Scientific Program

Conference Series Ltd invites all the participants across the globe to attend 6th International Conference on Big Data Analysis and Data Mining Park Inn by Radisson Hotel, London, United Kingdom.

Submit your Abstract
or e-mail to

datamining@brainstormingmeetings.com
datamining@brainstormingmeetings.com
datamining@speakerresearch.com

Scientific Program Day 1

Day 1 :

  • Data Mining Applications in Science, Engineering, Healthcare and Medicine Big Data in Nursing Research | Big Data Technologies | Big Data Analytics | Big Data Algorithm | Big Data Optimization | Forecasting from Big Data | Big Data Applications, Challenges and Opportunities | Data Mining and Machine Learning | Data Mining Methods and Algorithms | Data Mining Tools and Software | Data Mining Tasks, Processes and Analysis | Data Privacy and Ethics | Data Warehousing | Artificial Intelligence | Cloud Computing | Social Network Analysis | Business Analytics | Internet of Things (IOT)| Open Data | New Visualization Techniques | Search and Data Mining | Frequent Pattern Mining | Clustering | Complexity and Algorithms | Nanoinformatics | Renewable Energy |Forecasting with Big Data

Session Introduction

Paria Soleimani

South Tehran Branch, Islamic Azad University,Tehran, Iran

Title: Identifying the effective factors on brand value (Case study: Automobile companies of Tehran Stock Exchange)
Speaker
Biography:

Paria Soleimani, PhD, is assistant professor of industrial engineering at Azad University, South Tehran branch, Iran. She has authored numerous papers in the areas of statistical quality control, engineering statistics and statistical profile monitoring in high quality international journals.

Abstract:

Branding has been emerged as a competetive strategy in the recent times. There are two dominant theories regarding the evaluation of a brand’s value; the first is costumer-based, and the second is financial-based. The customer-based viewpoint belongs to the marketing and behaviorists, while the financial-based point of view is related to financial data and involves the hard aspect of the issue. In the second approach, Tobin’s Q index has been used as brand value since the early 1990s. Using a financial-based approach in automobile industry of Tehran stock exchange, applying a real data set, this paper makes an effort to identify the brand value and the financial factors that affect it. By reviewing the literature, templates, and the results of previous researches, we used data mining methods as a proper means. Decision tree techniques used to investigate the severity of factors. The results of C-5 decision tree method indicate that the brand’s age positively affects the brand value at a rate of 84%. Also, Quest Tree method indicates that the brand’s age positively affects the brand value at the similar rate. Hence, it is confirmed that the brand age positively affects its brand value. Moreover, according to the another hypothesis related to the effectiveness of market share, Quest Tree and C-5 results also show that the market share positively affects brand value at a rate of 16%. The results of Quest Tree and C-5 were same in this case too. However, due to the data mininig used methods, the expenses related to the marketing and research and development do not affect the brand value.

Karmen Kern Pipan

Ministry of Public Administration, Republic Slovenia

Title: Supporting improvements in decision making process using big data analytics in Ministry of Public Administration of Republic Slovenia
Speaker
Biography:

Karmen Kern Pipan has completed her PhD from University of Maribor. She started her career in the private sector in the field of informatics and telecommunications and later continued in public administration in different positions. More than a decade she was active as EFQM European assessor, certified lecturer and university teacher. Currently she works as Secretary and Project manager in the Ministry of Public Administration of Republic Slovenia in the IT Directorate. As an expert, she is involved in the field of data management, business intelligence and big data analytics to improve data based decision making in Slovenian public administration. She led an inter-ministerial task force for the preparation of the Slovenian Public Administration Development Strategy 2015-2020. She has presented several articles in different international conferences and professional sphere and published papers in reputed professional and scientific journals.

