# Questions tagged [signal-processing]

Numerical analysis of a digitized signal

292 questions
Filter by
Sorted by
Tagged with
0answers
28 views

### Clustering of an image sequence of a moving object

I have a set of 100 images of a man moving on the street. I remove the background and try to cluster the man using dbscan in each image seperately. Instead of getting one cluster (for the man), I get ...
1answer
476 views

### Intervention/Level Shift detection

I don't really know if this problem can be considered as an intervention detection/analysis problem. The data shown below is actually a sensor signal collected from an air booster. The air booster has ...
0answers
190 views

### How can I get the cumulant expression from the recursive relation between cumulant and moment?

I am reading some paper about high-order statistics https://link.springer.com/article/10.1007%2Fs11004-009-9258-9?LI=true. The paper gives two recursive expressions relating the multivariate cumulants ...
0answers
132 views

### estimating weights in lattice recursive least squares (LRLS)

I'm struggling to estimate the weights (W) from the forward and backward prediction coefficients (k) in Lattice recursive least squares (Lattice-RLS). The standard recursive least squares (RLS) ...
1answer
95 views

### Time series data - A metric to quantify a signal's intensity frequency and duration

I have an time series data with an appearance of a headache events over time. Each headache is characterized with intensity (1-5) and duration (in seconds). Therefore, the signal is represented in ...
0answers
194 views

### Calculating heartbeats per minute from a .wav file [closed]

I am working on a machine learning project relating to heart-Arrhythmia's. I want to be able to calculate heart beats per minute from a 30 second wav file as input. I am creating a mel-spectrogram ...
1answer
298 views

### Denoising technique for signal with beforehand known shape (linear and exponential)

I have a noisy signal which is linear and then exponential. I know the type (Gaussian additive noise) and degree (0.01) of noise. Part of the challenge is determining when the signal changed from ...
2answers
627 views

### ICA, how to check for Gaussian components?

Independent Component Analysis (ICA) requires that at most one of the additive subcomponents of a multivariate signal is Gaussian. If I do not know the distributions of the subcomponents, how do I ...
1answer
2k views

### Finding out frequency of peaks using the Fourier transform

I have a signal that varies in time as shown below. I have just shown a 5 s interval of data (from 97 s to 102 s). The sampling frequency is 1000 Hz. My goal is to find out the frequency of the ...
0answers
178 views

### Autocorrelation Exponential Decay Rate for feature selection

I have signals of a time series of length 50. I want to give a try to a PCA like method for classification extracting features from the signal. I am considering several summary descriptors (e.g, mean, ...
0answers
118 views

### How to estimate cutoff point for continuous varibles and binary output?

I have a simulated dataset comprising signals (binary) and a set of continuous inputs. When the continuous var goes up over than a threshold, the system is switched on, which means that the signal ...
1answer
51 views

### Why is phase reconstruction considered hard

I am studying deep learning models for single channel speech separation. I come across several recent methods: Permutation Invariant Training Deep Clustering Deep Attractor Network All of these ...
0answers
58 views

### Kurtosis to detect non-random signals in a spectrum

I have a spectrum that was created from a time series using the FFT. The spectrum has several man-made "channels" in it; some of these are one-bin wide, some are several adjacent bins wide (larger ...
1answer
186 views

### For two stochastic process $x_t$, $y_t$, how can the cross-covariance function between $x_t$ and $y_t$ at lag k different from that at lag -k?

