International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems

This paper presents a new Synchronization Adaptive Fuzzy Gain Scheduling PID controller (SAFGS-PIDc) for a class of Multiple-input multiple-output (MIMO) nonlinear systems with uncertainties. To achieve better adaptation properties, weighting factor is adapted to sum together the adaptive fuzzy control scheme and Fuzzy Gain Scheduler PID control (FGS-PIDc) method, such that both controllers can be incorporated at the same time. The FGS adjusts online the parameters of the conventional PID controller, and an Indirect Adaptive Fuzzy control (IAFc) scheme that uses feedback error function as inputs is constructed. In addition, each subsystem of MIMO system is able to adaptively compensate for uncertainties and external disturbance. Also, a robust control term is designed that aims to provide added robustness in the presence of uncertainties. The proposed scheme can overcome the controller singularity problem. While the proposed controller scheme requires the uncertainties to be bounded, it does not require this bound to be known. Thus, this control law can be used for the systems that the system’s models are quite unknown. The proposed method guarantees the stability of the closed-loop system based on Lyapunov theory. Finally, simulation studies demonstrate the usefulness and effectiveness of the proposed technique for controlling nonlinear.

As an extension of the fuzzy relation linear programming, geometric programming with single-variable term subject to max–min fuzzy relation equations is a nonlinear and non-convex problem. To deal with this problem, we develop the variable substitution method to find out all of the optimal solutions (if not unique). The variable substitution method is carried out by the resolution procedures with an illustrative example. In addition, the proposed method is applied to the optimization management in laboratory Peer-to-Peer network system.

Uncertainty is unavoidable and addressing the same is inevitable. That everything is available at our doorstep is due to a well-managed modern global supply chain, which takes place despite its efficiency and effectiveness being threatened by various sources of uncertainty originating from the demand side, supply side, manufacturing process, and planning and control systems. This paper addresses the demand- and supply-rooted uncertainty. In order to cope with uncertainty within the constrained multi-objective supply chain network, this paper develops a fuzzy goal programming methodology, with solution procedures. The probabilistic fuzzy goal multi-objective supply chain network (PFG-MOSCN) problem is thus formulated and then solved by three different approaches, namely, simple additive goal programming approach, weighted goal programming approach, and pre-emptive goal programming approach, to obtain the optimal solution. The proposed work links fuzziness in transportation cost and delivery time with randomness in demand and supply parameters. The results may prove to be important for operational managers in manufacturing units, interested in optimizing transportation costs and delivery time, and implicitly, in optimizing profits. A numerical example is provided to illustrate the proposed model.

Recently, De Baets et al. have characterized the fuzzy tolerance relations that a given strict order relation is compatible with. In general, the compatibility of a strict order relation with a binary fuzzy relation guarantees also the compatibility of its associated betweenness relation with that binary fuzzy relation. In this paper, we study the compatibility of an arbitrary ternary relation with a binary fuzzy relation. We prove that this compatibility can be expressed in terms of inclusions of the binary fuzzy relation in the traces of the given ternary relation.

In this paper, a new differential equation, driven by aleatory and epistemic forms of uncertainty, is introduced and applied to describe the dynamics of a stock price process. This novel class of differential equations is called uncertain stochastic differential equations(USDES) with uncertain jumps. The existence and uniqueness theorem for this class of differential equations is proposed and proved. An appropriate version of the chain rule is derived and applied to solve some examples of USDES with uncertain jumps. The differential equation discussed is applied in an American call option pricing problem. In this problem, it is assumed that the evolution of the stock price is driven by a Brownian motion, the Liu canonical process and an uncertain renewal process. MATLAB is employed for implementing the derived option pricing model. Results show that option prices from the proposed call option pricing formula increase as the jump size increases. As compared to the proposed call option pricing formula, the Black-Scholes overprices options for a certain range of strike prices and under-prices the same options for another range of exercise prices when the jump size is zero.

Majority of the e-commerce sites implement Recommender Systems (RS) to help users navigate through the large search space and assist their decision making process by suggesting products that the user may like. Collaborative Filtering (CF) is the most successful and widely used algorithm in the domain of RS. However, due to the exponential growth of the web in terms of both content and number of users, CF based RS face serious scalability issues. To alleviate this problem, we propose a clustering based CF approach using two hierarchical space partitioning data structures — K-d tree and Quadtree. We cluster or partition the users’ space of the system on the basis of user location and then use the resultant clusters for predicting ratings of a target user. Since the CF based recommendation algorithm is applied separately to the clusters and not on the entire rating data, it helps in bringing down the runtime of the algorithm substantially. We further measure spatial autocorrelation indices in the clusters to justify our clustering method. However, our objective is not only to reduce the runtime but also to maintain an acceptable recommendation quality. This requirement is rightly addressed by the proposed method which assures scalability, by processing very large datasets using the same computing resource. Moreover our proposed clustering scheme is oblivious of the underlying CF algorithm. Results from the extensive experiments conducted, show that our hierarchical clustering based recommendation approach reduces runtime of the standard CF algorithms by about 88%, 82%, 79% and 85% for MovieLens-100K, MovieLens-1M, Book-Crossing and TripAdvisor data respectively, while maintaining good recommendation quality.

The widespread application of clustering in various fields leads to the discovery of different clustering techniques in order to partition multidimensional data into separable clusters. Although there are various clustering approaches used in literature, optimized clustering techniques with multi-objective consideration are rare. This paper proposes a novel data clustering algorithm, Enhanced Kernel-based Exponential Grey Wolf Optimization (EKEGWO), handling two objectives. EKEGWO, which is the extension of KEGWO, adopts weight exponential functions to improve the searching process of clustering. Moreover, the fitness function of the algorithm includes intra-cluster distance and the inter-cluster distance as an objective to provide an optimum selection of cluster centroids. The performance of the proposed technique is evaluated by comparing with the existing approaches PSC, mPSC, GWO, and EGWO for two datasets: banknote authentication and iris. Four metrics, Mean Square Error (MSE), F-measure, rand and jaccord coefficient, estimates the clustering efficiency of the algorithm. The proposed EKEGWO algorithm can attain an MSE of 837, F-measure of 0.9657, rand coefficient of 0.8472, jaccord coefficient of 0.7812, for the banknote dataset.

Please send your abstracts (or copies of papers that you want to see reviewed here) to vladik@utep.edu, or by regular mail to Vladik Kreinovich, Department of Computer Science, University of Texas at El Paso, El Paso, TX 79968, USA.