Issues Encountered with Dataset Setup as Listed in the Paper

[blacksnail789521]

Hi,

I am attempting to set up the 7 datasets as listed in your paper, and I've encountered several issues. I was able to work with some datasets from UCI and UEA, but others presented challenges.

Successfully Accessed Datasets

PenDigits, EigenWorms, FingerMovements

• For these UEA datasets, there were no issues.

HAR

• The HAR dataset was downloaded from the UCI repository.
• After preprocessing, the HAR dataset matches the number of features and time length as expected.

Issues with Specific Datasets

Epilepsy

• There seems to be a confusion whether the Epilepsy dataset belongs to UCI or UEA, as discussed in this issue.
• When using the Epilepsy dataset from UEA, there is a mismatch in the number of features and the time length expected as per the paper. An illustration of the issue is shown below:

WISDM

• I encountered issues when trying to preprocess the dataset (downloaded from the UCI repository) with the provided code. The code references a specific file named WISDM_ar_v1.1_raw.txt, which was not available in the downloaded files.
• In an attempt to locate the correct version of the dataset, I searched Google and found a potential match on Kaggle.
• Despite finding this file and attempting to preprocess it, there remains a mismatch in the number of features and the time length compared to what is expected based on the information in the paper.

SHAR

• I am unable to locate the SHAR dataset. While I did find a related dataset on Kaggle, it does not contain a .mat file, which seems to be required for the preprocessing code provided.

I would appreciate any assistance or guidance on accessing and preprocessing these datasets correctly.

Thank you.

[mqwfrog]

Hi~

1. The confusion about the Eplipesy dataset has been explained in another issue you have commented on.
2. The source file of WISDM dataset "WISDM_ar_v1.1_raw.txt" cannot be uploaded due to file size limitations. I will email the source file to you later.
3. For more details about SHAR dataset, please refer to the paper "UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphones, D. Micucci and M. Mobilio and P. Napoletano".

[blacksnail789521]

Thank you for your assistance with the dataset issue I've encountered. May I kindly request that you also email me the source data for the SHAR dataset, which is compatible with your preprocessing code?

[mqwfrog]

My email was returned. Please check. [ Reason: Message's size exceed or recipient over quota. ]

[blacksnail789521]

I have sent you an email with the location where you can upload all the files. Thank you again for your help. :)

My email is: blacksnail789521@gmail.com, and I've sent the link to your email: mqw_sdu@mail.sdu.edu.cn

@mqwfrog I really appreciate your help, and thank you for your outstanding work.