Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: weighted fusion

Sortuj według:

Ogranicz wyniki do:

A feedback weighted fusion algorithm with dynamic sensor bias correction for gyroscope array

Yuan Ding, Qin Yongyuan, Shen Xiaowei, Wu Zongwei

Metrology and Measurement Systems

2021

Vol. 28, nr 1

161--179

Low-cost Micro-Electromechanical System (MEMS) gyroscopes are known to have a smaller size, lower weight, and less power consumption than their more technologically advanced counterparts. However, current low-grade MEMS gyroscopes have poor performance and cannot compete with quality sensors in high accuracy navigational and guidance applications. The main focus of this paper is to investigate performance improvements by fusing multiple homogeneous MEMS gyroscopes. These gyros are transformed into a virtual gyro using a feedback weighted fusion algorithm with dynamic sensor bias correction. The gyroscope array combines eight homogeneous gyroscope units on each axis and divides them into two layers of differential configuration. The algorithm uses the gyroscope array estimation value to remove the gyroscope bias and then correct the gyroscope array measurement value. Then the gyroscope variance is recalculated in real time according to the revised measurement value and the weighted coefficients and state estimation of each gyroscope are deduced according to the least square principle. The simulations and experiments showed that the proposed algorithm could further reduce the drift and improve the overall accuracy beyond the performance limitations of individual gyroscopes. The maximum cumulative angle error was -2.09 degrees after 2000 seconds in the static test, and the standard deviation (STD) of the output fusion value of the proposed algorithm was 0.006 degrees/s in the dynamic test, which was only 1.7% of the STD value of an individual gyroscope.

An optimal spectroscopic feature fusion strategy for MR brain tumor classification using Fisher Criteria and Parameter-Free BAT optimization algorithm

Kaur T., Saini B. S., Gupta S.

Biocybernetics and Biomedical Engineering

2018

Vol. 38, no. 2

409--424

In the present work, a fused metabolite ratio is proposed that integrates the conventional metabolite ratios in a weighted manner to improve the diagnostic accuracy of glioma brain tumor categorization. Each metabolite ratio is weighted by the value generated by the Fisher and the Parameter-Free BAT (PFree BAT) optimization algorithm. Here, feature fusion is formulated as an optimization problem with PFree BAT optimization as its underlying search strategy and Fisher Criterion serving as a fitness function. Experiments were conducted on the magnetic resonance spectroscopy (MRS) data of 50 subjects out of which 27 showed low-grade glioma and rest presented high-grade. The MRS data was analyzed for the peaks. The conventional metabolite ratios, i.e., Choline/N-acetyl aspartate (Cho/NAA), Cho/Creatine (Cho/Cr), were quan-titated using peak integration that exhibited difference among the tumor grades. The difference in the conventional metabolite ratios was enhanced by the proposed fused metabolite ratio that was duly validated by metrics of sensitivity, specificity, and the classification accuracy. Typically, the fused metabolite ratio characterized low-grade and high-grade with a sensitivity of 96%, specificity of 91%, and an accuracy of 93.72% when fed to the K-nearest neighbor classifier following a fivefold cross-validation data partitioning scheme. The results are significantly better than that obtained by the conventional metabolites where an accuracy equal to 80%, 87%, and 89% was attained. Prominently, the results using the fused metabolite ratio show a surge of 4.7% in comparison to Cho/Cr + Cho/NAA + NAA/Cr. Moreover, the obtained results are better than the similar works reported in the literature.