Abstract: The correlation of per-session network logs with trouble reports provided by the users/user devices via a trouble reporting app generates labeled training information used to train Machine Learning (ML) models that are subsequently used to infer, explain, and address service issues associated with an application service session. As such, the level of automation for Quality of Experience (QoE) management increases, while the accuracy of such QoE management increases and a subscriber's experience improves.

Abstract: We generally describe a detection system and a method for tracking a moving object. The detection system (101) comprises a sensor (102) which is configured to sense an event. The system further comprises a trigger detection module (108a) which is coupled to the sensor (102), wherein the trigger detection module (108a) is configured to identify the sensed event to be a trigger event. The system further comprises an imaging device (114) for imaging the trajectory of an object, and an imaging device control unit (112) for controlling the imaging device (114). The imaging device control unit (112) is coupled to the trigger detection module (180a), wherein the imaging device control unit (112) is configured to control the imaging device (114) in response to a trigger event being identified by the trigger detection module (108a).

Abstract: Methods and apparatus for root cause analysis. A method includes obtaining measurement data including measurements data of features of a system. The method further includes generating a prediction value by applying a trained machine learning model to the measurement data, and also generating feature impact values by applying a generated machine learning model explainer to the measurement data. The method further includes updating an ontological representation of connections between the features of the system and the prediction value using the generated feature impact values and, based on the updated ontological representation, outputting a proposed root cause that is responsible for the prediction value.

Abstract: The correlation of per-session network logs with trouble reports provided by the users/user devices via a trouble reporting app generates labeled training information used to train Machine Learning (ML) models that are subsequently used to infer, explain, and address service issues associated with an application service session. As such, the level of automation for Quality of Experience (QoE) management increases, while the accuracy of such QoE management increases and a subscriber's experience improves.

Abstract: There is provided a method for assessing network performance. The method includes acquiring network measurements indicative of any changes in a network following a change to a configuration of the network and data indicative of one or more factors capable of causing the changes in the network. The one or more factors are independent of the change to the configuration of the network. The method includes analysing the acquired network measurements and data to identify a contribution of the one or more factors to a key performance indicator (KPI) and a contribution of the change to the configuration of the network to the KPI. The KPI is predicted by a machine learning model and is a measure of the network performance following the change to the configuration of the network.

Abstract: A sensor control system (202) for managing at least a first set of one or more sensors (101) for monitoring a first domain of an industrial process and a second set of one or more sensors (102) for monitoring a second domain of the industrial process, wherein the sensor control system (202) comprises at least a first reinforcement learning, RL, agent (A1) and a second RL agent (A2), wherein the first and second RL agents were trained using reinforcement learning and a process graph (196) representing the industrial process.

Abstract: The present disclosure relates an evacuation management system, EMS, (40, 52, 60, 00, 200) operative to provide real-time evacuation information for evacuation of a building, triggered by alarm notification (S202). Based on determined (S214) precise real-time positions of personal ultra-wide band, UWB, devices, as determined by UWB real-time localization system, RTLS, a controller determines (S210) evacuation plans being personal UWB device specific in real-time. Based on individual evacuation plans and input from building facilities, real-time guidance information is defined (S208) and sent to each personal UWB device, providing guidance to person carrying said personal UWB device, in what direction to move (S212), to reach a safe area. Based on localization signals the UWB RTLSA then calculates updated positions of the personal UWB devices and sends to the evacuation management system. It is an advantage that trapped or injured people can be found, even in low visibility areas.

Abstract: A method for controlling a handling of a further object (90) which is handled at a site (10) by at least two different workstations (51, 52) and which is moved between the at least two different workstations,—determining a site plan of the site (10), the site plan indicating the at least two workstations at predefined positions in the site plan,—determining a trajectory of a first object (90) moving in the site (10) in an absolute coordinate system of the site,—deducing absolute positions of the at least two workstations (51, 52) in the absolute coordinate system from the determined trajectory of the first object,—using the absolute positions of the at least two workstations (51, 52) for controlling the handling of the at least one further object handled by the at least two workstations.

Abstract: An anchor system for a location system tracks a location of a tag device mounted to a mobile entity using a plurality of anchor devices. The anchor system comprises an anchor cable, a first anchor device affixed to the anchor cable, one or more second anchor devices affixed to the anchor cable, and a power supply circuit. Each of the second anchor device(s) is spaced from the first anchor device along a length of the anchor cable by a predetermined distance. The power supply circuit is operatively connected to the anchor cable and is configured to supply power to each of the anchor devices via the anchor cable. Each of the anchor devices is configured to wirelessly communicate with the tag device, e.g., which enables a remote network of processors in communication with the anchor devices to determine location data for the tag device.

Abstract: A technique for updating a positioning configuration in a positioning system comprising a plurality of anchor nodes for determining positions of tag devices within a localization area using radio technology is disclosed. A method implementation of the technique comprises determining (S202) an updated positioning configuration for at least one of a set of tag devices and a set of anchor nodes of the positioning system based on predefined positioning requirements that depend on a zone of the localization area in which the set of tag devices is currently located, and applying (S204) the updated positioning configuration to the at least one of the set of tag devices and the set of anchor nodes.

Abstract: A technique for assessing positioning qualities within a localization area of a positioning system comprising a plurality of anchor nodes for determining positions of tag devices within the localization area using radio technology is disclosed. A method implementation of the technique comprises determining (S202) a positioning deviation between an absolute position of a tag device and a relative position of the tag device, the absolute position of the tag device being determined by the positioning system using the plurality of anchor nodes and the relative position of the tag device being determined based on movement related measurements performed by the tag device relative to a previously determined absolute position of the tag device, and assessing (S204) a positioning quality for the absolute position based on the determined positioning deviation.

