Yaw/Heading optimization by Machine learning model based on MEMS magnetometer under harsh conditions

Hoang, Minh Long; Pietrosanto, Antonio

doi:10.1016/j.measurement.2022.111013

Cited by 11 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The system was designed by Python, a high-level, general-purpose programming language [31], based on ML library of Scikit-learn [32]. The integration of Scikit-learn to Python has been utilized in many ML applications effectively [33]- [35]. The proposed system can potentially speed up the large amount of data from the sensors [36]-[37] in health monitoring.…”

Section: Model Validation and Results Analysismentioning

confidence: 99%

K-centroid convergence clustering identification in one-label per type for disease prediction

Hoang,

Delmonte

2024

IJ-AI

View full text Add to dashboard Cite

Disease prediction is a high demand field which requires significant support from machine learning (ML) to enhance the result efficiency. The research works on application of K-means clustering supervised classification in disease prediction where each class only has one labeled data. The K-centroid convergence clustering identification (KC3I) system is based on semi-K-means clustering but only requires single labeled data per class for the training process with the training dataset to update the centroid. The KC3I model also includes a dictionary box to index all the input centroids before and after the updating process. Each centroid matches with a corresponding label inside this box. After the training process, each time the input features arrive, the trained centroid will put them to its cluster depending on the Euclidean distance, then convert them into the specific class name, which is coherent to that centroid index. Two validation stages were carried out and accomplished the expectation in terms of precision, recall, F1-score, and absolute accuracy. The last part demonstrates the possibility of feature reduction by selecting the most crucial feature with the extra tree classifier method. Total data are fed into the KC3I system with the most important features and remain the same accuracy.

show abstract

Section: Model Validation and Results Analysismentioning

confidence: 99%

K-centroid convergence clustering identification in one-label per type for disease prediction

Hoang,

Delmonte

2024

IJ-AI

View full text Add to dashboard Cite

show abstract

“…After a specified operation time, the obtained results drift away from the range of real angle estimation. In a bad case, the computed result can drift down about 50 degrees after 30 s [ 35 ].

where t i is the initial time of the heading rotation, t f is the stopped time and Δ t is the time loop.…”

Section: Methodsmentioning

confidence: 99%

“…After a specified operation time, the obtained results drift away from t range of real angle estimation. In a bad case, the computed result can drift down about degrees after 30 s [35].…”

Section: Nmni On Yaw Estimationmentioning

confidence: 99%

Fusion Filters between the No Motion No Integration Technique and Kalman Filter in Noise Optimization on a 6DoF Drone for Orientation Tracking

Hoang

Carratù

Paciello

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

The paper works on the new combination between the No Motion No Integration filter (NMNI) and the Kalman Filter (KF) to optimize the conducted vibration for orientation angles during drone operation. The drone’s roll, pitch, and yaw with just accelerometer and gyroscope were analyzed under the noise impact. A 6 Degree of Freedom (DoF) Parrot Mambo drone with Matlab/Simulink package was used to validate the advancements before and after fusing NMNI with KF. The drone propeller motors were controlled at a suitable speed level to keep the drone on the zero-inclination ground for angle error validation. The experiments show that KF alone successfully minimizes the variation for the inclination, but it still needs the NMNI support to enhance the performance in noise deduction, with the error only about 0.02°. In addition, the NMNI algorithm successfully prevents the yaw/heading from gyroscope drifting due to the zero-value integration during no rotation with the maximum error of 0.03°.

show abstract

“…On the other hand, Machine learning [ML] [ 18 , 19 , 20 ] approaches have demonstrated their high potential effectiveness in healthcare monitoring [ 21 ]. In [ 22 ], a support vector machine (SVM) model was implemented to predict the mental stress condition from the obtained heart rate.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Machine Learning Algorithms for Heartbeat Detection Based on Accelerometric Signals Produced by a Smart Bed

Hoang,

Matrella,

Ciampolini

2024

Sensors

View full text Add to dashboard Cite

This work aims to compare the performance of Machine Learning (ML) and Deep Learning (DL) algorithms in detecting users’ heartbeats on a smart bed. Targeting non-intrusive, continuous heart monitoring during sleep time, the smart bed is equipped with a 3D solid-state accelerometer. Acceleration signals are processed through an STM 32-bit microcontroller board and transmitted to a PC for recording. A photoplethysmographic sensor is simultaneously checked for ground truth reference. A dataset has been built, by acquiring measures in a real-world set-up: 10 participants were involved, resulting in 120 min of acceleration traces which were utilized to train and evaluate various Artificial Intelligence (AI) algorithms. The experimental analysis utilizes K-fold cross-validation to ensure robust model testing across different subsets of the dataset. Various ML and DL algorithms are compared, each being trained and tested using the collected data. The Random Forest algorithm exhibited the highest accuracy among all compared models. While it requires longer training time compared to some ML models such as Naïve Bayes, Linear Discrimination Analysis, and K-Nearest Neighbour Classification, it keeps substantially faster than Support Vector Machine and Deep Learning models. The Random Forest model demonstrated robust performance metrics, including recall, precision, F1-scores, macro average, weighted average, and overall accuracy well above 90%. The study highlights the better performance of the Random Forest algorithm for the specific use case, achieving superior accuracy and performance metrics in detecting user heartbeats in comparison to other ML and DL models tested. The drawback of longer training times is not too relevant in the long-term monitoring target scenario, so the Random Forest model stands out as a viable solution for real-time ballistocardiographic heartbeat detection, showcasing potential for healthcare and wellness monitoring applications.

show abstract

Yaw/Heading optimization by Machine learning model based on MEMS magnetometer under harsh conditions

Cited by 11 publications

References 24 publications

K-centroid convergence clustering identification in one-label per type for disease prediction

K-centroid convergence clustering identification in one-label per type for disease prediction

Fusion Filters between the No Motion No Integration Technique and Kalman Filter in Noise Optimization on a 6DoF Drone for Orientation Tracking

Comparison of Machine Learning Algorithms for Heartbeat Detection Based on Accelerometric Signals Produced by a Smart Bed

Contact Info

Product

Resources

About