Ontology-Based Model of Law Retrieval System for R&D Projects

Size: px
Start display at page:

Download "Ontology-Based Model of Law Retrieval System for R&D Projects"

Transcription

1 Ontology-Based Model of Law Retrieval System for R&D Projects Wooju Kim Yonsei University 50 Yonsei-ro, Seodaemun-gu, Seoul, Republic of Korea Minjae Won INNOPOLIS Foundation 27-5, 123 beon-gil, Expo-ro, Yuseong-gu, Daejeon, Republic of Korea Youna Lee Yonsei University 50 Yonsei-ro, Seodaemun-gu, Seoul, Republic of Korea Donghe Kim Korea Railroad Research Institute 176, Cheoldobangmulgwan-ro, Uiwang-si, Gyeonggi-do, Republic of Korea HaeMin Jung Yonsei University 50 Yonsei-ro, Seodaemun-gu, Seoul, Republic of Korea ABSTRACT Research and development projects have close relationship with laws. In some cases, new technologies resulted from R&D projects can t be used because some statutes restrict them. The reason of this problem is that researchers don t know exactly which laws can affect their R&D projects. To solve the issue, we suggest a model for law retrieval system that can be used by researchers of R&D projects to find related statutes. Input of this model is a query document that describes the main contents of a project. By using ontology, legal terms are extracted from the document and statutes defining them are retrieved as a set of related laws. After this searching process, statutes are provided to researchers with their ranks, which are assigned using relevance scores we developed. By using this model, we can make a system for researchers to search a list of statutes that may affect R&D projects, and finally, they can adjust their project s direction by checking the list, preventing their works from being useless. CCS Concepts Information systems Information retrieval Retrieval models and ranking Keywords Ontology; R&D; Law Retrieval System 1. INTRODUCTION In the long term point of view, the research and development process needs many steps from initial planning to final commercialization. In many cases, statutes related with new technology are revised or newly enacted during the period of its Publication rights licensed to ACM. ACM acknowledges that this contribution was authored or co-authored by an employee, contractor or affiliate of a national government. As such, the Government retains a nonexclusive, royalty-free right to publish or reproduce this article, or to allow others to do so, for Government purposes only. ICEC '16, August 17-19, 2016, Suwon, Republic of Korea Copyright is held by the owner/author(s). Publication rights licensed to ACM. ACM /16/08 $15.00 DOI: R&D process. Changes in the related laws can affect the research direction, causing all the investment to be wasted. Namely, the developed technology can t be commercialized even though considerable amount of budget was spent for the R&D project. Along with the financial issue, the problem of losing opportunity to enhance the technological competitiveness in the worldwide market also exists. In order to deal with these problems, it is necessary to identify a set of related statutes in time. In this article, we proposed a model of law retrieval system to search a set of statutes relevant with a query document. For researchers, query document can be a R&D plan document. On searching process, law ontology is used as a knowledge base that have information about legal elements like legal terms, statutes, etc. After getting relevant statutes from the ontology, ranking process based on legal term s importance in both query document and a set of statutes proceeds. Therefore, researchers can earn a list of statutes with ranking which indicates their priority to be checked. Finally, researchers can review relevant statutes and constitute their research plan well. The purpose of this model is to prevent R&D projects from failure in advance, ultimately allowing researchers to search related statute at all times during the R&D project. The rest of this paper is organized as follows: In section 2, we reviewed some related works. We explained our methodology in section 3, and described how we implemented the method as a system in section 4. Finally, we concluded this paper in section Related work In this study, we use ontology as the knowledge base to save statutes. Ontology Engineering is a typical technology that provides a clear way to structure the relationship between objects. Structured ontology can supplement semantic searching by storing the relationship related to the target domain. Ontology is using RDF (Resource Description Framework) and OWL (Web Ontology Language), defined by the standards in the World Wide Web Consortium. RDF and OWL have an advantage in integration with other systems because they are based on XML (extensive Markup Language), a widely used format using tag structure.

2 There are many cases that utilize ontology to store and represent information. The data from the different sources can be integrated through ontology, and it is possible to interpret semantics of data by using ontology s specified vocabulary. Researches that use ontology in legal domain are as follows. Lame (2005) applied ontology which contains meaningful relationship between the legal concepts to a legal search system, by using NLP (Natural Language Processing) technology. By utilizing text parsing and statistical analysis of the French legal documents, legal concepts are logically structured. Kim (2012) utilized ontologies for users who lack legal knowledge to change general terms into legal terms. Jo (2015) proposed a model based on ontology to build a legal information search engine, but it did not reach the actual implementation. There are not many studies using ontology as a knowledge base for storing relations about statutes. A lot of researches using ontology in legal domain were focused mainly on the relationship between general terms and legal terms. 3. Methodology In this section, we propose a methodology of searching statutes related with a query document and determining their ranking by measures, called relevance scores. The proposed approach is divided into two steps: (1) searching process and (2) ranking process. The overall process can be viewed in Figure 1. Searching process uses relationship between legal terms and statutes defining them. First, terms in query document are extracted using morpheme analyzer. Then only the legal terms are selected using information in law ontology. In the ranking process, we calculate weight of each legal term and determine the ranking of statutes by relevance score, computed using the legal term s weight. The underlying assumption is that importance of a legal term in both a query document and a set of relevant statutes affects relevance of statutes defining it. To calculate the weight, we use TF-IDF, a well-known weighting scheme, to get importance of a legal term in a set of relevant statutes. We also use centrality score computed by page-rank algorithm to get significance of a legal term in query document. We think that a query document can be regarded as a network of legal terms, and use semantic relations between them to get centrality in the document network. Finally, relevance score of a statute is calculated based on weight of legal terms defined by it. In section 3.1, we describe the searching process. We use morpheme analysis to extract nouns from query document and classify legal terms among them. Also, we get a set of statutes defining legal terms by querying law ontology. These statutes are judged to be relevant. In section 3.2, we propose measures to score and rank statutes related with query documents. 3.1 Searching process In our approach, legal terms are important concepts that connect a query document with statutes. To extract legal terms, we first used a morpheme analyzer to select only nouns. We filter out legal terms from the nouns and find a set of statutes defining each of them. These two jobs proceed simultaneously, using information in our developed law ontology. The law ontology is constructed using Open API service provided by Korea Ministry of Government Legislation ( and contains information of all the legal terms, statutes and relations between them. Ontology schema is shown in Figure 2. Figure 1. Overall process

