Abstract: A defect detection method and apparatus detecting a defect in an object. The method comprises: obtaining ultrasound scan data derived from an ultrasound scan of the object under consideration, the ultrasound scan data being in the form of a set of echo amplitude values representing the amplitude of echoes received from the object during ultrasound scanning at certain spatial and temporal points; processing the ultrasound scan data to remove echo amplitude values received after a predetermined threshold time; generating at least one image from the processed ultrasound scan data; subjecting each generated image to an automated defect recognition process to determine whether there is a defect in the portion of the object represented by the image; issuing a notification indicating whether or not a defect has been found; and, if a defect has been found, storing the result of the automated defect recognition process in a defect database.

Abstract: An image processing method to sample the image to generate patches. Feature vectors are extracted from the patches, and the extracted feature vectors are partitioned into clusters, where feature vectors in the same cluster share a common characteristic. A portion of interest in the image is segmented. An aggregate bounding region creation process is carried out by finding the largest segment and creating a bounding box around it; determining which cluster contains the most patches within the bounding box of the segment; and adding the patches of the determined cluster to an aggregate bounding region for the portion of interest. The aggregate bounding region creation process is repeated for each other segment in order of size. The resulting aggregate bounding region contains all the patches associated with the portion of interest. The patches which fall outside the resulting aggregate bounding region are then removed from the image.

Abstract: An automatic defect detection method for detecting a defect in an object comprises: obtaining ultrasound scan data of the object, dividing echo amplitude values of the data into a plurality of sub-sets; assessing each sub-set to determine whether any echo amplitude values resulted from a structure of interest; computing for each sub-set, using at least a representative position of the structure portion of the sub-set and of a neighboring sub-set, a preselected mathematical function which is directly or inversely proportional to a distance between the representative positions; identifying sub-sets having a computed value that does not meet a predetermined criterion as regions of the ultrasound scan data that require inspection; issuing a notification indicating whether or not a region requiring inspection has been found; and if a region requiring inspection been found, storing data identifying the region in a database.

Abstract: A defect detection method and apparatus detecting a defect in an object. The method comprises: obtaining ultrasound scan data derived from an ultrasound scan of the object under consideration, the ultrasound scan data being in the form of a set of echo amplitude values representing the amplitude of echoes received from the object during ultrasound scanning at certain spatial and temporal points; processing the ultrasound scan data to remove echo amplitude values received after a predetermined threshold time; generating at least one image from the processed ultrasound scan data; subjecting each generated image to an automated defect recognition process to determine whether there is a defect in the portion of the object represented by the image; issuing a notification indicating whether or not a defect has been found; and, if a defect has been found, storing the result of the automated defect recognition process in a defect database.

Abstract: An image processing method to sample the image to generate patches. Feature vectors are extracted from the patches, and the extracted feature vectors are partitioned into clusters, where feature vectors in the same cluster share a common characteristic. A portion of interest in the image is segmented. An aggregate bounding region creation process is carried out by finding the largest segment and creating a bounding box around it; determining which cluster contains the most patches within the bounding box of the segment; and adding the patches of the determined cluster to an aggregate bounding region for the portion of interest. The aggregate bounding region creation process is repeated for each other segment in order of size. The resulting aggregate bounding region contains all the patches associated with the portion of interest. The patches which fall outside the resulting aggregate bounding region are then removed from the image.

Abstract: A computer-implemented method of generating, from time-series data, a time-series of data sets for predictive analysis, comprises dividing the time-series data into evenly-sized overlapping segments of data, generating an image representing data for each segment, using the time-series data to determine a trend associated with each image, and storing each of the generated images and its associated trend as a data set. In some embodiments of the method the image from each stored data set is transformed into numerical vectors through a feature extraction process using a pre-trained convolutional neural network. The numerical vectors are stored in association with the data set, and the data sets and associated numerical vectors are used to predict the trend for a new time-series image which has been generated from any time-series data.

Abstract: An automatic defect detection method for detecting a defect in an object comprises: obtaining ultrasound scan data of the object, dividing echo amplitude values of the data into a plurality of sub-sets; assessing each sub-set to determine whether any echo amplitude values resulted from a structure of interest; computing for each sub-set, using at least a representative position of the structure portion of the sub-set and of a neighboring sub-set, a preselected mathematical function which is directly or inversely proportional to a distance between the representative positions; identifying sub-sets having a computed value that does not meet a predetermined criterion as regions of the ultrasound scan data that require inspection; issuing a notification indicating whether or not a region requiring inspection has been found; and if a region requiring inspection been found, storing data identifying the region in a database.