Abstract: A technique for determining a relative position of a preceding vehicle with respect to a succeeding vehicle in a vehicle platoon is disclosed, wherein the succeeding vehicle comprises at least two front tags and the preceding vehicle comprises at least two back tags, the front and back tags being configured to perform ranging measurements among each other using radio technology. A method implementation of the technique comprises determining (S202) pairwise distances between the front and back tags using ranging measurements performed by the front and back tags using the radio technology, and determining (S204) the relative position of the preceding vehicle with respect to the succeeding vehicle based on the determined pairwise distances.

Abstract: We generally describe a collision prevention system (100) comprising: a localization system (402) for determining positions of an autonomous vehicle (104) and a human (106); and a collision determination unit (404) coupled to or in communication with the localization system (402), wherein the collision determination unit (404) is configured to determine, based on the determined positions of the autonomous vehicle (104) and the human (106), whether a predefined condition for an anticipated collision of the autonomous vehicle (104) with the human (106) is met; wherein the collision prevention system (100) is configured to: lock the autonomous vehicle (104) if the predefined condition is met; alert the human (106) for whom the predefined condition for colliding with the autonomous vehicle (104) is met; and allow unlocking of the autonomous vehicle (104) to be performed or initialized by the alerted human (106) only.

Abstract: A technique for locating a target tag (110) using a short range radio based positioning system comprising a plurality of localization components (120) is provided, wherein the target tag (110) and the plurality of localization components (120) are configured to perform ranging measurements among each other using short range radio technology. A method implementation of the technique is performed by an orchestration component (100) of the positioning system and comprises sending, using long range radio technology, a ranging plan to the target tag (110) and one or more of the plurality of localization components (120), the ranging plan instructing the target tag (110) and the one or more of the plurality of localization components (120) to perform, using the short range radio technology, ranging measurements among each other enabling to locate the target tag (110).

Abstract: A computer system and computer-automated method for analyzing performance data in a utility network, such as electricity, gas or water supply, are described. A data set is provided that contains a log of a first time sequence of network events which are classified into event types. A second time sequence is generated from the first time sequence by aggregating the events into event groups, and at least a third time sequence is generated by aggregating the event groups into event super-groups. A multi-level time sequence event hierarchy is thus created. The multiple time-sequence levels are rendered into a visualization in which the different event types are visually distinct from each other. The visualization reveals to a domain expert patterns of behavior in the data set which can be used to detect current network problems and to predict future network supply and consumption, for example in a utility network operations center.

Abstract: A computer system and computer-automated method for analyzing performance data in a utility network, such as electricity, gas or water supply, are described. A data set is provided that contains a log of a first time sequence of network events which are classified into event types. A second time sequence is generated from the first time sequence by aggregating the events into In event groups, and at least a third time sequence is generated by aggregating the event groups into event super-groups. A multi-level time sequence event hierarchy is thus created. The multiple time-sequence levels are rendered into a visualization in which the different event types are visually distinct from each other. The visualization reveals to a domain expert patterns of behavior in the data set which can be used to detect current network problems and to predict future network supply and consumption, for example in a utility network operations center.

Abstract: It is disclosed a method, and a system (30) capable of localizing ball hit events on a sports court. From on acoustics data acquired (22) of ball hit events by individual distributed sensors or microphones, ball hitting patterns are identified (24) in the data from each individual sensor. Based on the identified ball hitting patterns and geometric constraints of a sports court and the distribution of sensors, ball hit events are detected (26). The localization of the detected ball bit events is determined (28) based on the geometrical constraints of the sports court and the sensor distribution. The system has a number of advantages of which some are that it is cheap to install, it is non-invasive, and that it can easily be extended to provide higher precision of ball hit event localization.

Abstract: A computer system and computer-automated method for analyzing sports performance data from a game. A data set is provided that contains a log of a first time sequence of game data events which are classified into event types. A second time sequence is generated from the first time sequence by aggregating the events into game patterns, and a third time sequence is generated by aggregating the game patterns into game strategies. A multi-level time sequence event hierarchy is thus created. These multiple time sequence levels are rendered into a visualization in which the different types at each level are visually distinct from each other. The visualization reveals to a game expert player or team behavior in the data set which can be used for player and team improvement.

Abstract: A computer system and computer-automated method for analyzing performance data in a telecommunications network. A data set is provided that contains a log of a first time sequence of network events which are classified into event types. A second time sequence is generated from the first time sequence by aggregating the events into event groups, and at least a third time sequence is generated by aggregating the event groups into event super-groups. A multi-level time sequence event hierarchy of at least three levels is thus created. The multiple time sequence levels are rendered into a visualization in which the different event types are visually distinct from each other. The visualization reveals to a domain expert patterns of behavior in the data set which can be used to detect current network problems and to predict future network loading, for example in a network operations center.

Abstract: An anchor system for a location system tracks a location of a tag device mounted to a mobile entity using a plurality of anchor devices. The anchor system comprises an anchor cable, a first anchor device affixed to the anchor cable, one or more second anchor devices affixed to the anchor cable, and a power supply circuit. Each of the second anchor device(s) is spaced from the first anchor device along a length of the anchor cable by a predetermined distance. The power supply circuit is operatively connected to the anchor cable and is configured to supply power to each of the anchor devices via the anchor cable. Each of the anchor devices is configured to wirelessly communicate with the tag device, e.g., which enables a remote network of processors in communication with the anchor devices to determine location data for the tag device.