• The Journal of the Korea Contents Association
• /
• v.21 no.12
• /
• pp.896-905
• /
• 2021

In the field of SIEM(Security information and event management), many studies try to use a feedback system to solve lack of completeness of training data and false positives of new attack events that occur in the actual operation. However, the current feedback system requires too much human inputs to improve the running model and even so, those feedback from inexperienced analysts can affect the model performance negatively. Therefore, we propose "active model improving feedback technology" to solve the shortage of security analyst manpower, increasing false positive rates and degrading model performance. First, we cluster similar predicted events during the operation, calculate feedback priorities for those clusters and select and provide representative events from those highly prioritized clusters using XAI (eXplainable AI)-based event visualization. Once these events are feedbacked, we exclude less analogous events and then propagate the feedback throughout the clusters. Finally, these events are incrementally trained by an existing model. To verify the effectiveness of our proposal, we compared three distinct scenarios using PKDD2007 and CSIC2012. As a result, our proposal confirmed a 30% higher performance in all indicators compared to that of the model with no feedback and the current feedback system.

• Proceedings of The KACE
• /
• 2017.08a
• /
• pp.247-249
• /
• 2017

프로그래밍 학습 시스템에서 자동 평가 기능은, 코드에 대한 실행 결과 외 다른 피드백을 제공할 수 있기 때문에, 그 피드백을 통해 학습자 스스로가 자신의 코드를 개선할 수 있다. 본 논문에서는 다양한 프로그래밍 학습 시스템에서 사용중인 자동 평가 기능을 비교하고, 지능형 프로그래밍 튜터링 시스템인 Everycoding에서의 새로운 자동 평가 기능을 소개한다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1994.10a
• /
• pp.466-471
• /
• 1994

To make a dynamic system a given desired motion trajectory, a new feedback error learning scheme is proposed which is based on the repeatability of dynamic system motion. This method is composed of feedforward and feedback control laws. A benefit of this control scheme is that the input pattern that generates the desired motion can be formed without estimating the physical parameters of system dynamics. The numerical simulations show the good performance of the proposed scheme

• The Journal of Korean Association of Computer Education
• /
• v.4 no.2
• /
• pp.85-95
• /
• 2001

Since documents on the Web are naturally partitioned into many document databases, the efficient information retrieval process requires identifying the document databases that are most likely to provide relevant documents to the query and then querying the identified document databases. We propose a neural net based user feedback learning mechanism for such an efficient information retrieval. Presented learning mechanism learns about underlying document databases using the relevance feedbacks obtained from user's retrieval experiences. For a given query, the learning mechanism, which is sufficiently trained, discovers the document databases associated with the relevant documents and retrieves those documents effectively.

• The Journal of Korean Association of Computer Education
• /
• v.14 no.5
• /
• pp.71-79
• /
• 2011

We designed and implemented a cooperative learning system using social network service which can be utilized on a smart phone for users to read each other's posting once they upload posting and to give feedback concerning the posting in real time without the need for accessing a relevant website, through the installation of a necessary application which makes it possible for learners to interact at any time in any place on a smart phone. The developed program is used as an intermediate tool for real-time communications so as to aid in solving the task of learners, and it was made to boost academic achievement as well as interest in learning through real-time interactions and feedback. Furthermore, the program was designed in such a way that an instructor actually helps learners by closely identifying their levels based on accumulated data.

• Journal of Internet Computing and Services
• /
• v.11 no.5
• /
• pp.71-80
• /
• 2010

The purpose of this research is to help IPTV (Internet Protocol Television) commercialization using newly produced educational contents in the area of entertainment and education which currently popular in the market. It is called, Stimulus $Tester^{TM}$, endow reaction time from the feedback of learning system, using a non-direct method, for example, a remote controller. Reaction time is the learning efficiency promotion mechanism that learner ascertain the learning condition of oneself by the time with solved questions from the solving the question in given time. Reaction time also play a key role that the learner may go through course which distribute the point to PC from Server. If this system is ready, we expect that the educational industry will gradually spread out. To verify the learning efficiency of this system, we concluded that the learning improvements, by an Internet-based and a paper-based test, of the increase by 51%, from 2.47min to 1.27min, during reaction of 7 days.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.01a
• /
• pp.197-198
• /
• 2018

전문대학 학생 대상의 프로그래밍 수업에서 한 학기 동안 교수자의 개별 피드백과 동료 피드백 활동을 교수 학습 시간에 지속적으로 진행하고 학기 종료 후 성적, 자아효능감, 성격 유형별로 교수자의 개별 피드백과 동료 피드백에 대한 만족도 차이를 비교 분석해 보았다.

• Journal of the Korean School Mathematics Society
• /
• v.24 no.3
• /
• pp.309-324
• /
• 2021

From the past to the present, general mathematics classes have pursued changes in the educational environment. However, due to the actual college education conditions, general lecture classes are taking place. In this study, we wanted to find teaching and learning methods that would help students in general lecture classes. As a result, one group that took notes about class content and provided feedback on individual tasks was more effective in math achievement than the group that provided feedback on the same task. In addition, one group who took notes on class content and provided feedback on individual assignments was more effective in math achievement than the group who took notes on class content and provided feedback on the same task.

• Korean Journal of Cognitive Science
• /
• v.20 no.3
• /
• pp.357-381
• /
• 2009

Although it is known that there are personality characteristic variances in the sensitivity to environmental feedback, the trait individual difference has scarcely been explored in the context of recognition memory decision. The present study investigated this issue by examining the relationship between the feedback-based adaptive flexibility of recognition criterion positioning and personality differences in general sensitivity to non-laboratory outcomes. Experiment 1 demonstrated that veridical feedback itself had little effect on the recognition decision criterion whereas Experiment 2 demonstrated that biased feedback manipulations selectively restricted to high confidence errors, induced shifts even in the overall Old/New category criterion. Critically, individual differences in stable personality characteristic linked to reward seeking(Behavioral Activation System-BAS) and anxiety avoidance (Behavioral Inhibition System-BIS) has been shown to predict the sensitivity of subjects to this form of feedback-induced criterion learning. This data further support the idea that incremental reinforcement-based learning mechanism not often considered important during explicit recognition decisions may play a key role in criterion setting.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05b
• /
• pp.537-540
• /
• 2004

Development of Learning system and learning activity based on web in accedence with development of information communication technology are active. From teaming system with web, teaching-teaming data for student's leaning level is not systematic and interactions between students and teachers are insufficiency. Only result of teaming evaluation is showed not supply reason what is correct or not and there is no relationship or linking deeping teaming. In this paper, we tried to improve the interaction between teachers and students by analyzing study system through virtual system on high school's Introduction to computer science. And we designed and implemented the WBI system Using ASP, the system is maximize the effect of study related to further study. It will improve the feedback between the teachers and the students and help the learners enlarge the faculty of comprehension ability.