Search

To increase the reliability of currency classification, a classification method using neural networks with multi-pattern vectors is proposed in this paper. The data space of samples are divided into three blocks, then the latter are further divided into four sub-pattern vectors, and kernel principal component analysis is applied to extract features and assemble feature vectors to train LVQ neural network classifier. We draw the conclusion by testing new fifth edition RMB including four kinds of inputting directions of 1 Yuan, 5 Yuan, 10 Yuan and 20 Yuan RMB, up to 800 samples that PCA can compress data and decrease dimension of input vectors, extract the feature vectors effectively, thus the high-level reliability can be achieved by using the LVQ network classifier.

Both Content analysis and link analysis have its advantages in measuring relationships among documents. In this paper, we propose a new method to combine these two methods to compute the similarity of research papers so that we can do clustering of these papers more accurately. In order to improve the efficiency of similarity calculation, we develop a strategy to deal with the relationship graph separately without affecting the accuracy. We also design an approach to assign different weights to different links to the papers, which can enhance the accuracy of similarity calculation. The experimental results conducted on ACM Data Set show that our new algorithm, S-SimRank,outperforms other algorithms.

This paper is concerned with a multi-resolution tool for screening paper formation variations in various frequency regions on production line. A paper web is illuminated by two red diode lasers and the reflected light recorded as two time series of high resolution measurements constitute the input signal to the papermaking process monitoring system. The time series are divided into blocks and each block is analyzed separately. The task is treated as kernel based novelty detection applied to a multi-resolution time series representation obtained from the band-pass filtering of the Fourier power spectrum of the series. The frequency content of each frequency region is characterized by a feature vector, which is transformed using the canonical correlation analysis and then categorized into the inlier or outlier class by the novelty detector. The ratio of outlying data points, significantly exceeding the predetermined value, indicates abnormalities in the paper formation. The tools developed are used for online paper formation monitoring in a paper mill.

Typically, personalized information recommendation services automatically infer the user profile, a structured model of the user interests, from documents that were already deemed relevant by the user. We present an approach based on Word Sense Disambiguation (WSD) for the extraction of user profiles from documents. This approach relies on a knowledge-based WSD algorithm, called JIGSAW, for the semantic indexing of documents: JIGSAW exploits the WordNet lexical database to select, among all the possible meanings (senses) of a polysemous word, the correct one. Semantically indexed documents are used to train a naive Bayes learner that infers "semantic", sense-baseduser profiles as binary text classifiers (user-likes and user-dislikes). Two empirical evaluations are described in the paper. In the first experimental session, JIGSAW has been evaluated according to the parameters of the Senseval-3 initiative, that provides a forum where the WSD systems are assessed against disambiguated datasets. The goal of the second empirical evaluation has been to measure the accuracy of the user profiles in selecting relevant documents to be recommended. Performance of classical keyword-based profiles has been compared to that of sense-based profiles in the task of recommending scientific papers. The results show that sense-based profiles outperform keyword-based ones.

In this paper we present a system which recognizes handwritten annotations on printed text documents and interprets their semantic meaning. This system processes in three steps. In the first step, document analysis methods are applied to identify possible gestures and text regions. In the second step, the text and gestures are recognized using several state-of-the-art recognition methods. In the fourth step, the actual marked text is identified. Finally, the recognized information is sent to the Semantic Desktop, the personal Semantic Web on the Desktop computer, which supports users in their information management. In order to assess the performance of the system, we have performed an experimental study. We evaluated the different stages of the system and measured the overall performance.

A method is proposed to analyze the preferred Modulation Transfer Function (MTF) of printing medium like paper for the image quality of printing. First, the spectral intensity distribution of printed image is simulated by changing the MTF of medium. Next, the simulated image is displayed on a high-precision LCD to reproduce the appearance of printed image. An observer rating evaluation experiment is carried out to the displayed image to discuss what the preferred MTF is. The appearance simulation of printed image was conducted on particular printing conditions: several contents, ink colors, a halftoning method and a print resolution (dpi). The experiments on different printing conditions can be conducted since our simulation method is flexible about changing conditions.

