Abstract: The described embodiments relate to methods and systems for data classification using a self-organizing map. Certain embodiments relate to a method of labeling data for training a classifier, comprising: obtaining data, the data comprising labeled data and unlabeled data; generating a self-organizing map of the data; and a labeling at least some of the unlabeled data based on proximity of the unlabeled data to labeled data within the self-organizing map to generate self-labeled data. The method may include training a classifier based on the labeled and self-labeled data. Other embodiments relate to systems and computer readable media configured to perform, or allow performance of, the method embodiments.

Abstract: A method of determining character value arrangement on a handheld keypad includes: specifying one or more parameters for evaluating keypad solutions for the handheld keypad by characterizing a user's physical operations on the handheld keypad; generating an initial set of keypad solutions for the handheld keypad; evaluating a fitness of the keypad solutions in the initial set based on the one or more parameters; selecting a first set of keypad solutions from the initial set based on the fitness of the keypad solutions in the initial set; generating additional solutions for the first set of keypad solutions from the keypad solutions in the first set; evaluating the fitness of the additional keypad solutions in the first set; and saving at least some key-associated character values based on the keypad solutions. The keypad includes input keys with which character values are associated, each having at least one alphanumeric indicia associated therewith.

Abstract: The described embodiments relate to methods and systems for data classification using a self-organizing map. Certain embodiments relate to a method of labeling data for training a classifier, comprising: obtaining data, the data comprising labeled data and unlabeled data; generating a self-organizing map of the data; and a labeling at least some of the unlabeled data based on proximity of the unlabeled data to labeled data within the self-organizing map to generate self-labeled data. The method may include training a classifier based on the labeled and self-labeled data. Other embodiments relate to systems and computer readable media configured to perform, or allow performance of, the method embodiments.