IMCOM 2018
  Conference History
  Journal Recommendation
  Conference Program
  Organizing Committee
  Program Committee
  Keynote Speakers
  Invited Speakers
  Conference Venue
  Travel Information
  Tourist Attractions
  Arts & Museums
  Call for Papers
  Submission Guidelines
  Registration Guidelines
  Presentation Guidelines
  Montage Video
Invited Speakers


Prof. Tru Hoang Cao
  Faculty of Computer Science & Engineering
  Ho Chi Minh City University of Technology
Chair of Information Science
  John von Neumann Institute
Vietnam National University, Ho Chi Minh City, Vietnam

Prof. Thanh Huu Nguyen
  School of Electronics and Telecommunications
Hanoi University of Science and Technology, Vietnam

Entity Recognition for Intelligent Information Management

Entity recognition is used here to name a broad task that recognizes textual mentions representing entities in a document. An entity is a named entity, i.e. one that is referred to by a proper name, or an abstract concept. Recognition levels may vary from as simple as classifying an entity into a predefined category, to as far as linking it to an appropriate entry in a knowledge base. In this sense, entity recognition covers or is related to a variety of problems under different names such as named entity recognition, coreference resolution, record linkage, entity disambiguation, and entity linking.
Firstly, this talk introduces entity recognition as a key component in natural language processing, knowledge discovery, and information management applications. It then presents state-of-the-art approaches and methods for entity recognition, in particular entity linking. Finally, it draws some open challenges in achieving a high accuracy entity recognition system. Recent proposed solutions and obtained results of our research in this area are also discussed in the talk.


Resource Efficient Virtual Network Embedding Based on Software-Defined Networking

Network Virtualization (NV) allows multiple heterogeneous architectures to simultaneously coexist on a shared infrastructure. Embedding multiple virtual networks (VNs) on a shared substrate deals with efficient mapping of virtual resources on the physical infrastructure and is referred to as the Virtual Network Embedding problem (VNE problem). Recently Software-Defined Networking (SDN) is considered as a potential technology that overcomes current limits in network virtualization as it provides a flexible, customizable way to abstract virtualized networks from physical infrastructure. However, since SDN is still in its infancy, there are still technical issues that need to be further investigated. In the first part of the talk, taxonomy and issues of network virtualization in SDN are addressed. In the second part, REsource reSERvation in generalized Virtual NETworks (ReServNet), a Software-Defined Networking platform designed for embedding multi-level virtual networks on physical infrastructure is developed. By defining new softwarized logical functions, ReServNet allows network administrators to create and manage multiple virtual networks on top of the physical network and allocate bandwidth resources to them accordingly. Moreover, the ReServNet framework allows for designing, prototyping, benchmarking and evaluating the performance of di_erent network embedding algorithms easily in real SDN virtualization environments.

Prof. Riri Fitri Sari
  Electrical Engineering Department
  Faculty of Engineering
CIO / Head
  Information System Development
  and Services
University of Indonesia, Indonesia

Prof. Sungyong Lee
  Department of Computer Engineering
  East-West Neo Medicinal u-Lifecare IT
  Research Center
Kyung Hee University, Korea

IoT for Intelligent Transport System Vs Crowdsourcing with Waze

This talk will discuss the development of the Internet of Things (IoT) with the use of sensors and devices and their implementation for the Intelligent Transportation System (ITS). We will discuss the development of the Intelligent Transport System and the supporting communication technologies development. We will be exposed to the phenomenal mobile application that has been quickly adopted by 150 million travelers for them to take part in the crowdsourcing of traffic information, called Waze. Waze was started in 2005 as an application that takes an open data approach to traffic and navigation. The theme of people as sensors and mining social media for meaningful information will be elaborated for the topic of intelligent transport system.

Can Big Data Open New Era of Personalized Healthcare?