We report on results of a paper-based lab study that used information on task performance, self appraisal and personal learning need assessment to validate the adaptation mechanisms for a work-integrated learning system. We discuss the results in the wider context of the evaluation of adaptive systems where the validation methods we used can be transferred to a work-based setting to iteratively refine adaptation mechanisms and improve model validity.

This article aims at presenting a methodological approach for classifying educational conference papers by employing a Bayesian Network (BN). A total of 400 conference papers were collected and categorized into 4 major topics (Intelligent Tutoring System, Cognition, e-Learning, and Teacher Education). In this study, we have implemented a 80-20 split of collected papers. 80% of the papers were meant for keywords extraction and BN parameter learning whereas the other 20% were aimed for predictive accuracy performance. A feature selection algorithm was applied to automatically extract keywords for each topic. The extracted keywords were then used for constructing BN. The prior probabilities were subsequently learned using the Expectation Maximization (EM) algorithm. The network has gone through a series of validation by human experts and experimental evaluation to analyze its predictive accuracy. The result has demonstrated that the proposed BN has outperformed Naive Bayesian Classifier, and BN learned from the training data.

This paper describes an approach to the use of citation links to improve the scientific paper classification performance. In this approach, we develop two refinement functions, a linear label refinement (LLR) and a probabilistic label refinement (PLR), to model the citation link structures of the scientific papers for refining the class labels of the documents obtained by the content-based Naive Bayes classification method. The approach with the two new refinement models is examined and compared with the content-based Naive Bayes method on a standard paper classification data set with increasing training set sizes. The results suggest that both refinement models can significantly improve the system performance over the content-based method for all the training set sizes and that PLR is better than LLR when the training examples are sufficient.

This paper examines the idea of artistic license of the interpreter as a positive aspect of composition. The possibilities of participating in the creative act beyond the role of the traditional interpreter are illustrated by tracing the development of malleability in score writing in selected works of the author. Starting with the standard score, examples are given for the various forms of malleable scores that lead up to the application of real-time electronic scores in which a concept of self-conduction is feasibly implemented for use in distributed ensembles.

We propose a method to search for illustrative sentences for English multiword expressions (MWEs) from a research paper database. We focus on syntactically flexible expressions such as "regard --- as." Traditionally, illustrative sentences that contain such expressions have been searched for by limiting the maximum number of words between the component words of the MWE. However, this method could not collect enough illustrative sentences in which clauses are inserted between component words of MWEs. We therefore devised a measure that calculates the distance between component words of an MWE in a parse tree, and use it for flexible expression search. We conducted experiments, and obtained a precision of 0.832 and a recall of 0.911.

High-precision linguistic and semantic analysis of scientific texts is an emerging research area. We describe methods and an application for extracting interesting factual relations from scientific texts in computational linguistics and language technology. We use a hybrid NLP architecture with shallow preprocessing for increased robustness and domain-specific, ontology-based named entity recognition, followed by a deep HPSG parser running the English Resource Grammar (ERG). The extracted relations in the MRS (minimal recursion semantics) format are simplified and generalized using WordNet. The resulting `quriples' are stored in a database from where they can be retrieved by relation-based search. The query interface is embedded in a web browser-based application we call the Scientist's Workbench. It supports researchers in editing and online-searching scientific papers.

This article proposes a Memetic Differential Evolution (MDE) for designing digital filters which aim at detecting defects of the paper produced during an industrial process. The MDE is an adaptive evolutionary algorithm which combines the powerful explorative features of Differential Evolution (DE) with the exploitative features of two local searchers. The local searchers are adaptively activated by means of a novel control parameter which measures fitness diversity within the population. Numerical results show that the DE framework is efficient for the class of problems under study and employment of exploitative local searchers is helpful in supporting the DE explorative mechanism in avoiding stagnation and thus detecting solutions having a high performance.

