Hi, thanks for your impressive work on SynthSleepNet!
In the paper, it is mentioned that "Each 30-s segment was labeled as 1 if an apnea/hypopnea event was detected".
However, since the events in the SHHS XML files have variable lengths and timestamps, the mapping to fixed 30-second epochs is not entirely clear
Could you kindly clarify the specific logic used to map the variable-length events (from SHHS XML files) to fixed 30-second epochs?
Do you have any plans to release the preprocessing code or pseudocode for this specific labeling step?
Thank you for your contribution to local OSA detection!
Hi, thanks for your impressive work on SynthSleepNet!
In the paper, it is mentioned that "Each 30-s segment was labeled as 1 if an apnea/hypopnea event was detected".
However, since the events in the SHHS XML files have variable lengths and timestamps, the mapping to fixed 30-second epochs is not entirely clear
Could you kindly clarify the specific logic used to map the variable-length events (from SHHS XML files) to fixed 30-second epochs?
Do you have any plans to release the preprocessing code or pseudocode for this specific labeling step?
Thank you for your contribution to local OSA detection!