3 3.1.1 Law ontology The role of law ontology in law retrieval system is to keep hierarchical relation between statutes and define relation between legal terms and statutes. There are seven classes in law ontology: Statute, Act, Decree, Rule, Domain, LegalTerm, and Organization. In our concerned range, laws are divided into three hierarchical groups: acts, decrees, and rules. Acts are broad principles. Acts need a set of low level principles like decrees and rules, because an act can t define every cases to apply itself. Enforcement decrees are middle-level statutes. They are also known as presidential decrees. Enforcement rules are the last range that we concern in this system. They are enacted by each ministry. There are three properties among them: hasact, hasdecree, and hasrule. Each property has two different domains and one range. A statute can have a set of reference statutes ( hasreference ), and can be grouped by legal domains, like transportation, territory, railroad, etc. ( hasdomain ) Rules are made by ministry, so it has its administering organization ( hasorganization ) Relation between legal terms and statutes Nouns from query document are classified into two categories: One is legal, and the other is not legal. Nouns in legal group are called legal terms, and they are officially defined by more than one statutes. If a noun is classified as not legal, it is abandoned for the next stage. For example, if there is a noun public transportation in a query document, we search the word in the ontology. Then, a statute named act on the support and promotion of utilization of mass transit system is retrieved as a law defining it. So, public transportation is now categorized as a legal term. One legal term can be defined by many laws, and one law can define multiple legal terms. Therefore, the relation between legal terms and laws is many-to-many. Each noun is queried to the ontology using SPARQL, the standard query language for ontologies, and if it is an individual of class LegalTerm, a set of statutes defining it which are connected by object property isdefinedby is stored for next process. 3.2 Ranking process All the statutes obtained from the previous process have some relevance with query document. But their degree of relevance differs from each other. Therefore, the list of statutes needs to be provided with appropriate ranking, so that researchers can determine which statute should be checked first. Figure 2 Ontology schema In this section, we propose six scoring measures that can evaluate statute s relevance with query document. These measures are calculated based on legal terms importance within both query document and a set of relevant statutes Importance of legal term in query document To measure degree of relevance of statutes, we focus on the role of legal terms. If a legal term is important in query document, then statutes defining it have strong possibility of high relevance. We use frequency concept as a basic weighting scheme and compute centrality score to complement it. Centrality score is a measure calculating importance of a node in the network including it. We consider a query document as a network of legal terms. PMI (Pointwise Mutual Information) is used as an edge weight for each node pair. PMI is calculated for a pair of two elements based on the co-occurrence probability. High PMI value means high relevance between them. Unlike original PMI formula, we don t apply logarithm because edge weight can t have value under 0. The network can be represented as a complete graph. After building a network for query document, we apply PageRank algorithm, one of the well-known methods for measuring centrality. PageRank value of a legal term represents relative significance in the document. So the term is near core semantic of the document Importance of legal term in a set of relevant statutes We calculate TF IDF to determine importance of legal terms in a set of relevant statutes. TF IDF (Term Frequency Inverse Document Frequency) is a statistical measure that explains how many times a word is used in a document from document set. TF IDF means importance of a legal term in the result set Relevance scores We propose six measures called relevance score to rank statutes. The purpose of these measures are to give researchers more information about priority. Concept of our relevance score is as follows. RelevanceScore = (Importance of term in query document) (Importance of term in a set of relevant statutes) That is, the degree of relevance depends on importance of the legal term in query document and a set of statutes. Therefore, a statute which defines core terms, gets high priority.

4 Three measures are based on only TF IDF concepts, while the others use centrality score to reflect additional information from query document. Sum of contribution (C-SUM): Sum of TF-IDF values of legal terms defined by the statute. We only consider whether it occurs in the whole document. C-SUM is computed as follows: RS C SUM (j) = tf idf(i, j, S), where i is for legal term, j is for statute, ST is a set of legal terms in query document, and S is a set of relevant statutes. Sum of contribution by sections (C-SUM-SC): Sum of TF-IDF values of legal terms defined by the statute, considering the number of sections term appears. We assume that a query document can be divided into multiple sections. So, if a legal term occurs in multiple sections, it can be judged as an important word. RS C SUM SC (j) = tf idf(i, j, k, S) numofsec(i, k), where numofsec is the number of sections that term i appears. Sum of average contribution by sections (C-SUM-AVG-SC): Sum of average contribution in each section. For each section, it adds TF-IDF of legal terms which are defined by the statute, and divides it by the total number of legal terms in each section. RS C SUM AVG SC (j) = tf idf(i, j, k, S), where SC(k) is the number of legal terms in section k. numofsec(i, k) SC(k) These measures are mainly computed by TF-IDF values of legal terms. These are methods of centrality contribution (CN) lines computed by weighted Centrality Score on TF-IDF. These two kind of lines have similar computing process, but different on the point of applying Centrality Score. Sum of network contribution (CN-SUM): C-SUM considering centrality score of the term. RS CN SUM (j) = tf idf(i, j, S) Centrality(i) Sum of network contribution (CN-SUM-SC): C-SUM-SC considering centrality score of the term. RS CN SUM SC (j) = tf idf(i, j, k, S) numofsec(i, k) Centrality(i) Sum of network contribution (CN-SUM-AVG-SC): C-SUM- AVG-SC considering centrality score of the term. RS CN SUM AVG SC (j) = tf idf(i, j, k, S) Centrality(i) numofsec(i, k) SC(k) Finally, rank for each statute based on these relevance scores is assigned. 4. Implementation We implemented a prototype system based on our methodology, and evaluated performance of proposed relevance scores. The purpose of this test is to prove our searching approach is useful in reality and our ranking measures, especially centrality-applied scores, are meaningful. 4.1 Prototype System Target is railroad domain, and summary documents of R&D plan are used as query documents. We used a part of the statute ontology which contains only individuals about railroad. Query documents and knowledge about railroad ontology are provided by KRRI (Korea Railroad Research Institute). To earn PMI values between legal terms, we used number of news articles. The number of articles is obtained by using API from Naver ( the most popular portal site in Korea. For example, suppose the number of articles containing both rail and transport is 100, while number of those containing either word is 50 and 30, respectively. Then the simple PMI value for edge weight is 100/50*30 = 1/15. The number of relevant statutes for query document 1 is 78, while document 2 has 73 statutes as result. 4.2 Evaluation of relevance scores To check each relevance score s performance, an answer set for query document is needed to evaluate ranks of retrieved statutes. But, there is two problems. First, an answer set should be based on real relevance of statutes with query document, but the relevance can t be appraised by machines. Second, even R&D experts in railroad domain don t know the whole set of statutes related with query document, which means the answer set is not prepared. To deal with these issues, researchers in KRRI manually evaluate the result of each query document. Namely, an answer set is defined after retrieval. They evaluate relation between query document and retrieved statutes, then assign one of the three degrees among highly relevant, possibly relevant, and irrelevant to each statute Evaluation measures To evaluate relevance scores, we use two measures, sum of ranks and average precision-recall. Sum of ranks (SR): Sum of ranks that relevant statutes have. If this value is big, it means lower ranks are assigned to relevant statutes, so performance of the relevance score is not good. Sum of ranks in the best case has a value of k*(k+1)/2 for the number of relevant statutes k. SR is computed as follows: H SR = rank(h) h H, where H is the set of highly relevant statutes and rank(h) is an assigned rank for statute h. If h is not contained in retrieved set, rank(h) is 0. Weighted sum of ranks (WSR): This measure also considers moderate statutes. WSR is computed as follows: H WSR = rank(h) rank(p) h H, where P is the set of possibly relevant statutes. Average precision & average recall (AP & AR): For a size of retrieved statutes set n, we calculate precision and recall for n times and get the average value. Precision of statute k is the number of relevant statutes which has lower rank than the rank of k, divided by the rank of k. P p P

