Abstract: Systems and methods are disclosed for a processor to control a user-interface of a wearable computer or a device connected to the wearable computer. The system and method includes monitoring of events received from sensors on the wearable computer or the device connected to the wearable computer, and performing a machine learning process to determine when the monitored event is a predefined impact gesture. On determination that the monitored event is a predefined impact gesture, the processor is configured to perform a predefined response in the user-interface corresponding to the predefined impact gesture.

Abstract: Methods and systems are provided for feature selection in machine learning, in which the features selected for inclusion in a prediction rule are selected based on statistical metric(s) of feature contribution and/or model fitness.

Abstract: Methods and systems are provided for feature selection in machine learning, in which the features selected for inclusion in a prediction rule are selected based on statistical metric(s) of feature contribution and/or model fitness.

Abstract: A method, a system, and a computer-readable medium for predicting a risk in a survival analysis for a plurality of individuals characterized by at least one predictor are disclosed. A method for estimating risk order of an individual, given information about a set of individuals, characterized by one or many predictors, and provided that direction of association between each predictor and the risk order is known, comprising the step of comparing the individual with each individual within the set of individuals, and estimating risk of individual based on set comparisons.

Abstract: Methods and systems are provided for feature selection in machine learning, in which the features selected for inclusion in a prediction rule are selected based on statistical metric(s) of feature contribution and/or model fitness.

Abstract: Methods and systems are provided for the induction and use of probabilistic patterns in data to support decisions under uncertainty. In an aspect, the proposed approach both suggests a decision and justifies the suggestion in a convenient form for an end-user (e.g., a physician). At least one probabilistic pattern of the form B(x)?C may be generated based on data for cases with known classification. Pattern-coded data may be generated for the known cases and for another case (e.g., a test case or a new case), by evaluating the data for the known cases and other case with the at least one probabilistic pattern. A classification decision may be made for the test case by subjecting the pattern-coded data to, for example, an ordering and ranking procedure or a voting procedure. Because the probabilistic patterns are readily interpretable, the end-user can verify the validity of both the patterns and the decision.