Chuangyin Dang

Global exponential stability of impulsive fuzzy Cohen-Grossberg neural networks with mixed delays and reaction-diffusion terms

This paper is concerned with the problem of exponential stability for a class of impulsive fuzzy Cohen-Grossberg neural networks with mixed time delays and reaction-diffusion. The mixed delays include time-varying delays and continuously distributed delays. Based on the Lyapunov method, Poincare Integral Inequality, and the linear matrix inequality (LMI) approach, we found some new sufficient conditions ensuring the global exponential stability of equilibrium point for impulsive fuzzy Cohen-Grossberg neural networks with mixed time delays and reaction-diffusion terms. These global exponential stability conditions depend on the reaction-diffusion terms and time delays. The results presented in this paper are less conservative than the existing sufficient stability conditions. Finally, some examples are given to show the effectiveness and superiority of the theoretical results.

Space Structure and Clustering of Categorical Data

Learning from categorical data plays a fundamental role in such areas as pattern recognition, machine learning, data mining, and knowledge discovery. To effectively discover the group structure inherent in a set of categorical objects, many categorical clustering algorithms have been developed in the literature, among which k-modes-type algorithms are very representative because of their good performance. Nevertheless, there is still much room for improving their clustering performance in comparison with the clustering algorithms for the numeric data. This may arise from the fact that the categorical data lack a clear space structure as that of the numeric data. To address this issue, we propose, in this paper, a novel data-representation scheme for the categorical data, which maps a set of categorical objects into a Euclidean space. Based on the data-representation scheme, a general framework for space structure based categorical clustering algorithms (SBC) is designed. This framework together with the applications of two kinds of dissimilarities leads two versions of the SBC-type algorithms. To verify the performance of the SBC-type algorithms, we employ as references four representative algorithms of the k-modes-type algorithms. Experiments show that the proposed SBC-type algorithms significantly outperform the k-modes-type algorithms.

Attribute reduction for sequential three-way decisions under dynamic granulation

Abstract In real-world decision making, sequential three-way decisions are an effective way of human problem solving under multiple levels of granularity. Making the right decision at the most optimal level is a crucial issue. To this end, we address the attribute reduction problem for sequential three-way decisions under dynamic granulation. By reviewing the existing definitions of attribute reducts, a new attribute reduct for sequential three-way decisions is defined, and a corresponding monotonic attribute significance measure is designed. An attribute reduction algorithm satisfying the monotonicity of the probabilistic positive region is developed. The relationships of the different attribute reducts, the probabilistic positive regions and the probabilistic positive rules for decision-theoretic rough set models are further discussed under global view, local view and sequential three-way decisions. Experimental results demonstrate that our method is effective. This study will provide a new insight into the attribute reduction problem of sequential three-way decisions.

Distributed algorithms for resource allocation of physical and transport layers in wireless cognitive ad hoc networks

In this paper, by integrating together congestion control, power control and spectrum allocation, a distributed algorithm is developed to maximize the aggregate source utility and increase end-to-end throughput. Despite the inherent difficulties of non-convexity and non-separability of variables in the original optimization problem, we are still able to obtain a decoupled and dual-decomposable convex formulation by applying an appropriate transformation and introducing some new variables. The objective is accomplished by the interaction and coordination among three sub-algorithms of the algorithm through the congestion prices. The convergence properties of the three sub-algorithms are also proved. Simulation results illustrate several other desirable properties of the proposed algorithm, including the impacts of node mobility and path and packet losses on convergence and robustness. This work is a preliminary attempt towards a systematic approach to jointly designing a congestion control sub-algorithm and a power control sub-algorithm coupled with a spectrum allocation sub-algorithm.

Grouping granular structures in human granulation intelligence

Abstract Human granulation intelligence means that people can observe and analyze the same problem from various granulation points of view, which generally acknowledge an essential feature of human intelligence. Each granulation view can generate a granular structure through dividing a cognitive target into some meaningful information granules. This means that a large number of granular structures can be generated from the cognitive target. However, people can group these granular structures and select some representative ones for problem solving. This leads to an interesting research topic: how to efficiently and effectively group a family of granular structures. To address this issue, we first introduce a granular structure distance to measure the difference between two granular structures within a unified knowledge representation. Then, we propose a framework for grouping granular structures, called GGS algorithm, which is used to efficiently partition them. Moreover, two indices denoted as DIS and APD are also designed for evaluating the performance of a grouping result of granular structures. Finally, experiments carried out for nine data sets show that the GGS algorithm comes as a sound solution from perspectives of its convergence, effectiveness and scalability. In this way we have proposed and experimented with the general framework for discovering the structure inherent in granular structures, which can be afterwards used to simulate intelligent behavior of human’s abilities of granular structure selection.