Nested parallel programming models, where the task graph associated to a computation is series-parallel are easy to program and show good analysis properties. These can be exploited for efficient scheduling, accurate cost estimation or automatic mapping to different architectures. Restricting synchronization structures to nested series-parallelism may bring performance losses due to a less parallel solution, as compared to more generic ones based in unstructured models (e.g. message passing).

Since the millennium, a quickly increasing number of research papers in the field of "computational trust and reputation" have appeared in the Computer Science literature. However, it remains hard to compare and evaluate the respective merits of proposed systems. We argue that rigorous use of formal probabilistic models enables the clear specification of the assumptions and objectives of systems, which is necessary for comparisons. To exemplify such probabilistic modeling, we present a simple probabilistic trust model in which the system assumptions as well as its objectives are clearly specified. We show how to compute (in this model) the so-called predictive probability: The probability that the next interaction with a specific principal will have a specific outcome. We sketch preliminary ideas and first theorems indicating how the use of probabilistic models could enable us to quantitatively compare proposed systems in various different environments.

We propose a new approach for the reconstruction of 3D CAD models from paper drawings. Our method uses a combination of the well-known fleshing-out-projections method and accumulation techniques from image processing to reconstruct part models. It should provide a comfortable method to handle inaccuracies and missing elements unavoidable in scanned paper drawings while giving the user the chance to observe and interactively control the reconstruction process.

In this paper, we developed an intelligent grading system, which scores descriptive examination papers automatically, based on Probabilistic Latent Semantic Analysis (PLSA) For grading, we estimated semantic similarity between a student paper and a model paper PLSA is able to represent complex semantic structures of given contexts, like text passages, and are used for building linguistic semantic knowledge which could be used in estimating contextual semantic similarity In this paper, we marked the real examination papers and we can acquire about 74% accuracy of a manual grading, 7% higher than that from the Simple Vector Space Model.

This paper presents a method that combines a greedy and an evolutionary algorithm to assign papers submitted to a conference to reviewers. The evolutionary algorithm tries to maximize match between the referee expertise and the paper topics, with the constraints that no referee should get more papers than a preset maximum and no paper should get less reviewers than an established minimum, taking into account also incompatibilities and conflicts of interest. A previous version of the method presented on this paper was tested in another conference obtaining not only a good match, but also a high satisfaction of referees with the papers they have been assigned; the current version has been also applied on that conference data, and to the conference where this paper has been submitted; results were obtained in a short time, and yielded a good match between reviewers and papers assigned to them, better than a greedy algorithm. The paper finishes with some conclusions and reflections on how the whole submission and refereeing process should be conducted.

The aim of our work is to provide support for reading (or skimming) scientific papers. In this paper we report on the task to identify concepts or terms with positive attributions in scientific papers. This task is challenging as it requires the analysis of the relationship between a concept or term and its sentiment expression. Furthermore, the context of the expression needs to be inspected. We propose an incremental knowledge acquisition framework to tackle these challenges. With our framework we could rapidly (within 2 days of an expert’s time) develop a prototype system to identify positive attributions in scientific papers. The resulting system achieves high precision (above 74%) and high recall rates (above 88%) in our initial experiments on corpora of scientific papers. It also drastically outperforms baseline machine learning algorithms trained on the same data.

The industrial design cycle starts with design then simulation, prototyping, and testing. When the tests do not match the design requirements the design process is started over again. It is important for students to experience this process before they leave their academic institution. The high cost of the prototype phase, due to CNC/Rapid Prototype machine costs, makes hands on study of this process expensive for students and the academic institutions. This document shows that the commercially available LEGO NXT Robot kit is a viable low cost surrogate to the expensive industrial CNC/Rapid Prototype portion of the industrial design cycle.

