-
Mite Mijalkov replied to the topic Within-subject edge importance in the forum General Help (Braph 2.0) 3 weeks ago
Hi Shrikanth,
Thank you for using Braph. Braph uses an FDR correction, which can indicate which edges remain significant after correcting for multiple comparisons. Additionally, one could visualize the subject matrices and check which edges have the strongest weight.
However, as there are many different methods published in the literature…[Read more]
-
Shrikanth started the topic Within-subject edge importance in the forum General Help (Braph 2.0) 3 weeks ago
Dear Braph Community,
What kind of statistics does Braph have for within-subject comparisons?
Where, each subject has a connectome and I am interested in the most significant edges of the connetome within subjects.Thank you.
Shrikanth -
Yu-Wei Chang replied to the topic Extracting Trained Parameters for Fine-Tuning Insights in BRAPH 2 Neural Network in the forum General Help (Braph 2.0) 3 weeks, 1 day ago
Hi Jo-Hsin,
Many thanks! Please don’t hesitate to reach out if you have any questions or need assistance.
-
Jo-Hsin Shih replied to the topic Extracting Trained Parameters for Fine-Tuning Insights in BRAPH 2 Neural Network in the forum General Help (Braph 2.0) 3 weeks, 1 day ago
Thank you.The way you guided me has been very helpful.
It has inspired me to seek more information in a similar manner.
I look forward to asking questions in the future as I come across them. -
Yu-Wei Chang replied to the topic Extracting Trained Parameters for Fine-Tuning Insights in BRAPH 2 Neural Network in the forum General Help (Braph 2.0) 1 month ago
Hi Jo-Hsin,
Thank you for your feedback in suing BRAPH 2.
Absolutely, it is possible to extract the learned parameters from a trained neural network model.
Let me to guide you through the process using the “example_NN_CON_WU_Classification_AdjacencyMatrix.m” script as an illustration. After line 69, kindly integrate the following code…[Read more]
-
Jo-Hsin Shih started the topic Extracting Trained Parameters for Fine-Tuning Insights in BRAPH 2 Neural Network in the forum General Help (Braph 2.0) 1 month ago
Hi BRAPH 2 Team,
I have been actively using the pipeline of neural networks. Since acquiring insights into the parameters learned by the model during training would greatly enhance me to explore the process of fine-tuning for my research.
Is it available to extract the relevant parameters from a model after it has undergone training ?
Many…[Read more]
-
Nabin Koirala replied to the topic Visualize correlation matrices in the forum General Help (Braph 2.0) 2 months, 2 weeks ago
Thank you.
-
Nabin Koirala replied to the topic Effect of Covariates in the measures in the forum General Help (Braph 2.0) 2 months, 2 weeks ago
Thanks! that’s what I wanted to know.
-
Anna Canal-Garcia replied to the topic Effect of Covariates in the measures in the forum General Help (Braph 2.0) 2 months, 3 weeks ago
Hi Nabin,
Yes, if you select partial Pearson correlation, the covariates are considered then. So, before measures are calculated.
Best regards,
Anna -
Nabin Koirala replied to the topic Effect of Covariates in the measures in the forum General Help (Braph 2.0) 2 months, 3 weeks ago
Hi Anna,
Thank you for your response. Yes, I select the Pearson with covariates. My question was rather when exactly during the processing the covariates are applied when I select this option. So, is the process as follows true ?
- The pearson correlation matrices for each group is created considering the covariates (or using residual).
- These…
-
Anna Canal-Garcia replied to the topic Effect of Covariates in the measures in the forum General Help (Braph 2.0) 2 months, 3 weeks ago
Hi Nabin,
If you are using a structural pipeline, you can adjust for covariates by selecting the partial Pearson correlation or partial Spearman correlation when creating the graph/network. If you do not select one of these options, covariates won’t be used in the analysis.
-
Yu-Wei Chang replied to the topic Visualize correlation matrices in the forum General Help (Braph 2.0) 2 months, 3 weeks ago
Thank you for choosing BRAPH 2. I’m here to help you with visualizing matrices at different densities using the GUI. Here are the steps:
- Right-click on the graph measure panel and a list will pop out. You can refer to the following screenshot.
http://braph.org/wp-content/uploads/2023/07/plot_graph_forum_answer-2.png - Click on “Plot Graph” in the…
- Right-click on the graph measure panel and a list will pop out. You can refer to the following screenshot.
-
Nabin Koirala started the topic Effect of Covariates in the measures in the forum General Help (Braph 2.0) 2 months, 3 weeks ago
Hi BRAPH team,
I was wondering at what step is the covariates applied during the computation. Is it already applied while computing measures? Or only while comparing them? I mean are the network measures computed on the residuals or it is used as ANCOVA for comparison?
Thank you.
Best,
Nabin -
Nabin Koirala started the topic Visualize correlation matrices in the forum General Help (Braph 2.0) 2 months, 3 weeks ago
Hi BRAPH team,
Is there a way to visualize the correlation matrices ? In BRAPH 1 it was very easy to see them but somehow could not find it in BRAPH 2. I am using structural BUD comparison for my analysis and would like to visualize the matrices at different densities.
Thank you for your support.
Best,
Nabin -
Nabin Koirala replied to the topic Efficiently extracting network measures from saved .b2 file in the forum General Help (Braph 2.0) 2 months, 3 weeks ago
Thanks Emiliano for your help on this.
-
Emiliano Gomez replied to the topic Efficiently extracting network measures from saved .b2 file in the forum General Help (Braph 2.0) 2 months, 4 weeks ago
This question was solved with the following example of code:
*Note***
In Nabin’s case the saved b2 file was a Comparison of Structural groups.[file, path, filterindex] = uigetfile(BRAPH2.EXT_ELEMENT, [‘Select the .b2 file.’]);
tmp = load(filename, ‘-mat’, ‘el’);
filename = fullfile(path, file);
tmp = load(filename, ‘-mat’, ‘el’);
comparison =…[Read more] -
Nabin Koirala started the topic Efficiently extracting network measures from saved .b2 file in the forum General Help (Braph 2.0) 3 months ago
Can I load the saved .b2 file in matlab and export all computed network measures in some format ? I should mention this that I know that I could click on them and get the table and save as .xlsx but I would prefer not to do that 20 times for all the measures. I have asked this before and Emiliano helped me with the script to extract those measures…[Read more]
-
Mite Mijalkov replied to the topic Betweenness Centrality – Normalized in the forum General Help (Braph 1.0) 3 months, 2 weeks ago
Dear Keivan,
Thank you for contacting us and for using Braph for your analysis.
The betweenness centrality in Braph has to option to provide both normalized and unnormalized values when used from the command line. However, if you are using the GUIs provided by Braph, then the default value is the normalized version.
The measure is normalized by…[Read more]
-
Keivan Baboli started the topic Betweenness Centrality – Normalized in the forum General Help (Braph 1.0) 4 months, 2 weeks ago
Hello,
I’m currently using Braph for brain network analysis and have a question about the betweenness centrality measure. In the results produced by Braph, is the betweenness centrality measure normalized?
If the betweenness centrality is indeed normalized, could you please provide some details about the normalization procedure or direct me to…[Read more]
-
paban started the topic degree in the forum General Help (Braph 1.0) 5 months ago
Dear Mite,
I have resolved the problem with the error message! It turned out to be related to my subject files. Now everything is working well, except that I don’t understand why the degree value is the same as my ROI number. I tried modifying the threshold, but nothing changed. Could you please explain this to me?
The best,
Veronique, - Load More