취업 및 행사 정보

금년  IEEE International Symposium on Wearable Computers(IEEE ISWC 2010, Chair: 전자과 박규호, 유회준 교수) 학회를 한국에서 유치하게 되었습니다. 그 일환으로 IEEE ISWC Technical Program Committee회의를 한국에서 하게 되었고, 이 기회에, 오는 73() 10:00 ~ 12:30ISWC Technical Program Committee Member들을 모시고, 세미나를 전자과 우리별 세미나실에서 개최하게 되었습니다. Mobile Wearable Computing에 관심 있는 분들의 많은 참석 부탁 드립니다.

 

일시: 2010 7 3일 오전 10시 ? 오후 1

장소: KAIST 전자과 2, 우리별 세미나실

 

< Session I : 10:00 ? 11:00 >

Title: Principle of Multiple-view Video Browsing Interface

Speaker: Kenji Mase (Nagoya Univ.)

Abstract: Owning to recent development of digital broadcasting, needs for interactive video contents are increasing. In such trend, multiple camera videos become useful in viewing video by stereogram or free view point. In opposite, the multiple camera videos are too much flexibility in user's operation to watch them easily. Therefore it is necessary for multiple camera videos to provide hints for users' searching scenes.

Then we developed a multi-point video viewing tool "Peg-Scope Viewer" and the Quality of View concept. Examples of multiple video shooting and its viewing will be given with the outline of the algorithms.

 

Title: Computing close to the reality

Speaker: Michael Beigl (TU Braunschweig)

Abstract: This talk will cover three aspects of computing close to the reality:

Bootstrapping activity recognition, programming the reality and analog communication and computing concepts. Our bootstrapping activity recognition system enables the collection of data for activity recognition while an initial recognition system is in operation. The approach thus allows constantly increasing recognition rates with minimal user interaction. Directly programming the reality addresses the problem of how to program computing systems that is embedded into the reality. Analog communication and computing presents an approach to allow for a more "natural" thus more efficient presentation and processing of information in pervasive computing systems.

 

< Session II : 11:10 ? 12:40>

Title: Opportunistic activity recognition - pushing activity recognition into the real world

Speaker: Daniel Roggen (ETH Zurich)

Abstract: Activity recognition established itself as a key source of information to devise smart environments and smart assistants. Yet, current activity recognition systems are often designed to operate in well-defined environment, with well-defined sensor placement and modality. This limits the applicability of activity recognition in wearable computing, where the location of sensors on body and their orientation may be subject to variations, e.g. to enhance user's comfort. Nowadays, there is a wide range of sensor available in the environment. However they can't be used as-is for activity recognition, as the kind and availability of sensors changes over time depending on the location of the user and with infrastructure upgrades. Thus, the configuration of sensors available at any point in time is dynamic. Within the EU project OPPORTUNITY we devise methods to recognize human activities with "opportunistic sensor configurations", that is sensors that just happen to be available around the user, as well as on his body or sensorized objects he carries with him. We investigate frameworks, as well as new learning and adaptive techniques, to exploit sensors opportunistically discovered for activity recognition.

 

Title: Walking with Porcupines

Speaker: Kristof Van Laerhoven (TU Darmstadt)

Abstract: What information can your activities reveal about you? One hypothesis states that the motions patterns that people perform throughout their days (and nights) tell a lot about their moods. This is for instance researched extensively in trials which monitor bipolar patients with wrist-worn sensors that log the wearer's movements for weeks or even months. Our aim is to contribute in this field by not just recording how much the user is moving around with their arms, but by recognizing detailed activities and actions, such as walking, using stairs, lifting weights, or cycling. We hope that long-term recording of this information will reveal patterns in the behavior of people, which can then be used to inform about unusual trends.

 

Title: A briefly looking back of wearable research course in china

Speaker: Dongyi Chen (Univ. of Electronic Science and Technology of China)

Abstract:

-       The projects on wearable computing, sponsored by national research funding, such as NSFC, 863program.

-       The works of the Chinese universities and research institutes engaged in wearable computing.

-       The international cooperation of China. 

-       My future research on wearable computing .