Prediction Using Cuckoo Search Optimized Echo State Network

Bala, Abubakar; Ismail, Idris; Ibrahim, Rosdiazli; Sait, Sadiq M.; Salami, Hamza Onoruoiza

doi:10.1007/s13369-019-04008-0

Cited by 11 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Echo state network is neural network which solves the complexities in Recurrent neural networks. Abubakar Bala et al [8] proposed an echo state network, in which cuckoo optimize search algorithm was used for right parameter and topology. It was observed that cuckoo search algorithm performed better than classical echo state network, particle swarm optimization and binary particle.…”

Section: Literature Surveymentioning

confidence: 99%

A survey on Cuckoo Search Algorithm for Optimization Problems

Verma¹,

Kumar²

2021

Preprint

View full text Add to dashboard Cite

show abstract

Section: Literature Surveymentioning

confidence: 99%

A survey on Cuckoo Search Algorithm for Optimization Problems

Verma¹,

Kumar²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The method was tested on the RUL prediction of turbofan engines and was better than the classical ESN. Moreover, cuckoo search optimization was used to optimize the ESN [22], [23]. The method was found to outclass classical ESN and other methods.…”

Section: Related Workmentioning

confidence: 99%

“…Thus, causing the linear regression to take a longer time. This is because it often involves either the multiplication of larger matrices and finding its inverse, its Singular Value Decomposing (SVD), or QR [20] 949.58 ± 78.82 313.68 BPSO [18] 277.60 ± 10.27 680.93 GOA [13] 292.66 ± 56.06 45.93 CS [23] 226.36 ± 8.04 176.89 DE [24] 233.86 ± 14.95 15.07 LSTM [10] 284.89 ± 146.60 3.56 Proposed 208.90 ± 10.61 37.83…”

Section: Challenges Of Esnmentioning

confidence: 99%

“…38 13.07 PSO [20] 812.05 ± 31.33 797.87 BPSO [18] 475.18 ± 4.53 1708.44 GOA [13] 856.84 ± 714.88 248.91 CS [23] 435.08 ± 3.42 285.91 DE [24] 435. 43 44 5.29 PSO [20] 953.00 ± 44.02 320.78 BPSO [18] 968.70 ± 199.83 681.01 GOA [13] 474.09 ± 117.44 56.45 CS [23] 265.79 ± 9.53 126.77 DE [24] 257.87 ± 22.32 8.35 LSTM [10] 544. 14 [40] 1275.31 ± 1092.…”

Section: Fd002mentioning

confidence: 99%

“…14 [40] 1275.31 ± 1092. 98 13.03 PSO [20] 1017.88 ± 28.49 800.23 BPSO [18] 522.03 ± 7.19 1683.29 GOA [13] 737.61 ± 285.27 226.38 CS [23] 452.15 ± 3.98 649.53 DE [24] 452.13 ± 3.66 161.71 LSTM [10] 1297.05 ± 254. 20 decomposition.…”

Section: Fd002mentioning

confidence: 99%

See 2 more Smart Citations

An Improved Grasshopper Optimization Algorithm Based Echo State Network for Predicting Faults in Airplane Engines

et al. 2020

Self Cite

View full text Add to dashboard Cite

In today's age of industrialization, sensor devices installed on equipment generate a vast amount of data. One of the engineers' main jobs is utilizing these data to provide better solutions to industrial problems. This availability of extensive data partly led to the creation of predictive maintenance (PdM). In PdM, existing and previous conditions of devices are used to predict their future behavior for optimal maintenance. Most of these PdM approaches are typical time-series predictions. Machine learning tools like Recurrent Neural Networks (RNNs) are excellent tools for time-series predictions. However, most RNNs suffer from training issues due to the unstable gradient problem. Thus, networks such as the Echo State Network (ESN), were designed to solve them. The ESN solves the gradient problem by training only the output weights using simple linear regression. Despite this ease, the selection of ESN parameters and topology is a considerable design challenge. This problem is often formulated as a typical optimization problem. Metaheuristic algorithms are known to be excellent tools for solving optimization problems. Hence, in this work, we design an improved Grasshopper Optimization Algorithm (GOA) based ESN. The proposed technique uses a new solution representation with a simplified attraction and repulsion mechanisms to enhance performance. Our target application is to predict the Remaining Useful Life (RUL) of turbofan engines. The method outperforms the Cuckoo Search (CS), Differential Evolution (DE), Particle Swarm Optimization (PSO), Binary PSO (BPSO), the original GOA, the classical ESN, deep ESN, and LSTM. We have provided all implemented codes and data at the GitHub repository.

show abstract