Genetic algorithms with subjective input for hearing assistance devices

A method of fitting a hearing assistance device using a genetic algorithm, comprising:

• using a processor to prepare a first population of a plurality of parent sets representing at least one device parameter;
• presenting a first pair being derived from the first population of the plurality of parent sets, the first pair comprising a first and second set and being presented to a user with assistance of the hearing assistance device;
• receiving a user selection of a preference between the first and second sets of the first pair;
• using the processor to determine a child set by operating on at least one set of the plurality of parent sets, the child set including a crossover of the at least one parent set, wherein the crossover includes an arithmetic or geometrical operation to real parameter values of the parent set instead of converting to and operating on bitstring values of the parent set;
• and
• using the processor to converge on a solution set using at least one of the crossover and a mutation, wherein the mutation includes replacing a lowest ranked parameter value in the parent set with a randomly generated parameter value and recording the lowest ranked parameter value in a memory to avoid the lowest ranked parameter value during subsequent random generation.

A method of fitting a hearing assistance device using a genetic algorithm, comprising:

• using a processor to prepare a first population of a plurality of parent sets representing at least one device parameter;
• presenting a first pair being derived from the first population of the plurality of parent sets, the first pair comprising a first and second set and being presented to a user with assistance of the hearing assistance device;
• receiving a user selection of a preference between the first and second sets of the first pair;
• using the processor to determine a child set by operating on at least one set of the plurality of parent sets, the child set including a mutation of the at least one parent set, wherein the mutation includes replacing a lowest ranked parameter value in the parent set with a randomly generated parameter value and recording the lowest ranked parameter value in a memory to avoid the lowest ranked parameter value during subsequent random generation;
• and
• using the processor to converge on a solution set using at least one of the mutation and a crossover.