3 rd International Conference on Artificial Intelligence and Applications (AIAP-2016)

Venue : Kremslehner Hotels Vienna - May 21 ~ 22, 2016, Vienna, Austria

Accepted Papers

  • Weights Stagnation in Dynamic Local Search for SAT
    Abdelraouf Ishtaiwi Faculty of Information Technology, University of Petra, Amman, Jordan
    Since 1991, tries were made to enhance the stochastic local search techniques (SLS). Some researchers turned their focus on studying the structure of the propositional satis ability problems (SAT )to better understand their complexity in order to come up with better algorithms. Other researchers focused in investigating new ways to develop heuristics that alter the search space based on some information gathered prior to or during the search process. Thus, many heuristics, enhancements and developments were introduced to improve SLS techniques performance during the last three decades. As a result a group of heuristics were introduced namely Dynamic Local Search (DLS) that could outperform the systematic search techniques. Interestingly, a common characteristic of DLS heuristics is that they all depend on the use of weights during searching for satis able formulas. In our study we experimentally investigated the weights behaviors and movements during searching for satis ability using DLS techniques, for simplicity, DDFW DLS heuristic is chosen. As a results of our studies we discovered that while solving hard SAT problems such as blocks world and graph coloring problems, weights stagnation occur in many areas within the search space. We conclude that weights stagnation occurrence is highly related to the level of the problem density, complexity and connectivity.
  • Corrosion Detection Using A.I. :A Comparison of Standard Computer Vision Techniques and Deep Learning Model
    Luca Petricca and Stian Broen ,Broentech Solutions A.S., Horten, Norway Tomas Moss and Gonzalo Figueroa, Orbiton A.S. Horten, Norway
    In this paper we present a comparison between standard computer vision techniques and Deep Learning approach for automatic metal corrosion (rust) detection. For the classic approach, a classification based on the number of pixels containing specific red components has been utilized. The code written in Python used OpenCV[1] libraries to compute and categorize the images. For the Deep Learning approach, we chose Caffe[2], a powerful framework developed at “Berkeley Vision and Learning Center” (BVLC). The test has been performed by classifying images and calculating the total accuracy for the two different approaches.
  • Semantic Analysis over Lessons Learned Contained in Social Networks for Generating Organizational Memory in Centers R&D
    Marco Javier Suárez Barón , UNITEC, Bogotá,Colombia
    This paper shows the construction of an organizational memory metamodel focused on R&D centers. The metamodel uses lessons learned extracted from corporative social networks; the metamodel aims to promote learning and management of organizational knowledge at these types of organizations. The analysis is applied initially from lessons learned on topics of R&D in Spanish language. The metamodel use natural languages processing together with ontologies for analyze the semantic and lexical the each lesson learned. The final result involves a knowledge base integrated by RDF files interrogated by SPARQL queries.
  • WalkSAT Based-Learning Automata for MAX-SAT
    Noureddine Bouhmala,Buskerud and Vestfold University College, Mats Oselan and Øyestein Br°adland, Agder University, Norway
    Researchers in artificial intelligence usually adopt the Satisfiability paradigm as their preferred methods when solving various real worlds decision making problems. Local search algorithms used to tackle different optimization problems that arise in various fields aim at finding a tactical interplay between diversification and intensification to overcome local optimality while the time consumption should remain acceptable. The WalkSATa algorithm for the Maximum Satisfiability Problem (MAX-SAT) is considered to be the main skeleton underlying almost all local search algorithms for MAX-SAT. This paper introduces an enhanced variant of WalkSAT using Finite Learning Automata. A benchmark composed of industrial and random instances is used to compare the effectiveness of the proposed algorithm against state-of-the-art algorithms.
  • Two Level Description of Kyrgyz Morphology in Nüve Framework
    Zuleyha Yiner and Atakan Kurt, Istanbul University, Kalmamat Khulamshayev, Fatih University and Harun R.Zafer, Marmara University, Turkey
    In this paper a description of Kyrgyz morphology is given in the two level morphology formalism and an implementation in the NUVE Framework is presented. The Kyrgyz morphology is defined in 2 steps: Firstly, Kyrgyz morphophonemic processes are expressed as a set of two level orthographic rules which are indeed lexical-to-surface transformations. Secondly, Kyrgyz morphotactics – the rules governing the order of morpheme affixations – are expressed as a finite state machines (FSA). We then implement the morphology in the NUVE morphologic machine translation framework. The implementation requires the orthography in the form of two level rules, the morphotactics in the form of a FSA along with a root/stem lexicon, and a suffix dictionary. NUVE is a framework, a successor to our previous machine translation framework DILMAC, for morphological parsing and morphological machine translation. The Turkish morphology is already defined in NUVE. With the description of Kyrgyz morphology, we will be able implement a morphological machine translator between Kyrgyz and Turkish.
  • A Two Phases Heuristic based method for the MinMax Regret Location Problem
    Sarah Ibri, Chlef university. Chlef, Algeria
    We are interested in solving the problem of locating a subset of facilities in the case of uncertainties and variations in the system parameters. Dealing with this problem using scenarios based approach needs an important computational e ort. The two phases pro- posed method in this paper combines both exact and heuristic approaches to minimize the maximum regret of the model. We proposed and compared three di erent heuristics to solve it and applied it to the case of locating emergency vehicles stations. The obtained results show that site selection based on the minimum average travel time is the most promising one.