IJARAI Volume 3 Issue 12

Paper 1: From the Perspective of Artificial Intelligence: A New Approach to the Nature of Consciousness

Abstract: Consciousness is not only a philosophical but also a technological issue, since a conscious agent has evolutionary advantages. Thus, to replicate a biological level of intelligence in a machine, concepts of machine consciousness have to be considered. The widespread internalistic assumption that humans do not experience the world as it is, but through an internal ‘3D virtual reality model’, hinders this construction. To overcome this obstacle for machine consciousness a new theoretical approach to consciousness is sketched between internalism and externalism to address the gap between experience and physical world. The ‘internal interpreter concept’ is replaced by a ‘key-lock approach’. Here, consciousness is not an image of the external world but the world itself. A possible technological design for a conscious machine is drafted taking advantage of an architecture exploiting self-development of new goals, intrinsic motivation, and situated cognition. The proposed cognitive architecture does not pretend to be conclusive or experimentally satisfying but rather forms the theoretical the first step to a full architecture model on which the authors currently work on, which will enable conscious agents e.g. for robotics or software applications.

Author 1: Riccardo Manzotti

Author 2: Sabina Jeschke

Keywords: consciousness; machine consciousness; multi agent system; genetic algorithms; externalism

PDF

Paper 2: Rough Approximations for Incomplete Information*

Abstract: Rough set under incomplete information has been extensively studied. Based on valued tolerance relation for incomplete information system, several approaches were presented to dealing with the attribute reductions and rule extraction. We point out some drawbacks in the existing papers for valued tolerance relation based rough approximations and propose a new kind of rough approximation operators which is a generalization of Pawlak approximation operators for complete information system. Some basic properties of the approximation operators are investigated.

Author 1: Jun-Fang LUO

Author 2: Ke-Yun QIN

Keywords: Rough set; tolerance relation; valued tolerance relation

PDF

Paper 3: Incremental Granular Modeling for Predicting the Hydrodynamic Performance of Sailing Yachts

Abstract: This paper is concerned with a design method for modeling Incremental Granular Model (IGM) based on Linguistic Model (LM) and Polynomial Regression (PR) from data set obtained by complex yacht hydrodynamics. For this purpose, we develop a systematic approach to generating automatic fuzzy rules based on Context-based Fuzzy C-Means (CFCM) clustering. This clustering algorithm builds information granules in the form of linguistic contexts and estimates the cluster centers by preserving the homogeneity of the clustered data points associated with the input and output space. Furthermore, IGM deals with localized nonlinearities of the complex system so that the modeling discrepancy can be compensated. After performing the design of 2nd order PR as the first global model, we refined it through a series of local fuzzy if-then rules in order to capture the remaining localized characteristics. The experimental results revealed that the presented IGM showed a better performance in comparison to the previous works for predicting the hydrodynamic performance of sailing yachts.

Author 1: Keun-Chang Kwak

Keywords: granular networks; particle swarm optimization; linguistic model; two-sided Gaussian contexts

PDF

Paper 4: What is the Right Illumination Normalization for Face Recognition?

Abstract: In this paper, we investigate the effect of some illumination normalization techniques on a simple linear subspace face recognition model using two distance metrics on three challenging, yet interesting databases. The research takes the form of experimentation and analysis in which five illumination normalization techniques were compared and analyzed using two different distance metrics. The performances and execution times of the various techniques were recorded and measured for accuracy and efficiency. The illumination normalization techniques were Gamma Intensity Correction (GIC), discrete Cosine Transform (DCT), Histogram Remapping using Normal distribution (HRN), Histogram Remapping using Log-normal distribution (HRL), and Anisotropic Smoothing technique (AS). Results showed that improved recognition rate was obtained when the right preprocessing method is applied to the appropriate database using the right classifier.

Author 1: Aishat Mahmoud Dan-ali

Author 2: Mohamed Moustafa

Keywords: face recognition; preprocessing; illumination

PDF

Paper 5: Checking the Size of Circumscribed Formulae

Abstract: The circumscription of a propositional formula T may not be representable in polynomial space, unless the polynomial hierarchy collapses. This depends on the specific formula T, as some can be circumscribed in little space and others cannot. The problem considered in this article is whether this happens for a given formula or not. In particular, the complexity of deciding whether CIRC(T) is equivalent to a formula of size bounded by k is studied. This theoretical question is relevant as circumscription has applications in temporal logics, diagnosis, default logic and belief revision.

Author 1: Paolo Liberatore

Keywords: Circumscription; computational complexity; belief revision.

PDF

Paper 6: A two-level on-line learning algorithm of Artificial Neural Network with forward connections

Abstract: An Artificial Neural Network with cross-connection is one of the most popular network structures. The structure contains: an input layer, at least one hidden layer and an output layer. Analysing and describing an ANN structure, one usually finds that the first parameter is the number of ANN’s layers. A hierarchical structure is a default and accepted way of describing the network. Using this assumption, the network structure can be described from a different point of view. A set of concepts and models can be used to describe the complexity of ANN’s structure in addition to using a two-level learning algorithm. Implementing the hierarchical structure to the learning algorithm, an ANN structure is divided into sub-networks. Every sub-network is responsible for finding the optimal value of its weight coefficients using a local target function to minimise the learning error. The second coordination level of the learning algorithm is responsible for coordinating the local solutions and finding the minimum of the global target function. In the article a special emphasis is placed on the coordinator’s role in the learning algorithm and its target function. In each iteration the coordinator has to send coordination parameters into the first level of sub-networks. Using the input X and the teaching ?? vectors, the local procedures are working and finding their weight coefficients. At the same step the feedback information is calculated and sent to the coordinator. The process is being repeated until the minimum of local target functions is achieved. As an example, a two-level learning algorithm is used to implement an ANN in the underwriting process for classifying the category of health in a life insurance company.

Author 1: Stanislaw Placzek

Keywords: neural network, learning algorithm, hierarchical structure, decomposition, coordination

PDF