Abstract: Systems and methods for training and implementing a machine learning algorithm to generate feature maps depicting spatial patterns of features associated with osteolysis, synovitis, or both. MRI data, including multispectral imaging data, are input to the trained machine learning algorithm to generate the feature maps, which may indicate features such as a location and probability of a pathology classification, a severity of synovitis, a type of synovitis, a synovial membrane thickness, and other features associated with osteolysis or synovitis. In some implementations, synovial anatomy are segmented in the MRI data before inputting the MRI data to the machine learning algorithm. These segmented MRI data may be generated using another trained machine learning algorithm.

Abstract: The present disclosure provides compositions and methods for producing transgenic plants and other organisms that exhibit increased production of mogroside compounds, in particular mogroside V, and the mogroside compounds, plants and plant parts so produced.

Abstract: A farming machine is configured to identify a plant from a captured image and select two or more treatment mechanisms to treat the plant. To do so, the farming machine identifies characteristics of the plant, determines a treatment for the plant, and determines the available treatment mechanisms. The farming machine determines which combination of treatment mechanisms will apply the determined treatment to the plant and actuates that combination of treatment mechanisms.

Abstract: As a farming machine travels through a field of plants, the farming machine accesses an image of a field including a plant and receives sensor signals from one or more sensors coupled to the farming machine. The farming machine applies the image and sensor signals to a computer model to determine a spatial relationship between a treatment mechanism of the farming machine and the plant. Determining the spatial relationship produces an uncertainty measurement for an expected position of the treatment mechanism respective to an expected position of the plant. The farming machine adjusts a treatment buffer based on the uncertainty measurement. The farming machine treats the plant in the field by applying the plant treatment to the plant based on the treatment buffer.

Abstract: A dynamic ergonomic surface system for use in a motor vehicle includes an ergonomic surface that is inlayed in a surrounding surface and transitions between states, including: a neutral state in which the ergonomic surface is consistent with the surrounding surface, and at least one ergonomic support state in which the ergonomic surface provides ergonomic support for a user operating an input device. The dynamic ergonomic surface system also includes a sensor system that detects events triggering the transition between states, and a controller that controls the ergonomic surface to transition between the states in response to the detected events.

Abstract: Digital image segmentation is provided. The method comprises training a neural network for image segmentation with a labeled training dataset from a first domain, wherein a subset of nodes in the neural net are dropped out during training. The neural network receives image data from a second, different domain. A vector of N values that sum to 1 is calculated for each image element, wherein each value represents an image segmentation class. A label is assigned to each image element according to the class with the highest value in the vector. Multiple inferences are performed with active dropout layers for each image element, and an uncertainty value is generated for each image element. Uncertainty is resolved according to expected characteristics. The label of any image element with an uncertainty above a threshold is replaced with a new label corresponding to a segmentation class based on domain knowledge.

Abstract: A method for digital image segmentation is provided. The method comprises training a neural network for image segmentation with a labeled training dataset from a first domain, wherein a subset of nodes in the neural net are dropped out during training. The neural network receives image data from a second, different domain. A vector of N values that sum to 1 is calculated for each image element, wherein each value represents an image segmentation class. A label is assigned to each image element according to the class with the highest value in the vector. Multiple inferences are performed with active dropout layers for each image element, and an uncertainty value is generated for each image element. The label of any image element with an uncertainty value above a predefined threshold is replaced with a new label corresponding to the class with the next highest value.

Abstract: A dynamic touch user interface system includes a touch-input interface, one or more visual indicators, and a plurality of sensors. The touch-input interface has a reference surface that covers one or more touch elements. The touch elements define an active area that allows user communication with a computer through touch. The active area is relocatable along the reference surface in response to detected circumstances. The visual indicators visually identify a location of the active area. The sensors detect the circumstances affecting a relocation of the active area.

Abstract: A method for digital image segmentation is provided. The method comprises training a neural network for image segmentation with a labeled training dataset from a first domain, wherein a subset of nodes in the neural net are dropped out during training. The neural network receives image data from a second, different domain. A vector of N values that sum to 1 is calculated for each image element, wherein each value represents an image segmentation class. A label is assigned to each image element according to the class with the highest value in the vector. Multiple inferences are performed with active dropout layers for each image element, and an uncertainty value is generated for each image element. The label of any image element with an uncertainty value above a predefined threshold is replaced with a new label corresponding to the class with the next highest value.

