No abstract

Heuristic hill-climbing search algorithm can do effectively pruning. In practice, it can be used to search a large hypothesis space to get an optimal or an approximate optimal solution. Beam search algorithm retains its advantage in efficiency while reducing the risk of converging to locally optimal hypotheses. Beam search algorithm is widely used in AI field. To k-size beam search, due to only k paths is maintained the key to optimize the accuracy of beam search is how to select the k paths. In most of search algorithms, the k candidates with the most high performance measure value are selected at each search step. In this paper, the author presented some methods of candidate selection of beam search approaches, and the thought of avoiding "full of blood brother nodes" is presented. The experiments were done on the UCI repository of machine learning databases.One useful perspective on machine learning is that it involves searching a very large space of possible hypotheses to determine one that best fits the observed data and any prior knowledge held by the learner [6] . Machine Learning could be described as searching through a huge hypothesis space, so as to get a target hypothesis consistent with observed data. For example, the hypothesis space searched by decision trees learning algorithm ID3 [1] is the set of possible decision trees. Algorithm ID3 can be characterized as searching the space for a decision tree best fits the training examples.In practice, to thoroughly search hypothesis space is impossible, and heuristic search is then a feasible choice. Hill-climbing algorithm can effectively prune while searching. In real problem solving, it can find out an optimal or approximate optimal solution. In fact, many well known algorithms, such as FOIL [2] , adopted hill-climbing search strategy to search corresponding hypothesis space.Guided by heuristic function, hill-climbing algorithm searches along only the "most promising" path. Due to its non-backtrack the hill-climbing algorithms converge most probably to a local optimal hypotheses.The beam search algorithms have keep down the character of effectiveness of hill-climbing algorithms in pruning. Meanwhile, it can reduce effectively the risk of converging to locally optimal hypotheses. Beam search strategy is widely used In AI area such as GAs and CN2-SD [4] etc.Beam search algorithmStep1: U root initial entrance of beam search Step2: V all children of nodes in U, U {} Step3: sort V according heuristic value of nodes Step4: U k nodes with the highest heuristic value in V ; where k is called the width of beam search Step5: if U≠{}and hasn't reached the goal goto Step2Step6: endThe beam search algorithm maintains a list of the k best candidates at each step, rather than a single best candidate. On each search step, descendants are generated for each of these best k candidates, and the resulting is again reduced to the k most promising members. Beam search keeps track of the most promising alternatives to the current top-rated hypothesis, so that all of their su...

In this work we model the noise properties of a computed radiography (CR) mammography system by adding an extra degree of freedom to a well-established noise model, and derive a variance-stabilizing transform (VST) to convert the signal-dependent noise into approximately signal-independent. The proposed model relies on a quadratic variance function, which considers fixed-pattern (structural), quantum and electronic noise. It also accounts for the spatial-dependency of the noise by assuming a space-variant quantum coefficient. The proposed noise model was compared against two alternative models commonly found in the literature. The first alternative model ignores the spatial-variability of the quantum noise, and the second model assumes negligible structural noise. We also derive a VST to convert noisy observations contaminated by the proposed noise model into observations with approximately Gaussian noise and constant variance equals to one. Finally, we estimated a look-up table that can be used as an inverse transform in denoising applications. A phantom study was conducted to validate the noise model, VST and inverse VST. The results show that the space-variant signal-dependent quadratic noise model is appropriate to describe noise in this CR mammography system (errors< 2.0% in terms of signal-to-noise ratio). The two alternative noise models were outperformed by the proposed model (errors as high as 14.7% and 9.4%). The designed VST was able to stabilize the noise so that it has variance approximately equal to one (errors< 4.1%), while the two alternative models achieved errors as high as 26.9% and 18.0%, respectively. Finally, the proposed inverse transform was capable of returning the signal to the original signal range with virtually no bias.

No abstract

No abstract