Abstract: According to an embodiment of the present invention, a computer implemented method and system for developing variables for model generation comprises: initiating, via an input to a computer, creation of a new variable for a dataset for model generation; extracting, by the computer, data relevant to the variable from one or more data sources; processing, by the computer, the extracted data to automatically generate an input variable; displaying, via a user interactive interface, the processed data relative to a target variable; modifying, via the user interactive interface, one or more parameters that define the input variable; executing, by the computer, the input variable by extracting code that captures the processing step to generate the input variable; and storing, in a database, the extracted code for the input variable.

Abstract: According to an embodiment of the present invention, a computer implemented method and system for developing variables for model generation comprises: initiating, via an input to a computer, creation of a new variable for a dataset for model generation; extracting, by the computer, data relevant to the variable from one or more data sources; processing, by the computer, the extracted data to automatically generate an input variable; displaying, via a user interactive interface, the processed data relative to a target variable; modifying, via the user interactive interface, one or more parameters that define the input variable; executing, by the computer, the input variable by extracting code that captures the processing step to generate the input variable; and storing, in a database, the extracted code for the input variable.

Abstract: Apparatus and method including acquiring a signal indicative of power consumption; detecting a transient in the signal; extracting a feature indicative of the transient, wherein extracting the feature includes: fitting a plurality of models to the transient, selecting one of the plurality of models as a model for the transient, and defining the feature indicative of the transient based on at least one parameter of the model for the transient; and classifying the transient based on the feature.

Abstract: An exercise monitoring method and system in one embodiment includes a communications network, a wearable transducer configured to generate physiologic data associated with movement of a wearer, and to form a communication link with the communications network, a system memory in which command instructions are stored, a user interface operably connected to the computer, and a system processor configured to execute the command instructions to receive the generated physiologic data, analyze the received physiologic data with a multilayer perceptron/support vector machine/hidden Markov (MSH) model, model the analyzed physiologic data, and generate feedback based on a comparison of the model and a stored exercise object.

Abstract: Apparatus and method including acquiring a signal indicative of power consumption; detecting a transient in the signal; extracting a feature indicative of the transient, wherein extracting the feature includes: fitting a plurality of models to the transient, selecting one of the plurality of models as a model for the transient, and defining the feature indicative of the transient based on at least one parameter of the model for the transient; and classifying the transient based on the feature.

Abstract: An exercise monitoring method and system in one embodiment includes a communications network, a wearable transducer configured to generate physiologic data associated with movement of a wearer, and to form a communication link with the communications network, a system memory in which command instructions are stored, a user interface operably connected to the computer, and a system processor configured to execute the command instructions to receive the generated physiologic data, analyze the received physiologic data with a multilayer perceptron/support vector machine/hidden Markov (MSH) model, model the analyzed physiologic data, and generate feedback based on a comparison of the model and a stored exercise object.

Abstract: A method for controlling energy consumption within a building includes providing at least one environment sensing device and at least one energy consumption sensing device associated with the building. Current data is collected from the environment sensing device and the energy consumption sensing device along with associated time-of-day data. A value of a future energy consumption parameter is predicted based upon the collected current data, the associated time-of-day data, and historic data collected from the environment sensing device and the energy consumption sensing device. A profile of future costs per unit of energy consumption as a function of time is determined. Energy consumption is controlled dependent upon the predicted future energy consumption parameter value and the determined profile of energy consumption costs.