Implementations of the subject technology provide object detection and/or classification for electronic devices. Object detection and/or classification can be performed using a radar sensor of an electronic device. The electronic device may be a portable electronic device. In some examples, object classification using a radar sensor can be based on an identification of user motion using radar signals and/or based on extraction of surface features from the radar signals. In some examples, object classification using a radar sensor can be based on time-varying surface features extracted from the radar signals. Surface features that can be extracted from the radar signals include a radar cross-section (RCS), a micro-doppler signal, a range, and/or one or more angles associated with one or more surfaces of the object.

Implementations of the subject technology provide object detection and/or classification for electronic devices. Object detection and/or classification can be performed using a radar sensor of an electronic device. The electronic device may be a portable electronic device. In some examples, object classification using a radar sensor can be based on an identification of user motion using radar signals and/or based on extraction of surface features from the radar signals. In some examples, object classification using a radar sensor can be based on time-varying surface features extracted from the radar signals. Surface features that can be extracted from the radar signals include a radar cross-section (RCS), a micro-doppler signal, a range, and/or one or more angles associated with one or more surfaces of the object.

A system and method for predicting mild cognitive impairment (MCI) related diagnosis and prognosis utilizing deep learning. More specifically, the system and method produce predictions of MCI conversions to Alzheimer's/dementia and prognosis related thereof. Using available medical imaging and non-imaging data a diagnosis and prognosis model is a deep learned model trained using transfer learning. An MCI-DAP server may then receive a request from a clinician to process predictions related to a target patient's diagnosis or prognosis. The target patient's medical data is retrieved and used to create a model for the target patient. Then details of the target patient's model and the diagnosis and prognosis model are compared, a prediction is generated, and the prediction is returned to the clinician. As new medical data becomes available it is fed into the respective model to improve accuracy and update predictions.

A system may include a transmitter node and a receiver node. Each node may include a communications interface including at least one antenna element and a controller operatively coupled to the communications interface, the controller including one or more processors, wherein the controller has information of own node velocity and own node orientation. Each node of the transmitter node and the receiver node may be in motion. Each node may be time synchronized to apply Doppler corrections associated with said node's own motions relative to a common reference frame. The common reference frame may be known to the transmitter node and the receiver node prior to the transmitter node transmitting signals to the receiver node and prior to the receiver node receiving the signals from the transmitter node.

A system may include a transmitter node and a receiver node. Each node may include a communications interface including at least one antenna element and a controller operatively coupled to the communications interface, the controller including one or more processors, wherein the controller has information of own node velocity and own node orientation. Each node of the transmitter node and the receiver node may be in motion. Each node may be time synchronized to apply Doppler corrections associated with said node's own motions relative to a common reference frame. The common reference frame may be known to the transmitter node and the receiver node prior to the transmitter node transmitting signals to the receiver node and prior to the receiver node receiving the signals from the transmitter node.

A method for estimating a spin of a projectile, the method comprising obtaining a first data series representing a radial velocity of a projectile over time in accordance with a radar signal reflected from the projectile, subtracting a center velocity of the first data series from the first data series to form a second data series representing a variation of the radial velocity of the projectile around the center velocity over time, dividing the second data series into respective time intervals, estimating, for each of the time intervals of the second data series, a frequency of the variation of the radial velocity of the projectile around the center velocity, and determining a spin of the projectile based on the estimated frequencies of the variation of the radial velocity of the projectile.

A method for estimating a spin of a projectile, the method comprising obtaining a first data series representing a radial velocity of a projectile over time in accordance with a radar signal reflected from the projectile, subtracting a center velocity of the first data series from the first data series to form a second data series representing a variation of the radial velocity of the projectile around the center velocity over time, dividing the second data series into respective time intervals, estimating, for each of the time intervals of the second data series, a frequency of the variation of the radial velocity of the projectile around the center velocity, and determining a spin of the projectile based on the estimated frequencies of the variation of the radial velocity of the projectile.

A system and method for quantifying Alzheimer's disease (AD) risk using one or more interferometric micro-Doppler radars (IMDRs) and deep learning artificial intelligence to distinguish between cognitively unimpaired individuals and persons with AD based on gait analysis. The system utilizes IMDR to capture signals from both radial and transversal movement in three-dimensional space to further increase the accuracy for human gait estimation. New deep learning technologies are designed to complement traditional machine learning involving separate feature extraction followed-up with classification to process radar signature from different views including side, front, depth, limbs, and whole body where some motion patterns are not easily describable. The disclosed cross-talk deep model is the first to apply deep learning to learn IMDR signatures from two perpendicular directions jointly from both healthy and unhealthy individuals. Decision fusion is used to integrate classification results from feature-based classifier and deep learning AI to reach optimal decision.

A system and method for quantifying Alzheimer's disease (AD) risk using one or more interferometric micro-Doppler radars (IMDRs) and deep learning artificial intelligence to distinguish between cognitively unimpaired individuals and persons with AD based on gait analysis. The system utilizes IMDR to capture signals from both radial and transversal movement in three-dimensional space to further increase the accuracy for human gait estimation. New deep learning technologies are designed to complement traditional machine learning involving separate feature extraction followed-up with classification to process radar signature from different views including side, front, depth, limbs, and whole body where some motion patterns are not easily describable. The disclosed cross-talk deep model is the first to apply deep learning to learn IMDR signatures from two perpendicular directions jointly from both healthy and unhealthy individuals. Decision fusion is used to integrate classification results from feature-based classifier and deep learning AI to reach optimal decision.

A system may include a mobile ad-hoc network (MANET) including a plurality of nodes. Each of the plurality of nodes is configured to transmit communication data packets and transmit beacons. Each of the plurality of nodes has passive spatial awareness. A first node has information of own node velocity, own node orientation, and a destination. The first node may be configured to: calculate a direct line or an arc from the first node to the destination; utilize passive spatial awareness; assess possible relay routes beyond the communication range and within the beacon range of the first node; determine a next relay node that is on one of the possible relay routes wherein the one of the possible relay routes may be closest to the direct line or the arc without being determined to be part of a dead-end route; and transmit a communication data packet to the next relay node.