Abstract: An auto-adaptive system is provided that includes a template builder that allows weighted templates to be created for computing auto-adaptive features, an auto-adaptive event locator that analyzes a data set to identify events, an event extractor that locates and extracts identified events and provides events for review by an event analyzer (operator or programmed module) to distinguish clutter data from target data, and an auto-adaptive risk analyzer that processes data related to hit rates, false alarm rates, alarm costs, and risk factors to determine return on investment information and receiver operator characteristic curves.

Abstract: The present invention is be directed to systems and methods that efficiently reduce cluttered data and identify useful information, in real-time. The disclosed auto-adaptive system distinguishes target data in data sets from clutter data that causes low target hit rates and high false alarm rates. Data set features may then be modified to account for changes over time, resulting in auto-adaptive alarm thresholds, higher target hits rates, and lower false alarm rates. In addition, data may be reduced to snip containing target information, while excluding large amounts of clutter data. Thereby, real-time data can be more readily understood and transmitted data can be reduced.

Abstract: Feature values, which may be multi-dimensional, collected over successive time slices, are efficiently processed for use, for example, in known adaptive learning functions and event detection. A Markov chain in a recursive function to calculate imputed values for data points by use of a “nearest neighbor” matrix. Only data for the time slices currently required to perform computations must be stored. Earlier data need not be retained. A data selector, referred to herein for convenience as a window driver, selects successive cells of appropriate adjacent values in one or more dimensions to comprise an estimation set. The window driver effectively indexes tables of data to efficiently deliver input data to the matrix. In one form, feature inputs are divided into subgroups for parallel, pipelined processing.

Abstract: A computer implemented method for processing audio data communicated between a first device and a second device over a data communication network, where one or more processors are programmed to perform steps include at a first device: receiving time series audio data comprising audio data over a time period; partitioning the audio data in a plurality of time segments; transforming the audio data in the plurality of time segments into a plurality of feature values; transmitting a subset of plurality of feature values over a data communication network; and at a second device: receiving the transmitted plurality of feature values from the data communication network; and transforming the feature values into the time domain to reproduce the time series audio data.

Abstract: In an auto-adaptive system, efficient processing generates predicted values in an estimation set in at least one dimension for a dependent data location. The estimation set comprises values for a dependent data point and a preselected number of spatial nearest neighbor values surrounding the dependent data point in a current time slice; The prediction may be made for time slices, seconds, hours or days into the future, for example. Imputed values may also be generated. A mean value sum of squares and cross product MVSCP matrix, inverse, and other learned parameters are used. The present embodiments require updating only one MVSCP matrix and its inverse per time slice. A processing unit may be embodied with selected modules each calculating a component function of feature value generation. Individual modules can be placed in various orders. More than one of each type of module may be provided.

Abstract: Feature values, which may be multi-dimensional, collected over successive time slices, are efficiently processed for use, for example, in known adaptive learning functions and event detection. A Markov chain in a recursive function to calculate imputed values for data points by use of a “nearest neighbor” matrix. Only data for the time slices currently required to perform computations must be stored. Earlier data need not be retained. A data selector, referred to herein for convenience as a window driver, selects successive cells of appropriate adjacent values in one or more dimensions to comprise an estimation set. The window driver effectively indexes tables of data to efficiently deliver input data to the matrix. In one form, feature inputs are divided into subgroups for parallel, pipelined processing.