About KSE >






Open Presentation of KSE Ph.D Student


Please attend an open presentation of KSE Ph.D student.



  ■ Date & Time : 10:00~, 1 June 2016(Wed)


  ■ Place : # 1222 Seminar Room, E2-1


  ■ Speaker : JUNGEUN KIM


  ■ Title : Differential Flattening: A Novel Framework for Community Detection in Multi-Layer Graphs


  ■ Abstract : multi-layer graph consists of multiple layers of weighted graphs, where the multiple layers represent the different aspects of relationships. Considering multiple aspects (i.e., layers) together is essential to achieve a comprehensive and consolidated view. In this paper, we propose a novel framework of differential flattening, which facilitates the analysis of multi-layer graphs, and apply this framework to community detection. Differential flattening merges multiple graphs into a single graph such that the graph structure with the maximum clustering coefficient is obtained from the single graph. It has two distinct features compared with existing approaches. First, dealing with multiple layers is done independently of a specific community detection algorithm whereas previous approaches rely on a specific algorithm. Thus, any algorithm for a single graph becomes applicable to multi-layer graphs. Second, the contribution of each layer to the single graph is determined automatically for the maximum clustering coefficient. Since differential flattening is formulated by an optimization problem, the optimal solution is easily obtained by well-known algorithms such as interior point methods. Extensive experiments were conducted using the LFR benchmark networks as well as the DBLP, 20 Newsgroups, and MIT Reality Mining networks. The results show that our approach of differential flattening leads to discovery of higher-quality communities than baseline approaches and the state-of-the-art algorithms.



  ■ Date & Time : 11:00~,  1 June 2016(Wed)


  ■ Place : # 1222 Seminar Room, E2-1


  ■ Speaker : SANGKEUN PARK


  ■ Title : Motives and Concerns of Dashcam Video Sharing


  ■ Abstract : Dashcams support continuous recording of external views that provide evidence in case of unexpected traffic-related accidents and incidents. Recently, sharing of dashcam videos has gained significant traction for accident investigation and entertainment purposes. Furthermore, there is a growing awareness that dashcam video sharing will greatly extend urban surveillance. Our work aims to identify the major motives and concerns behind the sharing of dashcam videos for urban surveillance. We conducted two survey studies (n=108, n=373) in Korea. Our results show that reciprocal altruism/social justice and monetary reward were the key motives and that participants were strongly motivated by reciprocal altruism and social justice. Our studies have also identified major privacy concerns and found that groups with greater privacy concerns had lower reciprocal altruism and justice motive, but had higher monetary motive. Our main findings have significant implications on the design of dashcam video-sharing services.



  ■ Date & Time : 17:00~,  3 June 2016(Fri)


  ■ Place : # 1222 Seminar Room, E2-1


  ■ Speaker : Daehee, Park


  ■ Title : Measuring Driver Distraction and Alert System


  ■ Abstract : Although, some researchers began to research regarding distractors and the vehicle crashes including distractions much earlier, an interest regarding driver distraction has significantly increased in these days. Driver distraction is one of the main issue for safety driving. National Highway Traffic Safety Administration (NHTSA) regards driver distraction is one of higher priority topic and they started to conduct relevant researches since 1991 (Ranney et al, 2001). In addition, the number of mobile phone-using drivers has increased dramatically, it is more than doubled between 2000 and 2005. NHTSA expected that the number of drivers using mobile phones or other smart technologies while driving will increase further. Albert et al (2015) suggested that using smartphone while driving such as surfing the web, getting notifications from social networks, phone conversations and texting influence on distraction and the performance of primary task of driving. In addition, a built-in infotainment system is getting complex, manual controlling of infotainment system increases driver distraction while driving.

  In the presentation, I will justify background of the research initially, then I will describe several definitions of driver distraction in different perspective. In addition, general types of driver distractions and many kinds of driver distraction will be discussed. Measuring driver distraction regarded as one of main issue, so that I will depict various measurements and will review relevant previous work. Finally, I will explain both how to measure it through deep learning and initial design for an alert system.




File Download:
  • 페이스북 공유
  • 트위터 공유
  • Google+ 공유
  • 인쇄하기