[작성자:] eeesch

▣ Title : Heterogeneous Processors and Hybrid Systems for Big Data and Analytics

▣ Speaker

: Dr.

Peter Hofstee (IBM)

▣ Date

& Time : Tuesday, May 21 (3:30 ~ 4:45pm)

▣ Place

: LG Research Building, Room #105

▣ Host

: Prof. Sungjoo Yoo (Tel. 2379)

▣ Abstract : Technology constraints increasingly allow heterogeneous processors, that combine multiple types of compute cores sharing memory, and hybrid systems, where different types of processors are combined at a system level, to gain a market advantage in spite of the challenges associated with programming such systems. This talk will briefly review the experience gained with the Cell Broadband Engine processor, including some of its applications in high-performance computing and embedded systems. Next the role of heterogeneity in commercial systems is discussed, and a hardware and software approach is discussed that allows for the integration of reconfigurable accelerators in high-performance and commercial systems. We discuss how these technologies can help us store and analyze the vast amounts of digital data of various types that are collected and the new levels of insight, foresight, and optimization that can be achieved.

 

▣ Title : Future

of Smart Industry

▣ Speaker

: Dr.JooYeon Lee(Executive Vice President of POSCO ICT CO., LTD.)

▣ Date

& Time : Friday, May 10 (2:00 ~ 3:30pm)

▣ Place

: LG Research Building, Room #101

▣ Host

: Prof. JinsooLee (Tel. 2230)

▣ Abstract :

1. Paradigm Change on Smart Industry

In

the past, the digital convergence mainly focused on industry-specific

integration using digital technology and IT solutions. On the other hand, Smart

Convergence emphasize the new values and business driven by users, integrating

high Intelligence using devices such as smart phone and smart pads. The main

driving forces spreading Smart Convergence are:

1.

SNS, 2. Smart Device (mobility), 3. Big Data, and 4. Spread of Cloud Computing.

2. Future Growth Model on Smart Industry

In

this section, future growth models on Smart Industry are:

1.Smart

Building,  2.Smart Grid,  3. Smart Transportation, 

4.

Smart School, 5. Smart Ad,  And more..

3. People whom Smart Industry is Looking

for

–

Keyword: Smart Life, Life Management

▣ Title : Design Automation of Electric Distribution Systems

▣ Speaker

: Dr.Gijoon Nam (IBM)

▣ Date

& Time : Tuesday, May 21 (2:00 ~ 3:15pm)

▣ Place

: LG Research Building, Room #102

▣ Host

: Prof. Sungjoo Yoo (Tel. 2379)

▣ Abstract :

Our

comfortable modern lifestyle is largely enabled by an abundant supply of

energy, and in the context of our homes and workplaces, that energy is

delivered in the form of electricity. Electricity is transported via

“Transmission” systems that span long distances, and

“Distribution” systems that are typically at the city level. In

looking at the energy distribution market and focusing on the design of such

systems, it is apparent that current engineering practice does not include significant

automation. From a VLSI point of view, these systems are designs based only on

simulation, -like designing an SoCwith Spice! This talk will examine this area, and show concrete examples of the

application of VLSI design automation techniques to the design and optimization

of electricity distribution systems. This work was done in partnership with an

energy consulting firm, and was demonstrated to several energy companies that

have all expressed intense interest in it. This is an area in which VLSI

researchers, with some small learning, can make significant contributions!

▣ Title : SMART & GREEN IT TECHNOLOGY

▣ Speaker

: Changhyun Kim (Samsung  Electro-Mechanics,  Executive Vice President)

▣ Date

& Time : Friday, May 3 (4:00 ~ 5:30pm)

▣ Place

: LG Research Building, Room #101

▣ Host

: Prof. HongjunePark  (Tel. 2234)

▣ Abstract :

인류의 문화가 과거부터 발전해 오면서 현재 기기의 혁신을

가져오고 있는 MOBILE

SET 시장의

동향을 소개하고,삼성이

전자부품 개발을 통해서 진행하고 있는몇가지GREEN ENERGY INNIVATION 활동

소개와 그 효과등을

전달하고자 함.

▣ Title :Field

robotics toward the real world

▣ Speaker

: Dr.Youngho Choi (KIRO)

▣ Date

& Time : Friday, May 3 (2:00 ~ 3:30pm)

▣ Place

: LG Research Building, Room #101

▣ Host

: Prof. Seyoung Oh  (Tel. 2214)

▣ Abstract :

Field

robot which is valuable in the real world requires more prerequisites than that

of the academic robot such as consideration of the trend and demands in the

market. This talk presents various field robotic researches which are going on

and conducted in the Korea Institute of Robot and Convergence in the first

section. I will then introduce the developing history of the world first

commercialized domestic window cleaning robot “WINDORO” from prototype to

production. In the last part of the talk, we will consider the difficulties of

developing commercially valuable robot and then I will give some advice to

overcome these difficulties.

