 views
Are there any recursive online max/min filters for time-series
Are there any online recursive filters that can approximate local, time-varying minimum and maximum values of a time series?
0
votes
1answer
15 views
Fourier analysis to retrieve components of individual spectra
I have a basic, simple question, I am a physics student, and searching internet gives me a lot of signal processing theory but couldn't find this basic answer, which I plan to implement in my speech ...
0
votes
0answers
7 views
How to model noisy signals in time knowing some expected behavior?
First off, pardon me for the very informal language and the lack of demonstrative media. I'll try to add some as soon as possible.
Imagine an 8bit grayscale image with a noisy background, two ...
0
votes
0answers
5 views
Classifying Motor Imagery in EEG Data
I am an undergraduate student who is trying to classify motor imagery from EEG data!
I have no experience working with EEG or any neuroscience background, I only have a very basic knowledge of how ...
1
vote
1answer
11 views
Different signal length for each batch
I wonder if it Is it possible to have a different signal length for each batch when training a model.
Batch 1 : all signals of length 1000
Batch 2 : all signals of length 2000
Batch 3 : all signals ...
0
votes
1answer
42 views
the concatenation of bivariate iid
suppose that $X \sim N\left( {0,{\sigma ^2}{I_2}} \right)$ is a bivariate white noise, and the samples ${X_1}, \cdots ,{X_N}$ are drawn from it, if we define the new random variable $Y$ with its ...
0
votes
0answers
6 views
Feature extraction for exponentially damped signals
I am looking into exponentially damped signals where it is a stationary signal (after implementing the Adfuller statistical test) and I would like to look into how can I extract meaningful features ...
0
votes
0answers
33 views
How to reflect more global patterns in timeseries?
I have some signal data of a robot recorded in every minute each day.
e.g.,
...
0
votes
0answers
13 views
0
votes
0answers
12 views
How can i compute noise (1 sigma error) given a signal
I have a signal organized as an image, i.e. a matrix. Each "pixel" has an error $\sigma_{i,j}$. Simplifying, let's assume that the error is the same for all the involved "pixels".
How can I compute ...
0
votes
0answers
6 views
How to choose from a group of parameters for every single estimation?
I have done a series of SNR-estimation with the ground-truth SNR from 0 to 15 dB at a step of 0.1 dB, 1000 samples each time. So there are 151 distributions and they all follow ExtremeValue ...
0
votes
0answers
8 views
compensation filter for effect of dependent variable
In my dataset, I have two variables A, B. Behavior of B depends on A. A varies from 0 to 100 and a transient event results in a spike in variable B, that looks like this:
It's effect lasts for a ...
0
votes
0answers
11 views
Spectra data augmentation
I am working on spectra dataset (magnetic resonance) and would like to perform data augmentation on top of that. I found this paper which doesn't seem to be clear (at least, to me) on what the exact ...
4
votes
0answers
75 views
Features for binary time-series event prediction
This question is somewhat inspired by the answer to Features for time series classification.
The difference to that question is that I have a dataset with multi-dimensional time-series where I have ...
1
vote
1answer
92 views
Cholesky decomposition or alternative for negatively correlated data simulations
I want to generate some signals that have a correlation distribution around a specific pre-defined correlation value (i.e., the distribution of the values of their correlation matrix is around a ...
0
votes
0answers
12 views
Discrete Fourier transform (DFT) of 2 signals using a single DFT
Given two different(x,y) and independent signals, can one find dft of both of them using a single dft chip and using that that chip only once. I tried finding dft of x+jy but was not able to find ...
0
votes
0answers
18 views
In covariance function of white Gaussian noise, where does the delta function come from?
In probability theory, for the covariance of white Gaussian noise, where does the delta function come from and how do you prove it?
2
votes
1answer
28 views
AR process stationarity
For $X[n] =aX[n-1]+W[n]$
When $W[n]$ is iid.
One can say that $X[n]$ is the output of $W[n]$ thrown into an LTI system.
So how can it be that $X[n]$ is not necessarily WSS, if we know that a WSS ...
0
votes
0answers
26 views
Math for Gaussian noise on top of another Gaussian noise
I have worked on this project for a while and I have some results. However, I want to communicate in my paper the mathematics involved.
When an image is introduced with 11 standard deviations, this ...
3
votes
1answer
65 views
Formulas for higher order cumulants
I want to calculate higher-order joint cumulants for 2 variables. I calculated the higher order single-variable and bivariate moments numerically. Now I need to combine them into cumulants (upto the ...
2
votes
0answers
23 views
Finding exponential decay in noisy vibration signal
I have to analyse vibrational signals for which the general assumption is that there is one dominant excitation and an exponential decay in amplitude thereafter.
