Approach For Automatic Extraction Research Articles

A syntactic component for Vietnamese language processing

This paper presents the development of a syntactic component for the Vietnamese language. We first discuss the construction of a lexicalized tree-adjoining grammar using an automatic extraction approach. We then present the construction and evaluation of a deep syntactic parser based on the extracted grammar. This is a complete system integrating necessary tools to process Vietnamese text, which permits to take as input raw texts and produce syntactic structures. A dependency annotation scheme for Vietnamese and an algorithm for extracting dependency structures from derivation trees are also proposed. At present, this is the first Vietnamese parsing system capable of producing both constituency and dependency analyses with encouraging performances: 69.33% and 73.21% for constituency and dependency analysis accuracy, respectively. The parser also compares favourably to a statistical parser which is trained and tested on the same data sets.

A novel approach for automatic extraction of semantic data about football transfer in sport news

Purpose – The purpose of this paper is to propose an automatic method to generate semantic annotations of football transfer in the news. The current automatic news integration systems on the Web are constantly faced with the challenge of diversity, heterogeneity of sources. The approaches for information representation and storage based on syntax have some certain limitations in news searching, sorting, organizing and linking it appropriately. The models of semantic representation are promising to be the key to solving these problems. Design/methodology/approach – The approach of the author leverages Semantic Web technologies to improve the performance of detection of hidden annotations in the news. The paper proposes an automatic method to generate semantic annotations based on named entity recognition and rule-based information extraction. The authors have built a domain ontology and knowledge base integrated with the knowledge and information management (KIM) platform to implement the former task (name...

Natural Language Processing (NLP) – A Solution for Knowledge Extraction from Patent Unstructured Data

Patents are valuable source of knowledge and are extremely important for assisting engineers and decisions makers through the inventive process. This paper describes a new approach of automatic extraction of IDM (Inventive Design Method) related knowledge from patent documents. IDM derives from TRIZ, the theory of Inventive problem solving, which is largely based on patent's observation to theorize the act of inventing. Our method mainly consists in using natural language techniques (NLP) to match and extract knowledge relevant to IDM Ontology. The purpose of this paper is to investigate on the contribution of NLP techniques to effective knowledge extraction from patent documents. We propose in this paper to firstly report on progress made so far in data mining before describing our approach.

A Semantic Web query Optimization Using Resource Description Framework

Abstract Semantic web mining can be defined as the problem of automatic extraction of information from the database and produce a structured output to the user queries. Most works in knowledge base system have focused on using axioms applying enrichment method, but was not efficient in detecting the document topic and hence resulted with the expanded queries. Although there is a straight forward approach for automatic extraction from a larger set of information, the problem of recognizing the second or higher order associations between the documents on the web still remains a challenging issue. Specifically, we present three folds architecture to process a class of well designed user queries based on Reuters-21578 Text Categorization Collection Data Set, called as Semantic Resource Description with Compound Protocol (SRD-CP). The first fold constructs a Semantic Pattern Tree based on the Resource Description Framework (RDF) query language for detecting the document topic name. The RDF query language uses compound structure to produce the result to the expanded user queries. The second fold is the design of compound structure in SRD-CP framework that consists of HTTP protocol and constrained application protocol to handle the complex query processing. Finally, the third fold includes the definition of word co-occurrences using the association frequency form with the help of the constructed SPT. Run Associate Apriori (RAA) algorithm is used to identify the second or higher order association between the web documents. The RAA algorithm in SRD-CP framework recognizes the association between web related documents and user fetched queries. SRD-CP framework is empirically evaluated using the dataset and is shown to be significantly more efficient in terms of document association level computation rate, processing time and user result retrieval rate.

Identification of Query Forms for Retrieving the Information From Deep Web

Web databases are now present everywhere. The data from the Deep Web can not be accessed by Search engine and web crawlers directly. The only way to access the hidden database is through query interfaces and filling up number of HTML forms for a specific domain [18]. In this paper a technique called QFORT (QUERY FORM RETRIEVAL TECHNIQUE) has been developed for identifying the relevant query form is presented. Retrieving information from deep web pages using wrappers is a fundamental problem arising in a huge range of web pages of vast practical interests. In this paper, we propose a novel technique to the problem of identifying the query forms from Web pages, which is one of the key problems in automatic extraction approach. The problem is resolved by many authors by using different technique Intensive experiments on real web sites show that the proposed technique can effectively help extracting desired data with high accuracies in most of the cases.

