Stack Exchange Network

Stack Exchange network consists of 175 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [signal-detection]

Signal Detection Theory (SDT) explains how a receiver detects a signal in noise as a function of the receiver's sensitivity to the signal & the receiver's bias or tendency to assert the presence of the signal whether it is there or not.

0
votes
0answers
5 views

What are the correct rejection- and miss-rate used for?

Say we have a two-alternative forced choice task on the basis of which we compute the four rates defined in signal detection theory, relating to hits, false alarms, correct rejections, and misses (HR, ...
0
votes
0answers
2 views

Signal detection theory: one-interval design (= yes-no task) and 2AFC design, test power and sample size

my research group and I read some more about signal detection theory and we were not able to find answers concerning the following questions. Therefore, we would appreciate your help very much! 1) We ...
2
votes
0answers
25 views

How does d-prime calculation relate to binomial mixed models with probit link?

for a study I tested participants in a same-different task (1AFC) about melodies. There were 3 versions of each melody (within-subjects factor "version"). So d-prime seems the natural response/...
2
votes
2answers
96 views

How do I calculate d' from experimental data?

In Signal Detection Theory, d' is defined by the z-scores of Hits and False Alarms: d' = z(Hits) - z(False Alarms). Say the task is to detect if a certain object is present in a series of pictures, ...
0
votes
0answers
20 views

How can I scale up the tiny effect size of a statistically significant effect?

Given a datastream with an embedded signal that is exceedingly faint, but is statistically significant (that is, a small effect size, but a real effect) how would one go about scaling up the signal of ...
1
vote
0answers
170 views

Pointwise Mutual Information (PMI) and Information Component (IC)

Pointwise Mutual Information (PMI) and the Information Component (IC) formula (https://link.springer.com/article/10.2165/00002018-200225060-00002) seem to be the same, PMI is mainly used in natural ...
0
votes
1answer
12 views

Proving that a maximum exists when finding the optimal criterion in SDT

When deriving that there is an optimal criterion in the Signal Detection Theory literature that maximizes Proportion Correct (PC), we usually arrive at the following expression by setting the first ...
0
votes
1answer
25 views

Is there an accepted way to interpret d' (d-prime) for evidence of detection

I have run a learning experiment, with a yes-no familiarity test at the end, and computed d' across various conditions. Is there some rule of thumb (perhaps dependent on sample size) as to how d' ...
1
vote
0answers
52 views

Why does d-prime of average hit and false alarm rates differ from the average d-prime of individual cases?

I'm reporting d-prime for a set of IDs. After setting a dprime() function, I use it to compute d-prime for each ID based on their hit and false alarm rates, saved ...
1
vote
0answers
130 views

A' (A prime) for extreme Hit rates and False Alarms

I am trying to compute the non parametric measure of sensitivity A' according to the following formula reported by Stanislav & Todorov (1999): $$ A'= .5+sign(H-F)*((H-F)^2+abs(H-F))/(4*max(H,F)-4*...
0
votes
0answers
12 views

How do I calculate sensitivity Index d' from a model statistics

I did a supervised classification on EEG data. The resulting BCILAB ML models have 5 fold cross validation and here are the statistics. ...
0
votes
1answer
211 views

HMM depmixS4 using a vector of known states to fit model

I am using the depmixS4 package to fit HMMs to RNAseq count data. My workflow is as follows: Stack reads into a 'stack' vector which looks like this: ...
0
votes
1answer
10 views

What is a technique for extracting the data pattern from experimental replicates?

