Abstract: There is provided a method for consolidating explanations associated with actions proposed based on a current state of a system and an intent. The method includes acquiring first and second explanations, the first and second explanations being associated with a proposed action or with different actions, wherein each of the first and second explanations includes one or more constraints, combining constraints from the first and second explanations to form a set of constraints D, generating a planning problem P=<K, A, I, G, Cost>, wherein K consists of a set of predicates F and the set of constraints D, wherein A represents a set of possible actions, I represents an initial state of the system, G represents a goal state of the system, and Cost represents cost values associated with each constraint, and determining a solution for the planning problem.

Abstract: Embodiments of the present application provide a radio frequency head coil (300), RE head coil. The RE head coil (300) comprises a coil former (310) comprising at least a first leg and a second leg arranged at a distance from each other to define a space there between, the coil former (310) being at least sectionally flexible and having at least one first fastening portion (315, 316) arranged adjacent to the space (314), and a respiratory mask (320) comprising a gas outlet (324) and at least one second fastening portion (322, 323), wherein in an operable condition in which the RE head coil (300) is adapted to be arranged at least in sections around a head of a patient (S) and in which the second fastening portion (322, 323) is adapted to be fastened to the first fastening portion (315, 316), the gas outlet (324) is disposed within the space (314).

Abstract: There is provided a computer implemented method for use in a distributed machine learning process for training a machine learning model, wherein the training is distributed across a plurality of computing nodes and updates to the machine learning model, as determined by the plurality of computing nodes, are aggregated using secure multi party computation. The method includes: i) obtaining an aggregated characteristic of updates to the machine learning model provided by a first subset of the plurality of computing nodes; ii) comparing the aggregated characteristic to an equivalent reference; and iii) identifying whether the first subset of nodes are contributing updates that are corrupting the machine learning model, based on the comparison.

Abstract: Methods and systems for power supply unit (PSU) control. A method includes measuring one or more properties of the PSU to obtain property measurements, and initiating transmission of the property measurements to a machine learning (ML) agent hosting a trained ML model. The method further includes receiving the property measurements at the ML agent, and processing the received property measurements using the trained ML model to generate suggested actions to be taken by the PSU. The method further includes predicting the effect of each of the suggested actions on the measured PSU properties, and selecting a subset of the suggested actions predicted to have a significant impact on the measured PSU properties. The method further includes initiating transmission of the selected subset of suggested actions to the PSU, and performing, at the PSU, the selected subset of suggested actions.

Abstract: Methods and systems for power supply unit (PSU) control. A method includes measuring one or more properties of the PSU to obtain property measurements, and initiating transmission of the property measurements to a machine learning (ML) agent hosting a trained ML model. The method further includes receiving the property measurements at the ML agent, and processing the received property measurements using the trained ML model to generate suggested actions to be taken by the PSU. The method further includes predicting the effect of each of the suggested actions on the measured PSU properties, and selecting a subset of the suggested actions predicted to have a significant impact on the measured PSU properties. The method further includes initiating transmission of the selected subset of suggested actions to the PSU, and performing, at the PSU, the selected subset of suggested actions.

Abstract: The present disclosure relates to a method for operating a medical imaging system (100), the method carried out by use of a data processing unit (120), the method comprising: obtaining (SI), by a computational prediction model, time-invariant patient information, generating (S2), by the computational prediction model, a patient profile parametrized based on at least the obtained time-invariant patient information, obtaining (S3), by the computational prediction model, at least one current clinical workflow parameter, providing (S4), by the computational prediction model, a prediction comprising at least a patient-specific operation workflow based on at least correlating the generated patient profile with the obtained current clinical workflow parameter, wherein the patient-specific operation workflow comprises a specific one of a selection of operational modes of the medical imaging system, and operating the medical imaging system (100) based on the specific one of the selection of operational modes.

Abstract: The present invention relates to a system and method for controlling transdermal and automatic release of a sedative during imaging of a subject. A sedation level of a patient is detected during an imaging procedure. An amount of sedative to be applied to the patient to sustain a certain level of sedation is calculated. Further, a time for releasing the amount of the sedative is calculated. The calculated amount of the sedative is released at the calculated time transdermally to the patient.

Abstract: Embodiments of the present application provide a radio frequency head coil (300), RE head coil. The RE head coil (300) comprises a coil former (310) comprising at least a first leg and a second leg arranged at a distance from each other to define a space there between, the coil former (310) being at least sectionally flexible and having at least one first fastening portion (315, 316) arranged adjacent to the space (314), and a respiratory mask (320) comprising a gas outlet (324) and at least one second fastening portion (322, 323), wherein in an operable condition in which the RE head coil (300) is adapted to be arranged at least in sections around a head of a patient (S) and in which the second fastening portion (322, 323) is adapted to be fastened to the first fastening portion (315, 316), the gas outlet (324) is disposed within the space (314).

Abstract: A system (SYS) and related method for imaging support. The system (SYS) comprises a stimulus delivery component (SDC) configured to cause a chemoreceptor stimulus in a patient residing in or at an imaging apparatus (IA). A response measuring component (RMC) measure a response of the patient to the stimulus, and a decision logic (DL) establishes, based on the measured response, a sedation status of the patient for the purpose of imaging the patient. An imaging operation can be modified, for instance, halted if the patient is no longer sufficiently sedated.