5 # relevant statutes whose rank < rank(k) Precision(k) = rank(k) And recall of statute k has the same numerator, but the denominator is the number of relevant statutes. Recall(k) = # relevant statutes whose rank < rank(k) # relevant statutes Evaluation result Sum of ranks and weighted sum of ranks for two summary document are presented in Table 1 and Figure 3. Large value of these measures means low performance. Table 1. Sum of ranks and weighted sum of ranks Document 1 Document 2 SR WSR SR WSR 1. CN-SUM CN-SUM-SC CN-SUM-AVG-SC C-SUM C-SUM-SC C-SUM-AVG-SC Figure 3. Sum of ranks and weighted sum of ranks In Table 2 and Figure 4, average precision and average recall of retrieved statutes are presented. Large value of these measures means high performance. Table 2. Average precision and Average recall Document 1 Document 2 AP AR AP AR 1. CN-SUM CN-SUM-SC CN-SUM-AVG-SC C-SUM C-SUM-SC C-SUM-AVG-SC Figure 4. Average precision and Average recall We can find out that CN scores show relatively high performance than C scores. That is, relevance scores using centrality score have better performance than those without centrality. 5. CONCLUSION In this research, we propose a statute retrieval system that can find a set of statutes which may affect R&D projects. This system searches statutes that are relevant to the project, considering the contents in query document. We use ontology as a knowledge base and design relevance scores that can help system to assign rank to each statute. This ranking system gives priority to users, helping them to decide which one should be seen before others. Through this system, researchers can check the statutes and adjust direction of their research. Since technologies about ontology are standardized, vocabularies and semantic structure in this research can be easily modified and reused in other ontologies about statutes. In other words, this model is a neutral model regardless of domain. 6. ACKNOWLEDGMENTS This research was supported and funded by Korean Railroad Research Institute. 7. REFERENCES [1] Brin, S. and Page, L., The anatomy of a large-scale hypertextual Web search engine, Computer Networks and ISDN Systems, Vol. 30, pp , [2] Church, K. W. and Hanks, P., Word association norms, mutual information, and lexicography, Comput. Linguist, Vol. 16, No. 1, pp , [3] Jo, D. W., Seo, M. J., and Kim, M. Ho., A Study on Legal Information Retrieval Engine based on Ontology, Korea Information Science Society, pp , [4] Kim, H. L., Kim, H. G., Personal Electronic Document Retrieval System Using Semantic Web/Ontology Technologies, The Journal of Society for e-business StudiesVol. 12, No. 1, pp , [5] Kim, J. H., Lee, J. S., Lee, M. J., Kim, W. J., and Hong, J. S., Term Mapping Methodology between Everyday Words and Legal Terms for Law Information Search System, Biblographic Info: J Intell Inform Syst, Vol. 18, No. 3, pp , [6] Lame, G., Using NLP Techniques to Identify Legal Ontology Components : Concepts and Relations, Artificial Intelligence and Law, Vol. 12, No. 4, pp , 2005.

6 [7] Mitschick, A., Ontology-based Indexing and Contextualization of Multimedia Documents for Personal Information Management Applications, International Journal on Advances in Software, Vol. 3, No. 1, 2 pp , 2010.

Automatic Tagging and Categorisation: Improving knowledge management and retrieval

Automatic Tagging and Categorisation: Improving knowledge management and retrieval Automatic Tagging and Categorisation: Improving knowledge management and retrieval 1. Introduction Unlike past business practices, the modern enterprise is increasingly reliant on the efficient processing

More information

INFORMATION RETRIEVAL IN CONSTRUCTION HAZARD IDENTIFICATION

INFORMATION RETRIEVAL IN CONSTRUCTION HAZARD IDENTIFICATION INFORMATION RETRIEVAL IN CONSTRUCTION HAZARD IDENTIFICATION Hyunsoo Kim*, Hyun-Soo Lee, Moonseo Park, and Sungjoo Hwang Department of Architectural Engineering, Seoul National University, Seoul, Korea

More information

Public Opinion Mining on Social Media: A Case Study of Twitter Opinion on Nuclear Power 1

Public Opinion Mining on Social Media: A Case Study of Twitter Opinion on Nuclear Power 1 , pp.224-228 http://dx.doi.org/10.14257/astl.2014.51.51 Public Opinion Mining on Social Media: A Case Study of Twitter Opinion on Nuclear Power 1 DongSung Kim 2 and Jong Woo Kim 2,3 2 222 Wangsimni-ro,

More information

Hybrid WOM Collection and Visualization Method for Reputation Rating in Online Community

Hybrid WOM Collection and Visualization Method for Reputation Rating in Online Community Indian Journal of Science and Technology, Vol 8(18), DOI: 10.17485/ijst/2015/v8i18/75931, August 2015 ISSN (Print) : 0974-6846 ISSN (Online) : 0974-5645 Hybrid WOM Collection and Visualization Method for

More information

Tag cloud generation for results of multiple keywords queries

Tag cloud generation for results of multiple keywords queries Tag cloud generation for results of multiple keywords queries Martin Leginus, Peter Dolog and Ricardo Gomes Lage IWIS, Department of Computer Science, Aalborg University What tag clouds are? Tag cloud

More information

A Study of an Agricultural Ontology Model for an Intelligent Service in a Vertical Farm

A Study of an Agricultural Ontology Model for an Intelligent Service in a Vertical Farm A Study of an Agricultural Ontology Model for an Intelligent Service in a Vertical Farm Taehyung Kim, NamJin Bae, MyeongBae Lee, Changsun Shin, Jangwoo Park and Yongyun Cho Dept. Information and Communication

More information

Semantic Web-Based Supplier Discovery Framework

Semantic Web-Based Supplier Discovery Framework Semantic Web-Based Supplier Discovery Framework Jaehun Lee 1, Kiwook Jung 1, Bo Hyun Kim 2, and Hyunbo Cho 1 1 Pohang University of Science & Technology, Pohang, Gyeongbuk, South Korea {jaehun_lee,kiwook,hcho}@postech.ac.kr