Abstract:

In 2017 the Ministry of Public Administration of Republic Slovenia (hereafter MPA) in collaboration with international company EMC Dell successfully implemented the pilot project for the use of big data tools. The pilot project - Big Data Analysis for HR efficiency improvement has been established as part of the development oriented strategy supporting ICT as an enabler for development of data driven public administration in Slovenia. This pilot project has been launched aiming to learn what big data tool installed on the Slovenian Governemental Cloud Infrastructure could enable in terms of research of HR data of our ministry to improve our efficiency. Therefore, pseudoanonymized internal data sources containing time management, HR database, finance database and public procurement had been combined with open data (postal codes of employees and weather) to identify potentials for improvement and possible patterns of behaviour. Gained experience showed that big data analytics could help improve the efficiency of MPA in decision-making by using different statistical and quantitative analysis. MPA has continued with projects in this field aiming to spread the gained experience and knowledge of big data tools among public employees by launching trainning programe in Administration Academy. The project has been successfully presented in a series of national and international events and conferences, where it gained considerable interest. The pilot project has been also published in the OECD Observatory of Public Sector Innovation (OPSI) among the most
innovative public sector cases.

Gyeongseok Oh

Sam Houston State University, USA

Title: Crime Prediction Using Administrative Big Data and Machine Learning
Speaker
Biography:

Gyeongseok (Jason) Oh began the SHSU Criminal Justice Ph.D. program in the Fall of 2017.  In 2016, he graduated from Florida State University with an M.S. in Criminology and Criminal Justice.  He also received an M.A. in Criminal Justice from Yongin University.  Before pursuing graduate studies, he worked as a detective in the Korean Police Agency for six years after obtaining his Bachelor’s degree from Korean National Police University.  He is currently working on the research project entitled, “Social media analysis of neighborhood sentiment and its impact on crime patterns” with Dr. Yan Zhang.  His primary research interests include crime analysis using Big Data and machine learning, policing, and biosocial criminology.

 

Abstract:

It is indisputable that machine learning techniques and big data analysis have become the main topics in almost all discipline of science and industry during the past decade. Concurrently, numerous governments in the world are collecting enough amount of administrative data that can be analyzed by machine learning techniques to investigate the causes of social phenomena and to improve the efficiency of public administration.  Despite the data analytic techniques and the capability of data storage have been remarkably improved, a large number of scholars in the field of social science hold conservative perspective on applying machine learning and big data analysis to explaining social phenomena. The goal of this study is to fill the void by providing empirical evidence. The present study will attempt to examine the validity of using administrative big data to predict crime incidents.  Records of calls for service through 311 mayor’s hotline system in Houston, Texas and the official crime reports of Houston Police Department were examined to assess whether signs of physical decay and the presence of social nuisance predict the crime incidents at neighborhood level.  The results of this study will corroborate the Broken Windows Theory and present new windows to explore the causes of crime.  Several policy implications for government and police administrators will be developed and discussed.

Petra Perner

IBaI, Germany

Title: Big Data, Sampling, and the Estimation of the True Error Rate
Speaker
Biography:

Prof. Petra Perner (IAPR Fellow) is the director of the Institute of Computer Vision and Applied Computer Sciences IBaI. She received her Diploma degree in electrical engineering and her PhD degree in computer science for the work on “Data Reduction Methods for Industrial Robots with Direct Teach-in-Programing”. Her habilitation thesis was about “A Methodology for the Development of Knowledge-Based Image-Interpretation Systems". She has been the principal investigator of various national and international research projects. She received several research awards for her research work and has been awarded with 3 business awards for her work on bringing intelligent image interpretation methods and data mining methods into business. Her research interest is image analysis and interpretation, machine learning, data mining, big data, machine learning, image mining and case-based reasoning.

Abstract:

Big Data leads to the acceptance that based on the large amount of data, the true error rate can be estimated without trouble. However, if this true has be proofed. Large data might not be well distributed in the solution space and subareas of the solution space might be overrepresented than other subareas. Therefore, it is important to know the true situation in the data sample.
We review in the talk what can be achieved with sampling, how the true error rate is estimated and what the measures that are calculated during the estimation of the error rate tell us about the true situation.

Ho-Chan Kwak

Korea Railroad Research Institute, Korea

Title: Prediction of Hourly Floating Population based on Mobile Phone Data in Korea
Speaker
Biography:

Dr. Kwak has completed his PhD at the age of 33 years from Seoul National University (SNU) and postdoctoral studies from Institute of Construction and Environmental Engineering in SNU. He is the senior researcher of Korea Railroad Research Institute (KRRI), a government-funded transportation science and technology research organization. He has studied in the fields of transportation big data (such as smart card data and mobile phone data etc.) analysis and application in order to improve the quality of mobility through future transportation technology. He has published more than 10 papers in transportation planning and safety related journals and performed more than 30 projects related in transportation engineering.