An Automatic Extraction Approach of Worm Signatures Based on Behavioral Footprint Analysis

This paper presents an automatic extraction approach of worm signatures based on behavioral footprint analysis. Firstly, the suspicious worm traffic is detected based on worm behavior and is an instance of the Sequential Change Point Detection. To make the detection mechanism insensitive to site and access pattern, a non-parametric Cumulative Sum (CUSUM) method is applied, thus making the detection mechanism much more generally applicable and its deployment much easier. Secondly, worm behavioral footprint is defined and classified. The chronicle formalism is applied to correlate the footprint in suspicious worm traffic. Finally, worm signatures are extracted and ascertained by the evaluation function. The experiment shows that the approach can extract worm signatures effectively and accurately. There is a conclusion that worm behavioral footprint can't identify the worm accurately, but it helps to locate worm signatures, so signatures can be extracted effectively.

A Novel Automatic Extraction Approach of Pollutants for Mobile Camera

Rapid and automatic extraction of pollutants is of great importance for mobile camera in real-world scenarios. In the moving process of robot, the camera is treated as dynamic background, and the pollutants on the camera are treated as static target. So as to realize the detection of static target in dynamic scene, this paper presents an automatic extraction algorithm for pollutants based on frame difference accumulation. Firstly, this algorithm can determine whether pollutants exist or not by the overall trend of gray histogram of the cumulative frame difference images. And then if existing pollutants, Otsu algorithm was adopted to adaptively calculate threshold to convert the gray image into binary image. In this paper, analysis of the important parameters of the algorithm - cumulative frame number and frame difference threshold was implemented. Moreover, feasibility of the algorithm was verified by experiments on the automatic extraction of pollutants for gun-type camera.

Automatyzacja w procesie detekcji obiektów archeologicznych z danych ALS

In this paper approaches of historical, archaeological object detection from airborne laser scanning (hereinafter referred to as ASL) data were shown. Presented approach of automatic extraction of potential charcoal pile was the analysis of a selected processing of digital terrain model. In this example, it was attempted to detect archaeological sites on a small test area by usage of template matching. Positive results have proved a great number of detected objects. Methodology applied in the research allowed for finding of a large percentage of measured objects indirectly. Presented approach was also assessed by the results of object extraction in respect to field measurements in the area of interest, as well as effectiveness of automation procedure.

Parametric Human Body Model for Digital Apparel Design

With the advance in 3D body scanning technology, it opens opportunities for virtual try-on and automatic made-to-measure in apparel products domain. This paper proposed a novel feature-based parametric method of human body shape from the cloud points of 3D body scanner [T2. Firstly, we improved the skeleton construction through adding and adjusting the position of joints. Secondly, automatic extraction approach of semantic feature cross-sections is developed based on the hierarchy. According to the unique distribution of cloud points of each cross-section of each body part, the extraction method of key points on the cross-section is described. Thirdly, we presented an interpolation approach of key points which fit cardinal spline to cross-section for each body part, in which tension parameter is used to represent the simple deformation of body shape. Finally, a connection approach of body part is proposed by sharing a boundary curve. The proposed method has been tested with our virtual human model (VHM) system which is robust and easier to use. The process generally requires about five minutes for generating a full body model that represents the body shape captured by 3D body scanner. The model can be imported in a CAD environment for application to a wide variety of ergonomic analyses.

Extracting Drug-Drug Interaction from the Biomedical Literature Using a Stacked Generalization-Based Approach

Drug-drug interaction (DDI) detection is particularly important for patient safety. However, the amount of biomedical literature regarding drug interactions is increasing rapidly. Therefore, there is a need to develop an effective approach for the automatic extraction of DDI information from the biomedical literature. In this paper, we present a Stacked Generalization-based approach for automatic DDI extraction. The approach combines the feature-based, graph and tree kernels and, therefore, reduces the risk of missing important features. In addition, it introduces some domain knowledge based features (the keyword, semantic type, and DrugBank features) into the feature-based kernel, which contribute to the performance improvement. More specifically, the approach applies Stacked generalization to automatically learn the weights from the training data and assign them to three individual kernels to achieve a much better performance than each individual kernel. The experimental results show that our approach can achieve a better performance of 69.24% in F-score compared with other systems in the DDI Extraction 2011 challenge task.

