Accepted Papers

  • Automating Curriculum Vitae Translations
    Gabriele Kahlout,University of Leeds, United Kingdom
    When applying for jobs abroad, a jobseeker must translate his CV. A great deal of time is expended on such translations. Although Google Translate translates any input text at no cost, its CV translations are poor. Couldthey be better? This paper illustrates how the translation of Italian CVs can be automatically improved by simplifyingthe input text. Still, these modifications result in a modestly improved translation.
  • From Public Polls to Tweets: Developing an Algorithm for Classifying Sentiment from Twitter Based on Computing with Words
    Saad M. Darwish,Magda M. Madbouly and Mohamed A. Hassan,Alexandria University, Egypt
    Uncertainty is an intrinsic part of sentiment analysis, the process of extracting opinion from text written in natural languages, especially when dealing with social media (Twitter data) which known as noisy texts. Although there are many researches have been done in sentiment analysis, accuracy in identifying sentiment from text is still far from satisfactory because many challenges. In this paper we propose a methodology for classifying sentiment from Twitter using Fuzzy sets and Computing with Words. We exploit its capability to operate on information described in natural language. Built up on the fuzzy principle, everything is allowed to be a matter of degree; our system uses part of speech tagging as feature, performing IF-THEN rules, in addition to use Generalized Constraints Language and possibilistic and probabilistic constraints to infer an answer to a query expressed in a natural language "which granule the tweet is belong?", the answer, also expressed in a natural language. The experimental results show that it is feasible to use Fuzzy Sets and Computing with Words to classify sentiment.
  • Image Type Water Meter Character Recognition Based on Embedded DSP
    LIU Ying, HAN Yan-bin and ZHANG Yu-lin,University of Jinan, China
    In the paper, we combined DSP processor with image processing algorithm and studied the method of water meter character recognition. We collected water meter image through camera at a fixed angle, the projection method is used to recognize those digital images. The experiment results show that the method can recognize the meter characters accurately and artificial meter reading is replaced by automatic digital recognition, which improves the working efficiency.
  • Go-Ahead: Improving prior-knowledge heuristics by using information retrieved from Play-Out Simulations.
    Gabriel Santos,UFU - Federal University of Uberlandia,Brazil
    In large wireless ad hoc networks, routing is a main issue as they include many nodes that span over relatively a large area. In such a scenario, finding smallest set of efficient routes would be a good approach for better communication. Algorithms that have been implemented in this area were found to be with higher message passing complexity and they were concerned only about the size of the Connected Dominating Set. This paper discusses the design and implementation of a distributed algorithm to compute connected dominating sets in a wireless network with less message complexity. The algorithm has been applied on networks with different network sizes and varying edge probability distributions. The algorithm outputs 40 % important nodes in the network to form back haul communication links with an approximation ratio 0.04 * â, + 1, where â, is the maximum node degree. The results confirm that the algorithm contributes to a better performance with reduced message complexity.
Copyright 速 AISO 2015