Abstract: A temperature control system for a motor vehicle includes a thermotactile user interface having a plurality of adjacent thermoelectric units arranged in an array, each thermoelectric unit having a thermoelectric surface whose temperature varies with an amount of current supplied to the thermoelectric unit. A controller controls the amount of current supplied to each thermoelectric unit such that the temperature of each thermoelectric surface in the array progressively increases or decreases along the array. The system also includes a sensor system that detects a user selection of one of the thermoelectric surfaces as corresponding to a desired temperature. In response to the detected user selection, the controller controls a temperature of a temperature controlled medium of the motor vehicle, e.g., controls the vehicle's cabin climate, to match the temperature of the selected thermoelectric surface.

Abstract: A velocity indication system of a vehicle includes one or more velocity sensors configured to sense a vehicle velocity and to generate velocity data therefrom. The system also includes a control unit configured to receive the velocity data and to generate a control signal based on the velocity data. The system also includes a tactile velocity indicator. The tactile velocity indicator includes a frame that defines an opening therein. The tactile velocity indicator also includes a haptic element, at least partially protruding from the opening so as to be touchable by a passenger of the vehicle via the opening. The tactile velocity indicator also includes an electric motor configured to drive the haptic element in response to the control signal to move relative to the frame according to a haptic element velocity that corresponds to the sensed vehicle velocity.

Abstract: A dynamic touch user interface system includes a touch-input interface, one or more visual indicators, and a plurality of sensors. The touch-input interface has a reference surface that covers one or more touch elements. The touch elements define an active area that allows user communication with a computer through touch. The active area is relocatable along the reference surface in response to detected circumstances. The visual indicators visually identify a location of the active area. The sensors detect the circumstances affecting a relocation of the active area.

Abstract: A system for holding a personal object for a motor vehicle is described. The system includes a segmented surface having a plurality of adjacent surface elements. The system also includes a plurality of actuators, each actuator associated with a surface element and configured to extend and/or retract the associated surface element. The system also includes a sensor system configured to detect circumstances affecting the holding of the personal object by the segmented surface. The system also includes a controller operably coupled to the actuators and the sensor system, the controller configured to selectively control the actuators to extend and/or retract associated surface elements based on the detected circumstances so as to form a holding area appropriate for holding the personal object.

Abstract: A temperature control system for a motor vehicle includes a thermotactile user interface having a plurality of adjacent thermoelectric units arranged in an array, each thermoelectric unit having a thermoelectric surface whose temperature varies with an amount of current supplied to the thermoelectric unit. A controller controls the amount of current supplied to each thermoelectric unit such that the temperature of each thermoelectric surface in the array progressively increases or decreases along the array. The system also includes a sensor system that detects a user selection of one of the thermoelectric surfaces as corresponding to a desired temperature. In response to the detected user selection, the controller controls a temperature of a temperature controlled medium of the motor vehicle, e.g., controls the vehicle's cabin climate, to match the temperature of the selected thermoelectric surface.

Abstract: A dynamic ergonomic surface system for use in a motor vehicle includes an ergonomic surface that is inlayed in a surrounding surface and transitions between states, including: a neutral state in which the ergonomic surface is consistent with the surrounding surface, and at least one ergonomic support state in which the ergonomic surface provides ergonomic support for a user operating an input device. The dynamic ergonomic surface system also includes a sensor system that detects events triggering the transition between states, and a controller that controls the ergonomic surface to transition between the states in response to the detected events.

Abstract: A velocity indication system of a vehicle includes one or more velocity sensors configured to sense a vehicle velocity and to generate velocity data therefrom. The system also includes a control unit configured to receive the velocity data and to generate a control signal based on the velocity data. The system also includes a tactile velocity indicator. The tactile velocity indicator includes a frame that defines an opening therein. The tactile velocity indicator also includes a haptic element, at least partially protruding from the opening so as to be touchable by a passenger of the vehicle via the opening. The tactile velocity indicator also includes an electric motor configured to drive the haptic element in response to the control signal to move relative to the frame according to a haptic element velocity that corresponds to the sensed vehicle velocity.

Abstract: A system for an adaptive touch user interface includes a visual display and an adaptive touch-input interface. The visual display is configured to display one or more interactive elements thereon in accordance with a software application that receives user input in connection with displayed information. The touch-input interface is configured to receive user input and communicate the user input to the software application. The touch-input interface also has a surface profile that is adaptable in connection with the display of the one or more interactive elements.

Abstract: A system for holding a personal object for a motor vehicle is described. The system includes a segmented surface having a plurality of adjacent surface elements. The system also includes a plurality of actuators, each actuator associated with a surface element and configured to extend and/or retract the associated surface element. The system also includes a sensor system configured to detect circumstances affecting the holding of the personal object by the segmented surface. The system also includes a controller operably coupled to the actuators and the sensor system, the controller configured to selectively control the actuators to extend and/or retract associated surface elements based on the detected circumstances so as to form a holding area appropriate for holding the personal object.