An Automatic Extraction Approach to Fractional Vegetation Cover of Saline Land with Digital Images

Fractional vegetation cover is an important variable in ecological environment and a key parameter in remote sensing estimation,which is needed in the modeling of the land-atmosphere exchanges of momentum,energy,water,and trace gases.Determination of fractional vegetation cover exactly is necessary for studies on plant transpiration,ground surface evaporation,soil degradation and salinization.Excess green,highlighting vegetation and inhibiting the interference of soil and shadow,was used as a contrast enhancement for identifying plants from soil regions.This study uses modified excess green index to extract fractional vegetation cover by analyzing RGB color features of corn,sorghum,mung beans and weeds growing in saline land in western Jilin Province.The digital images are geometrically corrected in order to eliminate distortion.The automatic extraction approach using modified excess green indexes which is about 40 for vegetation growing on the saline land of western Jilin Province accurately distinguishes vegetation from soil,derives plant and soil binary images,then calculates fractional covers of the four vegetation types.This paper chooses maximum likelihood method to contrast the results of MExG automatic classification.The covers of corn,sorghum,mung beans and weeds calculated by these two methods were compared by visual interpretation and t-test.The visual interpretation shows a very high probability.The t-tests indicate that the means of the four vegetation types extracted by maximum likelihood and MExG automatic classification show a high consistency.In addition,the true values of corn,sorghum,mung bean are obtained by digitizing these images using ArcGIS software to validate MExG approach.The accuracy of MExG method can reach 99%.The results show that the MExG automatic approach which achieves good classification results and is less labor and time intensive than maximum likelihood,can be a viable ground-based method to validate fractional cover products generated by remote sensing.

AUTOMATIC EXTRACTION OF BUILDING ROOFS FROM PICTOMETRY'S ORTHOGONAL AND OBLIQUE IMAGES

Abstract. Automatic extraction of buildings from digital images aims at detection of buildings from digital images and reconstruction of roof structure automatically. At Pictometry, more than 30 million images are captured every year and how to extract the useful information of objects on the ground from the existing image library for various applications is a big challenge we face now. In this paper, an automatic approach for extraction of building roof from digital orthogonal and oblique imagery is proposed. The proposed method uses image processing technique to derive the accurate 3D structure of building roof for accurate roof measurement, 3D modeling, computation of building footprints, etc. It consists of three major steps, i.e. extraction of roof corner and ridge points from the images, automatic matching of roof corner and ridge points between orthogonal and oblique images and grouping of the matched roof points to create roof facets. In this study, the modified Moravec operator is used to extract feature points from digital images. To find roof points which cannot be extracted by the point extractor, edge information is also extracted. Due to the nature of roof points, especially corner points and the difference between orthogonal and oblique images, a feature-based image matching technique is used to derive 3D information of roof corner and ridge points, instead of area-based matching. To match roof points correctly, edges associated with a corner or ridge point and their properties are used. After 3D roof points are generated, roof points belonging to the same roof facet are grouped together by using their spatial relations. Once points belonging to the same facet are found, a surface is fitted to the points and outliers can be removed during this process.

A Novel Approach for Extracting Students Temporal and Periodic Internet Usage Behaviors

Understanding the students’ temporal and periodic Internet usage behaviors are essential for administrators, instructors and course coordinators for evaluating Internet usage behaviors related to those students’ undertaken courses or programs. In this investigation we propose a new Web usage mining approach for automatic extraction and visualization of periodic and temporal based Internet usage behaviors of individual users. Our model is able to extract each individual user’s changes on periodic behaviors during different periods of a semester. There is lot of research papers in education and Web usage mining exists. We believe our work is totally different because our concern is extracting individual users’ behavior and we used Web site classification scheme for extracting each individual student’s behavior’s.

An Advanced Approach for Automatic Extraction of Planar Surfaces and their Topology from Point Clouds

An Advanced Approach for Automatic Extraction of Planar Surfaces and their Topology from Point Clouds

Automatic Constraint Based Test Generation for Behavioral HDL Models

With the emergence of complex high-performance microprocessors, functional test generation has become a crucial design step. Constraint-based test generation is a well-studied directed behavioral level functional test generation paradigm. The paradigm involves conversion of a given circuit model into a set of constraints and employing constraint solvers to generate tests for it. However, automatic extraction of constraints from a given behavioral hardware design language (HDL) model remained a challenging open problem. This paper proposes an approach for automatic extraction of word-level model constraints from the behavioral verilog HDL description. The scenarios to be tested are also expressed as constraints. The model and the scenario constraints are solved together using an integer solver to arrive at the necessary functional test. The effectiveness of the approach is demonstrated by automatically generating the constraint models for: 1) an exclusive-shared-invalid multiprocessor cache coherency model and 2) the 16-bit DLX-architecture, from their respective Verilog-based behavioral models. Experimental results that generate test vectors for high level scenarios like pipeline hazards, cache miss, etc., spanning over multiple time-frames are presented.

