Growing economy has boomed tourism, but intelligent travel planning services restrict long-term and stable tourism development. Typically, travel planning requires substantial time and cost. And currently, less focus ...
详细信息
Growing economy has boomed tourism, but intelligent travel planning services restrict long-term and stable tourism development. Typically, travel planning requires substantial time and cost. And currently, less focus on user preferences in most tourist attraction recommendations also results in low efficiency. In this paper, firstly, the K-means algorithm is introduced for clustering analysis of user behavior or interests, so as to better understand user preferences. Gaussian kernel density estimation and similarity measurement are also adopted to improve the traditional K-means algorithm, which provides the foundation for a tourist attraction recommendation model. Then, to further improve transportation route planning, the study introduces the ant colony algorithm, adaptive crossover strategy and local search algorithm to enhance the traditional genetic algorithm for an optimized travel path planning model. The outcomes show that the improved clustering algorithm possesses the highest accuracy of 0.96 and 0.78 in Iris and Glass datasets respectively, along with a sum of squared errors of 96.73 and 476.48 respectively. The shortest running time in the Yeast data-set is 1.22 s. The improved clustering algorithm with 50 nearest neighbors has an average absolute error value of 0.749, and its longest running time does not exceed 1 s. In summary, the model developed in this study is highly applicable to personalized recommendation services and efficient travel routes.
Cluster analysis is a process to classify data in a specified data set. In this field,much attention is paid to high-efficiency clustering algorithms. In this paper, the features in thecurrent partition-based and hier...
详细信息
Cluster analysis is a process to classify data in a specified data set. In this field,much attention is paid to high-efficiency clustering algorithms. In this paper, the features in thecurrent partition-based and hierarchy-based algorithms are reviewed, and a new hierarchy-basedalgorithm PHC is proposed by combining advantages of both algorithms, which uses the cohesionand the closeness to amalgamate the clusters. Compared with similar algorithms, the performanceof PHC is improved, and the quality of clustering is guaranteed. And both the features were provedby the theoretic and experimental analyses in the paper.
In order to solve security problem of clustering algorithm, we proposed amethod to enhance the security of the well-known lowest-ID clustering algorithm. This method isbased on the idea of the secret sharing and the (...
详细信息
In order to solve security problem of clustering algorithm, we proposed amethod to enhance the security of the well-known lowest-ID clustering algorithm. This method isbased on the idea of the secret sharing and the (k, n) threshold cryptography, Each node, whetherclusterhead or ordinary member, holds a share of the global certificate, and any k nodes cancommunicate securely. There is no need for any clusterhead to execute extra functions more thanrouting. Our scheme needs some prior configuration before deployment, and can be used in criticalenvironment with small scale. The security-enhancement for Lowest-ID algorithm can also be appliedinto other clustering approaches with minor modification. The feasibility of this method wasverified bythe simulation results.
Based on the full analysis of the advantages and disadvantages of the traditional K - means and BIRCH clustering algorithms, an improved incremental clustering algorithm based on the core tree is proposed. The optimal...
详细信息
Based on the full analysis of the advantages and disadvantages of the traditional K - means and BIRCH clustering algorithms, an improved incremental clustering algorithm based on the core tree is proposed. The optimal global parameters Eps and MinPts are adaptively calculated according to the KNN distribution and mathematical statistics to avoid manual intervention in the clustering process so as to realize the full automation of the clustering process. By improving the seed selection method for regional query, no missing operation is needed to effectively improve the efficiency of clustering. The algorithm can helps financial users to make reasonable financial investment strategies in coastal areas, to a certain extent, reduce the financial investment risk, with strong practical significance.
clustering techniques have been widely used for solving various engineering problems such as system architecture, modular product/system design, group technology, machine layout, and so on. Most of these problems use ...
详细信息
clustering techniques have been widely used for solving various engineering problems such as system architecture, modular product/system design, group technology, machine layout, and so on. Most of these problems use matrix formulation to model the problem. Once the matrix formulation for the problem is obtained, cluster analysis is used to group objects represented in the matrix into homogenous clusters based on object features. In this correspondence, a new efficient algorithm for clustering large n x n binary and nonbinary (weighted) matrices is presented. For an n x n incidence matrix, the algorithm first creates n clusters. Once the initial clusters are obtained, the algorithm uses improvement steps to continuously improve the quality of the solution obtained in the previous step. Modifications to the algorithm are presented for clustering n x m matrices. A detailed discussion on the effectiveness of the clustering algorithm when it is applied to matrices of various sizes and sparsity is also presented. The application of the n x n clustering algorithm developed in this correspondence is presented with the development of modular electrical/electronic vehicle door architectures.
