Variable precision rough set (VPRS) based on dominance relation is an extension of traditional rough set by which can handle preference-ordered information flexibly. This paper focuses on the maintenance of approximat...
详细信息
Dominance-based rough sets approach (DRSA) is an effective tool to deal with information with preference-ordered attribute domain. In practice, many information systems may evolve when attribute values are changed. Up...
详细信息
Ordinal decision tree (ODT) can effectively deal with monotonic classification problems. However, it is difficult for the existing ordinal decision tree algorithms to learning ODT from large data sets. Based on the va...
详细信息
ISBN:
(纸本)9781479986989
Ordinal decision tree (ODT) can effectively deal with monotonic classification problems. However, it is difficult for the existing ordinal decision tree algorithms to learning ODT from large data sets. Based on the variable consistency dominance based rough set approach (VC-DRSA), an ordinal random forest algorithm is proposed in this paper. Combining with the computing framework of MapReduce, the proposed ordinal random forest algorithm is paralleled on the platform of Hadoop, which improves the efficiency of the proposed algorithm. The feasibility and effectiveness of the proposed algorithm is verified by the experimental results.
In the textile industry,it is always the case that cotton products are constitutive of many types of foreign fibers which affect the overall quality of cotton *** the foundation of the foreign fiber automated inspecti...
详细信息
In the textile industry,it is always the case that cotton products are constitutive of many types of foreign fibers which affect the overall quality of cotton *** the foundation of the foreign fiber automated inspection,image process exerts a critical impact on the process of foreign fiber *** paper presents a new approach for the fast processing of foreign fiber *** approach includes five main steps,image block,image predecision,image background extraction,image enhancement and segmentation,and image *** first,the captured color images were transformed into gray-scale images;followed by the inversion of gray-scale of the transformed images;then the whole image was divided into several ***,the subsequent step is to judge which image block contains the target foreign fiber image through image *** we segment the image block via OSTU which possibly contains target images after background eradication and image ***,we connect those relevant segmented image blocks to get an intact and clear foreign fiber target *** experimental result shows that this method of segmentation has the advantage of accuracy and speed over the other segmentation *** the other hand,this method also connects the target image that produce fractures therefore getting an intact and clear foreign fiber target image.
In real world problems, the collected data vary from time to time, and therefore, the approximations of a concept by a variable precision rough set model(VPRS) should be correspondingly updated. This paper focuses on ...
详细信息
In real world problems, the collected data vary from time to time, and therefore, the approximations of a concept by a variable precision rough set model(VPRS) should be correspondingly updated. This paper focuses on developing incremental method to update set approximations of VPRS based on dominance relations. Under dynamic environments where an object is inserted or deleted, we present the updating principles and then develop the incremental method for updating approximation sets. The related theoretical results are presented with proofs, and illustrative examples are also given to support the effectiveness of the proposed method.
Dominance-based rough set approach(DRSA) can handle the attributes with preference orders, and therefore it has been widely applied in multi-criteria decision making problems. In real applications, the collected infor...
详细信息
Dominance-based rough set approach(DRSA) can handle the attributes with preference orders, and therefore it has been widely applied in multi-criteria decision making problems. In real applications, the collected information is updated from time to time which results in dynamic information systems, especially when the attributes or objects are inserted or deleted. The traditional DRSA needs to update the set approximations whenever the information systems change, which decreases the method efficiency greatly. For classification problems with multiple criteria, this paper presents incremental algorithms to update set approximations when an object is inserted or deleted, which is expected to be more efficient than computing the approximations from the scratch. The related theoretical results are presented with proofs, and illustrative examples are also given to support the effectiveness of the proposed incremental method.
Classification for large datasets is a classical problem in machinelearning. In this paper, we focus on effevtive classification algorithm for large datasets and imbalanced datasets. First, to deal with imbalanced da...
详细信息
Classification for large datasets is a classical problem in machinelearning. In this paper, we focus on effevtive classification algorithm for large datasets and imbalanced datasets. First, to deal with imbalanced dataset, we define the weight according to the size of positive and negative dataset. Then, a fast learning algorithm on large datasets called a core set weighted support vector machines(CSWSVM) is proposed. In the proposed approach, the corresponding core set(CS) can be solved by employing the core vector machine(CVM) or generalized CVM(GCVM), and then the weighted support vector machines(WSVM) can be used to implement classification for imbalanced datasets. Experimental results on UCI and USPS datasets demonstrate that the proposed method is effective.
Patch-level features are essential for achieving good performance in computer vision tasks. Besides well-known pre-defined patch-level descriptors such as scaleinvariant feature transform (SIFT) and histogram of orien...
详细信息
Feature weighting, which is considered as an extension of feature selection techniques, has been successfully applied to improve the performance of clustering. Focusing on the clustering based on a similarity matrix, ...
详细信息
ISBN:
(纸本)9781479902590
Feature weighting, which is considered as an extension of feature selection techniques, has been successfully applied to improve the performance of clustering. Focusing on the clustering based on a similarity matrix, we design an optimization model to minimize the fuzziness of similarity matrix by learning feature weights. The objective of this model is to get a more reasonable result of clustering through minimizing the uncertainty (fuzziness and non-specificity) of similarity matrix. To solving this optimization model effectively, we propose a new searching approach which integrates together multiple evolution strategies of both differential evolution and dynamic differential evolution. The experimental results on several benchmark datasets show that the performance of the proposed method is significantly improved compared to that of gradient-descent-based approach in terms of five selected clustering evaluation indices, i.e., fuzziness of similarity matrix, intra-class similarity, inter-class similarity, ratio of intra-class similarity to inter-class similarity.
Pathfinding is a typical task in many computer games, and its performance will affect the quality of game AI. In order to enhance the efficiency of multi-task pathfinding, case-based reasoning has been introduced in t...
详细信息
Pathfinding is a typical task in many computer games, and its performance will affect the quality of game AI. In order to enhance the efficiency of multi-task pathfinding, case-based reasoning has been introduced in traditional A* algorithm, called the CBMT method. The method needs to select representative paths which can cover the whole map to build a compact case base, which is difficult in large maps. Besides, repeatedly searching for similar cases for each pathfinding task would be a time consuming process. To address these problems, we provide a kd-tree case storage structure and case retrieval mechanical in the CBMT method. The pre-stored cases(previously found paths) are generated randomly and incrementally. The original flat storage structure of the cases is changed into the kd-tree structure. Since the searching space can be reduced by branch pruning in case retrieval, the pathfinding efficiency has been improved obviously, and the number of searched nodes is also reduced.
暂无评论