| 摘要 |
<p>An evolver program (4000) creates one or more classifier programs (1110) by examining and combining potential features, which may be from multiple signals. The output of the classifier program (1110) is compared to the desired output. One or more classifier programs (1110) is then created and optimized by the evolver program (4000) by means of genetic programming. The desired output is again compared to actual classifier program output and the difference is used as a measure of fitness (710) to guide the evolution of the classifier program (1110). The optimized classifier program (1110) provides a repeatable and accurate output. The classifier program (1110) may either operate within the program structure of the evolver program (4000) or it may be used as an independent program, as, for example, a controller for a powered prosthesis.</p> |