Neutrosophy (neutrosophic logic) is used to represent uncertain, indeterminate, and inconsistent information available in the real world. This article proposes a method to provide more sensitivity and precision to ind...
详细信息
Neutrosophy (neutrosophic logic) is used to represent uncertain, indeterminate, and inconsistent information available in the real world. This article proposes a method to provide more sensitivity and precision to indeterminacy, by classifying the indeterminate concept/value into two based on membership: one as indeterminacy leaning towards truth membership and the other as indeterminacy leaning towards false membership. This paper introduces a modified form of a neutrosophic set, called Double-Valued Neutrosophic Set (DVNS), which has these two distinct indeterminate values. Its related properties and axioms are defined and illustrated in this paper. An important role is played by clustering in several fields of research in the form of data mining, pattern recognition, and machine learning. DVNS is better equipped at dealing with indeterminate and inconsistent information, with more accuracy, than the Single-Valued Neutrosophic Set, which fuzzy sets and intuitionistic fuzzy sets are incapable of. A generalised distance measure between DVNSs and the related distance matrix is defined, based on which a clustering algorithm is constructed. This article proposes a Double-Valued Neutrosophic Minimum Spanning Tree (DVN-MST) clustering algorithm, to cluster the data represented by double-valued neutrosophic information. Illustrative examples are given to demonstrate the applications and effectiveness of this clustering algorithm. A comparative study of the DVN-MST clustering algorithm with other clustering algorithms like Single-Valued Neutrosophic Minimum Spanning Tree, Intuitionistic Fuzzy Minimum Spanning Tree, and Fuzzy Minimum Spanning Tree is carried out.
Modern distance education is a new Web-based form of education. Enhancing personalized teaching standard of distance learning site is an important and difficult research in the development of modern distance education...
详细信息
ISBN:
(纸本)9780769535579
Modern distance education is a new Web-based form of education. Enhancing personalized teaching standard of distance learning site is an important and difficult research in the development of modern distance education. Based on rough set (RS), Web learners clustering model, learning features reduction and clustering algorithm are presented, which provides a basis of personalized teaching strategies for distance learning website. Further research is to mine an process the dynamic personality of learner's knowledge, and then to provide services on achieving real-time personalized teaching requirement.
This research considering one working partition of order picking system as the research object, studies order batching problem and builds order batching model of fixed maximum order number. To solve the order batching...
详细信息
ISBN:
(纸本)9781538609958
This research considering one working partition of order picking system as the research object, studies order batching problem and builds order batching model of fixed maximum order number. To solve the order batching model, the storage location similarity coefficient is token as clustering index, at the same time clustering algorithm is designed. This paper explores the application analysis of the algorithm and introduces case data. Simulation results indicate that clustering algorithm achieves effective order processing operations by combining small orders into batches. So that it has validity and feasibility to order picking.
In this paper, we point out that the counterexample constructed by Yu et *** incorrect by using scientific computing software *** means that the example cannot negate the convergence theorem of maximum entropy cluster...
详细信息
In this paper, we point out that the counterexample constructed by Yu et *** incorrect by using scientific computing software *** means that the example cannot negate the convergence theorem of maximum entropy clustering ***, we construct an example to negate Theorem 1 in Yu’s paper, and we propose Proposition 3 to prove that the limit of the iterative sequence is a local minimum of the objective function while v varies and u remains ***, we give a theoretical proof of the convergence theorem of maximum entropy clustering algorithm.
For classical clustering algorithms, it is difficult to find clusters that have non-spherical shapes or varied size and density. In view of this, many methods have been proposed in recent years to overcome this proble...
详细信息
For classical clustering algorithms, it is difficult to find clusters that have non-spherical shapes or varied size and density. In view of this, many methods have been proposed in recent years to overcome this problem, such as introducing more representative points per cluster, considering both interconnectivity and closeness, and adopting the density-based method. However, the density defined in DBSCAN is decided by minPts and Eps, and it is not the best solution to describe the data distribution of one cluster. In this paper, a deviation factor model is proposed to describe the data distribution and a novel clustering algorithm based on artificial immune system is presented. The experimental results show that the proposed algorithm is more effective than DBSCAN, k-means, etc.
暂无评论