More information

The Michelin Curse: Expert Judgment Versus Public Opinion

The Michelin Curse: Expert Judgment Versus Public Opinion The Michelin Curse: Expert Judgment Versus Public Opinion Marco Del Vecchio marco@delvecchiomarco.com The University of Warwick ICUR 2017 Day 2 Outline 1 Introduction 2 The Data 3 Methodology and Hypotheses

More information

An intelligent medical guidance system based on multi-words TF-IDF algorithm

An intelligent medical guidance system based on multi-words TF-IDF algorithm International Conference on Applied Science and Engineering Innovation (ASEI 2015) An intelligent medical guidance system based on multi-words TF-IDF algorithm Y. S. Lin 1, L Huang 1, Z. M. Wang 2 1 Cooperative

More information

On utility of temporal embeddings for skill matching. Manisha Verma, PhD student, UCL Nathan Francis, NJFSearch

On utility of temporal embeddings for skill matching. Manisha Verma, PhD student, UCL Nathan Francis, NJFSearch On utility of temporal embeddings for skill matching Manisha Verma, PhD student, UCL Nathan Francis, NJFSearch Skill Trend Importance 1. Constant evolution of labor market yields differences in importance

More information

Oracle Knowledge Analytics User Guide

Oracle Knowledge Analytics User Guide Oracle Knowledge Analytics User Guide Working with Oracle Knowledge Analytics Reports Oracle Knowledge Version 8.4.2.2 April, 2012 Oracle, Inc. COPYRIGHT INFORMATION Copyright 2002, 2011, Oracle and/or

More information

Turn your data into ACTIONS DATA SCIENCE. Copyright 2017 Talentica Software (I) Pvt Ltd. All rights reserved. 01

Turn your data into ACTIONS DATA SCIENCE. Copyright 2017 Talentica Software (I) Pvt Ltd. All rights reserved. 01 Turn your data into ACTIONS DATA SCIENCE Copyright 2017 Talentica Software (I) Pvt Ltd. All rights reserved. 01 Give your product a Competitive Edge with DATA.SCIENCE Copyright 2017 Talentica Software

More information

Dow Jones Industry, Region and Subject Taxonomy

Dow Jones Industry, Region and Subject Taxonomy Dow Jones Industry, Region and Subject Taxonomy Features, Benefits and Application Dow Jones provides this taxonomy of industry, region, subject and company/organisation codes under the name Dow Jones

More information

Finding Similar Tweets and Similar Users by Applying Document Similarity to Twitter Streaming Data

Finding Similar Tweets and Similar Users by Applying Document Similarity to Twitter Streaming Data Proc. vol.6,no2,2013,pp.22-30 Schl. ITE Tokai Univ. Vol. xx,no.xx,20xx,pp.xxx -xxx Paper Paper Finding Similar Tweets and Similar Users by Applying Document Similarity to Twitter Streaming Data by Iwao

More information

TDWI Analytics Principles and Practices

TDWI Analytics Principles and Practices TDWI. All rights reserved. Reproductions in whole or in part are prohibited except by written permission. DO NOT COPY Previews of TDWI course books offer an opportunity to see the quality of our material

More information

Data Science, Investigations and Privacy Current Status, Challenges and Solutions

Data Science, Investigations and Privacy Current Status, Challenges and Solutions Data Science, Investigations and Privacy Current Status, Challenges and Solutions Starrett Consulting, Inc. Agenda Global Privacy Big Data and Data Science Introduction What are they? Data Science and

More information

Journal of Economic Cooperation and Development, 37, 3 (2016),

Journal of Economic Cooperation and Development, 37, 3 (2016), Journal of Economic Cooperation and Development, 37, 3 (016), 109-134 Determination of the Degree of Development and the Impact of the Information Environment on the Formation of A System of Social Control

More information

WM2016 Conference, March 6 10, 2016, Phoenix, Arizona, USA

WM2016 Conference, March 6 10, 2016, Phoenix, Arizona, USA Development of the Licensing Procedure and Regulatory Framework for the Spent Fuel Storage facility in Korea - 16423 Dae sik YooK*, Ho Jin Lee, Dongmyung LEE * Korea Institute of Nuclear Safety, 62 Gwahak-ro,

More information

Research on Influence of Job Characteristics of Social Workers at Welfare Institution for the Disabled on their Emotional Labor

Research on Influence of Job Characteristics of Social Workers at Welfare Institution for the Disabled on their Emotional Labor , pp.129-136 http://dx.doi.org/10.14257/astl.2016. Research on Influence of Job Characteristics of Social Workers at Welfare Institution for the Disabled on their Emotional Labor Jong-Pil Kim 1*, Sung-je

More information

Silvia Calegari, Marco Comerio, Andrea Maurino,

Silvia Calegari, Marco Comerio, Andrea Maurino, A Semantic and Information Retrieval based Approach to Service Contract Selection Silvia Calegari, Marco Comerio, Andrea Maurino, Emanuele Panzeri, and Gabriella Pasi Department of Informatics, Systems

More information

GS1 GLOBAL SMART PARKING SYSTEM: ONE ARCHITECTURE TO UNIFY THEM ALL

GS1 GLOBAL SMART PARKING SYSTEM: ONE ARCHITECTURE TO UNIFY THEM ALL 14th IEEE International Conference on Services Computing (SCC 2017) GS1 GLOBAL SMART PARKING SYSTEM: ONE ARCHITECTURE TO UNIFY THEM ALL Nhat Pham, Muhammad Hassan, Hoang Minh Nguyen and Daeyoung Kim Honolulu,

More information

Developing An Ontology-Based Representation Framework for Establishing Cost Analysis Knowledge Base for Construction Work Items

Developing An Ontology-Based Representation Framework for Establishing Cost Analysis Knowledge Base for Construction Work Items The 31st International Symposium on Automation and Robotics in Construction and Mining (ISARC 2014) Developing An Ontology-Based Representation Framework for Establishing Cost Analysis Knowledge Base for

More information

Text Analytics Software Choosing the Right Fit

Text Analytics Software Choosing the Right Fit Text Analytics Software Choosing the Right Fit Tom Reamy Chief Knowledge Architect KAPS Group http://www.kapsgroup.com Text Analytics World October 20 New York Agenda Introduction Text Analytics Basics

More information

A Study on the Prediction of Road Pavement Deterioration according to the Road Quality and ESAL 1

A Study on the Prediction of Road Pavement Deterioration according to the Road Quality and ESAL 1 , pp.108-112 http://dx.doi.org/10.14257/astl.2015.100.23 A Study on the Prediction of Road Pavement Deterioration according to the Road Quality and ESAL 1 Yongjun Lee 1, Minjae-Lee 2* 1Dept. of of Civil

More information

2016 U.S. PRESIDENTIAL ELECTION FAKE NEWS

2016 U.S. PRESIDENTIAL ELECTION FAKE NEWS 2016 U.S. PRESIDENTIAL ELECTION FAKE NEWS OVERVIEW Introduction Main Paper Related Work and Limitation Proposed Solution Preliminary Result Conclusion and Future Work TWITTER: A SOCIAL NETWORK AND A NEWS

