Recurrent neural networks optimized with a modified particle swarm optimization algorithm demonstrated significant potential for anomaly detection in ECG readings compared to other optimizers.
Do recurrent neural networks optimized with a modified particle swarm optimization algorithm improve anomaly detection in ECG sensor data compared to other optimizers?
Optimized recurrent neural networks demonstrate significant potential for automated anomaly detection in ECG readings.
Monitoring heart electrical activity is an effective way of detecting existing and developing conditions. This is usually performed as a non-invasive test using a network of up to 12 sensors (electrodes) on the chest and limbs to create an electrocardiogram (ECG). By visually observing these readings, experienced professionals can make accurate diagnoses and, if needed, request further testing. However, the training and experience needed to make accurate diagnoses are significant. This work explores the potential of recurrent neural networks for anomaly detection in ECG readings. Furthermore, to attain the best possible performance for these networks, training parameters, and network architectures are optimized using a modified version of the well-established particle swarm optimization algorithm. The performance of the optimized models is compared to models created by other contemporary optimizers, and the results show significant potential for real-world applications. Further analyses are carried out on the best-performing models to determine feature importance.
Minic et al. (Sun,) conducted a other in ECG anomalies. Recurrent neural networks optimized with particle swarm optimization vs. Models created by other contemporary optimizers was evaluated on Anomaly detection performance. Recurrent neural networks optimized with a modified particle swarm optimization algorithm demonstrated significant potential for anomaly detection in ECG readings compared to other optimizers.