Abstract: A computing device, the computing device comprising a processor configured to: receive audio information relating to one or more non-verbal sounds captured by a microphone in an environment of a user; receive motion information that is based on motion sensor data captured by a motion sensor, said motion information relating to motion of said user in the environment; process the audio information and the motion information to recognise an activity of said user; and output an activity recognition notification indicating said activity.

Abstract: A device or system is provided which is configured to detect one or more sound events and/or scenes associa ted with a predetermined context, and to provide an assistive output on fulfilment of that context.

Abstract: A method for recognising at least one of a non-verbal sound event and a scene in an audio signal comprising a sequence of frames of audio data, the method comprising: for each frame of the sequence: processing the frame of audio data to extract multiple acoustic features for the frame of audio data; and classifying the acoustic features to classify the frame by determining, for each of a set of sound classes, a score that the frame represents the sound class; processing the sound class scores for multiple frames of the sequence of frames to generate, for each frame, a sound class decision for each frame; and processing the sound class decisions for the sequence of frames to recognise the at least one of a non-verbal sound event and a scene.

Abstract: Electronic communications passing through a communication gateway or similar device for an enterprise can be monitored for indicators of malicious activity. When potentially malicious activity is identified, a user-based inquiry can be employed to identify potential sources of the malicious activity within the enterprise network. More specifically, by identifying a user that sourced the communication, instead of or in addition to a network address, devices within the enterprise network associated with the user can be located, analyzed, and remediated as appropriate.

Abstract: Sound detection and identification leads to responsiveness within an augmented reality environment. Information about an identified sound can be converted into a command for implementation by an augmented reality system, for display of a desired on-screen augmented reality effect.

Abstract: A magnetic filter carriage (16) for use in filtering contaminants from fluid in a high pressure fluid flow comprises a frame (18, 20, 22) arranged to support a plurality of magnet filter rods (42), such that the rods (42) are each supported at both ends thereof in a fixed orientation, for example parallel to one another. The frame (18, 20, 22) is adapted to be inserted within a pressure vessel (4) across the direction of fluid flow between a fluid inlet (7) and a fluid outlet (9) of the pressure vessel (4), and may be arranged such that more than about 90% of the flow across the vessel (4) passes through the frame (18, 20, 22). The rods (42) are mounted in a plurality of cassettes (36) which are easily removable for cleaning or replacement.

Abstract: Verification of presence of a detected target is carried out following an initial presence determination on the basis of detected non-verbal sound.

Abstract: Control of navigation of a content item is carried out by detection of non-verbal sound events. On the basis of receipt of one or more non-verbal sound event reports, a navigation tool is provided with a corresponding sequence of navigation commands. The correspondence between navigation command sequences and non-verbal sound events is established through analysis or markup of the content item.

Abstract: A computing device for controlling a user interface of the computing device, the computing device comprising a processor configured to: detect at least one target sound in a monitored environment; determine an operating mode of the computing device that is associated with the at least one target sound; output content, via the user interface of the computing device, that is associated with the operating mode, wherein the content prompts a user of the computing device to perform an action using an input device of the computing device to instruct the computing device to control a controllable device in the monitored environment in response to the recognition of the at least one target sound.

Abstract: A computing device for controlling a user interface of the computing device, the computing device comprising a processor configured to: detect at least one target sound in a monitored environment; determine an operating mode of the computing device that is associated with the at least one target sound; output content, via the user interface of the computing device, that is associated with the operating mode, wherein the content prompts a user of the computing device to perform an action using an input device of the computing device to instruct the computing device to control its own display in the monitored environment in response to the recognition of the at least one target sound.

Abstract: A system for monitoring and detecting the gait and other health related parameters of a user. One such parameter is monitoring of medication compliance and treatment session attendance done by a medication and liquid dispensing apparatus, which combines mechanical dispensing of medication. These parameters are provided in standard of care summaries to care providers, and are continually reported by the Optimum Recognition Blueprint as Standard of Care Summaries to care providers, as well as communicated to the end-user by the Virtual Caregiver Interface.

Abstract: A method for recognising at least one of a non-verbal sound event and a scene in an audio signal comprising a sequence of frames of audio data, the method comprising: for each frame of the sequence: receiving at least one sound class score, wherein each sound class score is representative of a degree of affiliation of the frame with a sound class of a plurality of sound classes; for a sound class score of the at least one sound class scores: determining a confidence that the sound class score is representative of a degree of affiliation of the frame with the sound class by processing a value for a property associated with the frame, wherein the value is processed using a learned model for the property; adjusting the sound class score for the frame based at least on the determined confidence.