More information

Prediction of Personalized Rating by Combining Bandwagon Effect and Social Group Opinion: using Hadoop-Spark Framework

Prediction of Personalized Rating by Combining Bandwagon Effect and Social Group Opinion: using Hadoop-Spark Framework Prediction of Personalized Rating by Combining Bandwagon Effect and Social Group Opinion: using Hadoop-Spark Framework Lu Sun 1, Kiejin Park 2 and Limei Peng 1 1 Department of Industrial Engineering, Ajou

More information

E x p e r t s t o Steer Cognitive Ap p l i c a t i o n s

E x p e r t s t o Steer Cognitive Ap p l i c a t i o n s I D C W H I T E P A P E R H ow S e m a n t ic Technologies Enable Domain E x p e r t s t o Steer Cognitive Ap p l i c a t i o n s July 2017 by Nick Tahamtan, IDC #CEMA42878117 Sponsored by Semantic Web

More information

An Approach to Ontology Development in Human Resources Management

An Approach to Ontology Development in Human Resources Management An Approach to Ontology Development in Human Resources Management Anamaria Szekely Babes Bolyai University, Faculty of Economic Sciences and Business Administration E-mail: b_ana_sz@yahoo.com Abstract

More information

A logistic regression model for Semantic Web service matchmaking

A logistic regression model for Semantic Web service matchmaking . BRIEF REPORT. SCIENCE CHINA Information Sciences July 2012 Vol. 55 No. 7: 1715 1720 doi: 10.1007/s11432-012-4591-x A logistic regression model for Semantic Web service matchmaking WEI DengPing 1*, WANG

More information

KANTARA: a Framework to Reduce ETL Cost and Complexity

KANTARA: a Framework to Reduce ETL Cost and Complexity KANTARA: a Framework to Reduce ETL Cost and Complexity Ahmed Kabiri #1, Dalila Chiadmi #2 # SIR Laboratory, Mohammadia Engineering School, MOHAMMED V UNIVERSITY IN RABAT 1 ahmed.kabiri@gmail.com 2 chiadmi@emi.ac.ma

More information

A Reputation-based DSS: the INTEREST Approach

A Reputation-based DSS: the INTEREST Approach A Reputation-based DSS: the INTEREST Approach Donato Barbagallo a, Saverio Bruno a, Cinzia Cappiello a, Chiara Francalanci, Maristella Matera a, and Lorenzo Radice a a Politecnico di Milano - Dipartimento

More information

The Qualitative way to analyse data Smart Indexing by i.know NV

The Qualitative way to analyse data Smart Indexing by i.know NV The Qualitative way to analyse data Smart Indexing by i.know NV i.know s Qualitative Analytics and Knowledge Streaming principles are based on a Smart Index of all your data. This Smart Indexing process

More information

Improving Web Service Clustering through Ontology Learning and Context Awareness

Improving Web Service Clustering through Ontology Learning and Context Awareness Improving Web Service Clustering through Ontology Learning and Context Awareness Banage Thenne Gedara Samantha Kumara A DISSERTATION SUBMITTTED IN FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR

More information

A Comparative Analysis of the Building Information Modeling Guides of Korea and Other Countries

A Comparative Analysis of the Building Information Modeling Guides of Korea and Other Countries A Comparative Analysis of the Building Information Modeling Guides of Korea and Other Countries Kyungran Hwang, Ghang Lee 2 ) Graduate Research Assistant, Department of Architectural Engineering, Yonsei

More information

The Job Classification System and Certification. Lists of Construction Industry - Focused on Construction Technicians

The Job Classification System and Certification. Lists of Construction Industry - Focused on Construction Technicians Contemporary Engineering Sciences, Vol. 7, 2014, no. 21, 1053-1060 HIKARI Ltd, www.m-hikari.com http://dx.doi.org/10.12988/ces.2014.49132 The Job Classification System and Certification Lists of Construction

More information

An Analysis Framework for Content-based Job Recommendation. Author(s) Guo, Xingsheng; Jerbi, Houssem; O'Mahony, Michael P.

An Analysis Framework for Content-based Job Recommendation. Author(s) Guo, Xingsheng; Jerbi, Houssem; O'Mahony, Michael P. Provided by the author(s) and University College Dublin Library in accordance with publisher policies. Please cite the published version when available. Title An Analysis Framework for Content-based Job

More information

Machine learning-based approaches for BioCreative III tasks

Machine learning-based approaches for BioCreative III tasks Machine learning-based approaches for BioCreative III tasks Shashank Agarwal 1, Feifan Liu 2, Zuofeng Li 2 and Hong Yu 1,2,3 1 Medical Informatics, College of Engineering and Applied Sciences, University

More information

Artificial Intelligence and Its Impact on the Global Travel Industry

Artificial Intelligence and Its Impact on the Global Travel Industry Artificial Intelligence and Its Impact on the Global Travel Industry Demystifying Emerging Technologies for the Global Travel Industry March 10, 2017 The Accelerating Pace of Technological Change Technological

More information

Concept-Based Readability of Web Services Descriptions

Concept-Based Readability of Web Services Descriptions Concept-Based Readability of Web Services Descriptions Pananya Sripairojthikoon, Twittie Senivongse Department of Computer Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok, Thailand

More information

Analytical Study on Term of Warranty Liability in Window and Door Work Defect in Apartment Building based on Occurred Defect Data

Analytical Study on Term of Warranty Liability in Window and Door Work Defect in Apartment Building based on Occurred Defect Data ISBN 978-81-934174-9-2 8th International Conference on Disaster Management, Building Design, Materials and Civil Engineering (DBMCE-17) Bangkok (Thailand) Dec. 25-26, 2017 Analytical Study on Term of Warranty

More information

Research on the Job Stress and Job Satisfaction of Social Workers at Welfare Institution for the Disabled

Research on the Job Stress and Job Satisfaction of Social Workers at Welfare Institution for the Disabled , pp.121-128 http://dx.doi.org/10.14257/astl.2016. Research on the Job Stress and Job Satisfaction of Social Workers at Welfare Institution for the Disabled Jong-Pil Kim 1*, Sung-je Cho 2** 1 Department

More information

Towards a Big Data-as-a-Service for Legislative Research in the National Assembly Library of Korea. Data Convergence Analysis Division

Towards a Big Data-as-a-Service for Legislative Research in the National Assembly Library of Korea. Data Convergence Analysis Division Towards a Big Data-as-a-Service for Legislative Research in the National Assembly Library of Korea Data Convergence Analysis 1. 2. 1 Amend the NAL Act and the Decree of NAL Organization Establish New