I collect the data of air pollution over the year. The data is 2D where the first axis is discrete scale (mass of pollutants in integer; 50, 51, 52...) and another axis is continuous scale (intensity)....
2
votes
1answer
61 views

Hit-&false-alarm-rates: cases of undefined denominator

I wish to apply SDT for an experiment whereby, while listening to a piece of music, subjects were asked to press a key when detecting a certain cue in the music. Based on the parts of the piece where ...
2
votes
1answer
155 views

Computing z-scores for hit & false-alarm rates in Signal Detection Theory

For each subject in my sample, I need to compute a sensitivity index, d-prime, defined in Signal Detection Theory as d' = z(HR) - z(FAR) where HR and FAR are the ...
1
vote
0answers
51 views

Building Neyman-Pearson test in 2D-space having only data for $H_0$ and $H_1$

Suppose we have some statistical data which is points in 2D-space. More precise sample space is upper right quarter of $\mathbb{R^2}$: $$\Omega = \{X | X=(x_1, x_2),\, x_1, x_2\in \mathbb{R_+}\}$$ ...
1
vote
0answers
14 views

How can I best determine the Signal/Noise of a pulsed signal?

I have this pulsed signal, and I would like to quantify the signal to noise ratio. Is there a preferred way to do this? My current approach is to filter the points that are obviously part of the ...
0
votes
0answers
14 views

How to obtain a signal/noise measurement from a video without a background control

I have a video with a periodic process that can be seen as a change in brightness of the frame. I am measuring the process by calculating the average brightness value of the frame and plotting it over ...
1
vote
0answers
473 views

Negative D-prime values; use absolute values?

I have calculated D-prime measurements for for a memory performance task. Subjects viewed images that were either old or new and had to indicate their response via a button press. Thus, their response ...
0
votes
0answers
14 views

Calculate ranges for control based on detection of biomarker

How do you calculate ranges (positive / negative) for the control assay based on the detection of a biomarker in samples? Here is some sample data: ...
0
votes
0answers
41 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 ...
1
vote
1answer
45 views

EEG waves measuring statistical significance of an event

I have recently gotten into a problem with EEG activity measurement. I need to prove (or disprove) that certain event triggered a statistically significant reaction in EEG activity. I know exactly at ...
2
votes
0answers
48 views

What is the distribution of $d'$?

In my experiment, repeated measures of $d'$ (computed from hit and false alarm rates) are computed for a small number of subjects (<10) under multiple (10) conditions. Primarily, I am interested to ...
0
votes
3answers
444 views

Confusion between true negatives and false positives (double negation?!)

Given the below term definitions ..my question is: why is the logical negation (opposite) of a false negative not a true negative? This would imply 1-α=β, which does not have to be the case. And ...
1
vote
0answers
184 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 ...
3
votes
0answers
406 views

Neural networks and signal-to-noise ratio

My guess is that neural networks do not work very well in noisy environments, i.e. the lower the signal-to-noise ratio, the worse the result of a neural network, if compared to other statistical ...
1
vote
0answers
38 views

Signal Extraction

I have following problem to show: let scalar valued signal $X_t$ be transmitted at time $t$ and received $Y_t = X_t + \epsilon_t$. Where $\epsilon_t$'s are zero mean noise. Suppose $E[X_t]=0$ for all ...
1
vote
0answers
139 views

Proportion of variance explained, prediction accuracy, and noisy criterion variables

A given criterion measure is corrupted by noise such that only 60% of its variance is attributable to a true signal. This noisy measure of outcome is regressed against some number of predictors and a ...
0
votes
1answer
228 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?
1
vote
1answer
21 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 ...
0
votes
0answers
773 views

What should I use to establish a threshold to detect threshold crossings?

I have data graphed in green here: I want to detect the peaks but I don't know how to define the threshold values. The blue lines are mean ± standard deviation. Using that, I would miss the three ...
0
votes
1answer
248 views

Statistical analysis of fourier transform of a 2D image (freaking AMAZING)

I'm a statistics grad student, and I just started getting into Digital-Image-Processing (an analogy for processing super-large contingency tables). In the book "Digital Image Processing" by Gonzalez ...
1
vote
0answers
98 views

Interpretation of diagonal detail for a 2D (Haar) Wavelet Transform

I am a statistics grad student, and I have just began exploring the topic of wavelet regression (specifically, Haar wavelets for discrete functions). I understand the generalization from a one ...
4
votes
2answers
6k views

What is the two alternative forced choice paradigm

Is a two alternative forced choice paradigm (2AFC) an experimental design?
1
vote
1answer
96 views

CNN localizing object?

