Heuristic techniques

ndCurveMaster uses heuristic techniques for curve fitting and implements scientific algorithms.

Finding the best combinations in 3D/4D/5D/6D/..nD models and selecting the best-fitting functions from the function set results in a large number of possible variants. Searching through all possible variants by using an exact algorithm is computationally expensive and time consuming. A heuristic approach has been implemented in ndCurveMaster software to solve this problem.

The best nonlinear functions and variable combinations are selected through randomization and looped searching through the use of the following methods:

• • • The “Randomly Iterated Search” method utilizes an algorithm where variables are randomized and base function are iterated. This algorithm is fast and efficient, but the solution is limited due to iteration. This algorithm will complete a search by its itself when the correlation coefficient value reaches its maximum.
    • The “Random Search” method utilizes an algorithm in which variables and base function are fully randomized. This method takes much more time than the “Auto-Fit” method, but the solution is unlimited due to a randomization process. This algorithm will not finish searching by itself. In this method the user has to manually stop the searching by clicking the ESC key. The user can also carry out a search for an unlimited time when using this method.
    • The "Advanced Search" method utilizes algorithms that are applied in the “Random Search” and “Randomly Iterated Search” method.

These methods improve the discovery of better models. The disadvantage of these heuristic techniques is that the solution is not as optimal as the exact approach. But multiple searches allow the user to find a solution which is closer to an optimal result.

The effect of using the heuristic algorithm is that even when you use the same data set each time:

• • • the method of finding the best models is different,
    • the models may be different.

Therefore it would be advisable to try to repeatedly fit models to the same data.

Back to Contents