Solving long haul airline disruption problem caused by groundings using a distributed fixed-point computational approach to integer programming

Abstract Disruptions are prevalent phenomenons that prevent airline from operating as original scheduled. This paper adopts the iterative fixed-point method for integer programming proposed by Dang and Ye [1] to generate feasible flight routes that are used to construct an aircraft reassignment in response to the grounding of one aircraft. Two division methods are proposed with which the solution space can be divided into several independent segments and implemented a distributed computation. The second division method is emphasized in this paper for the good performance of partial feasible flight routes which are generated by this division approach. Comparison with CPLEX CP Optimizer [2] shows that less partial feasible flight routes which are generated by Dang’s algorithm [1] are required to find an aircraft reassignment when disruptions happen, and this division method is more promising when dealing with long haul airline disruption problem.

Distributed resource allocation with fairness for cognitive radios in wireless mobile ad hoc networks

Both spectrum sensing and power allocation have crucial effects on the performance of wireless cognitive ad hoc networks. In order to obtain the optimal available subcarrier sets and transmission powers, we propose in this paper a distributed resource allocation framework for cognitive ad hoc networks using the orthogonal frequency division multiple access (OFDMA) modulation. This framework integrates together the constraints of quality of service (QoS), maximum powers, and minimum rates. The fairness of resource allocation is guaranteed by introducing into the link capacity expression the probability that a subcarrier is occupied. An incremental subgradient approach is applied to solve the optimization problems that maximize the weighted sum capacities of all links without or with fairness constraints. Distributed subcarrier selection and power allocation algorithms are presented explicitly. Simulations confirm that the approach converges to the optimal solution faster than the ordinary subgradient method and demonstrate the effects of the key parameters on the system performance. It has been observed that the algorithms proposed in our paper outperform the existing ones in terms of the throughput and number of secondary links admitted and the fairness of resource allocation.

Asynchronous H∞ filtering for linear switched systems with average dwell time

This paper is concerned with the H∞ filtering problem for a class of continuous-time linear switched systems with the asynchronous behaviours, where ‘asynchronous’ means that the switching of the filters to be designed has a lag to the switching of the system modes. By using the Lyapunov-like functions and the average dwell time technique, a sufficient condition is obtained to guarantee the asymptotic stability with a weighted H∞ performance index for the filtering error system. Moreover, the results are formulated in the form of linear matrix inequalities that are numerical feasible. As a result, the filter design problem is solved. Finally, an illustrative numerical example is presented to show the effectiveness of the results.

Joint opportunistic power and rate allocation for wireless ad hoc networks: An adaptive particle swarm optimization approach

In this paper, the joint opportunistic power and rate allocation (JOPRA) algorithm, which aims at maximizing the sum of source utilities while minimizing power allocation for all links in wireless ad hoc networks, is solved by means of an improved adaptive particle swarm optimization (IAPSO), which can overcome some limitations of the traditional dual and subgradient method. Compared with the original APSO, in our IAPSO, the maximum movement velocity of the particles changes dynamically, a modified replacement procedure with no introduced additional parameters is employed in constraint handling, and the state of the optimization run and the diversity in the population are taken into account in stopping criteria. It is shown that the proposed JOPRA algorithm can fast converge to the optimum and reach larger total data rate and utility while less total power is consumed. The efficiency of our approach is further illustrated via numerical comparison with the original APSO. This work is a beneficial attempt to integrate adaptive evolutionary algorithms with the resource allocation in wireless ad hoc networks.

Local rough set: A solution to rough data analysis in big data

Abstract As a supervised learning method, classical rough set theory often requires a large amount of labeled data, in which concept approximation and attribute reduction are two key issues. With the advent of the age of big data however, labeling data is an expensive and laborious task and sometimes even infeasible, while unlabeled data are cheap and easy to collect. Hence, techniques for rough data analysis in big data using a semi-supervised approach, with limited labeled data, are desirable. Although many concept approximation and attribute reduction algorithms have been proposed in the classical rough set theory, quite often, these methods are unable to work well in the context of limited labeled big data. The challenges to classical rough set theory can be summarized with three issues: limited labeled property of big data, computational inefficiency and over-fitting in attribute reduction. To address these three challenges, we introduce a theoretic framework called local rough set, and develop a series of corresponding concept approximation and attribute reduction algorithms with linear time complexity, which can efficiently and effectively work in limited labeled big data. Theoretical analysis and experimental results show that each of the algorithms in the local rough set significantly outperforms its original counterpart in classical rough set theory. It is worth noting that the performances of the algorithms in the local rough set become more significant when dealing with larger data sets.