'raw_vibration_signals' folder contains the raw vibration singal data batches, saved in TDMS file format. TDMS and TDMS_INDEX files of different runs are saved in corresponding folders named by the run name. The signal can be read by:
```
from nptdms import TdmsFile

data_dict = {}
print_flag = True
with TdmsFile.open(<file_path>) as tdms_file:
    for group in tdms_file.groups():
        for channel in group.channels():
            if print_flag:
                print("Channel name:", channel.name)
                print(channel.properties)
                print_flag = False
            data = channel[:]
            absolute_times = channel.time_track()
            start_time = channel.properties['wf_start_time']
            data_dict[idx] = {'data': data, 'times': absolute_times, 'start_time': start_time}
```

The rest of the folders contain the extracted statistical features from the batches along with the target deltaSa values, which refer to the change of surface roughness.

The 'extracted_statistical_features' folder contains the extracted statistical featutures and delta Sa of all the batches. The run can be identified through file names. To read the features, you can use the following code:
```
import numpy as np

data = np.loadtxt(<file_path>)
```