Abstract: A method and associated apparatus for generating a neural network computation graph. The method includes receiving, by a compiler, a computation graph representing a neural network. The computation graph includes a plurality of nodes, each node associated with an operator of the neural network. The compiler receives a list of fusion patterns associated with a target hardware execution device, and analyzes the computation graph using the list of fusion patterns. The compiler generates one or more fused operators based on the analysis, each fused operator including at least two operators of the plurality of operators which can be fused. The compiler generates a new computation graph representing the neural network that includes at least a first fused operator of the generated one or more fused operators.

Abstract: An apparatus and method are disclosed for user and moving vehicle detection in which sensor data for a portable device is processed to determine whether the portable device is in a moving vehicle. Following a determination the portable device is in a moving vehicle, the sensor data is to characterize an association between the user and the portable device to determine whether the portable device is connected to the user. If the user is connected to the portable device, it is then determined if the portable device is being held in hand. If the portable device is held in hand, it is then determined if the user is operating the moving vehicle. Output from an image sensor of the portable device may be used in determining if the user is the operator.

Abstract: An apparatus and method are disclosed for characterizing motion of a platform. Motion sensor data from a portable device having a sensor assembly may be obtained. The portable device may be within the platform and tethered or untethered, and the mobility of the portable device may be constrained or unconstrained within the platform. Following a determination the platform is moving, motion dynamics of the portable device that are independent from motion dynamics of the platform may be identified and motion sensor data corresponding to motion of the platform and motion sensor data corresponding to the identified independent motion of the portable device may be separated from the obtained motion sensor data. Accordingly, motion sensor data corresponding to motion of the platform that is independent of motion of the portable device may be output. This may be used to derive operator analytics for assessing performance.

Abstract: An apparatus and method are disclosed for cart navigation using a portable device that is conveyed by the cart, but may be tethered or untethered and wherein mobility of the portable device may be constrained or unconstrained within the cart. The cart may be any apparatus propelled by on foot motion of a user. The portable device may have an integrated sensor assembly integrated with at least one sensor outputting data representing motion of the portable device. From the motion sensor data, it may be determined if the portable device is in a cart motion mode, if the cart is moving and an effective motion frequency for the portable device. Further, the motion sensor data may be reconstructed, a heading misalignment angle calculated and steps taken by the user detected. From this information, dead reckoning for the cart may be performed so that a navigation solution may be provided.

Abstract: A survey for building fingerprint maps for an area may be achieved using map information to generate a grid of nodes and links, then transforming the grid to a directed graph, generating an improved tour that entirely traverses the directed graph and providing at least one survey route based at least in part on the tour to a surveyor that will perform the survey route. The provided survey route may be traversed with at least one device having an integrated sensor assembly that outputs data representing motion of the device and recording signal measurements with each device at a plurality of positions to generate a fingerprint map. The traversal of the provided survey route may be assessed through in-route assessment and/or post-route assessment. Depending on the assessment, the provided survey route may be re-traversed or a next survey route may be scheduled.

Abstract: An apparatus and method are disclosed for characterizing motion of a platform. Motion sensor data from a portable device having a sensor assembly may be obtained. The portable device may be within the platform and tethered or untethered, and the mobility of the portable device may be constrained or unconstrained within the platform. Following a determination the platform is moving, motion dynamics of the portable device that are independent from motion dynamics of the platform may be identified and motion sensor data corresponding to motion of the platform and motion sensor data corresponding to the identified independent motion of the portable device may be separated from the obtained motion sensor data. Accordingly, motion sensor data corresponding to motion of the platform that is independent of motion of the portable device may be output. This may be used to derive operator analytics for assessing performance.

Abstract: The navigation solution of a portable device may be enhanced using map information. Sensor data for the portable device may be used to derive navigation solutions at a plurality of epochs over a first period of time. Position information for the device may be estimated at a time subsequent to the first period of time using the navigation solutions. Map information for an area encompassing a current location of the portable device may also be obtained. Multiple hypotheses regarding possible positions of the portable device may be generated using the estimated position information and the map information. By managing and processing the hypotheses, estimated position information for at least one epoch during the first period of time may be updated. An enhanced navigation solution for the at least one epoch may be provided using the updated estimated position information and an uncertainty measure may be derived for the enhanced navigation solution.

Abstract: An apparatus and method are disclosed for cart navigation using a portable device that is conveyed by the cart, but may be tethered or untethered and wherein mobility of the portable device may be constrained or unconstrained within the cart. The cart may be any apparatus propelled by on foot motion of a user. The portable device may have an integrated sensor assembly integrated with at least one sensor outputting data representing motion of the portable device. From the motion sensor data, it may be determined if the portable device is in a cart motion mode, if the cart is moving and an effective motion frequency for the portable device. Further, the motion sensor data may be reconstructed, a heading misalignment angle calculated and steps taken by the user detected. From this information, dead reckoning for the cart may be performed so that a navigation solution may be provided.

Abstract: The navigation solution of a portable device may be enhanced using map information. Sensor data for the portable device may be used to derive navigation solutions at a plurality of epochs over a first period of time. Position information for the device may be estimated at a time subsequent to the first period of time using the navigation solutions. Map information for an area encompassing a current location of the portable device may also be obtained. Multiple hypotheses regarding possible positions of the portable device may be generated using the estimated position information and the map information. By managing and processing the hypotheses, estimated position information for at least one epoch during the first period of time may be updated. An enhanced navigation solution for the at least one epoch may be provided using the updated estimated position information and an uncertainty measure may be derived for the enhanced navigation solution.

Abstract: An apparatus and method are disclosed for user and moving vehicle detection in which sensor data for a portable device is processed to determine whether the portable device is in a moving vehicle. Following a determination the portable device is in a moving vehicle, the sensor data is to characterize an association between the user and the portable device to determine whether the portable device is connected to the user. If the user is connected to the portable device, it is then determined if the portable device is being held in hand. If the portable device is held in hand, it is then determined if the user is operating the moving vehicle. Output from an image sensor of the portable device may be used in determining if the user is the operator.

Abstract: A method and system for determining the mode of motion or conveyance of a device, the device being within a platform (e.g., a person, vehicle, or vessel of any type). The device can be strapped or non-strapped to the platform, and where non-strapped, the mobility of the device may be constrained or unconstrained within the platform and the device may be moved or tilted to any orientation within the platform, without degradation in performance of determining the mode of motion. This method can utilize measurements (readings) from sensors in the device (such as for example, accelerometers, gyroscopes, etc.) whether in the presence or in the absence of navigational information updates (such as, for example, Global Navigation Satellite System (GNSS) or WiFi positioning). The present method and system may be used in any one or both of two different phases, a model building phase or a model utilization phase.