Table 8 Performance comparison with other state-of-the-art SNN models
Reference and Year | Dataset Used | Model/Algorithm Used | Accuracy (in %) |
|---|---|---|---|
López-Vázquez et al. [36], 2019 | UCI Machine Learning Repository for PD | Grammatical Evolution (GE)-based SNN | 88.75% |
Kerman et al. [37], 2022 | Spike data collected from different regions of Brain | Spiking MLP | 93% |
Siddique et al. [38], 2023 | Spike data from the neurons in the subthalamic nucleus region | Spiking LSTM | 99.48% |
Proposed model [Dataset#1] | UCI Machine Learning Repository for PD [51] | Time-varying Synaptic Efficacy Function based SNN (SEFRON) | 100% |
Proposed model [Dataset#2] | UCI Machine Learning Repository: Parkinson Dataset with replicated acoustic features [52] | Time-varying Synaptic Efficacy Function based SNN (SEFRON) | 91.94% |