Abstract: A computer-implemented model for protecting an artificial intelligence (AI) model from tampering is provided. The method includes determining a convergence of the AI model. The method further includes, responsive to the determining, identifying a set of baseline parameters of the converged AI model. The method further includes generating a first watermark for the converged AI model based on applying one or more transformations to each baseline parameter from the set of baseline parameters, wherein the first watermark comprises a value external to the converged AI model.

Abstract: A controller node (18) and method for determining a network parameter are provided. The controller node (18) determines (S240) type information associated with wireless devices which are connected to a radio network node. The controller node (18) further determines (S250) the network parameter based on the type information.

Abstract: A method (200) for identifying a fault in data representing a target variable of a system is disclosed. The system comprises a plurality of variables and each variable is represented by a data stream. The method comprises obtaining a reference data set for a set of variables in the system including the target variable (202), obtaining an operational data set for the set of variables in the system including the target variable (204) and, for each of the reference and operational data sets, constructing an adjacency matrix between the target variable and the other variables in the set of variables (208), wherein the adjacency matrix is constructed on the basis of a metric calculated between the target variable and the other variables of the set (208a).

Abstract: A method of allocating radio resources in a cellular network by a network node associated with a destination cell. Prior to a handover of a moving user equipment (UE) from an originating cell to the destination cell, receiving a moving user resource requirement and a predicted handover time for the moving UE, estimating a total resource requirement comprising a sum of the moving user resource requirement and an initial resource requirement comprising a sum of resource requirements of other UEs in the destination cell, determining whether a capacity of the destination cell is sufficient to provide for the total resource requirement.

Abstract: The present invention is a method and system for collection of exhaust emissions installed in vehicles and disposal thereof, based on pollution conditions of the surrounding environment, said conditions identified either from sensors installed on the vehicles themselves, or by means of an external service, e.g. the Internet, cloud service, etc.

Abstract: The present disclosure is directed towards a data storage setting arrangement in a federated database system that includes applications configured to handle data in corresponding databases. The arrangement includes a communication interface for obtaining application requirement data (AIC) related to database usage, a database determining unit for predicting database type using the application requirement data and selecting database based on the database type prediction, a processing type determining unit for predicting database processing type based on the application requirement data and selecting database processing type based on the processing type prediction, a data model creating unit for creating a data model for storing of data in the database based on the application requirement data and an instantiating unit for instantiating a connection between the application and the selected database based on the selected database processing type and data model.

Abstract: The present disclosure relates to a method performed by a network element in an operator network for assessing a quality of experience (QoE) of a service for a radio device. The method comprises receiving a first value of a key performance indicator (KPI) of the service from the radio device. The method also comprises receiving a second value of the KPI from the operator network serving the radio device. The method also comprises comparing the first and the second values of the KPI, and determining any deterioration of the QoE over the operator network, based on said comparing. The present disclosure also relates to a method of the radio device as well as to the network element and the radio device.

Abstract: A method of allocating radio resources in a cellular network by a network node associated with a destination cell. Prior to a handover of a moving user equipment (UE) from an originating cell to the destination cell, receiving a moving user resource requirement and a predicted handover time for the moving UE, estimating a total resource requirement comprising a sum of the moving user resource requirement and an initial resource requirement comprising a sum of resource requirements of other UEs in the destination cell, determining whether a capacity of the destination cell is sufficient to provide for the total resource requirement.

Abstract: The present invention is a method and system for collection of exhaust emissions installed in vehicles and disposal thereof, based on pollution conditions of the surrounding environment, said conditions identified either from sensors installed on the vehicles themselves, or by means of an external service, e.g. the Internet, cloud service, etc.

Abstract: A method for identifying influence paths in a communication network comprising a plurality of users is disclosed. The method comprises identifying network parameters indicative of a strength of connection between users of the network, combining the identified parameters to calculate a connection strength between users of the network, storing the calculated connection strengths as edge weights between the users of the network, identifying a source user and a target user for a path, and calculating a path between the source user and the target user according to the stored edge weights. Also disclosed is a method for compression of a network and a network element and computer readable medium.

Abstract: The present disclosure relates to a method performed by a network element in an operator network for assessing a quality of experience (QoE) of a service for a radio device. The method comprises receiving a first value of a key performance indicator (KPI) of the service from the radio device. The method also comprises receiving a second value of the KPI from the operator network serving the radio device. The method also comprises comparing the first and the second values of the KPI, and determining any deterioration of the QoE over the operator network, based on said comparing. The present disclosure also relates to a method of the radio device as well as to the network element and the radio device.