This paper is concerned with a multi-resolution tool for analysis of a time series aiming to detect abnormalities in various frequency regions. The task is treated as a kernel based novelty detection applied to a multi-level time series representation obtained from the discrete wavelet transform. Having a priori knowledge that the abnormalities manifest themselves in several frequency regions, a committee of detectors utilizing data dependent aggregation weights is build by combining outputs of detectors operating in those regions.

The main topic of the article is to give a detailed description of the new and promising quadtree decomposition texture analysis method used for paper formation determination. Paper formation or configuration of fibers, fines and fillers in the two-dimensional spatial xy-domain of the paper is a very important property and image analysis application for the paper industry. The basis of the method is the successive quadtree decomposition process resulting in a two-dimensional block partitioning of the formation structure image analysed. In this context the blocks represents a unit of variation, and the size of a quadtree block is controlled by a set of different parameters. In addition to the primary features detected by the algorithm, characterization of a large set of secondary features is performed, including gradient analysis and spatial distribution analysis.

3D Geographical Information Systems need 3D representations of objects and, hence, 3D data acquisition and reconstructions methods. Developments in these two areas, however, are not compatible. While numerous operational sensors for 3D data acquisition are readily available on the market (optical, laser scanning, radar, thermal, acoustic, etc.), 3D reconstruction software offers predominantly manual and semi-automatic tools (e.g. Cyclone, Leica Photogrammetry Suite, PhotoModeler or Sketch-up). The ultimate 3D reconstruction algorithm is still a challenge and a subject of intensive research. Many 3D reconstruction approaches have been investigated, and they can be classified into two large groups, optical image-based and point cloud-based, with respect to the sensor used, which can be mount on different platforms.

This paper proposes a colored paper mosaic rendering technique based on image segmentation that can automatically generate a torn and tagged colored paper mosaic effect. The previous method[12] did not produce satisfactory results due to the ineffectiveness of having to use pieces of the same size. The proposed two methods for determination of paper shape and location that are based on segmentation can subdivide an image area by considering characteristics of image. The first method is to generate a Voronoi polygon after subdividing the segmented image again using a quad tree. And the second method is to apply the Voronoi diagram on each segmentation layer. Through these methods, the characteristic of the image is expressed in more detail than the previous colored paper mosaic rendering method.

Automatic summaries are often subject to several criticisms (e.g., lack of cohesion and coherence). In this paper, we propose an approach that uses coherent Summary-Schemas (templates) conceived from the rhetorical structure of scientific papers including their abstracts. The Summary-Schemas embed rhetorical roles specified by signatures (sets of positional, structural, linguistic and thematic features) that guide the search for appropriate sentences in the source text.

Engineering solutions are generally documented in assembly and part drawings and bill of materials. A great benefit, qualitatively and commercially, can be achieved if these paper based storages can be transformed into digital information archives. The process of this transformation is called reconstruction. The reconstruction process of paper based assembly drawings consists of four steps: digitization; vectorization/ interpretation; 3D reconstruction of the parts and the 3D reconstruction of the assembly.This paper evaluates existing commercial systems worldwide for interpretation of paper based mechanical engineering drawings. For a complete reconstruction process a 3D reconstruction is needed. This functionality is already supported by some CAD systems to a certain extent, but it still remains a major topic of research work. One CAD system which converts 2D CAD models into 3D CAD models is presented. Finally, after the reconstruction of the parts the whole assembly can be reconstructed. Until now, no system for the automatic reconstruction of assemblies is available. In our paper we present a general approach for automatic reconstruction of 3D assembly model data by interpretation of mechanical engineering 2D assembly drawings, their part drawings, and the bill of materials.

Capturing and understanding mathematics from print form is an important task in translating written mathematical knowledge into electronic form. While the problem of syntactically recognising mathematical formulas from scanned images has received attention, very little work has been done on semantic validation and correction of recognised formulas. We present a first step towards such an integrated system by combining the Infty system with a semantic analyser for matrix expressions. We applied the combined system in experiments on the semantic analysis of matrix images scanned from textbooks. While the first results are encouraging, they also demonstrate many ambiguities one has to deal with when analysing matrix expressions in different contexts. We give a detailed overview of the problems we encountered that motivate further research into semantic validation of mathematical formula recognition.

