Wyniki wyszukiwania - Biblioteka Nauki

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Acoustic Source Localization Using Kernel-based Extreme Learning Machine in Distributed Microphone Array

100%

Wang R. , Chen Z. , Yin F.

Archives of Acoustics

2021

tom Vol. 46, No. 1

67--78

Acoustic source localization using distributed microphone array is a challenging task due to the influences of noise and reverberation. In this paper, acoustic source localization using kernel-based extreme learning machine in distributed microphone array is proposed. Specifically, the space of interest is divided into some labeled positions, and the candidate generalized cross correlation function in each node is treated as the feature mapped into the hidden nodes of extreme learning machine. During the training phase, by the implementation of kernel function, the output weights of the classifier are calculated and do not need to be tuned. After the kernel-based extreme learning machine (K-ELM) is well trained, the measured generalized cross correlation data are fed into the K-ELM classifier, and the output is the estimated acoustic source position. The proposed method needs less human intervention for both training and testing and it does not need to calibrate the node in advance. Simulation and real-world experimental results reveal that the proposed method has extremely fast training and testing speeds, and can obtain better localization performance than steered response power, K-nearest neighbor, and support vector machine methods.

Analysis of the effect of seasonal changes on sensitive parameters of LAI based Penman–Monteith evapotranspiration model based on particle swarm algorithm

75%

Duan H. , He X. , Zhao H. , Jin X. , Xu H. , Wang R.

2023

tom Vol. 71, no. 2

1033--1043

The existing researches for leaf area index (LAI)-based Penman–Monteith evapotranspiration (ET) model (PML) are mostly carried out at yearly scale and the analysis of effects of seasonal change and different underlying surface conditions on model parameters is scarce. This study emphasizes on the influences of seasonal change and diverse land surface conditions on ET by optimizing the sensitive parameters, namely soil evaporation coefficient f and maximum stomatal conductance gsx, with particle swarm algorithm. This analysis is based on the observations of eight flux stations in China. The model performance is reasonable with a best Pearson r of 0.87. The seasonal calibration results indicate parameters change evidently in different seasons and have obvious spatial heterogeneity. The seasonal calibration method has an obvious effect on improving the ET accuracy in spring, which is mostly influenced by regional temperature and relative humidity. This study further demonstrates the need to dynamically adjust model parameters over time with PML model for evapotranspiration simulations, rather than simply setting these parameters to constants depended on subsurface conditions such as land use type.