In some implementations, an angle sensor may receive a first x-component value and a first y-component value from a first set sensing elements and a second x-component value and a second y-component value from a second set of angle sensing elements. The angle sensor may perform a safety check including determining a first range of angles associated with a target object based on a relationship between a magnitude of the first x-component value and a magnitude of the first y-component value; determining a second range of angles associated with the target object based on a relationship between a magnitude of the second x-component value and a magnitude of the second y-component value; and determining whether the second range of angles is a subset of the first range of angles. The angle sensor may output an indication of a result of the safety check.

Systems and methods are provided for improving statistical and machine learning drift detection models that monitor computing health of a data center environment. For example, the system can receive streams of sensor data from a plurality of sensors in a data center; clean the streams of sensor data; generate, using a machine learning (ML) model, an anomaly score and a dynamic threshold value based on the cleaned streams of sensor data; determine, using the ML model and based on the anomaly score and the dynamic threshold value, a correctness indicator for a first sensor in the plurality of sensors; and using the correctness indicator, correct the first sensor.

A denoising apparatus, including a Micro-Electro-Mechanical System, MEMS, sensor circuit, which is configured to generate a measurement signal in response to a physical quantity. The measurement signal includes a useful signal component indicative of the physical quantity and an attack signal component due to an attack on the MEMS sensor circuit. The denoising apparatus further includes a machine learning circuitry, which is configured to estimate the useful signal component based on the measurement signal. The machine learning circuitry is trained based on training signals comprising known useful signal components and known attack signal components.

A denoising apparatus, including a Micro-Electro-Mechanical System, MEMS, sensor circuit, which is configured to generate a measurement signal in response to a physical quantity. The measurement signal includes a useful signal component indicative of the physical quantity and an attack signal component due to an attack on the MEMS sensor circuit. The denoising apparatus further includes a machine learning circuitry, which is configured to estimate the useful signal component based on the measurement signal. The machine learning circuitry is trained based on training signals comprising known useful signal components and known attack signal components.

Methods and apparatus for prosing a sensor IC package having first and second sets of magnetic field sensing elements and a third set of magnetic field sensing elements located between the first and second positions, wherein the first, second, and third sets of magnetic field sensing elements have a first axis of sensitivity and a second axis of sensitivity, wherein the first and second axes of sensitivity are orthogonal. The sensor IC package is positioned in relation to a target comprising a two-pole magnet and the first and second axes of sensitivity are perpendicular to an axis about which the target rotates. Differential signals are processed to determine an absolute position of the target. A first secondary angle position is generated from the first and third sets of magnetic field sensing elements.

Embodiments determine anomalies in sensor data generated by a sensor by receiving an evaluation time window of clean sensor data generated by the sensor. Embodiments receive a threshold value for determining anomalies. When the clean sensor data has a cyclic pattern, embodiments divide the evaluation time window into a plurality of segments of equal length, wherein each equal length comprises the cyclic pattern. When the clean sensor data does not have the cyclic pattern, embodiments divide the evaluation time window into a pre-defined number of plurality of segments of equal length. Embodiments convert the evaluation time window and each of the plurality of segments into corresponding curves using Kernel Density Estimation (“KDE”). For each of the plurality of segments, embodiments determine a Kullback-Leibler (“KL”) divergence value between corresponding curves of the segment and the evaluation time window to generate a plurality of KL divergence values.

Embodiments determine anomalies in sensor data generated by a sensor by receiving an evaluation time window of clean sensor data generated by the sensor. Embodiments receive a threshold value for determining anomalies. When the clean sensor data has a cyclic pattern, embodiments divide the evaluation time window into a plurality of segments of equal length, wherein each equal length comprises the cyclic pattern. When the clean sensor data does not have the cyclic pattern, embodiments divide the evaluation time window into a pre-defined number of plurality of segments of equal length. Embodiments convert the evaluation time window and each of the plurality of segments into corresponding curves using Kernel Density Estimation (“KDE”). For each of the plurality of segments, embodiments determine a Kullback-Leibler (“KL”) divergence value between corresponding curves of the segment and the evaluation time window to generate a plurality of KL divergence values.

In one aspect, an integrated circuit (IC) includes a magnetic-field sensor. The magnetic field sensor includes a first and second magnetoresistance circuitries configured to receive a magnetic field signal from a target and convert the magnetic field signal received to a first signal and second signal; analog circuitry configured to receive the first and second signals; digital circuitry configured to receive a first and second analog output signals from analog circuitry and to convert the first and second analog output signals to a first and second digital signals representing a first and second channel output signals; and diagnostic circuitry configured to receive, from the digital circuitry, an input signal related to a separation of the first and second channel output signals, and configured to provide a test signal at a pin of the IC indicating whether a distance between the IC and the target complies with at least one rule.

Systems and methods herein use a sensing circuit to detect an overvoltage at a voltage node as a drain current. A current-mode comparator converts the detected current into a control signal, which is provided to a control circuit. The control circuit uses the control signal cut of a bias current to turn off switches in a protection circuit to create a high-impedance electrical path between the voltage node and the to-be-protected voltage node.

Systems and methods herein use a sensing circuit to detect an overvoltage at a voltage node as a drain current. A current-mode comparator converts the detected current into a control signal, which is provided to a control circuit. The control circuit uses the control signal cut of a bias current to turn off switches in a protection circuit to create a high-impedance electrical path between the voltage node and the to-be-protected voltage node.