This contains the codebase for the FBCSP Toolbox. Please refer to fbcsptoolbox.github.io for information on the toolbox.
For reporting any problems, please use the issues tab of this repo.
This contains the codebase for the FBCSP Toolbox. Please refer to fbcsptoolbox.github.io for information on the toolbox.
For reporting any problems, please use the issues tab of this repo.
The FeatureSelect class returns inconsistent shapes when doing MIBIF feature extraction from the FBCSP paper.
As expected, when first extracting the top k, k = 4 in the FBCSP paper case, MIBIF features, the length of each feature vector is 4, however, in the next line of code:
paired_features_idx = self.select_CSP_pairs(features_selected, self.n_csp_pairs)
The output shape is inconsistent. It is either a vector of six or eight elements. I am fairly certain it should not be this way. Ran into the issue when I was trying to evaluate model results on A01E.
I can't seem to find the License document for this code base. Do please include in the repo. Thanks.
Seems like you are not really using the frequency bank, as the 'coeficient' never called and nowhere else happens frequency windowing...
Did I miss something?
2.1. BAND-PASS FILTERING The first stage employs a filter bank that decomposes the EEG into multiple frequency pass bands using causal Chebyshev Type II fil- ter. A total of 9 band-pass filters are used, namely, 4–8, 8–12, . . ., 36–40 Hz. Various configurations of the filter bank are as effective, but these band-pass frequency ranges are used because they yield a stable frequency response and cover the range of 4–40 Hz.
Lines 34 to 35 in 9647b78
Hi,
I use the code
conda env create --name fbcsp --file fbcsp.yml
to install the package in linux,
however, it indicated the following error,
Collecting package metadata (repodata.json): ...working... done
Solving environment: ...working... failed
ResolvePackageNotFound:
Any suggestions about why this happened will be very helpful! Thank u!!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.