Commonsense and context: a novel approach for automatic extraction of generic statements

Commonsense and context: a novel approach for automatic extraction of generic statements

Data fusion of high-resolution satellite imagery and LiDAR data for automatic building extraction

This paper aims to present a new approach for automatic extraction of building footprints in a combination of the IKONOS imagery with pan-sharpened multi-spectral bands and the low-sampled (∼ 0.1 points/m 2) airborne laser scanning data acquired from the Optech's 1020 ALTM (Airborne Laser Terrain Mapper). Initially, a laser point cluster in 3D object space was recognized as an isolated building object if all the member points were similarly attributed as building points by investigating the height property of laser points and the normalized difference vegetation indices (NDVI) driven from IKONOS imagery. As modelling cues, rectilinear lines around building outlines collected by either data-driven or model-driven manner were integrated in order to compensate the weakness of both methods. Finally, a full description of building outlines was accomplished by merging convex polygons, which were obtained as a building region was hierarchically divided by the extracted lines using the Binary Space Partitioning (BSP) tree. The system performance was evaluated by objective evaluation metrics in comparison to the Ordnance Survey's MasterMap®. This evaluation showed the delineation performance of up to 0.11 (the branching factor) and the detection percentage of 90.1% (the correctness) and the overall quality of 80.5%.

Automatic extraction and delineation of single trees from remote sensing data

In this paper, we present a novel approach for the automatic extraction of trees and the delineation of the tree crowns from remote sensing data, and report and evaluate the results obtained with different test data sets. The approach is scale-invariant and is based on co-registered colour-infrared aerial imagery and a digital surface model (DSM). Our primary assumption is that the coarse structure of the crown, if represented at the appropriate level in scale-space, can be approximated with the help of an ellipsoid. The fine structure of the crown is suppressed at this scale level and can be ignored. Our approach is based on a tree model with three geometric parameters (size, circularity and convexity of the tree crown) and one radiometric parameter for the tree vitality. The processing strategy comprises three steps. First, we segment a wide range of scale levels of a pre-processed version of the DSM. In the second step, we select the best hypothesis for a crown from the overlapping segments of all levels based on the tree model. The selection is achieved with the help of fuzzy functions for the tree model parameters. Finally, the crown boundary is refined using active contour models (snakes). The approach was tested with four data sets from different sensors and exhibiting different resolutions. The results are very promising and prove the feasibility of the new approach for automatic tree extraction from remote sensing data.

Extraction, matching, and pose recovery based on dominant rectangular structures

Man-made environments possess many regularities which can be efficiently exploited for image-based rendering as well as robotic navigation and localization tasks. In this paper, we present an approach for automatic extraction of dominant rectangular structures from a single view and show how they facilitate the recovery of camera pose, planar structure, and matching across widely separated views. In the presented approach, the rectangular hypothesis formation is based on a higher-level information encoded by the presence of orthogonal vanishing directions, the dominant rectangular structures can be detected and matched despite the presence of multiple repetitive structures often encountered in a variety of buildings. Different stages of the approach are demonstrated on various examples of images of indoor and outdoor structured environments.

Automatic road-side extraction from large scale imagemaps

In recent years, many approaches have been exploited for automatic road extraction. Most of these approaches are based on edge detection algorithms. In this paper, a new object-based approach for automatic extraction of main roads in large scale imagemaps is proposed. The gray-scale imagemap is converted to a simplified imagemap using Gray_scale Morphological Algorithms (GMA). At this point, the proposed algorithm consists of two parallel stages. The first stage deals with straight lines extraction and the second stage deals with roads skeleton extraction.In the first stage, the simplified imagemap is segmented and converted to a binary image. Next, the binary imagemap objects are labeled and then, the straight line segments are extracted. In the second stage, the resolution of the simplified imagemap is reduced so that the width of roads are reduced to 2–3 pixels. Next, the reduced resolution image is converted to a binary image. Then, the skeleton of roads in the binary reduced resolution image is extracted.By combining the results from the two stages, the roadsides are extracted. The skeleton of roads and straight line segments are combined using searching road-side algorithm. The test area was an imagemap with a scale of 1:8000 over the Kish region of Iran. The program for this study is developed in Visual C++ language under Windows 98 operating system.