Deep Learning for Magnetic Field Estimation

The efficiency of the metal detection method using deep learning with data obtained from multiple magnetic impedance (MI) sensors was investigated. The MI sensor is a passive sensor that detects metal objects and magnetic field changes. However, when detecting a metal object, the amount of change in the magnetic field caused by the metal is small and unstable with noise. Consequently, there is a limit to the detectable distance. To effectively detect and analyze this distance, a method using deep learning was applied. The detection performances of a convolutional neural network (CNN) and a recurrent neural network (RNN) were compared from the data extracted from a self-impedance sensor. The RNN model showed better performance than the CNN model. However, in the shallow stage, the CNN model was superior compared to the RNN model. The performance of a deep-learning-based (DLB) metal detection network using multiple MI sensors was compared and analyzed. The network was detected using long short-term memory and CNN. The performance was compared according to the number of layers and the size of the metal sheet. The results are expected to contribute to sensor-based DLB detection technology.

Download Full-text

Deep Learning for Fingerprint Localization in Indoor and Outdoor Environments

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi9040267 ◽

2020 ◽

Vol 9 (4) ◽

pp. 267 ◽

Cited By ~ 2

Author(s):

Da Li ◽

Yingke Lei ◽

Xin Li ◽

Haichuan Zhang

Keyword(s):

Magnetic Field ◽

Deep Learning ◽

Clustering Algorithm ◽

Fingerprint Image ◽

Density Peak ◽

Localization Accuracy ◽

Localization System ◽

Outdoor Environments ◽

Indoor And Outdoor Environments ◽

Indoor And Outdoor

Wi-Fi and magnetic field fingerprinting-based localization have gained increased attention owing to their satisfactory accuracy and global availability. The common signal-based fingerprint localization deteriorates due to well-known signal fluctuations. In this paper, we proposed a Wi-Fi and magnetic field-based localization system based on deep learning. Owing to the low discernibility of magnetic field strength (MFS) in large areas, the unsupervised learning density peak clustering algorithm based on the comparison distance (CDPC) algorithm is first used to pick up several center points of MFS as the geotagged features to assist localization. Considering the state-of-the-art application of deep learning in image classification, we design a location fingerprint image using Wi-Fi and magnetic field fingerprints for localization. Localization is casted in a proposed deep residual network (Resnet) that is capable of learning key features from a massive fingerprint image database. To further enhance localization accuracy, by leveraging the prior information of the pre-trained Resnet coarse localizer, an MLP-based transfer learning fine localizer is introduced to fine-tune the coarse localizer. Additionally, we dynamically adjusted the learning rate (LR) and adopted several data enhancement methods to increase the robustness of our localization system. Experimental results show that the proposed system leads to satisfactory localization performance both in indoor and outdoor environments.

Download Full-text

Magnetic Field Analysis of Surface-Mounted Permanent-Magnet Motors

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.52-54.285 ◽

2011 ◽

Vol 52-54 ◽

pp. 285-290

Author(s):

Yi Chang Wu ◽

Feng Ming Ou ◽

Bo Wei Lin

Keyword(s):

Magnetic Field ◽

Permanent Magnet ◽

Magnetic Circuit ◽

Circuit Model ◽

Field Analysis ◽

Permanent Magnet Motors ◽

Element Analysis ◽

Magnetic Field Analysis ◽

Field Estimation ◽

The Magnetic Field

The prediction of the magnetic field is a prerequisite to investigate the motor performance. This paper focuses on the magnetic field estimation of surface-mounted permanent-magnet (SMPM) motors based on two approximations, i.e., the magnetic circuit analysis and the finite-element analysis (FEA). An equivalent magnetic circuit model is applied to analytically evaluate the magnetic field of a SMPM motor with exterior-rotor configuration. The two-dimensional FEA is then applied to numerically calculate the magnetic field and to verify the validity of the magnetic circuit model. The results show that the errors between the analytical predictions and FEA results are less than 6%. It is of benefit to further design purposes and optimization of SMPM motors.

Download Full-text

Solar flare forecasting model using 3D magnetic field data

10.5194/egusphere-egu2020-13298 ◽

2020 ◽

Author(s):

Xin Huang

Keyword(s):

Magnetic Field ◽

Deep Learning ◽

Solar Flare ◽

Solar Flares ◽

Field Data ◽

Active Regions ◽

Forecasting Model ◽

Magnetic Field Data ◽

The Magnetic Field

<p>Solar flares originate from the release of the energy stored in the magnetic field of solar active regions. Generally, the photospheric magnetograms of active regions are used as the input of the solar flare forecasting model. However, solar flares are considered to occur in the low corona. Therefore, the role of 3D magnetic field of active regions in the solar flare forecast should be explored. We extrapolate the 3D magnetic field using the potential model for all the active regions during 2010 to 2017, and then the deep learning method is applied to extract the precursors of solar flares in the 3D magnetic field data. We find that the 3D magnetic field of active regions is helpful to build a deep learning based forecasting model.</p>

Download Full-text

A Deep Learning Technique for Automated Detection of ULF Waves in Swarm Time Series

10.5194/egusphere-egu2020-8796 ◽

2020 ◽

Author(s):

Alexandra Antonopoulou ◽

Constantinos Papadimitriou ◽

Georgios Balasis ◽

Adamantia Zoe Boutsi ◽

Konstantinos Koutroumbas ◽

...

