Many methods based on rough sets to deal with incomplete information system have been proposed in recent years. However, they are only suitable for the nominal datasets. So far only a few methods based on rough sets t...
详细信息
The generalization error bounds for the entire input space found by current error models using the number of effective parameters of a classifier and the number of training samples are usually very loose. But classifi...
详细信息
Since its introduction, rough set theory has demonstrated its usefulness in many applications where imprecise and inconsistent information is involved. An important area of its application is in the induction of decis...
详细信息
Several ongoing projects in the MAPLE (Multi-Agent Planning and learning) lab at UMBC and the machinelearning Systems Group at JPL focus on problems that we view as central to the development of persistent agents. Th...
详细信息
Nearest neighbor classifier (NNC) is stable to the change of the training data set while sensitive to the variation of the feature set. The combination of multiple NNCs on different subsets of features may outperform ...
详细信息
Nearest neighbor classifier (NNC) is stable to the change of the training data set while sensitive to the variation of the feature set. The combination of multiple NNCs on different subsets of features may outperform the standard NNC. In this paper, we develop a new method called FC-MNNC based on feature subset clustering for combining multiple NNCs to obtain better performance than that using a single NNC. In this method, GA is used for clustering features to form different feature subsets according to the combination classification accuracy. Multiple NNCs based on the corresponding feature subsets are parallel and independent to classify one pattern. The final decision is aggregated by majority voting rule, which is a simple and efficient technique. To demonstrate the performance of FC-MNNC, we select four UCI databases in our experiments. The proposed FC-MNNC is compared with (i) standard NNC, (ii) feature selection using GA in individual NNC and (iii) feature subset selection using GA in multiple NNCs. The experimental results show that the accuracy of FC-MNNC is better than that of the standard NNC and feature selection using GA in individual classifier. The performance of FC-MNNC is not worse than that of feature subset selection using GA in multiple NNCs. It is also demonstrated that FC-MNNC is robust to irrelevant features.
We present an algorithm for learning a quadratic Gaussian metric (Mahalanobis distance) for use in classification tasks. Our method relies on the simple geometric intuition that a good metric is one under which points...
We present an algorithm for learning a quadratic Gaussian metric (Mahalanobis distance) for use in classification tasks. Our method relies on the simple geometric intuition that a good metric is one under which points in the same class are simultaneously near each other and far from points in the other classes. We construct a convex optimization problem whose solution generates such a metric by trying to collapse all examples in the same class to a single point and push examples in other classes infinitely far away. We show that when the metric we learn is used in simple classifiers, it yields substantial improvements over standard alternatives on a variety of problems. We also discuss how the learned metric may be used to obtain a compact low dimensional feature representation of the original input space, allowing more efficient classification with very little reduction in performance.
It has been shown that the optimal solution for the matching problem in multi-target tracking, when both estimated measuring bearing data and actual measuring data are known, can be found from among N different matchi...
详细信息
Many methods based on rough sets to deal with incomplete information system have been proposed in recent years. However, they are only suitable for the nominal datasets. So far only a few methods based on rough sets t...
详细信息
Many methods based on rough sets to deal with incomplete information system have been proposed in recent years. However, they are only suitable for the nominal datasets. So far only a few methods based on rough sets to deal with incomplete information system with continuous-attributes have been proposed. In this paper we propose one generalized model of rough sets to reduce continuous-attributes in an incomplete information system. The definition of a relative discernible measure is firstly proposed, which is the underlying concept to redefine the concepts of knowledge reduction such as the reduct and core. The advantage of the proposed method is that instead of preprocessing continuous data by discretization or fuzzification, we can reduce an incomplete information system directly based on the generalized model of rough sets. Finally, a numerical example is given to show the feasibility of our proposed method.
The generalization error bounds for the entire input space found by current error models using the number of effective parameters of a classifier and the number of training samples are usually very loose. But classifi...
详细信息
The generalization error bounds for the entire input space found by current error models using the number of effective parameters of a classifier and the number of training samples are usually very loose. But classifiers such as SVM, RBFNN and MLPNN, are really local learningmachines used for many application problems, which consider unseen samples close to the training samples more important. In this paper, we propose a localized generalization error model which bounds above the generalization error within a neighborhood of the training samples using stochastic sensitivity measure (expectation of the squared output perturbations). It is then used to develop a model selection technique for a classifier with maximal coverage of unseen samples by specifying a generalization error threshold. Experiments by using eight real world datasets show that, in comparison with cross-validation, sequential learning, and two other ad-hoc methods, our technique consistently yields the best testing classification accuracy with fewer hidden neurons and less training time.
Since its introduction, rough set theory has demonstrated its usefulness in many applications where imprecise and inconsistent information is involved. An important area of its application is in the induction of decis...
详细信息
Since its introduction, rough set theory has demonstrated its usefulness in many applications where imprecise and inconsistent information is involved. An important area of its application is in the induction of decision rules for decision problems. Recently, there are studies for applying rough set theory in decision related to ordering where items are ordered by assigning to them an ordinal class label such as excellent, good, fair, bad. In this paper we examine a particular situation of ordinal decision which has not been considered in previous studies. We introduce some new concepts in relation to reducts of such ordinal decision systems and proposed a way to find these reducts using a concept similar to discernibility matrix.
暂无评论