Abstract: Systems and methods in accordance with many embodiments of the invention include a motion evaluation system that trains a model to evaluate motion (such as, but not limited to, gait) through images (or video) captured by a single image capture device. In certain embodiments, motion evaluation includes predicting clinically relevant variables from videos of patients walking from keypoint trajectories extracted from the captured images.

Abstract: Techniques for a natural language processing (NLP) system to implement more than one assistant are described. The NLP system may receive a natural language input corresponding to more than one user command. The NLP system may respond to a first command, of the natural language input, using a TTS voice of a first NLP system assistant. The NLP system may respond to a second command, of the natural language input, using a TTS voice of a second NLP system assistant.

Abstract: A rear suspension bicycle having a suspension pivot point sufficiently above a crank axis (front sprocket/chainring) to provide predominantly rearward axle path and require an idler pulley to route a drive belt/chain. A tensioner is located between the idler pulley and the front sprocket/chainring to accommodate virtual chain growth and maintain appropriate tension on drive belt/chain. The tensioner includes a pivoting member with a pulley mounted thereto, a spring arm connected to the pivoting member at a defined angle, and a spring located between the spring arm and a frame. The pivoting member/pulley pivot away from the suspension pivot point to accommodate the virtual chain growth created when vertical rear wheel travel of bicycle increases. The pivoting member/pulley pivot back toward the suspension pivot point to maintain appropriate tension when vertical rear wheel travel decreases. A spring returning to its steady state size (e.g., expanding) is used to maintain tension.

Abstract: A rear suspension chain drive bicycle having a routing pulley to route an untensioned portion of a chain drive to a tensioned portion of the chain drive to reduce chain growth experienced thereby. The use of the routing pulley to reduce chain growth enable a derailleur to accommodate addition vertical rear wheel travel. The routing pulley can be used in high pivot and low pivot rear suspension bicycles. High pivot bicycles have a rear suspension pivot point sufficiently above a crank axis (front chainring) to provide predominately rearward axle path and require an idler pulley to route the chain drive. The routing pulley is located above the front chain ring and for the high pivot bicycle is located close to the idler pulley.

Abstract: An electrically actuated propeller pitch control system includes a propeller hub assembly, a propeller assembly, and a crosshead drive system. The propeller hub assembly rotates about the central axis during operation of watercraft. The propeller assembly is configured to selectively rotate a propeller blade. The crosshead drive system includes an electric motor, a transmission, and a lead screw that rotates about the central axis.

Abstract: An electrically actuated propeller pitch control system includes a propeller hub assembly, a propeller assembly, and a crosshead drive system. The propeller hub assembly rotates about the central axis during operation of watercraft. The propeller assembly is configured to selectively rotate a propeller blade. The crosshead drive system includes an electric motor, a transmission, and a lead screw that rotates about the central axis.

Abstract: An electrically actuated propeller pitch control system includes a propeller hub, a propeller assembly, and a crosshead drive system. The propeller hub rotates about the central axis during operation of watercraft. The propeller assembly is coupled to rotate with the propeller hub during operation of the watercraft. The crosshead drive system includes an electric motor, a lead screw, and a pitch position indicator system configured to indicate a pitch angle of propeller blades.

Abstract: Techniques for selecting a skill component to process a natural language input are described. When a natural language input is received, natural language understanding (NLU) output data representing the natural language input is generated, and skill components (capable of processing the NLU output data) are determined. Thereafter, rules (for preventing the invocation of skill components) are implemented in a tiered manner, resulting in the determination of a subset of the skill components. The subset of skill components is ranked using a machine learning model(s), and the top-ranked skill component is called to process the NLU output data.

Abstract: Techniques for a natural language processing (NLP) system to implement more than one assistant are described. The NLP system may receive a natural language input corresponding to more than one user command. The NLP system may respond to a first command, of the natural language input, using a TTS voice of a first NLP system assistant. The NLP system may respond to a second command, of the natural language input, using a TTS voice of a second NLP system assistant.

Abstract: Techniques for a natural language processing (NLP) system to implement more than one assistant are described. The NLP system may receive a natural language input corresponding to more than one user command. The NLP system may respond to a first command, of the natural language input, using a TTS voice of a first NLP system assistant. The NLP system may respond to a second command, of the natural language input, using a TTS voice of a second NLP system assistant.

