Machine-Learning Detection Algorithms for Large Barkhausen Jumps in Cluttered Environment

Modern magnetic sensor arrays conventionally use state-of-the-art low-power magnetometers such as parallel and orthogonal fluxgates. Low-power fluxgates tend to have large Barkhausen jumps that appear as a dc jump in the fluxgate output. This phenomenon deteriorates the signal fidelity and effectively increases the internal sensor noise. Even if sensors that are more prone to dc jumps can be screened out during production, the conventional noise measurement does not always catch the dc jumps because of their sparsity. Moreover, dc jumps persist in almost all the sensor cores although at a slower but still intolerable rate. Even if dc jumps could be easily detected in a shielded environment, when deployed in the presence of natural noise and clutter, it can be hard to positively detect them. This letter fills this gap and presents algorithms that distinguish dc jumps embedded in natural magnetic field data. To improve resistance to noise, we developed two machine-learning algorithms that employ temporal and statistical physical-based features of a preacquired and well-known experimental dataset. The first algorithm employs a support vector machine classifier, while the second is based on a neural network architecture. We compare these new approaches to a more classical kernel-based method. To that purpose, the receiver operating characteristic curve is generated, which allows diagnosis ability of the different classifiers by comparing their performances across various operation points. The accuracy of the machine-learning-based algorithms over the classic method and the rapid convergence of the corresponding receiver operating characteristic curves are demonstrated.