I have created smoothened envelopes ...
1
vote
0answers
62 views
What is the laplace transform of the below given PDF?
Really am interesting to know more about statistical properties of the following PDF , of the Random variable $z$:
$$F(\sigma,\mu,z)= \frac{(z-\sigma )^2 \exp \left(-\frac{(z-\sigma )^2
\sqrt{\left(...
0
votes
0answers
11 views
Can a DNN learn the GCC-PHAT algorithm?
How would you create a DNN (and its training dataset) such that it is able to copy the GCC-PHAT algorithm?
0
votes
0answers
11 views
Signal/Wavelet Clustering
Problem Setting
In an experiment:
I have 3 signal sources and 10 sensors each generating wavelets as time goes by.
The distances from each source to sensors change from experiment to experiment.
...
0
votes
0answers
10 views
Performance measure for estimation for acoustic impulse response
In searching for a performance measure for assert the estimation quality of acoustic impulse responses.
Ideal Acoustic Impulse Responses (AIRs) are usually modelled as trains of impulses:
$$ h(t) = \...
0
votes
0answers
11 views
Signal Embeddings using the skip-gram or CBOW model
So my work involves looking at a bunch of waveforms in the context of classifying events. I often am looking for new ways to represent my waveforms, and in my searching, I came across audio embeddings ...
1
vote
3answers
176 views
why is an MA process equivalent to a FIR filter?
John Cook claims that a FIR filter is equivalent to an MA process.
But FIR filter is just a function of the previous inputs:
$y_t = \phi(B)x_t$
and an MA process is a function of the previous ...
2
votes
0answers
35 views
Signal Decomposition
I have two time dependent signal sources X & Y. Both can be modeled as having a linear combination of time dependent individual components and common components; so X(t)=a(t)+C(t)+noise, Y(t)=b(t)+...
5
votes
1answer
92 views
Viral topics. How to describe and characterize bumps in time series of tag-activity on Meta Stack Exchange
Background
There is much dissatisfaction on StackExchange. This can now be covered in over 250 questions on meta (see 1 and 2). In response to that I made a recent meta-post and supported it with the ...
2
votes
0answers
49 views
Detecting specific points in (noisy) dataset
In my recent work I've came across a problem where I need to find certain points in quickly oscillating data. Let's work with syntethic data instead of real measurements and ignore the noise for the ...
1
vote
1answer
38 views
How to discard the first spike after auto-correlation and handle sloping auto-correlation output [closed]
Disclaimer: I am not very mathematically inclined and am mostly looking to be pointed in the right direction.
I have various signals that I am putting through an auto-correlation function that uses ...
0
votes
0answers
19 views
How to determine causal relationship between two temporal signals?
I have two noisy temporal 1D signals and knowledge that one drives the other, to some degree. You can see this because there are some temporary spikes in the first signal that (sometimes, if they're ...
0
votes
0answers
44 views
zero-lag filter: size of negative part of filter weights: when in-phase with sinusoid?
This question is about negative weights in causal filters and their effect on the lag, or "synchronization" with a sinusoidal signal.
There are a few types of moving averages that use negative ...
0
votes
0answers
54 views
How to search for irregular signals: Fourier, DWT or k-means?
See my notebook here
I want to search for irregular time signals in a data set of ~3 500 000 time signals. I can't give a clear definition of irregular signal, but it must fulfil the criteria of: not ...
1
vote
0answers
37 views
Cepstrum: quefrency scale to frequency scale
Can someone please explain to me how to convert a quefrency scale to the corresponding freqncy?
For example consider this:
A voice signal is measured at 50kHz sampling frequency and FFT power ...
4
votes
1answer
57 views
Can I use a LSTM Autoencoder to compute similarity between two variable-length audio signals?
I would like to compute the similarity between audio signals of different length.
One way of doing it is to train a RNN (LSTM/GRU) Autoencoder and extract the hidden layer representation - feature ...
1
vote
1answer
172 views
Intuition of the convergence of sample ACF
One of the problems in Brockwell and Davis book about time series is to show that
1) if
\begin{equation}
x_t = a + b t
\end{equation} then the sample autocorrelation ($\hat{\rho}(h)$) converges to ...
0
votes
0answers
63 views
Benefits of ML in signal processing
There is plenty of research on ML in signal processing. The majority of it, so it seams to me, is about showing feasibility of ML-based receivers (end-to-end or individual functional blocks of). To me,...
0
votes
0answers
54 views
Interpreting Normalized Cross Correlation
I'm having difficult understanding how to interpret a normalized cross correlation after using the function in Matlab for my research project. I've read through the Matlab help page and several other ...