For two stochastic process $x_t$, $y_t$, how can the cross-covariance function between $x_t$ and $y_t$ at lag k different from that at lag -k? For some reason, I can't scrape my head around this. ...
0answers
64 views

### Signal to Noise Ratio of a train of pulses

My signal was a train of rectangular pulses consisted of eight pulses with interval between pulses of 36 s with a temporal resolution of 0.1 s. I added a Gaussian noise oscillations with zero mean and ...
1answer
190 views

### How to deal with changing variance in data sets

I've done an entry level stats course, so my knowledge is very limited in regards to this topic. I'm dealing with large datasets (~3000-9000 data points), and trying to pick signals out of the noise ...
1answer
332 views

### How to explain exponential plus Gaussian noise

I have some noisy signal. When I substract real (for calibration it is known) or filtered signal I get residuals. When I plot distribution of these residuals I see that it is sum of exponential and ...
0answers
224 views

### Trying to find a pattern given multiple FFT data sets using Amplitude, Frequency, and Phase

I have about 90+ audio files that I have the FFT data in frequency, amplitude, and phase. I'm trying to find patterns that are found throughout the 90+ audio files but I'm at a loss. I can create ...
2answers
211 views

### Efficient way to detect outlier peaks in periodic signal

I have a set of traces (1D array), and i need to align them, the problem is that, using generic methods ( cross-correlation, dynamic time wrap), would be very slow to align 1 million trace, each with ...
1answer
105 views

### how we input speech signal waveforms in two deep learning algorithms?

I am working with deep learning algorithms like CNN and RNN.I always wonder what is the best way to input wave form type data in to the deep learning algo. I know there are methods like wavelet or mel ...
0answers
117 views

### Time-series Decay identification

Are there any known techniques or methods to extract and identify decays from a time-series of data? By "extract and identify" I mean finding similar features as those in the blue boxes in the ...
0answers
25 views

### Predicting instantaneous ECG Signal

I have an ECG signal and want to predict the nth instance of signal based on previous m samples. Which of these (or some other) solution will be best suitable for it: Using past m samples as ...
1answer
77 views

### About solving a convex optimization problem

Is there any solution for the following convex optimization problem?: \begin{equation} \text{argmin}_{\mathbf{X}} ||\mathbf{X} + \mathbf{Y}||_F^2 + \lambda ||\mathbf{Z} - \mathbf{FX}||_1 \end{equation}...
1answer
595 views

### mutual information of two identical signals [duplicate]

library(infotheo) > mutinformation(c(1,2,3),c(1,2,3))  1.098612 > mutinformation(c(1,1,1),c(1,1,1))  0 Why is there a difference? I keep reading that ...
0answers
867 views

### Get the amplitude of the components of a periodic signal from Fourier (FFT)/Wavelets analysis

I have a signal looking approximatively as the one in the first subplot below (*), and I would like to: extract the periods of the main components of the signal; associate an amplitude to these ...
0answers
70 views

### Stabilizing variance that decreases over time in oscillating timeseries

I have some oscillating timeseries data that decreases in mean and variance over time. I am interested in stabilizing or normalizing the variance with some relatively straightforward transformation. ...
0answers
1k views

### How to properly calculate the cross-correlation?

I'm writing a simple C program that calculates the cross-correlation between two data sets. Although I've done a good search on how the calculation should be performed, I couldn't figure out some ...
0answers
304 views

### Basic EMG classification (time series)

I'm trying to learn how to classify bio-signals, and I'm starting with EMG signals from hand gestures, since a lot of data exists on this topic. My problem is understanding how test the probability of ...
0answers
73 views

### Detecting period patterns in time series data

Suppose I have a large dataset of my transaction history (the date, the amount). I want to identify transactions which are recurrent (e.g. my phone bill every month, my rent every week, etc.) from the ...
1answer
421 views

### Mathematical approach for finding baseline shifts in data

I have a raw signal from a sensor which is attached in this question . The x-axis is time, and the y-axis is the signal response. As you can see from the data, the baseline of the noisy signal shifts ...
0answers
96 views

### 2D Sensor data alignment by correlation

I have an analog Video Signal in Octave (=Matlab). It is sampled by 14Msample/s. By autocorrelation I have found the line frequency of 15,625KHz. I have 896 samples per Line. But when I transfrom now ...
1answer
80 views

### What is a d-prime experiment

I am reading about Roc curves and have encountered the term ""D-prime experiment" does anyone know what it is?
0answers
60 views