Abstract: Network resource configuration is provided by receiving subscriber data, the subscriber data relating to network related activities and subscriber related activities of subscribers in a group of subscribers of a network operator of a communications system. A churn score is determined for each subscriber in the group of subscribers based on a set of churn score parameters for the subscriber data, the churn score representing probability of a subscriber to churn. A subgroup of subscribers is determined from the group of subscribers based on the churn score. A network resource configuration in the communications system is determined for the subgroup of subscribers based on the churn score. Information relating to the determined network resource configuration and/or a service related to the determined network resource configuration is transmitted.

Abstract: A method for identifying influence paths in a communication network comprising a plurality of users is disclosed. The method comprises identifying network parameters indicative of a strength of connection between users of the network, combining the identified parameters to calculate a connection strength between users of the network, storing the calculated connection strengths as edge weights between the users of the network, identifying a source user and a target user for a path, and calculating a path between the source user and the target user according to the stored edge weights. Also disclosed is a method for compression of a network and a network element and computer readable medium.

Abstract: The present disclosure is directed towards a data storage setting arrangement in a federated database system that includes applications configured to handle data in corresponding databases. The arrangement includes a communication interface for obtaining application requirement data (AIC) related to database usage, a database determining unit for predicting database type using the application requirement data and selecting database based on the database type prediction, a processing type determining unit for predicting database processing type based on the application requirement data and selecting database processing type based on the processing type prediction, a data model creating unit for creating a data model for storing of data in the database based on the application requirement data and an instantiating unit for instantiating a connection between the application and the selected database based on the selected database processing type and data model.

Abstract: The present disclosure is directed towards a connection tuning arrangement for tuning connection parameters of databases in a federated database system. The database system includes a least one application configured to access one or more databases. The connection tuning arrangement includes a data stream monitoring unit configured to monitor a number of application specific parameters in data streams of an application, the monitoring being performed in at least one context, and learn the behaviour of the data streams. A performance tuning unit is configured to tune connection parameters based on the behaviour.

Abstract: Network resource configuration is provided by receiving subscriber data, the subscriber data relating to network related activities and subscriber related activities of subscribers in a group of subscribers of a network operator of a communications system. A churn score is determined for each subscriber in the group of subscribers based on a set of churn score parameters for the subscriber data, the churn score representing probability of a subscriber to churn. A subgroup of subscribers is determined from the group of subscribers based on the churn score. A network resource configuration in the communications system is determined for the subgroup of subscribers based on the churn score. Information relating to the determined network resource configuration and/or a service related to the determined network resource configuration is transmitted.

Abstract: In one aspect, the teachings herein provide a method and apparatus for identifying the new network affiliation of a churned subscriber that has moved from an old network operator to a new network operator. Knowing the new network affiliation of a former subscriber provides a number of significant advantages to the old network operator. By way of non-limiting example, the old network operator can undertake new or adjusted advertising targeted at retaining remaining subscribers of like demographics. Additionally or alternatively, the old network operator can review pricing and service plans from the new network operator that are comparable to that used by the former subscriber, and make competitive pricing or service adjustments.

Abstract: In one aspect, the teachings herein provide a method and apparatus for identifying the new network affiliation of a churned subscriber that has moved from an old network operator to a new network operator. Knowing the new network affiliation of a former subscriber provides a number of significant advantages to the old network operator. By way of non-limiting example, the old network operator can undertake new or adjusted advertising targeted at retaining remaining subscribers of like demographics. Additionally or alternatively, the old network operator can review pricing and service plans from the new network operator that are comparable to that used by the former subscriber, and make competitive pricing or service adjustments.

Abstract: The present invention relates to an iterative method and an apparatus for distribution-independent detection of intermediate outliers and outliers in the distribution tail of streamed data. A considerable sequence of streamed data is sequentially read and subsequently assigned to matching bins. The bins are adaptively allocated when, where and if they are needed. Each bin range expands concurrently with the distribution range of the accumulating items assigned to the bin, adding a margin. For every N'th read item, overlapping or adjoining bins are merged, whereupon the bins are assessed for insider preclusion. Information regarding outliers is extracted from the remaining outlier bins when the entire data sequence has been processed.

Abstract: The present invention relates to an iterative method and an apparatus for distribution-independent detection of intermediate outliers and outliers in the distribution tail of streamed data. A considerable sequence of streamed data is sequentially read and subsequently assigned to matching bins. The bins are adaptively allocated when, where and if they are needed. Each bin range expands concurrently with the distribution range of the accumulating items assigned to the bin, adding a margin. For every N'th read item, overlapping or adjoining bins are merged, whereupon the bins are assessed for insider preclusion. Information regarding outliers is extracted from the remaining outlier bins when the entire data sequence has been processed.