With the evolution of bioinformatics in conjunction with technology, healthcare has grown from individual to global scale. Consequently, healthcare and IT professionals are utilizing technology to its best for providing better medical services and facilities. With this evolution, the surge of accumulating personal data from human activities and vital signs for better healthcare and wellbeing services has grown exponentially. Personal gadgets and electronics like smart phones and watches are well equipped with sensors acquiring various types of vital signs and activity information. Clinical data is complemented with this accumulated personal data for medical, well-being, and care-giving reasons. Personal data generated by human beings due to interactions with the environment is of various types and magnitude. To support this variety and volume of personal data, information technology is providing numerous platforms. However, these platforms are limited either by scope, magnitude or efficiency. A cumulative resolution that can handle this large volume of heterogeneous personal data with efficiency continues to be missing. To support large volumes, we have big data technologies, however these technologies need to be exploited further to handle heterogeneity with efficiency. Thus, a new era of personalized healthcare support information technology platform can be achieved.
To embrace this evolution, we have proposed a comprehensive healthcare platform called "Mining Minds" that is based on a layered architecture and provides high quality personalized services. Mining minds platform takes benefit from the technology of big data with respect to the variety as well as volume, mapping of life events through sensory environment with reasoning and prediction to process the real-time data for providing personalized services. The platform will benefit the users in the form of personalized life quality improving services, Silver business services, proactive way to control the chronic disease services, and life care services.

Prof. Sajal K. Das
The Daniel St. Clair Endowed Chair Professor
Chair of Computer Science Department
Missouri University of Science
  and Technology, Rolla, USA

Prof. Dong In Kim
College of Information and Communication
Sungkyunkwan University, Korea

Participatory Urban Sensing: Challenges and Opportunities

Mobile phones have evolved from basic communication device to powerful sensing platform with a rich set of built in sensors, such as microphone, GPS, accelerometer, and so on. They also provide convenient wireless interfaces (e.g., Bluetooth, WiFi) to connect to the external sensors. This led to what is called participatory urban sensing and monitoring applications that including healthcare, environmental noise, pollution, traffic conditions, and infrastructure protection. However, there exits significant challenges in terms of energy efficiency of mobile devices, sensing coverage, localization, quality of collected data, privacy and security, and middleware services. This talk will highlight the challenges and issues in participatory urban sensing and also describe the research opportunities in this emerging field. New solutions will be presented along with directions for future research.

Large-Scale Small Cells via Hierarchical Cooperation: The Evolution Path beyond 4G Cellular

Heterogeneous cellular networks (HCNs), consisting of macrocells overlaid with small cells (e.g., femtocells, picocells, microcells) provide a fast, flexible, cost-efficient, and fine-tuned design and expansion for existing cellular wireless networks to satisfy the ever increasing demand for network capacity. In HCNs, small cells serve as offloading spots in the radio access network to offload users and their associated traffic from congested macrocells. However, due to their large-scale deployment in random locations, limited transmit power, and the lack of complete coordination, the coexistence and efficient operation of small cells is very challenging. In this talk, we discuss the coexistence challenges posed to small cells and show that, with "hierarchical cooperation" (e.g., clustering and spectrum sensing), small cells can overcome the posed challenges and efficiently coexist in a multitier cellular wireless network. Then, we provide a general view of the evolution path beyond 4G cellular, considering the migration to higher frequency band (e.g., beyond 10 GHz) to accommodate very large number of antennas (i.e., massive MIMO), which will be a potential technology for small cells.

Prof. Jin Hyung Kim
Computer Science Department, KAIST, Korea
Board of Directors, Appcenter Movement
National Database Forum, Korea

Prof. Yoshifumi Masunaga
  School of Social Informatics
Deputy Director
  International Exchange Center
Aoyama Gakuin University, Kanagawa, Japan
Professor emeritus
Ochanomizu University, Tokyo, Japan

Scene Text Recognition : An informal comparison of KAIST Approaches with Google Goggles App on difficult images

Three approaches for scene text recognition will be presented in this talk: color-based, edge-based, and part-based approaches. Although features of color, edge and part-relationship are utilized in all of the three approaches, there are differences on the main focus in each of these approaches. The color-based approach focuses on image segmentation mainly based on color, while the edge-based approach focuses on edge following to extract text objects. The part-based approach is an attempt to directly pin point existence of character parts in image. Each of the three approaches has merits and demerits. The text extraction results of these approaches will be compare with Google Goggles on some representative images known 'difficult' in the community. So, one may feel how these approaches behave in difficult images.