▣ Title : Pedestrian

Navigation Techniques for Smartphone Users

▣ Speaker

: Prof. ChangookPark

▣ Date

& Time : Friday, April  26 (2:00

~ 3:30pm)

▣ Place

: LG Research Building, Room #101

▣ Host

: Prof. Sangchul  Won  (Tel. 2221)

▣ Abstract :

The

demand for navigating a user with a hand-held device, especially in GPS

degraded and denied environments such as indoors and in urban canyons, has

tremendously increased over the last few years. Smartphones are attractive platforms for navigation

systems due to their small size, low cost and diversity of sensors feasible for

positioning. Most of such smartphones are equipped with GPS chip, MEMS sensors (including accelerometers,

gyroscopes, magneto-meters and barometers) along with other gadgets such as

camera and Wi-Fi. In the current state of the art in MEMS technology, the

accuracy of the inertial sensors is not good enough for getting position

information by integration of the sensor outputs over longer durations of time.

Thus MEMS based pedestrian navigation exploits the kinematics of human walk

using the inertial sensor data in a different way than the classical double

integration of acceleration in traditional Inertial Navigation Systems (INS).

The observation from all of these navigation sources should be also fused

together using Kalman filters. In this talk, various emerging

navigation technologies for pedestrian will be introduced.

▣ Title : The Development of Highly

Radiation-Hardened Remote Controlled Robot in Nuclear Power

Plants

▣ Speaker

: Dr. SeunghoKim(KAERI)

▣ Date

& Time : Friday, April  12 (2:00

~ 3:30pm)

▣ Place

: LG Research Building, Room #101

▣ Host

: Prof. Seyoung Oh (Tel. 2214)

▣ Abstract :

The Research goal at Nuclear Robotics

Lab. is to develop a Highly Radiation-Hardened Robot for

nuclear industry applications under the circumstances of limiting direct human

access due to high-level of radiation. Tasks involved are video surveillance

and inspection of primary equipment, repair of damaged parts, and maintenance

of subsidiary units. Ongoing research is oriented to

the development of teleoperated robotic system and its core technology, focusing on the laboratory-based work as

well as taking out it to nuclear industry field.

▣ Title : Open Innovation: A new paradigm for

R&D

▣ Speaker

: Director. ChanikPark(Samsung Electronics)

▣ Date

& Time : Friday, April  5 (2:00

~ 3:30pm)

▣ Place

: LG Research Building, Room #101

▣ Host

: Prof. Sungjoo Yoo  (Tel. 2379)

▣ Abstract :

In this talk, I am going to present an

open innovation paradigm which has obtained popularity in industrial R&D.

First,  I will introduce

several real-life examples.  After

explaining traditional R&D process, representative open innovation cases in

IT companies will be presented.  For example,  Xerox, IBM,  P&G and

Samsung show diverse aspects of their closed and open innovation

framework.

Finally, I’d like to conclude my talk by

giving three main messages for students who are pursuing innovative

achievements in their career.

!StartFragment>

▣Title : 엔지니어의 business world에서의 career도전

▣Speaker : Ph.D.Junghoon Lee(베인&컴퍼니코리아)

▣Date&Time : Friday, March 29 (2:00~3:30)

▣Place : LG Research Building Room #101

▣Host : 컴퓨터공학과, 전자과, ITCE, CITE

▣Abstract : 약간 건조하게 표현하자면, 엔지니어들은 대체로 개개인의 career 개발에 있어서 타 전공자 대비 관심의 폭과 깊이가 적다. 그 결과 대체로 엔지니어의 career path는 단조로운 편이다. 그 근본원인 중 하나로, 강의자는 엔지니어들의 다양한 엔지니어링 외적인 career에 대해 지식이 부족함을 꼽고자 한다. 금번 강의에서는 다양한 career option을 미래의 공학도들에게 제시하고자 하며, 그 중에서도 business world를 대상으로 여러 career option을 제시하고 interactive하게 토론한다.

▣ Title : Exploiting parallelism in processing

large scale multi-dimensional datasets

▣ Speaker

: Beomseok Nam (UNIST Assistant Professor)

▣ Date

& Time : Friday, March 22 (2:00 ~ 3:30pm)

▣ Place

: LG Research Building, Room #101

▣ Host

: Prof. Sungjoo Yoo  (Tel. 2379)

▣ Abstract :

This

talk will present two different ways of exploiting parallelism in processing

large-scale multi-dimensional datasets.  The general purpose computing on

graphics processing unit (GP-GPU) has emerged as a new cost effective parallel

computing paradigm in high performance computing research that enables large

amount of scientific data to be processed in parallel. A common access pattern

into such scientific data analysis applications is multi-dimensional range

query, but inherently multi-dimensional indexing trees such as R-Trees are not

well suited for GPU environment because of their irregular tree traversal

patterns. Traversing irregular tree search path makes it hard to maximize the

utilization of massively parallel processing units in GPU. In this talk, I

would introduce two novel R-tree traversal algorithms for traversing

multi-dimensional indexes, which convert recursive access to sequential access

into hierarchical tree nodes.

 The

second half of this talk would discuss how to leverage cached data in

distributed cache infrastructure using task parallelism.  As more servers are added to distributed and

parallel systems, larger memory space becomes available for caching data

objects. However the cached objects are dispersed and traditional query

scheduling policies that take into account only load balancing do not

effectively utilize the increased cache space. This talk would introduce and

compare batch job scheduling policies that employ statistical prediction

methods and probability distribution estimations derived from recent queries in

order to improve both load balancing and cache hit ratio in shared-nothing

environment.