This talk will consider rigorous mathematics and the nature of proof. It begins with an historical perspective and follows the development of formal mathematics. The talk will conclude with examples demonstrating that understanding the relationship between formal mathematics and rigorous proof can assist with both the discovery and the quality of real proofs of real results.

One of the most important problems for development of intelligent agents is adaptation to the environment. In this paper we briefly describe Helli-Respina soccer simulator team that uses a new self-adaptive method named Dynamic Multi-Behavior Assessment (DMBA). By using built-in behavior manager named dynamic behavior transformer method lets the agent can choose the best algorithms to decide during the game. This system always tries to choose a set of available algorithms to get the best result against each opponent. The main objective in this research is how to choose a set of algorithms dynamically to get the best result against an opponent.

Diagrams play an important role in human problem solving. In response to a challenging assignment, three students produced diagrams and subsequent verbal protocols that offer insight into human cognition. The diversity and richness of their response, and their ability to address the task via diagrams, provide an incisive look at the role diagrams play in the development of expertise. This paper recounts how their diagrams led and misled them, and how the diagrams both explained and drove explanation. It also considers how this process might be adapted for a computer program.

This paper addresses the problem of extracting three-dimensional geometric information from a single, uncalibrated image of a scene.

WISDOM++ is an intelligent document processing system that transforms a paper document into HTML/XML format. The main design requirement is adaptivity, which is realized through the application of machine learning methods. This paper illustrates the application of symbolic learning algorithms to the first three steps of document processing, namely document analysis, document classification and document understanding. Machine learning issues related to the application are: Efficient incremental induction of decision trees from numeric data, handling of both numeric and symbolic data in first-order rule learning, learning mutually dependent concepts. Experimental results obtained on a set of real-world documents are illustrated and commented.

The automated supervision system for online teaching is volatile in current teaching observation. Hence, it requires additional comprehensive, analytical, and realistic discussion on how the automatic supervision method can be applied to high school teaching. This paper integrated remote supervision with machine learning algorithms (IRS-MLA) proposed for the online English teaching audit process. Here, IRS-MLA simulates the implementation of supervision methodologies in the teaching process according to English online teaching’s real needs. Furthermore, searching the performance and stating the learning process for students from the teachers’ perspectives and their students measures the teacher’s teaching process. This paper presents the studies for evaluating the classic English language online supervision and explores this method’s functional impact. This analysis’s findings show that the model developed in this paper worked well and validated based on the case study report. This study validates the proposed IRS-MLA with the highest performance ratio of 97.8%, the accuracy of 96%, the efficiency of 99.3%, and a success ratio of 98%, compared to existing models.

We have developed a new idea generation support system, GUNGEN DX II. GUNGEN DX II supports the KJ method. GUNGEN DX II has two functions for handling a large number of ideas. The draft islands generating function supports the idea-grouping step of the KJ method. The function supports the grouping of many ideas intuitively by dropping an idea from the top of a window. The sentence convert function supports the sentence-writing step of the KJ method. The function generates a sentence using island titles semi-automatically. We carried out the KJ method using 544, 287 and 58 ideas. The results of the experiments are shown below. (1)Students could perform all the steps of the KJ method using over 500 ideas in one day. (2)If there are draft islands, students may be able to group more than 500 ideas. (3)More time was required for writing a sentence using 544 ideas.

The annual Robocup soccer competition is an excellent opportunity for our robotics and agent research. We view the competition as a rigorous testbed for our methods and a unique way of validating our ideas. After two years of competition, we have begun to understand what works (we won the competition in Tokyo 97) and what does not work (we failed to advance to the second round in Paris 98). This paper presents an overview of our goals in Robocup, our philosophy in building soccer playing robots and the methods we are employing in our efforts.