Abstract:

The floating population is useful to figure out dynamic activities in urban area. Therefore, the prediction of floating population is required to practical use in urban and transportation planning. In Korea, the hourly floating population is estimated based on communication log of mobile phone. The communication log contains contents such as communication location, origin of mobile phone user. This paper is aimed to predict hourly floating population using mobile phone data, macroscopic data such as socio-economic index, and several data mining techniques. The data collected in Seoul, the capital of Korea, is used in this study. Also, the prediction accuracy by data mining technique is compared with each other, and the best model to predict hourly floating population is proposed in this study.

Jiyoung Song

Korea Railroad Research Institute, Republic of Korea

Title: Development of estimation model of the infectious diseases spread using big data
Speaker
Biography:

Jiyoung Song has completed her PhD at the age of 32 years from University of Science and Technology in the city Dae-Jeon in Republic of Korea, School of Transportation Engineering and B.S., M.S., from Siberian Transport University in the city Novosibirsk in Russia. She is the senior researcher of future transportation policy division in Korea Railroad Research Institute from 2016. She has involved in more than 10 research projects; Development of assessment techniques for risk-based safety management system, Study on Development of Universal Railway System in Northeast Asia, Development of the Spatiotemporal Mobility Analyzer for the Improvement of Transportation Convenience, Technical Development of Public Transportation Planning & Operation Efficiency etc. and she has published more than 30 papers in reputed journals.

Abstract:

A system to quickly estimate the spread of infectious diseases is needed due to the fear and threat of infectious disease spread all around the world. It is necessary to simulate the disease spread estimation model that is specific to each region and environment of each country. Korea needs environmentally optimized disease spread simulation technology. The combination of real-world data on population and human mobility and disease spread models is a global trend to enhance predictive power. Utilization of Big Data makes it possible to improve the reality of infectious disease spread model. Government of Korea Activating the opening and sharing of public information and we have environment in which a variety of evidence can be obtained to increase the reliability of disease spread estimation.

In this study we developed Evidence-Based Mathematical Model based on the Mathematical model of the basic infectious diseases spread to strengthen forecasting ability with predictive power verification by real data. To analysing model used Population flow data, Demographic data and Geographical (GIS) data. City bus operation data and Travel data between freeway tollgates are obtained for a population flow analysis. Resident registration demographics and flow population are obtained from the Ministry of Government Administration and Home Affairs and Telecommunication data respectively. Administrative district boundary data are used as a GIS data. Final analysis model shows spread effect of infectious disease caused by wide-area movement. The distinction of this study is that the analysis can be advanced by converging data. However to apply model for real environmental more comprehensive data on human movement and specific appropriate infectious disease model choice according to the infectious disease are needed.

Irfan Mohiuddin

King Saud University Riyadh, Saudi Arabia

Title: Quality Assessment of User Generated Content on Twitter–A Deep Learning Based Approach
Speaker
Biography:

IRFAN MOHIUDDIN received his M.Sc. in Computer Science from King Saud University, Riyadh-Saudi Arabia, where he is currently working as a Researcher while pursuing his Ph.D. degree in Computer Science. His research interests include Data Science, Social Media Data Analysis, Cloud Computing, Virtualization and Social Internet of Things.

Abstract:

Social Media today is a platform for millions of active users globally to share their content. Each second, there are thousands of messages or comments posted on different social networks. With these staggering numbers of user generated content (UGC), challenges are bound to surface. One such challenge is to assess the quality of UGC in social media because the content generated in social media could have positive or negative impact on fellow users and common people too. Low quality content not only impacts the users’ content browsing experience, but also deteriorate the aesthetic value of social media. Therefore, our aim is to assess the quality of content accurately to promote the propagation of high quality content. Successful assessment of quality of UGC in social media fosters the growth of high utility UGC, which could be used by other applications and organizations for societal or organizational benefits. In this paper, we propose a deep learning based model, that leverages the quality assessment of UGC. The experimental results demonstrate that our proposed model results in high accuracy and low loss.