Abstract: This disclosure relates to learning with transformed data such as determining multiple training samples from multiple data samples. Each of the multiple data samples comprises one or more feature values and a label that classifies that data sample. A processor determines each of the multiple training samples by randomly selecting a subset of the multiple data samples, and combining the feature values of the data samples of the subset based on the label of each of the data samples of the subset. Since the training samples are combinations of randomly chosen data samples, the training samples can be provided to third parties without disclosing the actual training data. This is an advantage over existing methods in cases where the data is confidential and should therefore not be shared with a learner of a classifier, for example.

Abstract: Described herein is an energy harvesting system comprising a transducer and a processor. The transducer generates an electric signal from ambient energy. The processor is configured to process the electric signal to perform pattern recognition of the electric signal so as to determine and output a characteristic of a source of the ambient energy. The pattern recognition comprises statistical analysis and frequency domain analysis.

Abstract: Described is device for monitoring an activity. The device comprises a transducer that generates electric power from the activity and an energy store that stores the electric power over consecutive time intervals. The device further comprises a transmitter that periodically transmits the stored energy as an activity pulse indicative of an activity classification.

Abstract: Described is an energy harvesting system comprising a transducer that generates an electric signal from ambient energy, and a processor adapted to process the electric signal to determine and output a characteristic of a source of the ambient energy. The characteristic may be a spoken word classification.

Abstract: Described is an energy harvesting system comprising a transducer that generates an electric signal from ambient energy, and a processor adapted to process the electric signal to determine and output a characteristic of a source of the ambient energy. The characteristic may be a spoken word classification.

Abstract: This disclosure relates to analyzing log data of a system. This comprises evaluating a first graph model with multiple log events in the log data. The first graph model comprises a first set of nodes connected by a first set of edges representing a first behaviour. A processor determines a first correspondence value based on the first graph model and indicative of a correspondence between the multiple log events and the first behaviour. The processor repeats the steps of evaluating the first graph model for one or more further graph models representing one or more further behaviors and determining the first correspondence value to determine one or more further correspondence values. The processor finally determines a classification of the multiple log events as representing one of the behaviors based on the correspondence values. The use of multiple graph models allows a more granular classification than binary intrusion detection.

Abstract: This disclosure relates to learning from distributed data. In particular, it relates to determining multiple first training samples from multiple first data samples. Each of the multiple first data samples comprises multiple first feature values and a first label that classifies that first data sample. A processor determines each of the multiple first training samples by selecting a first subset of the multiple first data samples such that the first subset comprises data samples with corresponding one or more of the multiple first feature values, and combining the first feature values of the data samples of the first subset based on the first label of each of the first data samples of the first subset. The resulting training samples can be combined with training samples from other databases that share the same corresponding features and entity matching is unnecessary.

Abstract: A computer-implemented method, software and system for determining a service demand in a service network are disclosed. A first information indicative of prior proportion knowledge of elements of the service demand is received. Two or more elements of the service demand represent service volumes for two or more pairs of zones and the first information indicates reference relative relationships between the two or more elements of the service demand. Second information indicative of instances of service at specific locations in the service network are received. The service demand is determined by minimising a cost function. The cost function is based on the first information and the second information.

Abstract: Computer-implemented methods, software, and computer systems for authenticating a user. Authentication includes presenting on a first user interface a challenge set of cognitive information elements (400) to the user that comprises a cognitive challenge that has a reference solution based on an intersection of the challenge set of cognitive information elements and a secret set of cognitive information elements. Biometric features of the user can be extracted from a response made by the user to the cognitive challenge on a second user interface, and the user can be authenticated if the biometric feature extracted from the response matches a reference biometric feature.

Abstract: There is provided a computer-implemented method for controlling operation of a plurality of devices of a facility that consume energy. The method comprises obtaining parameters of an energy model representing the energy consumed by the plurality of devices of the facility, the energy model including a first plurality of variables for operating the plurality of devices and a second plurality of variables for scheduling activities to be conducted in the facility; receiving requests for the activities to be conducted in the facility, the requests including requirements in relation to the activities; and automatically determining, based on the energy model, values of the first plurality of variables to control the operation of the plurality of devices, and values of the second plurality of variables that meet the requirements in relation to the activities.

Abstract: An alternating current (AC) power flow analysis in an electrical power network. Based on information relating to buses and transmission lines connecting the buses in the electrical power network, a convex approximation of AC power flows in the electrical power network is determined. The convex approximation of the AC power flows comprises convex approximation of nonlinear cosine terms associated with active power components and reactive power components of the AC power flows. A convex objective function associated with the electrical power network is optimised using the convex approximation of the AC power flows.