For classying images/objects CNNs are one possible or even the state-of-the-art solution but what if one wants to localize an object in an image? I thought if I use only convolutional layers without (...
0
votes
0answers
51 views

How to determine what % of variance is due to noise (with limited data)

this is a difficult question and perhaps not answerable without further data. I have a list of staff that get monthly scores that are averages of customer ratings. (95%, 75%, 89%) So, the most ...
1
vote
3answers
356 views

find peaks from response signal

My subject is to model the response of micro-organisms to the pollution of the media (one specific pollutant). We analyse the response (production of a substance) through time that is linked to the ...
3
votes
0answers
20 views

Evaluation of circle detectors

I have several circle detectors. I want to evaluate their performance in finding the spherical steel markers in X-ray images. The radii of the circles are distributed in a narrow range around 8 px. ...
2
votes
1answer
268 views

Identifying intervals in a time series

I know, I know, this must have been covered many times before, but my belief is that I don't need the usual robust solution... Here is a time series: I would like to automatically detect the ...
3
votes
0answers
426 views

Calculating ROC curve for two gaussian distributions with equal variance

I recall a simple formula in a paper which relates the distance between two gaussian distributions (what psychologists refer to as d') to the ROC curve under the assumption that both distributions ...
1
vote
1answer
1k views

Figuring out Signal to Noise Ratio of Spectral data?

I have some Raman spectral data of a chemical: Each spectrum consist of multiple tuples of (wavenumber, intensity) I have multiple instances of ...
0
votes
1answer
684 views

Time series analysis (removing effect of external factor)

I'm currently working on detecting the response from a sensor with the following profile: The sensor responds to temperature fluctuations and I was wondering if y'all could suggest methods to "remove"...
1
vote
0answers
204 views

outlier / anomaly detection in high frequency time series data

I am collecting stats from a number of different sensors on a racing car. They update every millisecond and are plotted to a real-time graph. I can see the graph update an observe trends and ...
2
votes
2answers
2k views

What is the best function to fit onto a “flat top gaussian”?

I am studying some signal and I am trying to make an automated algorithm that can extract the parameters for my signal. First let me describe a bit, I have a light emiting object crossing a window of ...
7
votes
2answers
818 views

Frequency jump detection

It is generally known that 'jumps' in frequency data are difficult to estimate. In the current literature, many different techniques for estimating such jumps have been tested and often with ...
2
votes
1answer
71 views

Searching for signal in a somewhat noisy landscape

I'm trying to implement a system to identify regions of high signal content in the presence of a noisy landscape. By high signal content, I simply mean intensity values significantly above background ...
3
votes
0answers
243 views

How to determine rise time of a signal from its noisy background timeseries?

I have temperature vs. time data from a thermometer. The data was recorded using a DAQ system, has a stable background level, and some random noise. At a certain time, the temperature begins to rise ...
10
votes
2answers
11k views

d prime with 100% hit rate probability and 0% false alarm probability

I would like to calculate d prime for a memory task that involves detecting old and new items. The problem I have is that some of the subjects have hit rate of 1 and/or false alarm rate of 0, which ...
6
votes
3answers
1k views

How to calculate confidence intervals for Precision & Recall (from a signal detection matrix)?

I built a detector to detect a binary outcome and then took a random sample from the population. From this, I can create a signal detection/confusion matrix (hit, miss, false alarm, correct rejection)...
11
votes
1answer
2k views

Connections between $d^\prime$ (d-prime) and AUC (Area Under the ROC Curve); underlying assumptions

In machine learning we may use the area under the ROC curve (often abbreviated AUC, or AUROC) to summarise how well a system can discriminate between two categories. In signal detection theory often ...