Multiclass Classification of Systolic and Diastolic Peaks on Open Benchmark PPG Signals: Performance Evaluation

Photoplethysmogram (PPG) signals contain valuable health information that is in the relation between volumetric variations of blood circulation and cardiovascular respiratory systems. This study introduces performance evaluation on open clinical benchmark PPG with a multiclass neural network random weights (NNRW) classification method for systolic peak diastolic point detection. The best detection crucial to be achieved at early stage extracting further addition future predictions cardiovascular-related illness. Various datasets have been introduced, however, there lack annotations. Due annotation information, it time-consuming prepared. One suitable dataset has previously evaluated, cannot generalized rely upon only one dataset. Therefore, generalization, new found year 2018 our own collected data from normal participants utilized this study. findings exhibit more convincing overall accuracy Gmean testing results 94.86 94.74 percent, respectively. comparison previous work indicate proposed methodology predict PPG-based multi-class points generalizable.