Show Posts

This section allows you to view all posts made by this member. Note that you can only see posts made in areas you currently have access to.


Messages - fmk

Pages: 1 ... 5 6 [7] 8 9 ... 16
91
AI use in Regional Simulation (BRAILS) / Re: General Questions
« on: September 22, 2021, 11:07:42 PM »
1. yes a street view like image
2. it is a binary classifier that was trained using images of buildings on stilts versus buildings on the ground, see sample images here: https://nheri-simcenter.github.io/BRAILS-Documentation/common/user_manual/modules/foundationElevationClassifier.html

now we do have a module about to be released (October 2021) that provides a calculation of height of first floor level above the soil that goes beyond the image classifiers. It is part of BRAILS being developed at UCLA to determine needed info (roof pitch, roof elevation, first floor level). We have used the software in our testbeds to provide this information for our regional inventories.

92
General Questions / MOVED: Choosing the best parameters using quoFEM
« on: September 22, 2021, 09:50:05 PM »
This topic has been moved to Uncertainty Quantification (quoFEM).

https://simcenter-messageboard.designsafe-ci.org/smf/index.php?topic=180.0

93
General Questions / MOVED: Running on quoFEM
« on: September 22, 2021, 09:49:29 PM »
This topic has been moved to Uncertainty Quantification (quoFEM).

https://simcenter-messageboard.designsafe-ci.org/smf/index.php?topic=191.0

94
Uncertainty Quantification (quoFEM) / Re: Choosing the best parameters using quoFEM
« on: September 17, 2021, 05:18:22 PM »
Rashad,  DesignSafe is down till Monday (20 Sept 2021) now. The executables because of their size are kept there.

95
Uncertainty Quantification (quoFEM) / Re: Choosing the best parameters using quoFEM
« on: September 15, 2021, 09:08:02 PM »
DesignSafe-ci is down for maintenance as they are upgrading the machine used to store their files. Scheduled to be back up tomorrow

96
AI use in Regional Simulation (BRAILS) / Re: General Questions
« on: September 13, 2021, 04:03:00 PM »
Thanks for the question. You point out a weakness in the documentation which I will work to get improved.

The soft story model is an image classifier that utilizes a convolution neural network (CNN). Like the roof classifier and occupancy classifier, the training and test sets for the CNN used a collection of labelled images. The image sets for the soft story classifier consists of a set of street-view photos of buildings that were labelled as either being a soft story or not a soft story (with many of the labels being obtained from lists of weak story buildings obtained online, e.g. Santa Monica (https://www.arcgis.com/apps/webappviewer/index.html?id=05191306d93d4c04827773b8d2151cd7), Berkeley (https://www.cityofberkeley.info/softstory/) and others). 

For a more generic under standing of CNN's use in image classification see: https://developers.google.com/machine-learning/practica/image-classification

Better approaches to detecting soft stories are indeed possible that could include for example detecting floor levels and performing calculations as you suggest.

97
AI use in Regional Simulation (BRAILS) / Re: General Questions
« on: August 30, 2021, 03:44:04 PM »

Can you be a bit more specific, for example are you looking at the different individual BRAILS modules or are you using CityBuilder.  You might want to look at day 1 of the material presented for a recent workshop that SimCenter gave in which image classification is discussed:

https://nheri-simcenter.github.io/SimCenterAI_Workshop2021/source/lecture_videos.html#day-1-introduction-to-machine-learning-part1-2-and-part3-and-brails

There is no manual processing of images to create images used in CityBuilder when they are downloaded from Google. What a user using the individual modules does to their images before they use any of the modules in BRAILS is up to the user; we don't do any manual processing.

98
Earthquake Engineering (EE-UQ) / Re: Random variables of a database in EE-UQ
« on: August 17, 2021, 07:46:04 PM »
it is not possible with what is currently released. it is planned in the next release (due end Sept) when we will include more of the functionality of quoFEM in EE-UQ.

Depending on what you are doing with the earthquake selection, you might be able to use quoFEM now, to do what you want.

99
Wind Engineering (WE-UQ) / Re: Load factor
« on: July 12, 2021, 10:00:26 PM »

sorry send via email: fmckenna AT berkeley DOT edu

100
Regional Hazard Simulation (R2D, rWhale) / Re: Errors for Training Material Data
« on: July 09, 2021, 05:22:13 PM »
I have updated the training examples. they are the same as the ones in the tool. the old examples have been removed. thanks for pointing it out.

101
Wind Engineering (WE-UQ) / Re: Load factor
« on: July 07, 2021, 04:24:50 PM »
the event files were not in what you sent .. in addition to scaling the load factor do you also scale the timestep?

https://nheri-simcenter.github.io/WE-UQ-Documentation/common/technical_manual/desktop/WEUQ/scalingWindTunnelData.html

102
Regional Hazard Simulation (R2D, rWhale) / Re: Errors for Training Material Data
« on: July 01, 2021, 11:13:18 PM »
can you confirm the errors only occur for the examples downloaded from the trainingMaterial folder on downloads page and not from examples from within the tool

103
Regional Hazard Simulation (R2D, rWhale) / Re: Errors for Training Material Data
« on: July 01, 2021, 09:44:51 PM »
can you go into preferences and change the App-id from rWhale-2.4.0u3 to rWhale-stampede-2.4.0u3 .. save the changes and try running again

104
Wind Engineering (WE-UQ) / Re: Load factor
« on: June 29, 2021, 05:05:43 AM »
Azin

I will need your files to see what is up.

frank

105
Wind Engineering (WE-UQ) / Re: recorder options for base shear and PID
« on: June 10, 2021, 03:59:44 PM »
Azin,

you could use the UserDefined EDP with some opensees scripts (the first would create recorder recording reactions at all base nodes or ele forces, the second would be the post processing script, that would open the recorder and sum whatever columns)

ps. thanks for the papers.

Pages: 1 ... 5 6 [7] 8 9 ... 16