More information

Knowledge Management

Knowledge Management Decision Support Systems and Intelligent Systems, Seventh Edition Chapter 9 Knowledge Management 9-1 Learning Objectives Define knowledge. Learn the characteristics of knowledge management. Describe organizational

More information

Follower Behavior Analysis via Influential Transmitters on Social Issues in Twitter

Follower Behavior Analysis via Influential Transmitters on Social Issues in Twitter Follower Behavior Analysis via Influential Transmitters on Social Issues in Twitter Chonbuk National University, CAIIT, Dept. of Computer Science & Engineering, Korea {kyjeong0520, selfsolee}@chonbuk.ac.kr

More information

Leveraging the Social Breadcrumbs

Leveraging the Social Breadcrumbs Leveraging the Social Breadcrumbs 2 Social Network Service Important part of Web 2.0 People share a lot of data through those sites They are of different kind of media Uploaded to be seen by other people

More information

A Fuzzy Multiple Attribute Decision Making Model for Benefit-Cost Analysis with Qualitative and Quantitative Attributes

A Fuzzy Multiple Attribute Decision Making Model for Benefit-Cost Analysis with Qualitative and Quantitative Attributes A Fuzzy Multiple Attribute Decision Making Model for Benefit-Cost Analysis with Qualitative and Quantitative Attributes M. Ghazanfari and M. Mellatparast Department of Industrial Engineering Iran University

More information

AI vs. Automation. The newest technologies for automatic tagging. semantic STAFFING

AI vs. Automation. The newest technologies for automatic tagging. semantic STAFFING October 18, 2017 Copyright 2017 Taxonomy Strategies LLC and Semantic Staffing. All rights reserved. Taxonomy Strategies semantic STAFFING AI vs. Automation The newest technologies for automatic tagging

More information

Seed-driven Document Ranking for Systematic Reviews in Evidence-Based Medicine

Seed-driven Document Ranking for Systematic Reviews in Evidence-Based Medicine Seed-driven Document Ranking for Systematic Reviews in Evidence-Based Medicine Grace E. Lee and Aixin Sun School of Computer Science and Engineering Nanyang Technological University (NTU), Singapore Systematic

More information

Influencer Communities. Influencer Communities. Influencers are having many different conversations

Influencer Communities. Influencer Communities. Influencers are having many different conversations Influencer Communities Influencers are having many different conversations 1 1.0 Background A unique feature of social networks is that people with common interests are following (or friend-ing) similar

More information

Evaluation System for Defense IT Project in Korea: Post- Implementation Stage

Evaluation System for Defense IT Project in Korea: Post- Implementation Stage Evaluation System for Defense IT Project in Korea: Post- Implementation Stage Sangho Lee 1, Chong-Hyun Song 2* Abstract Performance measurement is not an easy task. However, it is necessary to measure

More information

AI vs. Automation. The Current State of Automated Content Tagging. semantic STAFFING

AI vs. Automation. The Current State of Automated Content Tagging. semantic STAFFING March 28, 2018 Copyright 2018 Taxonomy Strategies LLC and Semantic Staffing. All rights reserved. Taxonomy Strategies semantic STAFFING AI vs. Automation The Current State of Automated Content Tagging

More information

ML Methods for Solving Complex Sorting and Ranking Problems in Human Hiring

ML Methods for Solving Complex Sorting and Ranking Problems in Human Hiring ML Methods for Solving Complex Sorting and Ranking Problems in Human Hiring 1 Kavyashree M Bandekar, 2 Maddala Tejasree, 3 Misba Sultana S N, 4 Nayana G K, 5 Harshavardhana Doddamani 1, 2, 3, 4 Engineering

More information

WKU-MIS-B11 Management Decision Support and Intelligent Systems. Management Information Systems

WKU-MIS-B11 Management Decision Support and Intelligent Systems. Management Information Systems Management Information Systems Management Information Systems B11. Management Decision Support and Intelligent Systems Code: 166137-01+02 Course: Management Information Systems Period: Spring 2013 Professor:

More information

Calculation of Annual Maintenance and Replacement Cost of Water Supply System through LCC Analysis

Calculation of Annual Maintenance and Replacement Cost of Water Supply System through LCC Analysis Calculation of Annual Maintenance and Replacement Cost of Water Supply System through LCC Analysis Hyundong Lee*,**, Usman Rasheed*,**, Myeongsik Kong* and Hongcheol Shin*** *Environment and Plant Engineering

More information

Reputation trust Score Evaluation for E-Commerce Using Feedback Rating and Comments

Reputation trust Score Evaluation for E-Commerce Using Feedback Rating and Comments Reputation trust Score Evaluation for E-Commerce Using Feedback Rating and Comments Vinaya Ramesh Firake BE(IT),ME(CSE) Abstract: Reputation trust is one of the important factors of the development of

More information

NONDESTRUCTIVE EVALUATION BY ANALYSIS FOR DENSITY OF CRACK IN TUNNEL & UNDERGROUND STRUCTURES WITH TUNNEL SCANNER

NONDESTRUCTIVE EVALUATION BY ANALYSIS FOR DENSITY OF CRACK IN TUNNEL & UNDERGROUND STRUCTURES WITH TUNNEL SCANNER XVIII IMEKO WORLD CONGRESS Metrology for a Sustainable Development September, 17 22, 2006, Rio de Janeiro, Brazil NONDESTRUCTIVE EVALUATION BY ANALYSIS FOR DENSITY OF CRACK IN TUNNEL & UNDERGROUND STRUCTURES

More information

Improving the Response Time of an Isolated Service by using GSSN

Improving the Response Time of an Isolated Service by using GSSN Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology ISSN 2320 088X IMPACT FACTOR: 5.258 IJCSMC,

More information

UNED: Evaluating Text Similarity Measures without Human Assessments

UNED: Evaluating Text Similarity Measures without Human Assessments UNED: Evaluating Text Similarity Measures without Human Assessments Enrique Amigó Julio Gonzalo Jesús Giménez Felisa Verdejo UNED, Madrid {enrique,julio,felisa}@lsi.uned.es Google, Dublin jesgim@gmail.com

More information

Building Cognitive applications with Watson services on IBM Bluemix

Building Cognitive applications with Watson services on IBM Bluemix BusinessConnect A New Era of Thinking Building Cognitive applications with services on Bluemix Bert Waltniel Cloud 1 2016 Corporation A New Era of Thinking What is Bluemix? Your Own Hosted Apps / Services

More information

Trend Extraction Method using Co-occurrence Patterns from Tweets

Trend Extraction Method using Co-occurrence Patterns from Tweets Information Engineering Express International Institute of Applied Informatics 2016, Vol.2, No.4, 1 10 Trend Extraction Method using Co-occurrence Patterns from Tweets Shotaro Noda and Katsuhide Fujita