Abstract: Techniques for performing runtime ranking of skill components are described. A skill developer may generate a rule indicating a skill component is to be invoked at runtime when a natural language input corresponds to a specific context. At runtime, a virtual assistant system may implement a machine learned model to generate an initial ranking of skill components. Thereafter, the virtual assistant system may use skill component-specific rules to adjust the initial ranking, and this second ranking is used to determine which skill component to invoke to respond to the natural language input. Overtime, if a rule results in beneficial user experiences, the virtual assistant system may incorporate the rule into the machine learned model.

Abstract: Techniques for a natural language processing (NLP) system to implement more than one assistant are described. The NLP system may receive a natural language input from a device. The NLP system may also receive one or more signals representing one or more assistants to be implemented with respect to the natural language input. The NLP system may intelligently select an assistant to be invoked with respect to the natural language input. Once the assistant is selected, the NLP system may cause content, output to a user, to have characteristics specific to the assistant.

Abstract: Techniques for a natural language processing (NLP) system to implement more than one assistant are described. The NLP system may receive a natural language input corresponding to more than one user command. The NLP system may respond to a first command, of the natural language input, using a TTS voice of a first NLP system assistant. The NLP system may respond to a second command, of the natural language input, using a TTS voice of a second NLP system assistant.

Abstract: Systems and methods in accordance with many embodiments of the invention include a motion evaluation system that trains a model to evaluate motion (such as, but not limited to, gait) through images (or video) captured by a single image capture device. In certain embodiments, motion evaluation includes predicting clinically relevant variables from videos of patients walking from keypoint trajectories extracted from the captured images.

Abstract: Techniques for a natural language processing (NLP) system to implement more than one assistant are described. The NLP system may receive a natural language input corresponding to more than one user command. The NLP system may respond to a first command, of the natural language input, using a TTS voice of a first NLP system assistant. The NLP system may respond to a second command, of the natural language input, using a TTS voice of a second NLP system assistant.

Abstract: The invention discloses diagnostic techniques based on single cell genomics, consisting of obtaining a blood sample, enriching a sub-population of cells present in the blood sample, sequestering individual cells or group of cells from the blood sample, obtaining sequencing data from the sequestered cells or group of cells, using genetic variant information to determine the provenance of the cells, and genetically analyzing the cells of the correct provenance to provide a diagnostic readout. Using the cell-based testing techniques of the invention, the number of false positives is greatly reduced when compared to cell-free DNA (cfDNA) based traditional testing techniques. The invention may be effectively employed for non-invasive prenatal (NIPT) diagnostics, oncological testing and other diagnostic procedures.

Abstract: An apparatus for co-extruding a liquid around a periphery of a stream of meat as the meat is extruded into a casing includes a collar, a tube end connected within the collar, and a co-axial stuffing tube having a proximal end connected to the tube end. The stuffing tube has concentric inner and outer layers and a longitudinal channel between the inner and outer layers extending from the proximal end of the stuffing tube to a distal end of the stuffing tube. A liquid inlet port in the collar is in fluid communication with the longitudinal channel. Methods include co-extruding the liquid from the longitudinal channel at a distal end of the stuffing tube as the stream of meat is extruded from within the inner layer of the stuffing tube such that the liquid and the meat are not combined until both are extruded into a casing.

Abstract: An apparatus for co-extruding a liquid around a periphery of a stream of meat as the meat is extruded into a casing includes a collar, a tube end connected within the collar, and a co-axial stuffing tube having a proximal end connected to the tube end. The stuffing tube has concentric inner and outer layers and a longitudinal channel between the inner and outer layers extending from the proximal end of the stuffing tube to a distal end of the stuffing tube. A liquid inlet port in the collar is in fluid communication with the longitudinal channel. Methods include co-extruding the liquid from the longitudinal channel at a distal end of the stuffing tube as the stream of meat is extruded from within the inner layer of the stuffing tube such that the liquid and the meat are not combined until both are extruded into a casing.

Abstract: Techniques for a natural language processing (NLP) system to implement more than one assistant are described. The NLP system may receive a natural language input corresponding to more than one user command. The NLP system may respond to a first command, of the natural language input, using a TTS voice of a first NLP system assistant. The NLP system may respond to a second command, of the natural language input, using a TTS voice of a second NLP system assistant.