Lightning Whistler Wave Speech Recognition Based on Grey Wolf Optimization Algorithm

Abstract

The recognition algorithm of the lightning whistler wave, based on intelligent speech, is the key technology to break the bottleneck of massive data and study the temporal and spatial variation rules of the lightning whistler wave. However, its recognition effect depends on the hyperparameters determined by manual experiments repeatedly, which takes a great deal of time and cannot guarantee the best recognition effect of the model. Therefore, we proposed the lightning whistler wave recognition algorithm based on grey wolf optimization (GWO). In this paper, the GWO algorithm is used to automatically find the best value of hyperparameters of Long Short-Term Memory (LSTM) in their limited searching space. Here we consider the number of hidden units (hu) and learning rate (lr) as the hyperparameters to be optimized, and the spatial coordinate (hu, lr) as the grey wolf position. By the end of the GWO process, we obtain the position of the wolf king α with the optimal hu and lr searched by the GWO algorithm. Then we use the optimal hu and lr to configure LSTM and perform supervised learning on the train set to obtain the final lightning whistler wave speech recognition model. Through experimental verification, the recognition model based on the GWO not only overcomes the uncertainty of the traditional model relying on manual finetuning of parameters and realizes the mechanism of automatic search and acquisition of hyperparameters, but also its recognition effect improves by about 2% in accuracy, F1score, and other metrics compared with the model trained by manually setting hyperparameters.

Research on Dynamic Economic Dispatch Optimization Problem Based on Improved Grey Wolf Algorithm

“…Ge et al [19] used an improved GWO to optimize the UAV path-planning problem in an oilfield environment and achieved satisfactory results. Wang et al [20] used a discrete GWO to solve the stacking problem, which effectively solved this problem and surpassed most of the previously reported metaheuristics; Yuan et al [21] used GWO to solve the lightning whistle acoustic voice recognition problem, and the accuracy of its recognition results was 2% higher compared to the common recognition methods. Dokur et al [22] used GWO to solve a short-term wind speed-prediction problem with a multilayer perceptron, and the results showed that the algorithm was more effective than other algorithms.…”

“…The critical treatment or the random treatment within the boundary is generally used, and the critical proximity treatment is used for these constraints in this study. To facilitate the processing, a new boundary constraint is formed as shown in Formulas (20) and (21).…”

A novel modeling approach for the magnetorheological brake system based on improved LSTM

“…However, it is a huge challenge to choose suitable hyperparameters without fixed theoretical guidance, and hence manual adjustment would be carried out over a long time and high cost and the optimal solution may not be obtained. Therefore, an intelligent optimization algorithm was proposed to solve this problem such as the whale optimization algorithm [25], differential evolution algorithm [26] and particle swarm optimization (PSO) algorithm [27], wolf optimization algorithm [28,29].…”