Social Computing and the Development of WikiBOK

"Social computing" is a keyword in contemporary society. However, if we ask anew what the term social computing means, we realize that its definition has not necessarily been clarified. This presentation first investigates when questions are raised about "social computing." Then we investigate what social computing means, and a formal model of social computing is described in contrast with the traditional computing scheme. Whether the Wikipedia article on social computing that states "social computing is a general term for an area of computer science..." is correct or not is also discussed.
Collective intelligence is the heart of the concept of social computing. This presentation then reports on the WikiBOK project. This project aims to develop a body of knowledge (BOK) of "social informatics" as a collective intelligence. In contrast to a BOK for a mature discipline such as computer science, the formulation of a BOK for a new discipline, such as social informatics, life science, and sustainability science, is difficult because academics in such a new discipline cannot present it in its entirety par avance. Therefore, a bottom-up and open collaborative approach based on collective intelligence seems promising, and contrasts strongly with the traditional style in which a BOK is formulated by the authorities in the field in a top-down manner. We report on the design and implementation of WikiBOK which is a wiki-based system for open collaboration on the Web. The current status of the construction of a Social Informatics BOK (SIBOK) using WikiBOK is also presented.

Prof. Cristina M. Pinotti
Professor of Computer Science
Department of Computer Science and Math.
University of Perugia, Italy
Associate Researcher at ISTI
National Council of Research (CNR), Italy

Prof. Masaru Kitsuregawa
Executive Director
  Earth Observation Data Integration
  and Fusion Research Initiative (EDITORIA)
  Center for Information Fusion
  Institute of Industrial Science
The University of Tokyo, Japan

Duty-Cycle Wireless Sensor Networks for Critical Infrastructures

We focus on Duty-Cycle Wireless Sensor Networks (DC-WSNs) as a sustainable, emerging technology suitable for remote and unattended monitoring of Critical Infrastructures (CI). CI are physical and information networks, services and assets which, if disrupted or destroyed, would have a serious impact on the health, safety, security or economic well-being of citizens. If deployed on a Critical Infrastructure, the DC-WSN provides a sustainable monitoring facility that conveys different kinds of sensed data to a centralized operating center or, in case of major damages, the DC-WSN can continue its tasks in unattended mode.
In this talk, we consider DC-WSNs populated by a large number of tiny sensors and by few more powerful devices, called actors. The anonymous and energy-constrained sensors are distributed at random in a wide area and operate according to different sleep-awake schedules. The actors are authorized to organize the sensors into their vicinity into short-lived actor-centric sensor networks. For such DC-WSNs, we propose centralized and semi-distributed protocols for (i) sensor localization and (ii) data dissemination. The sleep-awake schedules and the density of the WSN are the network parameters in our model. The percentage of sensors localized, of sensors to which data are distributed, the time delay to achieve it, and the power consumption of the whole network are the performance metrics used in the analysis of our protocols.

Yet another monetization scheme for Info-plosion

Information explosion (Info-plosion) is one of the most notable phenomenon in 21st century. Search engine companies invented how to monetize the search keywords. This talk will introduce a yet another efforts to monetize the human activities done in Info-plosion and Info-Grand Voyage projects in Japan. In digital helper experiments, we extracted movement pattern from 3000 participants with GPS mobile phones, which significantly improved the convergence. In experiments on healthcare for metabolic syndrome, we did the mining against activity information from accelerometer sensors and found the recommendations based on it were quite useful for life style related disease. In both experiments, info-plosion and its analytics were a key enabler.

  Home | Conference | Venue | Call for Papers  
  Phone: +82-31-299-4642