Abstract: A respiratory pressure therapy (RPT) device is disclosed for treatment of respiratory-related disorders. The RPT device includes a pressure generator, a pneumatic block, a chassis and a device outlet for delivering a supply of flow of gas to a patient interface. The RPT device also comprises an integrated humidifier including a water reservoir. An RPT device is also disclosed that includes a wireless data communication interface integrated with the housing and configured to connect to another device or a network.

Abstract: A respiratory pressure therapy (RPT) device is disclosed for treatment of respiratory-related disorders. The RPT device includes a pressure generator, a pneumatic block, a chassis and a device outlet for delivering a supply of flow of gas to a patient interface. The RPT device also comprises an integrated humidifier including a water reservoir. An RPT device is also disclosed that includes a wireless data communication interface integrated with the housing and configured to connect to another device or a network.

Abstract: A respiratory pressure therapy (RPT) device is disclosed for treatment of respiratory-related disorders. The RPT device includes a pressure generator, a pneumatic block, a chassis and a device outlet for delivering a supply of flow of gas to a patient interface. The RPT device also comprises an integrated humidifier including a water reservoir. An RPT device is also disclosed that includes a wireless data communication interface integrated with the housing and configured to connect to another device or a network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for machine learning models for adjusting communication parameters. In some implementations, data for each device in a set of multiple communication devices is obtained. A machine learning model is trained based on the obtained data. The model can be trained to receive an indication of a geographic location and predict a communication setting capable of providing at least a minimum level of efficiency. After training the machine learning model, an indication of a predicted communication setting for a particular communication device is generated. A determination is then made whether to change a current communication setting for the particular communication device based on the predicted communication setting.

Abstract: A garment for providing circulatory-related disorder therapy includes a skin contacting layer, a backing layer, and a coupling. The backing layer is coupled to the skin contacting layer such that the skin contacting layer and the backing layer form a plurality of macro-chambers. A first one of the plurality of macro-chambers is partitioned into a plurality of micro-chambers. Each of the plurality of micro-chambers is in direct fluid communication with at least one other of the plurality of micro-chambers. The coupling is coupled to the backing layer and is configured to supply pressurized air directly into the first macro-chamber such that the pressurized air is delivered to a first one of the plurality of micro-chambers of the first macro-chamber.

Abstract: A flow generator is configured to pressurize a flow of breathable gas to within a range of about 2-30 cm H2O for delivery to a patient's airways. The flow generator includes a blower with at least one impeller and a motor configured to drive the at least one impeller. The flow generator also includes a substantially planar blower mount configured to support the blower. The blower mount includes a flexible blower receptacle portion configured to receive and support the blower. The blower receptacle portion includes an outlet opening that is axially aligned with an air outlet of the blower. The flow generator also includes housing that encloses the blower and the blower mount. The housing has an inner surface that engages a perimeter of the blower mount.

Abstract: A blower includes a housing including an inlet and an outlet, a motor to drive a rotatable shaft, first and second impellers provided to the shaft, the first and second impellers each including a plurality of impeller blades, a first stationary component provided to the housing and including stator vanes downstream of the first impeller, and a second stationary component provided to the housing and including stator vanes downstream of the second impeller. A first set of stator vanes of the first stationary component is provided around the motor and are configured and arranged to direct airflow along the motor, to de-swirl the airflow and to decelerate air to increase pressure. A blower including a third impeller and third stationary component positioned above the first impeller is also described.

Abstract: The present technology is directed to a respiratory pressure therapy system, that includes a plenum chamber pressurisable to a therapeutic pressure above ambient air pressure, a seal-forming structure to form a seal with an entrance to the patients airways to maintain said therapeutic pressure in the plenum chamber throughout the patients respiratory cycle in use, a positioning and stabilising structure constructed and arranged to provide an elastic force to hold the seal-forming structure in a therapeutically effective position on the patients head, a blower configured to generate the flow of air and pressurise the plenum chamber to the therapeutic pressure. the blower having a motor, the blower being connected to the plenum chamber such that the blower is suspended from the patients head and the axis of rotation of the motor is perpendicular to the patients sagittal plane, and a power supply configured to provide electrical power to the blower.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training and using machine learning models to classify network traffic as IoT traffic or non-IoT traffic and managing the traffic based on the classification. In some implementations, machine learning parameters of a local machine learning model trained by the edge device is received each of at least a subset of a set of edge devices. The machine learning parameters received from an edge device are parameters of the local machine learning model trained by the edge device based on local network traffic processed by the edge device and to classify the network traffic as Internet of Things (IoT) traffic or non-IoT traffic. A global machine learning model is generated, using the machine learning parameters, to classify network traffic processed by edge devices as IoT traffic or non-IoT traffic.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for machine learning models for adjusting communication parameters. In some implementations, data for each terminal in a set of multiple satellite terminals is obtained. A machine learning model is trained based on the obtained data. The model can be trained to receive an indication of a geographic location and predict a satellite beam capable of providing at least a minimum level of efficiency for communication at the geographic location. After training the machine learning model, an indication of a predicted satellite beam for a particular location is generated for a particular geographic location. A determination is then made whether to change the current satellite beam for a terminal at the particular geographic location based on the predicted satellite beam.

