Reservoir Echo State Network for Classification of Multivariate Time Series

Multivariate time series (MTS) classification has been tackled using various methods, including Reservoir Computing (RC), which generates efficient vectorized representations like reservoir state (RS). RS shines when handling extensive classes or training sets but demands longer processing and subst...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings (IEEE International Conference on High Performance Computing Workshops) S. 61 - 62
Hauptverfasser: Purkayastha, Basab Bijoy, Barma, Shovan
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 18.12.2023
Schlagworte:
Analytical models
Benchmark testing
Computational modeling
Distributed Memory Parallelism
Echo State Network
Electrocardiography
Memory management
Multivariate Time Series Classification
Parallel Computing
Reservoir Computing
Shared Memory Parallelism
Time series analysis
Training
ISSN:2770-0135
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Multivariate time series (MTS) classification has been tackled using various methods, including Reservoir Computing (RC), which generates efficient vectorized representations like reservoir state (RS). RS shines when handling extensive classes or training sets but demands longer processing and substantial memory. Addressing this, in this study we present the Parallel Reservoir Echo State Network (PR- ESN), an optimized parallel training and evaluation algorithm rooted in the ESN principle. It leverages both CPU-shared memory and parallel distributed memory architecture to efficiently capture reservoir state's optimal model space representation, addressing computational challenges in MTS analysis. Distinguishing itself from previous works, PR- ESN combines distributed parallel processing at the network level and shared memory multiprocessing at the node level. This results in reduced memory requirements and faster processing, making it a significant contribution to the field. Key features include PR-ESN's distributed training and evaluation, shared memory parallelization, and MSR concatenation for comprehensive analysis of distributed model space representations. Testing on real-world MTS and benchmark ECG data proves PR-ESN-based classifiers achieve superior accuracy and faster processing times with optimal memory usage. Testing on real-world MTS and benchmark ECG data proves PR-ESN-based classifiers achieve superior accuracy and faster processing times with optimal memory usage.
ISSN:2770-0135
DOI:10.1109/HiPCW61695.2023.00019