### Continuous entropy comparison

I have a continuos time signal (speech signal) and I will add noise to it at different SNRs. I want to compare the entropy or the original signal (clean speech) with the noisy ones. The idea is to ...
0answers
212 views

### Detecting a tremor given accelerometer data

I'm trying to figure out what technique to use in order to detect a tremor in accelerometer data. I have the acceleration in the x, y and z coordinates. I've plotted 4 graphs of this data below with ...
0answers
81 views

### Filtering time series to forecast with specific error distribution

I have a time series of weather data (wind). I would like to create a signal from this time series such that the distribution of the difference between the two signals has very specific properties. (...
0answers
28 views

### Understanding shape of laplacian-embedded signal

I have a periodic signal for which I: a) extract main signal mode b) split that signal mode into windows of size 20 and create vectors of size 20 and c) do Laplacian embedding for this collection ...
0answers
890 views

### Signal Processing Steps for Raw Accelerometer Data

A project I am engaged with involves taking raw accelerometer data (in g's ) and analyzing for the existence of tremors (the accelerometer is attached to an individuals hand). I am relatively new to ...
1answer
1k views

### Rubberband baseline correction

I am trying to code the method called "Rubber-band baseline correction" for baseline correction of vibrationnal spectra. Could somebody please, explain me how does this method works? or provide any ...
0answers
133 views

### Learn a fined-grained periodic function from coarse-grained periodic functions

I'm a Machine Learning practitioner but not a Signal Processing practitioner. I have data and I assume they generated by an any periodic function (periodic wave), not necessarily sinusoidal. So I ...
1answer
33 views

### Find probabilistic relationships between multiple signals

Suppose that there are a large number of stochastic signals. I want to: Partition them into a set of groups so that different groups are almost independent with each other. Find a small number of key ...
0answers
143 views

### Accuracy of exponential decay parameter estimates comparing different models

I am wondering what approach is more accurate for estimating parameters between two different models of exponentially decaying signal data. The signal decays very rapidly and only a few samples can ...
1answer
123 views

### How to detect the change points in a signal?

I have a signal that I obtained by computing the pixel-based-sum of the difference between consecutive image frames in a video. Basically, I want to detect whenever there is a lack of continuity ...
1answer
2k views

### Spectral density of a time series R implementation explanation

I am doing signal analysis for the fist time and am using the implementation to found in the stats package to obtain the spectral density of a time series, so I can know which frequencies of the ...
0answers
56 views

### Setting threshold in Sohn & al. (1999) Voice Activity Detection Algorithm

In  an algorithm based on statistical modeling of the frequency bins of a signal in order to determine if it contains speech or not. There is two hypothesis H0 (speech absent) and H1 (speech ...
1answer
94 views

### SURF algorithm failing?

I am currently working on misalignment correction and after some research found a nice matlab toolbox for this purpose capable of doing Lucas-Kanade, ECC among others. I had success when using a ...
1answer
305 views

### Test for fractional Brownian motion in Matlab

Is there a test in Matlab if a time series satisfies properties of being a fractional Brownian motion?
1answer
18 views

### Looking at Time Vs Index

I have a collection of times, and I'm trying to analyze relative distances between different times. When visualizing this data, does it make sense to plot (idx,time), where idx in the index of a set ...
1answer
29 views

### periodicity within Signal [closed]

I am actually measuring the current of a dc motor, it takes values between, and I want to be able to find periodic peaks within my signal. My motor is connected to a spindel, the goal is to detect any ...
1answer
1k views

### How to specify exact rise-to-peak and decay-to-baseline times in an exponential function, generating a waveform?

I am attempting to model the fluorescent signal emitted by a fluorescent calcium indicator (lights up when there is calcium influx into a cell). According to , the following formula works as a ...
1answer
20 views

### Determine the n largest intervals of noise in an audio file

I have audio files that contain interviews with long periods of silence. n - Number of interviews for a given audio file. I need to split the audio into periods where the interviews are actually ...