Abstract: Systems and methods for determining a model for predictive inference on an operation of a machine. A processor is configured to acquire time series data, the times series data includes training data and test data, the time series data represents an operation of the machine for a period of time, and the training data includes observations labeled with an outcome of the predictive inference. Apply recursive and stable filters for filtering at a training time, at a test time or both, such that a data point in the filtered time series data corresponds to an observation in the time series data that is a function of the corresponding observation and past observations in the time series data preceding the corresponding observation. Determine the model for the predictive inference using the training data, based on filtering the training data with filters to produce filtered time series data, and store in memory.

Abstract: Systems and methods for determining a pattern in time series data representing an operation of a machine. A memory to store and provide a set of training data examples generated by a sensor of the machine, wherein each training data example represents an operation of the machine for a period of time ending with a failure of the machine. A processor configured to iteratively partition each training data example into a normal region and an abnormal region, determine a predictive pattern absent from the normal regions and present in each abnormal region only once, and determine a length of the abnormal region. Outputting the predictive pattern via an output interface in communication with the processor or storing the predictive pattern in memory, wherein the predictive pattern is a predictive estimate of an impending failure and assists in management of the machine.

Abstract: A method detects an object in an image. The method extracts a first feature vector from a first region of an image using a first subnetwork and determines a second region of the image by processing the first feature vector with a second subnetwork. The method also extracts a second feature vector from the second region of the image using the first subnetwork and detects the object using a third subnetwork on a basis of the first feature vector and the second feature vector to produce a bounding region surrounding the object and a class of the object. The first subnetwork, the second subnetwork, and the third subnetwork form a neural network. Also, a size of the first region differs from a size of the second region.

Abstract: Systems and methods for determining a model for predictive inference on an operation of a machine. A processor is configured to acquire time series data, the times series data includes training data and test data, the time series data represents an operation of the machine for a period of time, and the training data includes observations labeled with an outcome of the predictive inference. Apply recursive and stable filters for filtering at a training time, at a test time or both, such that a data point in the filtered time series data corresponds to an observation in the time series data that is a function of the corresponding observation and past observations in the time series data preceding the corresponding observation. Determine the model for the predictive inference using the training data, based on filtering the training data with filters to produce filtered time series data, and store in memory.

Abstract: Systems and methods for determining a pattern in time series data representing an operation of a machine. A memory to store and provide a set of training data examples generated by a sensor of the machine, wherein each training data example represents an operation of the machine for a period of time ending with a failure of the machine. A processor configured to iteratively partition each training data example into a normal region and an abnormal region, determine a predictive pattern absent from the normal regions and present in each abnormal region only once, and determine a length of the abnormal region. Outputting the predictive pattern via an output interface in communication with the processor or storing the predictive pattern in memory, wherein the predictive pattern is a predictive estimate of an impending failure and assists in management of the machine.

Abstract: A controller for controlling an operation of an air-conditioning system conditioning an indoor space includes a data input to receive state data of the space at multiple points in the space, a memory to store a code of a reinforcement learning algorithm and a history of the state data and a history of control commands having been applied to the air-conditioning system, wherein the history of the control commands is associated with the state data and history of rewards, a processor coupled to the memory determines a value function outputting a cumulative value of the rewards and transmits a control command by using the reinforcement learning algorithm, and a data output to receive the control command from the processor and transmit a control signal to the air-conditioning system, wherein the control signal controls at least one actuator of the air-conditioning system according to the control command.

Abstract: A method detects an object in an image. The method extracts a first feature vector from a first region of an image using a first subnetwork and determines a second region of the image by processing the first feature vector with a second subnetwork. The method also extracts a second feature vector from the second region of the image using the first subnetwork and detects the object using a third subnetwork on a basis of the first feature vector and the second feature vector to produce a bounding region surrounding the object and a class of the object. The first subnetwork, the second subnetwork, and the third subnetwork form a neural network. Also, a size of the first region differs from a size of the second region.

Abstract: A method selects one or more power sources in a hybrid electric vehicle (HEV) at a particular moment in time for a current route to optimize energy consumption for the HEV, wherein the HEV includes one or more electric engines (EC) and one or more internal combustion engines, by first determining, in an off-line processor, a regression model that predicts a terminal cost of a state along a route from features associated with the route and the vehicle, using a computed true costs-to-go of multiple states from multitude of real or imaginary routes. In an online processor in the HEV, truncated dynamic programming is performed using the regression model to estimate a terminal cost at an end of a truncated time horizon for a current route. Then, one or more of the power sources are selected for the one or more EC and the one or more ICE based on a minimal cost-to-go of a current state.

Abstract: A method selects one or more power sources in a hybrid electric vehicle (HEV) at a particular moment in time for a current route to optimize energy consumption for the HEV, wherein the HEV includes one or more electric engines (EC) and one or more internal combustion engines, by first determining, in an off-line processor, a regression model that predicts a terminal cost of a state along a route from features associated with the route and the vehicle, using a computed true costs-to-go of multiple states from multitude of real or imaginary routes. In an online processor in the HEV, truncated dynamic programming is performed using the regression model to estimate a terminal cost at an end of a truncated time horizon for a current route. Then, one or more of the power sources are selected for the one or more EC and the one or more ICE based on a minimal cost-to-go of a current state.