Abstract: The present disclosure provides a computer-implemented method for enhancing vision for a vision impaired user. The method comprises, for a point in an input image, determining (210) a weight for the point based on visual importance of the point in the input image; comparing (220) the weight for the point to a threshold; and if the weight for the point meets the threshold, determining (230) a first output value for an imaging element of a vision enhancement apparatus so that a difference between the first output value and an intensity level of a portion of the input image neighbouring the point increases with the weight, wherein the difference is at least one Just-Noticeable-Difference of the vision enhancement apparatus, such that when the first output value is applied to the imaging element of the vision enhancement apparatus to create a first visual stimulus, the first visual stimulus is substantially perceivable by the vision impaired user.

Abstract: This disclosure relates to processing colour images to reconstruct hyperspectral images from the colour images. An image processor determines an output hyperspectral image by determining for each point of the output hyperspectral image a combination of multiple hyperspectral prototype components to correspond the output hyperspectral image to the input image. Each of the multiple hyperspectral prototype components comprises multiple component values associated with respective wavelengths and each of the multiple component values is based on multiple points of training image data associated with the wavelength of that component value. Since the component values are based on multiple points of the training image, relationships between points in the training image, such as texture, can be used to reconstruct the hyperspectral image data, which leads to a more robust and more accurate reconstruction.

Abstract: The disclosure concerns estimating an illumination spectrum of a pixel of hyperspectral or multispectral image data. A processor determines an optimised illumination spectrum for a first point based on an initial illumination spectrum and based on associations between the first point and multiple second points of multiple instances of the image data, wherein each of the multiple instances is associated with a refined amount of image information. It is possible to determine the illumination spectrum per pixel of the original image data without clustering pixels or restrictive assumptions but instead by utilising the associations for the statistical inference on the illumination spectrum.

Abstract: The present disclosure provides a computer-implemented method for representing intensity levels indicative of a first type of sense of a subject (150) by parameter values for a different second type of sense of the subject (150). The method comprises determining (210) a first parameter value for the second type of sense representing a first intensity level indicative of the first type of sense; and determining (220) a second parameter value for the second type of sense representing a second intensity level indicative of the first type of sense with reference to the first parameter value, wherein the first parameter value differs from the second parameter value by at least one Just-Noticeable-Difference (JND) of the second type of sense of the subject (150).

Abstract: The present invention generally relates to failure prediction of an infrastructure (110). A failure likelihood for one or more components of an infrastructure (110) is determined. History data (210) representing prior failures of the components of the infrastructure (110) is applied (230-250) to a Bayesian nonparametric statistical model using a beta process. Then the failure likelihood of one or more components of the infrastructure from the Bayesian nonparametric statistical model is estimated (270). Aspects of the invention include computer-implemented methods (200, 300), software and computer systems (100).

Abstract: This disclosure concerns the determination of electronic multispectral or hyperspectral images, such as by a processor in a camera. The processor receives first image sensor signals that are associated with a first wavelength and with multiple first imaging elements at respective first imaging element locations. The processor determines a spline approximation to the first image sensor signals across the first imaging element locations and determines the multispectral or hyperspectral image data by interpolating the spline approximation at the pixel location. Finally, the image data is stored on a data store. Using splines to interpolate the image sensor signals outperforms other methods, which means increased image quality due to more accurate interpolation. More specifically, using splines leads to a more accurate spectrum at each point and reduced spectral error compared to other methods.

Abstract: This disclosure relates a processor determining a network map of a transport network by. The processor optimises for each of multiple sets of nodes a travel cost of trips with a start node and an end node in that set. This way, the processor selects from each of the multiple sets one node as a hub. The travel cost is based on whether the start node or end node is the hub. The processor then optimises for each node a direct travel time between that node and a hub to select an optimised hub for that node. Finally, the processor determines a network map comprising the selected hubs connected by a first transport mode and the remaining nodes connected to the selected hub by a second transport mode. Passengers need to change less often at the hub because the hub is placed at the most popular destination or origin.

Abstract: This disclosure relates to generating shares of secret data represented by secret data elements based on a first threshold for the number of shares that allow determining the secret data. The shares are determined based on the secret data, one or more random data elements added to the secret data and coefficients of a systematic maximum distance separable (MDS) code. The MDS code has a number of input data elements that is equal to the first threshold and that is also equal to the number of secret data elements plus the number of the one or more random data elements. The method of determining shares can be used for different data sets and multiple pairs of the shares can be generated to allow performing an operation between the first secret data with the second secret data based on distributed processing of each of the multiple pairs.

Abstract: This disclosure concerns the determination of improved exposure parameters of an image capturing device, such as a multi-spectral or hyper-spectral camera. A processor receives or determines image values for multiple points of an image and receives first one or more exposure parameters that were used to generate the image values. The processor then determines a distribution of the image values. For each point of the image data the processor then determines an enhanced value by equalizing the distribution of the image values. Finally, the processor determines the one or more improved exposure parameters of the image capturing device, such that the one or more improved exposure parameters adjust the received or determined image values towards the enhanced image values. When the exposure parameters are used for capturing a further image, the further image will be enhanced.