Magnetometer calibration improvement using wavelet and genetic algorithm

Hu, Xiangchao; Pang, Hongfeng; Fu, Liangrui; Pan, Mengchun

doi:10.1002/tee.22345

Cited by 3 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ASLC model [6] has been raised to decrease the spending time of the manual singing label calibration process [7]. It takes both the singing and the coarse labels as the input to estimate the accurate labels, as shown in Fig.…”

Section: Related Workmentioning

confidence: 99%

“…We utilize the fully convolutional neural network (FCNN) [6] as the predictive function

F

. This FCNN mainly can be divided into two parts: a feature extractor and a predictor, as shown in Fig.…”

Section: Approachmentioning

confidence: 99%

“…But the available data are insufficient to train a perfect AST model such that human annotators are required to calibrate the automatically transcribed labels [5]. To accelerate the manual calibration process, the automatic singing label calibration (ASLC) model [6] has been proposed. Different from the AST model, the ASLC model takes advantage of the coarse labels (coarse singing annotations) which are pre‐generated from the corresponding musical annotation and LyRiCs (LRC) file as an extra input to enhance the neural networks (in the real‐world applications, the musical notation and LRC file are collected from the web [7]).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Transfer Learning Using Musical Instrument Audio for Improving Automatic Singing Label Calibration

Fu,

Rui,

Deng

et al. 2024

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

Automatic Singing Label Calibration (ASLC) aims to enhance the labeling accuracy of coarse singing labels through the analysis of raw audio. However, the ASLC model faces limitations due to the challenges and costs associated with generating or augmenting real‐world songs. To address this problem, we propose a novel approach to strengthen limited singing audio using easily available musical instrument audio. Directly using the musical instrument audio as a data augmentation for the singing audio is unreliable due to the distinct differences between vocal and instrumental sounds. Therefore, we employ transfer learning, which allows relevant knowledge to be transferred from one domain to another. In the pre‐training stage, the ASLC model learns to predict the accurate labels from the musical instrument audio. We then consider the vocal as a special musical instrument and fine‐tune the pretrained ASLC model using a singing annotation data set. Experimental results demonstrate that our transfer learning‐based approach outperforms the original ASLC model. By leveraging the readily available musical instrument audio, our method achieves improved performance in enhancing the labeling accuracy of singing audio. © 2024 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC.

show abstract

Section: Related Workmentioning

confidence: 99%

“…We utilize the fully convolutional neural network (FCNN) [6] as the predictive function

F

. This FCNN mainly can be divided into two parts: a feature extractor and a predictor, as shown in Fig.…”

Section: Approachmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Transfer Learning Using Musical Instrument Audio for Improving Automatic Singing Label Calibration

Fu,

Rui,

Deng

et al. 2024

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

show abstract

“…Therefore, for measuring attitude of high-speed rotating projectiles, special working conditions, i.e., high temperature, high pressure, high overload, and high speed, as well as the requirements of low cost and small size preclude the use of many sensors. The magnetometer can be widely used in attitude estimation of rotating objects [12,13,14,15,16,17,18] after undergoing a calibration and compensation process [19,20,21], thanks to its features of reliable performance, low cost, and no error accumulation.…”

Section: Introductionmentioning

confidence: 99%

A Novel Method for Estimating Pitch and Yaw of Rotating Projectiles Based on Dynamic Constraints

An¹,

Wang

Liu

et al. 2019

Sensors

View full text Add to dashboard Cite

This paper addresses the difficult problem of measuring the attitude of a high-spinning projectile and presents a novel method for estimating the pitch and yaw angles of the projectile in flight. The method is based on analysis of the external moment of the rotating projectile during flight and theoretical derivations obtained from the dynamics’ equations. First, the principle of zero-crossing method is introduced, which explains the process of geomagnetic azimuth and roll measurements by the non-orthogonal geomagnetic sensor combination. Then, the dynamics constraint equations between the Euler angles and flight-path angle, trajectory deflection angle of the projectile are derived using the dynamics equations of the projectile rotating around the centroid, and analysis of the flight characteristics of the projectile in stable flight. Next, the spatial orientation relationship between pitch, yaw angles and magnetic azimuth is established based on the physical principle of geomagnetic azimuth. Finally, the pitch and yaw angles are estimated using the unscented Kalman filter (UKF), with the dynamics constraint equations serving as the driving equations. In the UKF prediction stage, the Runge-Kutta method is used to discretize the state equation that improves the prediction accuracy. Simulation results show that the proposed method can be used to accurately calculate the pitch and yaw angles, and results of experimental data processing also verify the feasibility of the proposed method for real-world applications.

show abstract

“…Zhang et al 7 presented a perfect offline estimation algorithm. In the study of Hu and Pang, 8 a genetic algorithm is proposed to calibrate the magnetometer error, and wavelets are proposed for noise cancellation. These two algorithms are considered to be effective for the calibration of the magnetometer.…”

Section: Introductionmentioning

confidence: 99%

Two-Step Adaptive Augmented Unscented Kalman Filter for Roll Angles of Spinning Missiles Based on Magnetometer Measurements

Yan

Chen

Tian

2018

Measurement and Control

View full text Add to dashboard Cite

It is critical to measure the roll angle of a spinning missile quickly and accurately. Magnetometers are commonly used to implement these measurements. At present, the estimation of roll angle parameters is usually performed with the unscented Kalman filter algorithm. In this paper, the two-step adaptive augmented unscented Kalman filter algorithm is proposed to calibrate the biaxial magnetometer and circuit measurements quickly, which allows accurate estimates of the missile roll angle. Unlike the existing algorithms, the state vector of the algorithm is based on the missile roll angle parameters and the error factors caused by the magnetometer and the measurement circuit errors. Next, a two-step fast fitting algorithm is used to fit the initial value. After satisfying the stop rule, the state vector of the filter is configured to estimate the roll angle parameters and the calibration parameters. This method is evaluated by running numerous simulations. In the experiment, the algorithm completes the calibration of the magnetometer and the measurement circuit 1 s after the missile launches, with a sampling rate of 1 ms and an output roll attitude angle with a 0.0015 rad precision. The conventional unscented Kalman filter algorithm requires more time to achieve such a high accuracy. The simulation results demonstrate that the proposed two-step augmented unscented Kalman filter outperforms the conventional unscented Kalman filter in its estimation accuracy and convergence characteristics.

show abstract

Magnetometer calibration improvement using wavelet and genetic algorithm

Cited by 3 publications

References 23 publications

Transfer Learning Using Musical Instrument Audio for Improving Automatic Singing Label Calibration

Transfer Learning Using Musical Instrument Audio for Improving Automatic Singing Label Calibration

A Novel Method for Estimating Pitch and Yaw of Rotating Projectiles Based on Dynamic Constraints

Two-Step Adaptive Augmented Unscented Kalman Filter for Roll Angles of Spinning Missiles Based on Magnetometer Measurements

Contact Info

Product

Resources

About