Keyword(s):

Magnetic Field ◽

Deep Learning ◽

Building Blocks ◽

Data Availability ◽

Topside Ionosphere ◽

Ulf Waves ◽

Dense Layer ◽

Ulf Wave ◽

The Earth ◽

Swarm Satellites

<p>Ultra-low frequency (ULF) magnetospheric plasma waves play a key role in the dynamics of the Earth&#8217;s magnetosphere and, therefore, their importance in Space Weather studies is indisputable. Magnetic field measurements from recent multi-satellite missions (e.g. Cluster, THEMIS, Van Allen Probes and Swarm) are currently advancing our knowledge on the physics of ULF waves. In particular, Swarm satellites, one of the most successful mission for the study of the near-Earth electromagnetic environment, have contributed to the expansion of data availability in the topside ionosphere, stimulating much recent progress in this area. Coupled with the new successful developments in artificial intelligence (AI), we are now able to use more robust approaches devoted to automated ULF wave event identification and classification. The goal of this effort is to use a deep learning method in order to classify ULF wave events using magnetic field data from Swarm. We construct a Convolutional Neural Network (CNN) that takes as input the wavelet spectra of the Earth&#8217;s magnetic field variations per track, as measured by each one of the three Swarm satellites, and whose building blocks consist of two convolution layers, two pooling layers and a fully connected (dense) layer, aiming to classify ULF wave events in four different categories: 1) Pc3 wave events (i.e., frequency range 20-100 MHz), 2) non-events, 3) false positives, and 4) plasma instabilities. Our primary experiments show promising results, yielding successful identification of more than 95% accuracy. We are currently working on producing larger training/test datasets, by analyzing Swarm data from the mid-2014 onwards, when the final constellation was formed, aiming to construct a dataset comprising of more than 50000 wavelet image inputs for our network.</p>

Download Full-text

Deep-Learning-Based Accelerated and Noise-Suppressed Estimation (DANSE) of quantitative Gradient Recalled Echo (qGRE) MRI metrics associated with Human Brain Neuronal Structure and Hemodynamic Properties

10.1101/2021.09.10.459810 ◽

2021 ◽

Author(s):

Sayan Kahali ◽

Satya V.V.N. Kothapalli ◽

Xiaojian Xu ◽

Ulugbek S Kamilov ◽

Dmitriy A Yablonskiy

Keyword(s):

Magnetic Field ◽

Deep Learning ◽

Noise Suppression ◽

Ground Truth ◽

Least Square ◽

Biophysical Model ◽

Neuronal Structure ◽

Brain Maps ◽

Computational Speed ◽

Phase Images

Purpose: To introduce a Deep-Learning-Based Accelerated and Noise-Suppressed Estimation (DANSE) method for reconstructing quantitative maps of biological tissue cellular-specific, and hemodynamic-specific, from Gradient-Recalled-Echo (GRE) MRI data with multiple gradient-recalled echoes. Methods: DANSE method adapts supervised learning paradigm to train a convolutional neural network for robust estimation of and maps free from the adverse effects of macroscopic (B0) magnetic field inhomogeneities directly from the GRE magnitude images without utilizing phase images. The corresponding ground-truth maps were generated by means of a voxel-by-voxel fitting of a previously-developed biophysical quantitative GRE (qGRE) model accounting for tissue, hemodynamic and -inhomogeneities contributions to GRE signal with multiple gradient echoes using nonlinear least square (NLLS) algorithm. Results: We show that the DANSE model efficiently estimates the aforementioned brain maps and preserves all features of NLLS approach with significant improvements including noise-suppression and computation speed (from many hours to seconds). The noise-suppression feature of DANSE is especially prominent for data with SNR characteristic for typical GRE data (SNR~50), where DANSE-generated and maps had three times smaller errors than that of NLLS method. Conclusions: DANSE method enables fast reconstruction of magnetic-field-inhomogeneity-free and noise-suppressed quantitative qGRE brain maps. DANSE method does not require any information about field inhomogeneities during application. It exploits spatial patterns in the qGRE MRI data and previously-gained knowledge from the biophysical model, thus producing clean brain maps even in the environments with high noise levels. These features along with fast computational speed can lead to broad qGRE clinical and research applications.

Download Full-text