Journal of Intelligent & Fuzzy Systems - Volume 23, issue 4

Authors: Orsenigo, Carlotta | Vercellis, Carlo

Article Type: Research Article

Abstract: In the context of classification most efforts have been devoted to deriving accurate prediction models from a set of examples whose class is supposed to be known with certainty. However, there are situations where class labels are affected by an intrinsic vagueness, as in ranking customers for marketing campaigns or credit approval. In this paper we propose a new two-phase fuzzy classification method aimed at generating accurate classification rules when labels are uncertain. In the first phase, an ensemble method is applied in order to derive the value of the class membership function for each example in the dataset. In …the second phase, an optimal classification model is obtained by solving a fuzzy variant of discrete support vector machines. Computational tests performed on benchmark and real world marketing and credit risk datasets show the effectiveness of the proposed method when it is compared to alternative classification techniques. Furthermore, the tests reveal that the new fuzzy discrete SVM model is a robust regularization method capable of generating stable classification rules, reducing the variance of the error and smoothing out the noise due to outliers. Show more

Keywords: Data mining, fuzzy sets, support vector machines, marketing, credit risk

DOI: 10.3233/IFS-2012-0493

Citation: Journal of Intelligent & Fuzzy Systems, vol. 23, no. 4, pp. 101-110, 2012

Authors: Mirian, Maryam S. | Araabi, Babak N. | Ahmadabadi, Majid Nili | Siegwart, Roland R.

Article Type: Research Article

Abstract: Rapid increase in the size and complexity of sensory systems demands for attention control in real world robotic tasks. However, attention control and the task are often highly interlaced which demands for interactive learning. In this paper, a framework called METAL (mixture-of-experts task and attention learning) is proposed to cope with this complex learning problem. METAL consists of three consecutive learning phases, where the first two phases provide an initial knowledge about the task, while in the third phase the attention control is learned concurrently with the task. The mind of the robot is composed of a set of tiny …agents learning and acting in parallel in addition to an attention control learning (ACL) agent. Each tiny agent provides the ACL agent with some partial knowledge about the task in the form of its decision preference- called policy as well. The ACL agent in the third phase learns how to make the final decision by attending the least possible number of tiny agents. It acts on a continuous decision space which gives METAL the ability to integrate different sources of knowledge with ease. A Bayesian continuous RL method is utilized at both levels of learning on perceptual and decision spaces. Implementation of METAL on an E-puck robot in a miniature highway driving task along with farther simulation studies in Webots™ environment verify the applicability and effectiveness of the proposed framework, where a smooth driving behavior is shaped. It is also shown that even though the robot has learned to discard some sensory data, probability of raising aliasing in the decision space is very low, which means that the robot can learn the task as well as attention control simultaneously. Show more

Keywords: Attention control learning, decision space, perceptual space, bayesian continuous RL, learning to drive

DOI: 10.3233/IFS-2012-0500

Citation: Journal of Intelligent & Fuzzy Systems, vol. 23, no. 4, pp. 111-128, 2012

Authors: Du, Xinyu | Ying, Hao | Lin, Feng

Article Type: Research Article

Abstract: A hybrid system is a system containing a mixture of discrete event components and continuous variable components. The existing hybrid system modeling methods are effective to handle crisp cases but can be difficult to represent deterministic uncertainties and subjectivity inherited in many real-world applications. We generalize the crisp hybrid system framework to a fuzzy hybrid system framework by using fuzzy set theory; the latter contains the former as a special case. We utilize fuzzy sets, type-1 and type-2, to capture and represent uncertainties in the hybrid system's states and variables. We develop algorithms to calculate fuzzy states and their transitions …and propose a parallel composition method for modeling a (complex) fuzzy hybrid system through composing its components. This new formal, mathematical framework, capable of modeling a hybrid system with fuzzy states and various types of continuous dynamic processes, regardless whether they are available explicitly or implicitly (e.g., fuzzy systems and neural networks), establishes a basis for systematic study of the fuzzy hybrid systems. It can also be employed for computer simulation investigation, analogous to the discrete event simulation methodology. An example fuzzy hybrid system involving fuzzy differential equations as continuous variable component is provided to illustrate the new theory. Show more

Keywords: Hybrid systems, discrete event systems, continuous variable systems, fuzzy sets, type-2 fuzzy sets

DOI: 10.3233/IFS-2012-0501

Citation: Journal of Intelligent & Fuzzy Systems, vol. 23, no. 4, pp. 129-141, 2012

Authors: Masood, M.K. | Hew, Wooi Ping | Rahim, Nasrudin Abd.

Article Type: Research Article

Abstract: This paper reviews the use of Adaptive Neuro-Fuzzy Inference Systems (ANFIS) for vector-controlled induction motor drives. While conventional schemes do not deal well with the highly nonlinear nature of motor control, fuzzy logic with its adjustability and neural networks with their adaptability have been shown to be excellent alternatives. ANFIS combines the advantages of fuzzy logic and neural networks and yields excellent results when used at various stages of the motor control process. The most prominent use of ANFIS with motor drives has been for parameter estimation, speed control and torque and flux control. The merits and demerits of these …methods are examined. This paper is intended to serve as a reference for researchers considering the use of ANFIS for the control of motor drives. Show more

Keywords: ANFIS, induction motor, flux, parameter, torque

DOI: 10.3233/IFS-2012-0502

Citation: Journal of Intelligent & Fuzzy Systems, vol. 23, no. 4, pp. 143-158, 2012