Abstract: Methods and systems for monitoring a communication network using machine-learning techniques are disclosed. In some implementations, a forecasted amount of traffic for a communication network is determined using one or more network traffic forecasting models being configured to generate the forecasted amount of traffic based on data indicating one or more previous amounts of traffic for the communication network. A measure of network health is generated based on a measured amount of traffic and the forecasted amount of traffic. Data indicating one or more characteristics of the communication network is processed using one or more machine learning models to generate a predicted measure of network health for a future time period. An indication of the predicted measure of network health for the future time period is provided.

Abstract: A flow generator is configured to pressurize a flow of breathable gas to within a range of about 2-30 cm H2O for delivery to a patient's airways. The flow generator includes a blower with at least one impeller and a motor configured to drive the at least one impeller. The flow generator also includes a substantially planar blower mount configured to support the blower. The blower mount includes a flexible blower receptacle portion configured to receive and support the blower. The blower receptacle portion includes an outlet opening that is axially aligned with an air outlet of the blower. The flow generator also includes housing that encloses the blower and the blower mount. The housing has an inner surface that engages a perimeter of the blower mount.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training and using machine learning models to classify network traffic as IoT traffic or non-IoT traffic and managing the traffic based on the classification. In some implementations, machine learning parameters of a local machine learning model trained by the edge device is received each of at least a subset of a set of edge devices. The machine learning parameters received from an edge device are parameters of the local machine learning model trained by the edge device based on local network traffic processed by the edge device and to classify the network traffic as Internet of Things (IoT) traffic or non-IoT traffic. A global machine learning model is generated, using the machine learning parameters, to classify network traffic processed by edge devices as IoT traffic or non-IoT traffic.

Abstract: An impeller for use in a centrifugal blower, the impeller includes a hub defining an axis of rotation for the impeller; a plurality of inclined blades, the plurality of inclined blades extending away from the hub; and a plurality of reverse inclined blades, the plurality of reverse inclined blades extending away from the hub. Each of the plurality of inclined blades are joined to an adjacent inclined blade at least in part by a reverse inclined blade.

Abstract: A humidifier assembly is configured to humidify a pressurized flow of breathable gas from a flow generator of a CPAP unit and includes a base configured to be attached to the flow generator, the base including a recess portion. A water receptacle is configured to be received within the recess portion of the base and includes a floor and a flange around an opening at the top of the water receptacle. A lid is hingedly attached to the base and is configured to pivot between an open position and a closed position. This lid includes a top wall, an outer depending wall, an inner depending wall in the form of a double wall, and an outlet pipe. A lid seal is attached to an underside of the top wall of the lid by way of a tongue and groove structure. A catch is located on the base and configured to lock the lid in the closed position.

Abstract: A garment for providing circulatory-related disorder therapy includes a skin contacting layer, a backing layer, and a coupling. The backing layer is coupled to the skin contacting layer such that the skin contacting layer and the backing layer form a plurality of macro-chambers. A first one of the plurality of macro-chambers is partitioned into a plurality of micro-chambers. Each of the plurality of micro-chambers is in direct fluid communication with at least one other of the plurality of micro-chambers. The coupling is coupled to the backing layer and is configured to supply pressurized air directly into the first macro-chamber such that the pressurized air is delivered to a first one of the plurality of micro-chambers of the first macro-chamber.

Abstract: A flow regulating valve for a respiratory treatment system is disclosed, as well as a vent arrangement comprising the flow regulating valve. The flow regulating valve may include an inlet, an outlet, and a variable conduit in fluid communication with the inlet and the outlet. The variable conduit may include a movable portion that may move to vary an impedance of the variable conduit, thereby regulating a flow rate of the air travelling through the variable conduit. Advantageously, the flow regulating valve may thus reduce wastage of air (e.g. humidified air) that is exhausted from a respiratory treatment system, while maintaining sufficient washout of air.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training and using machine learning models to classify network traffic as IoT traffic or non-IoT traffic and managing the traffic based on the classification. In some implementations, machine learning parameters of a local machine learning model trained by the edge device is received each of at least a subset of a set of edge devices. The machine learning parameters received from an edge device are parameters of the local machine learning model trained by the edge device based on local network traffic processed by the edge device and to classify the network traffic as Internet of Things (IoT) traffic or non-IoT traffic. A global machine learning model is generated, using the machine learning parameters, to classify network traffic processed by edge devices as IoT traffic or non-IoT traffic.

Abstract: A respiratory pressure therapy (RPT) device is disclosed for treatment of respiratory-related disorders. The RPT device includes a pressure generator, a pneumatic block, a chassis and a device outlet for delivering a supply of flow of gas to a patient interface. The RPT device also comprises a humidifier including a water reservoir.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training and using machine learning models to classify network traffic as IoT traffic or non-IoT traffic and managing the traffic based on the classification. In some implementations, machine learning parameters of a local machine learning model trained by the edge device is received each of at least a subset of a set of edge devices. The machine learning parameters received from an edge device are parameters of the local machine learning model trained by the edge device based on local network traffic processed by the edge device and to classify the network traffic as Internet of Things (IoT) traffic or non-IoT traffic. A global machine learning model is generated, using the machine learning parameters, to classify network traffic processed by edge devices as IoT traffic or non-IoT traffic.