Abstract: A dense point cloud (DPC) is generated for a physical object. 2D digital images of the physical object are obtained. Object extractors are defined. A sparse point cloud (SPC) is created from the 2D digital images. A modified SPC is obtained by first applying the object extractors to the 2D digital images to exclude pixels from the 2D digital images and then excluding the datapoints in the SPC that correspond to the pixels that have been excluded from the 2D digital images. The datapoints of the SPC that do not represent the object are excluded from being included in the modified SPC. The DPC is generated by integrating information obtained from the pixels in the 2D digital images with the modified SPC.

Abstract: A method for a feasibility check of a new RAN slice performed by a network node is provided. The method includes computing a first estimate of occupied resources for each resource within at least one of the network node and a cell of the network node. The first estimate performed for each resource using historical data of a measurement of utilization of each resource. The method further includes applying a trained supervised machine learning model to provide a second estimate of resource demand for each resource for the new RAN slice. The method further includes comparing a sum of the first estimate and the second estimate to a defined threshold value; and admitting the new RAN slice when the sum has a value not greater than the defined threshold value per resource.

Abstract: The present disclosure provides a method of configuring a Radio Access Network (RAN) node to use one or more RAN functions. The method comprises obtaining input data for the RAN node, in which the input data comprises configuration information performance information for the RAN node. Based on the input data, one or more target performance indicators and a constraint on one or more resources for the RAN node, an optimisation process is used to select one or more RAN functions for activation by the RAN node. The optimisation process uses one or more models for predicting, based on the input data and a selection of RAN functions, usage of the one or more resources and a value of the one or more target performance indicators. The RAN node is configured to use the one or more selected RAN functions.

Abstract: Embodiments herein disclose a method for selecting a machine learning model to be deployed in an execution environment having resource constraints. The method comprises receiving, by an apparatus, a request for a machine learning model solving a task T using a feature set F. Further, the method includes retrieving, from a model store, a first set of machine learning models that solves the task T using at least a subset of features F. The complexity of each machine learning model in the first set of machine learning models is calculated. The method includes determining, from the first set of machine learning models, at least one suitable machine learning model to be deployed, wherein the determining is based on the calculated complexity and the resource constraints of the execution environment.

Abstract: Embodiments herein disclose a method for selecting a machine learning model to be deployed in an execution environment having resource constraints. The method comprises receiving, by an apparatus, a request for a machine learning model solving a task T using a feature set F. Further, the method includes retrieving, from a model store, a first set of machine learning models that solves the task T using at least a subset of features F. The complexity of each machine learning model in the first set of machine learning models is calculated. The method includes determining, from the first set of machine learning models, at least one suitable machine learning model to be deployed, wherein the determining is based on the calculated complexity and the resource constraints of the execution environment.

Abstract: Methods, devices, and a system for prediction of Radio Access Network performance. A device for training a prediction model for predicting Radio Access Network performance obtains information associated with at least one network element; determines a tag for the at least one network element, wherein the tag is based on a network environment property of the at least one network element; and determines, based on the tag, a cluster to be associated with the at least one network element. The device determines a performance indicator value for the at least one cluster, creates a training set comprising the performance indicator value of at least one cluster; and trains a prediction model using the training set. The prediction model trained by the device can be used by a device for prediction of Radio Access Network performance.

Abstract: Embodiments herein disclose a method performed by a computing device (11) for handling an object in one or more recorded images of a structure. The computing device (11) receives from one or more mobile devices (15), at least two recorded images of the structure. The computing device (11) aligns the at least two recorded images vertically and/or horizontally based on the structure and/or an object in the at least two recorded images. The computing device (11) further computes a location similarity of the object in the at least two recorded images by comparing location values of the object in the aligned at least two recorded images, and computes a visual similarity of the object in the at least two recorded images by comparing visual characteristics of the object. The computing device (11) further determines whether the object is the same or not in the at least two recorded images.

Abstract: There is provided a method for estimating power saved in a first network. The method is performed by a system. The method includes estimating the power saved in the first network as a difference between: a relationship between power consumption in the first network as a function of physical resource block usage in the first network when a power saving feature is deactivated in the first network, and at least one data point indicative of the power consumption in the first network for a physical resource block usage value when the power saving feature is activated in the first network.

Abstract: Presented are methods for performing a constant time flow lookup utilizing parallel processing technology. The methods are suitable for multiprocessor and/or multi-core processor computing environments. The method generates hash table driven tables of exact flow matching patterns and then provides the generated tables to parallel processing based flow selection procedure that iteratively finds the highest priority flow from the exact flow matching patterns. The method is scalable based on the linear relationship between the number of processors and/or processor cores and the time required to perform the lookup. The method is also portable because it does not require any special or custom hardware typically associated with this type of lookup.

Abstract: Presented are methods for performing a constant time flow lookup utilizing parallel processing technology. The methods are suitable for multiprocessor and/or multi-core processor computing environments. The method generates hash table driven tables of exact flow matching patterns and then provides the generated tables to parallel processing based flow selection procedure that iteratively finds the highest priority flow from the exact flow matching patterns. The method is scalable based on the linear relationship between the number of processors and/or processor cores and the time required to perform the lookup. The method is also portable because it does not require any special or custom hardware typically associated with this type of lookup.