Abstract: Decision-making equipment (22) is configured for link change decision-making using reinforcement learning. The decision-making equipment (22) is configured to track rewards (30-1, . . . 30-M) earned for, and outcomes (28-1, . . . 28-M) of, respective link change decisions (26-1, . . . 26-M). In some embodiments, possible outcomes of a link change decision to change a serving link of a wireless device to a target link include at least: a change of the serving link of the wireless device from the target link to another link; and a network-initiated disconnect of the wireless device from the target link. Regardless, the decision-making equipment (22) is also configured to make a link change decision (28-(M+1)) based on the tracked rewards (30-1, . . . 30-M) and outcomes (28-1, . . . 28-M).

Abstract: An estimated or predicted dose for radiotherapy treatment may be generated based on a partial dose map including dose information only for one or more regions of interest within a treatment site, by use of a properly trained machine learning system such as a U-Net or a V-Net. Said partial dose map typically set to fulfil clinical goals. A method of training such a machine learning system is also disclosed.

Abstract: An estimated or predicted dose for radiotherapy treatment may be generated based on a partial dose map including dose information only for one or more regions of interest within a treatment site, by use of a properly trained machine learning system such as a U-Net or a V-Net. Said partial dose map typically set to fulfil clinical goals. A method of training such a machine learning system is also disclosed.

Abstract: A method (100) for generating a treatment plan specifying an irradiation of a patient, the method comprising: a dose inference stage (112), including using a model to infer a spatial dose from patient data; a dose mimicking stage (116), including executing a robust optimization process to generate a deliverable treatment plan which is consistent with the inferred spatial dose, wherein the robust optimization considers a plurality of scenarios relating to patient data uncertainty.

Abstract: A touch sensing apparatus is disclosed for detecting touch pressure, comprising a panel that defines a touch surface, the panel having a perimeter, a plurality of emitters arranged along the perimeter, wherein the emitters emit light across the panel, a plurality of detectors arranged along the perimeter, whereby the detectors are arranged to receive at least part of said light as detection light, wherein the touch sensing apparatus is configured to determine, as a touch object deflects the panel along a normal of the touch surface, a difference in the received detection light between deflection of the panel from a first position (p1) to a second position (p2) along the normal, and determine a pressure of the touch object against the touch surface based on said difference.

Abstract: The disclosure relates to a sliding door operator system (1) for opening and closing an opening (2), comprising: a track (3) configured to be mounted at an upper part (21) of the opening (2), one or more sliding door(s) 10 slidably connected to the track (3) and comprising a door leaf (4) configured to be moved along the track (3) between an open (o) and closed (c) position, and a drive unit (5) mounted on the door leaf (4), moveably connected to the track (3) and arranged to move the door leaf (4) between the closed position (c) and the open position (o). The disclosure further relates to a drive unit (5) for moving a sliding door leaf (4) between an open and a closed position (O, C) and a control system (11) for regulating one or more sliding door (10).

Abstract: A touch sensing apparatus is disclosed comprising a touch surface, and a touch sensor configured to determine a first set of coordinates on the touch surface of an object in contact with the touch surface. The touch sensing apparatus is configured to determine a virtual brush angle associated with the object, determine a movement of the object to a second set of coordinates determine an updated virtual brush angle for the object in dependence on a position of the second set of coordinates relative to the first set of coordinates, and output the second set of coordinates and the updated virtual brush angle. An associated method is also disclosed.

Abstract: A method of predicting the behaviour of one or more objects on a touch surface of a touch-sensitive apparatus comprises outputting an object position value of a first time series describing a position of the one or more objects on the touch surface. The method further comprises outputting an object position value of a second time series describing a position of the one or more objects on the touch surface. The object position value of the second time series is outputted before the corresponding object position value of the first time series. The method yet further comprises predicting the behaviour of the one or more objects based at least on the object position values of the second time series.

Abstract: A method of predicting the behaviour of one or more objects on a touch surface of a touch-sensitive apparatus comprises outputting an object position value of a first time series describing a position of the one or more objects on the touch surface. The method further comprises outputting an object position value of a second time series describing a position of the one or more objects on the touch surface. The object position value of the second time series is outputted before the corresponding object position value of the first time series. The method yet further comprises predicting the behaviour of the one or more objects based at least on the object position values of the second time series.

Abstract: A touch sensing apparatus is disclosed comprising a touch surface, and a touch sensor configured to determine a first set of coordinates on the touch surface of an object in contact with the touch surface. The touch sensing apparatus is configured to determine a virtual brush angle associated with the object, determine a movement of the object to a second set of coordinates determine an updated virtual brush angle for the object in dependence on a position of the second set of coordinates relative to the first set of coordinates, and output the second set of coordinates and the updated virtual brush angle. An associated method is also disclosed.

Abstract: A web-like or sheet-like semi-finished product capable of forming a polymeric foam composite material by heat treatment, which semi-finished product is formed by a web-like or sheet-like fibrous material and a mixture having curable resin and unexpanded thermoplastic particles of at least two different qualities with mutually different expansion temperature introduced into the fibrous material are provided, in which thermoplastic particles of at least one of these qualities remain unexpanded in the semi-finished product. A polymeric foam composite material is also formed by such a semi-finished product. Furthermore, methods for producing such a semi-finished product and such a polymeric foam composite material are provided.

Abstract: A web-like or sheet-like semi-finished product capable of forming a polymeric foam composite material by heat treatment, which semi-finished product is formed by a web-like or sheet-like fibrous material and a mixture having curable resin and unexpanded thermoplastic particles of at least two different qualities with mutually different expansion temperature introduced into the fibrous material are provided, in which thermoplastic particles of at least one of these qualities remain unexpanded in the semi-finished product. A polymeric foam composite material is also formed by such a semi-finished product. Furthermore, methods for producing such a semi-finished product and such a polymeric foam composite material are provided.

Abstract: To reduce current density in a transistor in an IC comprising a plurality of interdigitated drain, source and gate fingers (10, 11, 12) a first current distributing plate (1) is part of a metal layer of the IC and is connected by first vias (5) to all drain fingers (10) and a second current distributing plate (2) is also part of the metal layer of the IC and is connected by second vias (6) to all source fingers (11).

Abstract: Fluid dispensing apparatus (10) for selectively dispensing desired quantities of a fluid under pressure. The apparatus includes a base plate (14) having a dispensing passage (16) extending about a first axis (18); a valve arrangement (20) associated with the dispensing passage (16), and a piezoelectric transducer (22) acting on the valve arrangement (20) to effect displacement of the valve arrangement between a first position in which the dispensing passage (16) is closed and a second position in which the dispensing passage is connected to a source of the fluid under pressure. The valve arrangement (20) includes a slide valve (24), with the slide valve and the piezoelectric transducer (22) being arranged such that during at least initial displacement of the valve arrangement from the second position towards the first position, the slide valve (24) is displaced in a direction transverse to the first axis (18).