More information

From Algal Biomass to Bioenergy via Semantic Web and Linked data

From Algal Biomass to Bioenergy via Semantic Web and Linked data From Algal Biomass to Bioenergy via Semantic Web and Linked data Monika Solanki* 1 and Johannes Skarka 2 1 Aston Business School Aston University, Birmingham, UK m.solanki@aston.ac.uk 2 Karlsruhe Institute

More information

IBM WebSphere Service Registry and Repository, Version 6.0

IBM WebSphere Service Registry and Repository, Version 6.0 Helping you get the most business value from your SOA IBM Repository, Version 6.0 Highlights Provide clear visibility into service Use other standard registries associations and relationships while and

More information

From Syntactic Standards to Semantic Standards in the Agri-Food Logistics Domain

From Syntactic Standards to Semantic Standards in the Agri-Food Logistics Domain From Syntactic Standards to Semantic Standards in the Agri-Food Logistics Domain Linda Oosterheert 1, Michael van Bekkum 1, Jack Verhoosel 1, Christopher Brewster 2 1 TNO, Capitool 10, 7521 PL Enschede,

More information

The Factors on Elderly Employment Project Outcome: Appropriation of work, Job Training Satisfaction, Intra-organizational Cooperation

The Factors on Elderly Employment Project Outcome: Appropriation of work, Job Training Satisfaction, Intra-organizational Cooperation The Factors on Elderly Employment Project Outcome: Appropriation of work, Job Training Satisfaction, Intra-organizational Cooperation Cin Jae Chang Abstract The purpose of the study was to examine the

More information

A Preliminary Study on Text Mining Based Human Resource Allocation in a Construction Project

A Preliminary Study on Text Mining Based Human Resource Allocation in a Construction Project A Preliminary Study on Text Mining Based Human Resource Allocation in a Construction Project Sangil Han a and Ghang Lee a a Yonsei University, Republic of Korea E-mail: hancowr@gmail.com, glee@yonsei.ac.kr

More information

Design of a Conceptual Reference Framework for Reusable Software Components based on Context Level

Design of a Conceptual Reference Framework for Reusable Software Components based on Context Level www.ijcsi.org 26 Design of a Conceptual Reference Framework for Reusable Software Components based on Context Level V. Subedha 1, Dr. S. Sridhar 2 1 Research Scholar, Department of CSE, Sathyabama University

More information

Establishment of Low Energy Building materials and Equipment Database Based on Property Information

Establishment of Low Energy Building materials and Equipment Database Based on Property Information IOP Conference Series: Materials Science and Engineering PAPER OPEN ACCESS Establishment of Low Energy Building materials and Equipment Database Based on Property Information To cite this article: Yumin

More information

Managing Knowledge in the Digital Firm

Managing Knowledge in the Digital Firm Chapter 12 Managing Knowledge in the Digital Firm 12.1 2006 by Prentice Hall OBJECTIVES Assess the role of knowledge management and knowledge management programs in business Define and describe the types

More information

Components of a semantic enterprise

Components of a semantic enterprise Components of a semantic enterprise Gary Carlson, Gary Carlson Consulting Christine Connors, TriviumRLG LLC Semantic Technology Conference San Francisco, CA June 23, 2010 Gary Carlson Gary Carlson brings

More information

Final Project Report CS224W Fall 2015 Afshin Babveyh Sadegh Ebrahimi

Final Project Report CS224W Fall 2015 Afshin Babveyh Sadegh Ebrahimi Final Project Report CS224W Fall 2015 Afshin Babveyh Sadegh Ebrahimi Introduction Bitcoin is a form of crypto currency introduced by Satoshi Nakamoto in 2009. Even though it only received interest from

More information

high-level radioactive waste in Korea include Law No "Nuclear Safety Act", Nuclear Safety Commission Regulation No. 14 "Rules on Technical Stan

high-level radioactive waste in Korea include Law No Nuclear Safety Act, Nuclear Safety Commission Regulation No. 14 Rules on Technical Stan Strategic and Technical Aspects in RD&D Program Development for HLW Disposal System in Korea JeongHyoun Yoon*, JeongHwan Lee and SeungHyun Kim Radioactive Waste Disposal R&D Department, Korea Radioactive

More information

Lioma, Christina Amalia: Part of Speech n-grams for Information Retrieval

Lioma, Christina Amalia: Part of Speech n-grams for Information Retrieval Lioma, Christina Amalia: Part of Speech n-grams for Information Retrieval David Nemeskey Data Mining and Search Research Group MTA SZTAKI Data Mining Seminar 2011.05.12. Information Retrieval Goal: return

More information

Assessment Center in Korean Government

Assessment Center in Korean Government Part 1 Assessment Center in Korean Government 24, Sep., 2008 Namock Kim Deputy Director Ministry of Public Administration and Security 1 1. About MOPAS < Organization Structure of Korean Government > President

More information

An Integrated Knowledge Base for Sustainability Indicators

An Integrated Knowledge Base for Sustainability Indicators An Integrated Knowledge Base for Sustainability Indicators Lida Ghahremanloo School of Computer Science and Information Technology, RMIT University GPO Box 2476, Melbourne 3001, Victoria, Australia lida.ghahremanloo@rmit.edu.au

More information

Text Analytics Mini-Workshop Quick Start

Text Analytics Mini-Workshop Quick Start Text Analytics Mini-Workshop Quick Start Tom Reamy Chief Knowledge Architect KAPS Group Program Chair Text Analytics World Knowledge Architecture Professional Services http://www.kapsgroup.com Agenda Introduction

More information

Semantic Enrichment and the Information Manager

Semantic Enrichment and the Information Manager WHITEPAPER Semantic Enrichment and the Information Manager Turning Content into Insight It is more resource intensive to bring a drug to market than ever before: Pharmaceutical companies spend an average

More information

BUSINESS DEVELOPMENT INTELLIGENCE MONITORING FOR LAW FIRMS

BUSINESS DEVELOPMENT INTELLIGENCE MONITORING FOR LAW FIRMS WHITEPAPER BUSINESS DEVELOPMENT INTELLIGENCE MONITORING FOR LAW FIRMS Most major law firms engage in intelligence monitoring to spot new business opportunities and inform attorneys about important developments

More information

EDM Council Memorandum

EDM Council Memorandum 1 EDM Council Memorandum TO: RE: Financial Conduct Authority RegTech & Advanced Analytics (regtech@fca.org.uk) Using Technology to Achieve Smarter Regulatory Reporting FR: John Bottega, Executive Director,

More information

A Reference Model of Smart Library

A Reference Model of Smart Library , pp.80-84 http://dx.doi.org/10.14257/astl.2014.63.16 A Reference Model of Smart Library Hee-Kyung Moon 1, Ju-Ri Kim 1, Sung-Kook Han 1, Jin-Tak Choi 2 1 Department of Computer Engineering, Wonkwang University,