Abstract: The present invention relates to a patient marker (10). The marker is configured to be placed on or inside a patient. The marker comprises a specific structure (20). When the marker is placed on or inside the patient, and the patient is positioned at least partially within an image acquisition unit of an imaging system, the marker is configured such that an image acquired by the imaging system comprises image data of the specific structure of the marker. The marker is configured such that image data of the specific structure of the marker comprises information useable to identify the marker. The marker is configured such that image data of the specific structure of the marker comprises information useable to define at least one parameter relating to an examination of the patient.

Abstract: An improved X-ray imaging system. The system comprises an X-Ray radiation source configured to emit an X-ray beam towards an object to be imaged and an X- ray detector configured to detect X-rays which have passed through the object.

Abstract: In the current diagnostic imaging workflow, transfer of handicapped patients between a hospital bed to a patient support of an imaging system and back is performed manually, which may be physically exhausting for staff and uncomfortable for the patient being transferred. Furthermore, this should be avoided in an autonomous scanning environment. Accordingly, the present application proposes an approach for enabling patient pain detection and reduction when using a patient transfer device configured to transfer a patient between a first and a second patient support.

Abstract: The present invention relates to patient routing. In order to provide a more efficient patient flow for autonomous image acquisition, a method is provided for controlling a patient transfer apparatus within a healthcare facility.

Abstract: This technology relates to systems and methods for effective selection of disparate distributed power sources for smart grid in near real time manner to meet the specific power demand. Power from the plurality of disparate power sources is received and then one or more power sources among the plurality of disparate power sources are selected based on one or more predefined requirements. At least one effective power source is determined from the one or more power sources by applying one or more algorithm based on number and range of the one or more power sources. The one or more algorithm comprise Complete Karmarkar Karp (CKK), pbrute, Heuristic based pbrute. A signal for selection of the at least one effective power source is generated and the signal is sent to a circuit switcher to supply the power from the at least one effective power sources to the smart grid.

Abstract: A system and method for generating an optimized operating schedule for a plurality of heterogeneous wireless network appliances managed by a gateway device in a closed area network is disclosed. An amount of energy consumed by each network appliance as well as preassigned operational priority values assigned to each network appliance per time slot over the designated time period is considered. A plurality of proposed operation schedules are iteratively generated, wherein each proposed operation schedule selectively assigns the network appliances to operate at various time slots based on their assigned operational priority values. An optimized schedule is selected which has a determined lowest aggregated total utility cost and a greatest aggregated operations value for the network appliances in the subset. The selected optimized schedule is then implemented by the gateway device to manage operation of the network appliances in the closed area network.

Abstract: A system, medium and method of managing, via a gateway device, to wirelessly communicate with a plurality of network appliances in a closed local area network is disclosed. A data message is received from a first network appliance configured to communicate data in association with a first application profile. The first application profile is retrieved from a locally stored application profile database upon being identified. A database is accessed at the gateway device containing policy information of the first network appliance and evaluated for one or more policy parameters. A first instruction command is generated at the gateway device based on the accessed policy information, wherein the instruction command conforms with the first application profile to instruct the first network appliance to perform a specified action. The instruction command is wirelessly transmitted from the gateway device to the first network appliance to cause it to perform a specified action.

Abstract: This technology relates to systems and methods for effective selection of disparate distributed power sources for smart grid in near real time manner to meet the specific power demand. Power from the plurality of disparate power sources is received and then one or more power sources among the plurality of disparate power sources are selected based on one or more predefined requirements. At least one effective power source is determined from the one or more power sources by applying one or more algorithm based on number and range of the one or more power sources. The one or more algorithm comprise Complete Karmarkar Karp (CKK), pbrute, Heuristic based pbrute. A signal for selection of the at least one effective power source is generated and the signal is sent to a circuit switcher to supply the power from the at least one effective power sources to the smart grid.

Abstract: A method and system for adaptive aggregation of data in a Wireless Sensor Network (WSN) is disclosed. The method receiving one or more packets produced from a plurality of sensor nodes at an aggregator sensor node. The method further includes categorizing and storing the received packets in the buffer queue of the aggregator node. Then initiating an aggregation process by selecting an aggregation mechanism. The aggregation mechanism is selected based on the feedback value and a special instruction. The aggregated packets are forwarded to the base station based on an aggregation function.

Abstract: A system and method for generating an optimized operating schedule for a plurality of heterogeneous wireless network appliances managed by a gateway device in a closed area network is disclosed. An amount of energy consumed by each network appliance as well as preassigned operational priority values assigned to each network appliance per time slot over the designated time period is considered. A plurality of proposed operation schedules are iteratively generated, wherein each proposed operation schedule selectively assigns the network appliances to operate at various time slots based on their assigned operational priority values. An optimized schedule is selected which has a determined lowest aggregated total utility cost and a greatest aggregated operations value for the network appliances in the subset. The selected optimized schedule is then implemented by the gateway device to manage operation of the network appliances in the closed area network.

Abstract: A system, medium and method of managing, via a gateway device, to wirelessly communicate with a plurality of network appliances in a closed local area network is disclosed. A data message is received from a first network appliance configured to communicate data in association with a first application profile. The first application profile is retrieved from a locally stored application profile database upon being identified. A database is accessed at the gateway device containing policy information of the first network appliance and evaluated for one or more policy parameters. A first instruction command is generated at the gateway device based on the accessed policy information, wherein the instruction command conforms with the first application profile to instruct the first network appliance to perform a specified action. The instruction command is wirelessly transmitted from the gateway device to the first network appliance to cause it to perform a specified action.