Abstract: A computer-implemented method of generating, from time-series data, a time-series of data sets for predictive analysis, comprises dividing the time-series data into evenly-sized overlapping segments of data, generating an image representing data for each segment, using the time-series data to determine a trend associated with each image, and storing each of the generated images and its associated trend as a data set. In some embodiments of the method the image from each stored data set is transformed into numerical vectors through a feature extraction process using a pre-trained convolutional neural network. The numerical vectors are stored in association with the data set, and the data sets and associated numerical vectors are used to predict the trend for a new time-series image which has been generated from any time-series data.

Abstract: Embodiments include a hybrid data storage system including a tabular data storage system configured to store a plurality of fixed values as tabular data; and a graph data storage system configured to store a data graph; and a multi-storage logic layer unifying access mechanisms to each of the tabular data storage system and the graph data storage system; wherein each of the fixed values in the table occupies a table entry and constrains a property of a vertex in the data graph; the graph data storage system being configured to store the data graph as a plurality of vertices linked by edges, each edge linking a specified pair of vertices as a subject vertex and an object vertex, the plurality of edges including, for each of the plurality of fixed values stored by the tabular data storage system, an edge specifying the vertex for which a property is constrained by the fixed value as the subject vertex and a pointer vertex as the object vertex, the pointer vertex encoding a pointer to the table entry occupied by

Abstract: Tagging of resources in order to associate them is described. In an embodiment it is possible to assign tags to resources or switch between resources with different tags, in the context of current work being undertaken by a user. For example, from a single application window that is currently used, a user is able to switch to other resources by tag in an embodiment. Different embodiments illustrate how tags may have multiple purposes and those purposes may evolve thus enabling associated resources to be exposed in different ways. In some embodiments rich metadata about tag usage and/or the use of resource associated with a tag is stored and used to provide additional functionality. Examples are described in which persistence of resources associated with tags is provided and may involve representation of resources such as by duplication of files or by creating alternative representations of resources.

Abstract: Recommending a media item may include, for example, a statistical model of media consumption is applied to media session consumption data from a community of users to infer parameters of the model. The model comprises a first probability distribution for each user defining a likelihood of the user having a latent characteristic for a session, and a second probability distribution for each latent characteristic defining a likelihood of a user selecting a media item given the latent characteristic. In another example, the inferred parameters are provided to a recommendation engine arranged to recommend media items. The recommendation engine uses the model with inferred parameters and data describing media items newly consumed by a user to infer a current latent characteristic for a current session of the user, and uses them to generate recommended media items for the user in the current session based on the current latent characteristic.

Abstract: Media item recommendation is described. In one example, a statistical model of media consumption is applied to media session consumption data from a community of users to infer parameters of the model. The model comprises a first probability distribution for each user defining a likelihood of the user having a latent characteristic for a session, and a second probability distribution for each latent characteristic defining a likelihood of a user selecting a media item given the latent characteristic. In another example, the inferred parameters are provided to a recommendation engine arranged to recommend media items. The recommendation engine uses the model with inferred parameters and data describing media items newly consumed by a user to infer a current latent characteristic for a current session of the user, and uses them to generate recommended media items for the user in the current session based on the current latent characteristic.

Abstract: A graph representation of a web site is generated by identifying blocks of links on web pages. Each block of links is represented by a node in the graph representation and connections between the nodes provide information on the re-use of blocks between pages.

Abstract: Tagging of resources in order to associate them is described. In an embodiment it is possible to assign tags to resources or switch between resources with different tags, in the context of current work being undertaken by a user. For example, from a single application window that is currently used, a user is able to switch to other resources by tag in an embodiment. Different embodiments illustrate how tags may have multiple purposes and those purposes may evolve thus enabling associated resources to be exposed in different ways. In some embodiments rich metadata about tag usage and/or the use of resource associated with a tag is stored and used to provide additional functionality. Examples are described in which persistence of resources associated with tags is provided and may involve representation of resources such as by duplication of files or by creating alternative representations of resources.

Abstract: A graph representation of a web site is generated by identifying blocks of links on web pages. Each block of links is represented by a node in the graph representation and connections between the nodes provide information on the re-use of blocks between pages.