More information

Introduction to Computational Advertising

Introduction to Computational Advertising Introduction to Computational Advertising ISM293 University of California, Santa Cruz Spring 2009 Instructors: Ram Akella, Andrei Broder, and Vanja Josifovski 1 Questions about last lecture? We welcome

More information

Prospect of Technology for Public Transit Planning using Smart Card Data

Prospect of Technology for Public Transit Planning using Smart Card Data Prospect of Technology for Public Transit Planning using Smart Card Data Inmook Lee 1 and Suk-mun Oh and Jae Hong Min Department of Railway Policy & Strategy, Korea Railroad Research Institute, 360-1 Woram-dong,

More information

Argo: a platform for interoperable and customisable text mining

Argo: a platform for interoperable and customisable text mining Argo: a platform for interoperable and customisable text mining Sophia National Centre for Text Mining School of Computer Science The University of Manchester Overview Sharing tools, resources and text

More information

Identification of conclusive association entities in biomedical articles

Identification of conclusive association entities in biomedical articles Liu Journal of Biomedical Semantics (2019) 10:1 https://doi.org/10.1186/s13326-018-0194-9 RESEARCH Open Access Identification of conclusive association entities in biomedical articles Rey-Long Liu Abstract

More information

Study of category score algorithms for k-nn classifier

Study of category score algorithms for k-nn classifier Study of category score algorithms for k-nn classifier H. KOU1,G. Gardarin1>2 lprismlaborato~, Universi~ of Versailles Saint-Quentin, France 2e-xmlmediaInc., France Abstract In the context of document

More information

A Study on Estimating Maintenance Cost due to Bridge Pavement Service Period 1

A Study on Estimating Maintenance Cost due to Bridge Pavement Service Period 1 , pp.30-34 http://dx.doi.org/10.14257/astl.2015.100.07 A Study on Estimating Maintenance Cost due to Bridge Pavement Service Period 1 Yongjun Lee 1, Minjae-Lee 2* 1Dept. of of Civil Engineering, Chungnam

More information

Intelligent Business Transaction Agents for Cross-Organizational Workflow Definition and Execution

Intelligent Business Transaction Agents for Cross-Organizational Workflow Definition and Execution Intelligent Business Transaction Agents for Cross-Organizational Workflow Definition and Execution Mohammad Saleem 1, Paul W.H. Chung 1, Shaheen Fatima 1, Wei Dai 2 1 Computer Science Department, Loughborough

More information

An Algorithm for Mobile Computing Opinion Mining In Multilingual Forms By Voice and Text Processing

An Algorithm for Mobile Computing Opinion Mining In Multilingual Forms By Voice and Text Processing 2018 IJSRST Volume 4 Issue 5 Print ISSN: 2395-6011 Online ISSN: 2395-602X Themed Section: Science and Technology An Algorithm for Mobile Computing Opinion Mining In Multilingual Forms By Voice and Text

More information

Development of Demand Prediction Simulator based on Multiple Water Resources

Development of Demand Prediction Simulator based on Multiple Water Resources Available online at www.sciencedirect.com ScienceDirect APCBEE Procedia 10 (2014 ) 224 228 ICESD 2014: February 19-21, Singapore Development of Demand Prediction Simulator based on Multiple Water Resources

More information

MODERNIZING EMPLOYEE HR SUPPORT

MODERNIZING EMPLOYEE HR SUPPORT LOOK INSIDE: The changing world of work, the best ways to provide employee support, demystifying artificial intelligence, what to look for in AI, HR, and chatbots. MODERNIZING EMPLOYEE HR SUPPORT USING

More information

ESCO strategic framework

ESCO strategic framework ESCO (2015) SEC 002 FINAL ESCO (2015) BOA 003 FINAL 2 June 2015 ESCO strategic framework Vision, mission, position, added value and guiding principles Purpose of the document This document presents a strategic

More information

Collaborative Ontology Management

Collaborative Ontology Management Deep Dives into TopBraid EVN, Part 2: Collaborative Ontology Management February 25, 2016 Copyright 2015 TopQuadrant Inc. Slide 1 Collaborative Ontology Management Today s Program I. What can TopBraid

More information

The Perspective of B2MML Based on Implementation Feng Wang1, a, FuCheng Pan1, b, Peng Li1, c

The Perspective of B2MML Based on Implementation Feng Wang1, a, FuCheng Pan1, b, Peng Li1, c 2nd International Conference on Automation, Mechanical Control and Computational Engineering (AMCCE 2017) The Perspective of B2MML Based on Implementation Feng Wang1, a, FuCheng Pan1, b, Peng Li1, c 1

More information

Text Classification Advantage via Taxonomy

Text Classification Advantage via Taxonomy WHITE PAPER Text Classification Advantage via Taxonomy By: Seth Grimes, Alta Plana Corporation Page 2 I. Introduction This paper addresses the numerous challenges of automated text data handling, for applications

More information

TURNING TWEETS INTO KNOWLEDGE

TURNING TWEETS INTO KNOWLEDGE TURNING TWEETS Image removed due to copyright restrictions. INTO KNOWLEDGE An Introduction to Text Analytics Twitter Twitter is a social networking and communication website founded in 2006 Users share

More information

MINING SUPPLIERS FROM ONLINE NEWS DOCUMENTS

MINING SUPPLIERS FROM ONLINE NEWS DOCUMENTS MINING SUPPLIERS FROM ONLINE NEWS DOCUMENTS Chih-Ping Wei, Department of Information Management, National Taiwan University, Taipei, Taiwan, R.O.C., cpwei@im.ntu.edu.tw Lien-Chin Chen, Department of Information

More information

Performance Analysis of Anti-collision Algorithm for Tag Identification Time Improvement

Performance Analysis of Anti-collision Algorithm for Tag Identification Time Improvement , pp.1-10 http://dx.doi.org/10.14257/ijseia.2014.8.3.01 Performance Analysis of Anti-collision Algorithm for Tag Identification Time Improvement Chang-Su Kim 1, Bong-Im Jang 1 and Hoe-Kyung Jung 1* 1 PaiChai

More information

Usage-Centric Mobile Business Performance Metrics: Framework and Case Study

Usage-Centric Mobile Business Performance Metrics: Framework and Case Study Usage-Centric Mobile Business Performance Metrics: Framework and Case Study Ahyoung Kim1, Junwoo Lee1, Mucheol Kim2* 1 Electronics 2 Sungkyul and Telecommunications Research Institute, 218, Gajeong-ro,

More information

Latent Semantic Analysis. Hongning Wang

Latent Semantic Analysis. Hongning Wang Latent Semantic Analysis Hongning Wang CS@UVa VS model in practice Document and query are represented by term vectors Terms are not necessarily orthogonal to each other Synonymy: car v.s. automobile Polysemy:

More information