search

WH-Wei / SIAT-Lower-Limb-Motion-Dataset-Codes

These codes for reading, pre-processing of sEMG, splitting of sEMG into windows of various sizes, extracting of sEMG features, normalization of extracted features, generation of sample data, and making log files are provided for easy handling of the SIAT Lower Limb Motion Dataset (SIAT-LLMD). 代码可以用于SIAT-LLMD，便于读取数据、预处理肌电信号、分窗、肌电特征提取、归一化、生成数据样本并记录日志文件。当然，有些代码（例如：'EMGbox_WWH.py'）也可以用于处理数据集之外的肌电信号。
GNU General Public License v3.0
26 stars 2 forks source link

About a Gaussian process regression model was employed to predict the angle and torque associated with the joints during WAK, UPS, and DNS. #5

Open LINHYYY opened 1 week ago

LINHYYY commented 1 week ago

Hello, I take the liberty to bother you again, I wonder if it is possible to expose or provide the code for the prediction of the Gaussian process regression model? I didn't find the corresponding content in your exposed code, and I'd love to learn about this part of the implementation. Thanks again.

LINHYYY commented 3 days ago

I've successfully gotten the result files of 'emg_features' through the code: 'Heat.mat', 'emg_features_examples.mat'. I observed that the 'example' in 'emg_features' is the shape of x 9 6. But I don't know what it is made up of and how to use these two MAT files for regression prediction. I'm just an undergraduate student now, it's a bit difficult for me, I'm very much looking forward to receiving replies and help from the author or other friends, thank you.

LINHYYY commented 1 day ago

Haha I'm back, and after three days of research in my spare time, I came up with a more credible answer to 'x*9*6' of 'examples.shape'. The first thing that is obvious is the 'x', which represents the total data volume of the sample data, which is easy to figure out in the code.The second is '9', I looked at the following values in the variable of 'examples' in matlab, combined with the '.csv' file should correspond to the number of nine electrodes in the original data. Finally, there is the '6', which is the shape that puzzles me the most, and after I have looked through the paper many times, I found that under Figure 9, there is an introduction to the 'Du's sEMG feature', which states that the six characteristic variables are: IEMG, VAR, WL, ZC, SSC, WAMP. Just now I found this 2006 paper and determined that this should be what the '6' means.

But I'm not sure if I'm right in my thinking and haven't tried to do regression model training yet. So if there are any mistakes, please feel free to point them out, and I will apply to contribute my code to this project after the reproduction, including some of the code files I wrote for some other issues such as dataset format and so on. Many thanks to the author for his open source and contributions.