Key result
Particle swarm optimization motif detection beats existing methods with faster execution and ~93% F1-measure.
Why the study?
Motif detection in ECG signal sequences requires improved methods for identifying repetitive patterns with enhanced accuracy and execution time.
A novel motif detection mechanism using Particle Swarm Optimization improves the accuracy and execution time of ECG signal analysis.
The motif discovery mechanism is used for the analysis of the ECG signal along with the efficient particle swarm optimization algorithm. In this method motif detection in the ECG signal sequences is presented. The proposed method is based upon the variable length of motif and detected the repetitive patterns in input ECG signal. This method has been visualized to analyse the signal data under the in-depth vigilant analytical method. Optimization of signals in the proposed method is performed by Particle Swarm Optimization technique (PSO) for improving the quality of signals. The data set used in this work is collected from the University of California, Riverside (UCR). The performance of the proposed method is measured using various parameters like Execution time, Precision, Recall and F1-measures. The performance of the proposed method is compared with existing methods in terms of accuracy and execution time. The Execution time and Accuracy of proposed method is in more improved form than the existing methods.
No takes yet. Share an insight, caveat, or question.
Ramandeep Kaur (2017) studied ECG signal analysis (n=200). Particle Swarm Optimization (PSO) based motif detection vs. Brute Force, Moen Keogh, Random Projection, MDLats was evaluated on Execution time and Accuracy (Precision, Recall, F1-measure). The proposed Particle Swarm Optimization-based motif detection method achieved an execution time between 662 and 682 ms, outperforming existing methods like MDLats, with an F1-measure up to 93%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: