Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
528268 | Information Fusion | 2013 | 9 Pages |
An important limitation of fuzzy integrals for information fusion is the exponential growth of coefficients for an increasing number of information sources. To overcome this problem a variety of fuzzy measure identification algorithms has been proposed. HLMS is a simple gradient-based algorithm for fuzzy measure identification which suffers from some convergence problems. In this paper, two proposals for HLMS convergence improvement are presented, a modified formula for coefficients update and new policy for monotonicity check. A comprehensive experimental work shows that these proposals indeed contribute to HLMS convergence, accuracy and robustness.
► HLMS is a gradient descent algorithm for identifying Choquet integral coefficients. ► Two modifications are proposed to ensure convergence: update formula, monotonicity check. ► The revised version is deeply studied according to convergence, accuracy, robustness. ► Its properties make HLMS a powerful algorithm for fuzzy measure identification.