Abstract: Disclosed is a fastener that includes a nut with a threaded bore that includes a head on one end having three recesses, a cylindrical outer surface and a tapered ramp on the other end, a bolt that includes a head, a threaded portion engaged with the threaded bore, a recess next to the bolt head and an enlarged shank between the threads and the recess, where the outer diameter of the recess is smaller than a major diameter of the threaded bore of the nut and where an outer diameter of the shank is larger than a major diameter of the bolt threads, and a sleeve with a unthreaded bore positioned between the tapered ramp and the bolt head with one end crimped into the recess such that the internal diameter of the crimped sleeve bore is smaller than the major diameter of the threads on the bolt.

Abstract: A catheter includes a handle with torquing and steering mechanisms. The torquing mechanism includes a rotatable nosecone and a bearing coupled to the nosecone to be rotatable therewith. The bearing is concentrically disposed over a shaft of the catheter and is configured to transmit a torque from the nosecone to the shaft when the nosecone is rotated. The steering mechanism includes a rack coupled to the bearing to be slideable therewith and a pull wire having a proximal end attached to the bearing and a distal end attached to a distal portion of the shaft. Rotation of the nosecone causes an entire length of the shaft to rotate and axial movement of the rack tensions the pull wire to bend the distal portion of the shaft. A valve relief component is slidingly disposed over the shaft and is configured to dock onto the handle when not in use.

Abstract: Electronic communications passing through a communication gateway or similar device for an enterprise can be monitored for indicators of malicious activity. When potentially malicious activity is identified, a user-based inquiry can be employed to identify potential sources of the malicious activity within the enterprise network. More specifically, by identifying a user that sourced the communication, instead of or in addition to a network address, devices within the enterprise network associated with the user can be located, analyzed, and remediated as appropriate.

Abstract: A catheter based balloon enabled prosthetic heart valve delivery device is provided. The balloon enabled delivery device is configured to deploy a prosthetic heart valve through inflation. The balloon enabled delivery device is further configured to reduce or prevent migration of the prosthetic heart valve during deployment. Migration is prevented through a combination of balanced inflation of the balloon, inflation fluid flow balancing structures, retention rings, retention covers, and balloon surface treatments.

Abstract: An apparatus includes physical layer circuitry with lanes to couple the apparatus to endpoint devices. a first input/output (I/O) controller to couple a first processor to the physical layer circuitry, and a second I/O controller to couple a second processor to the physical layer circuitry. The first and second I/O controllers are compatible with a Peripheral Component Interconnect Express (PCIe)-based protocol. The apparatus also includes a flexible input/output adapter (FIA) coupling the first and second I/O controllers to the lanes. The FIA selectively assigns access to each lane of the lanes by either the first or second I/O controller. The apparatus also includes a power management controller (PMC) communicably coupled to the FIA. The PMC causes the FIA to dynamically assign access to at least one of the lanes by the first or second I/O controller without a reboot cycle.

Abstract: A system for monitoring and detecting the gait and other health related parameters of a user. One such parameter is monitoring of medication compliance and treatment session attendance done by a medication and liquid dispensing apparatus, which combines mechanical dispensing of medication. These parameters are provided in standard of care summaries to care providers, and are continually reported by the Optimum Recognition Blueprint as Standard of Care Summaries to care providers, as well as communicated to the end-user by the Virtual Caregiver Interface.

Abstract: A method, and system, of digital room correction for a device, such as a smart speaker, including a loudspeaker. The method comprises capturing audio from an environment local to the device, for example from one or more microphones of a smart speaker. The captured audio is then processed to recognize one or more categories of sound. A digital room correction procedure may then be controlled dependent upon recognition and/or analysis of at least one of the categories of sound.

Abstract: A method of training a non-verbal sound class detection machine learning system, the non-verbal sound class detection machine learning system comprising a machine learning model configured to: receive data for each frame of a sequence of frames of audio data obtained from an audio signal; for each frame of the sequence of frames: process the data for multiple frames; and output data for at least one sound class score representative of a degree of affiliation of the frame with at least one sound class of a plurality of sound classes, wherein the plurality of sound classes comprises: one or more target sound classes; and a non-target sound class representative of an absence of each of the one or more target sound classes; wherein the method comprises: training the machine learning model using a loss function.