• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.911-913
• /
• 2013

The user's context awareness is important to the reliability of sensors data. The sensor data is constantly change to external temp, internal& external environment and vibration. This noise environment is affecting that the data collected information from sensors. Of course this method of digital filter and inference algorithm specifically request for the use of ripple noise and action inference. In this paper, experiment was a comparison of the KF(Kalman Filter) and WMAF(Weight Moving Average Filter) for noise decrease and distortion prevention according to user behavior. And, we compared the EWDF(Extended Weight Dual Filter) with several filer. In an experiment, in contrast to other filter, the proposed filter is robust in a noise-environment.

• Annual Conference of KIPS
• /
• 2020.05a
• /
• pp.401-404
• /
• 2020

현재 전자상거래에서 사용되는 협업 필터링은 고객이 입력한 평점 정보를 이용하여 추천 시스템을 구축한다. 하지만 기존의 평점 정보는 고객이 직접 입력해야 하므로 데이터 희소생의 문제가 있고 허위정보를 가려내지 못한다는 문제점 또한 존재한다. 본 논문에서는 기존 평점 정보 기반의 협업 필터링 추천 시스템의 문제점을 해결하기 위해, 온라인 고객 행동 정보를 활용한 협업 필터링 알고리즘을 제안하였다. 실험 결과 본 연구에서 제안한 Collaborative Filtering based on Online Behavior Information (BICF) 알고리즘이 기존의 평점 기반 협업 필터링 방식보다 우수한 성능을 보임을 보여주었다.

• Journal of Korea Multimedia Society
• /
• v.16 no.8
• /
• pp.962-971
• /
• 2013

In this paper, we propose a method to infer the user's behavior and situation through collected data from multi-sensor equipped with a smart clothing and it was implemented as a smart-phone App. This smart-clothes is able to monitor wearer users' health condition and activity levels through the gyro, temp and acceleration sensor. Sensed vital signs are transmitted to a bluetooth-enabled smart-phone in the smart-clothes. Thus, users are able to have real time information about their user condition, including activities level on the smart-application. User context reasoning and behavior determine is very difficult using multi-sensor depending on the measured value of the sensor varies from environmental noise. So, the reasoning and the digital filter algorithms to determine user behavior reducing noise and are required. In this paper, we used Multi-black Filter and SVM processing behavior for 3-axis value as a representative value of one.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.1
• /
• pp.1-8
• /
• 2016

In the recently, violent crime and accidental crime has been generated continuously. Consequently, people anxiety has been heightened. The Closed Circuit Television (CCTV) has been used to ensure the security and evidence for the crimes. However, the video captured from CCTV has being used in the post-processing to apply to the evidence. In this paper, we propose a flexible multi-level models for estimating whether dangerous behavior and the environment and context for pedestrians. The situation analysis builds the knowledge for the pedestrians tracking. Finally, the decision step decides and notifies the threat situation when the behavior observed object is determined to abnormal behavior. Thereby, tracking the behavior of objects in a multi-region, it can be seen that the risk of the object behavior. It can be predicted by the behavior prediction of crime.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.3
• /
• pp.71-78
• /
• 2013

In this paper, we propose a method to infer the user's behavior and situation through collected data from multi-sensor equipped with a smart clothing and it was implemented as a smartphone App. User context reasoning and behavior determine is very difficult using single sensor depending on the measured value of the sensor varies from environmental noise. So, the reasoning and the digital filter algorithms to determine user behavior reducing noise and are required. In this paper, we used EWMA, Kalman Filter and SVM processing behavior for 3-axis value as a representative value of one.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.349-350
• /
• 2008

지능 로봇은 표현 가능한 사물, 공간을 모델링하기 위해 주변 환경을 인지하고, 자신이 수행할 수 있는 행동을 결합하여 임무를 수행하게 된다. 이를 위해 온톨로지를 사용하여 사물, 공간, 상황 및 행동을 표현하고 특정 임무 수행을 위한 자바 기반 Rule을 통해 다양한 추론 방법을 제공하는 로봇 지식 체계를 사용하였다. 사용된 로봇 지식 체계는 생성되는 인스턴스가 자료의 클래스와 속성 값이 일관성 있고 다른 자료와 모순되지 않음을 보장해 준다. 이러한 로봇 지식 체계를 효율적으로 사용하기 위해서는 완전한 온톨로지 인스턴스의 생성이 밑받침 되어야 한다. 하지만 실제 환경에서 로봇이 Vision Sensor를 통해 사물을 인식할 때 False Positive False Negative와 같은 인식 오류를 발생시키는 문제점이 있다. 이를 보완 하기 위해 본 논문에서는 물체와 물체간의 Spatial Relation, Temporal Relation과 각 물체마다의 인식률 및 속성을 고려하여 물체 인식 오류에서도 안정적으로 인스턴스 관리를 가능하게 하는 Rule 기반의 일식오류 검출 필터를 제안한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.01a
• /
• pp.63-64
• /
• 2020

본 논문에서는 딥러닝을 이용한 작업자 위험 행동 모니터링 선행 연구에 기반해, 엣지 컴퓨팅 기반 딥러닝을 사용하여 클라우드에 대한 의존성 문제를 해결하였다. 작업자는 IoT 안전벨트와 영상 전송 안전모를 통해 정보를 수집, 처리한다. 또한 LSTM 방식에서 개량된 필터를 통한 FFNN 딥러닝 방법을 사용하여 작업자 위험 행동 패턴 분석을 하며 선행 연구의 작업자 행동 모니터링 시스템을 엣지 컴퓨팅 기반 위에서 구현하였다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.9
• /
• pp.835-840
• /
• 2008

This paper proposes an enhanced recommendation technique for personalized e-commerce portal analyzing various attitudes of customer. The attitudes are classifies into three types such as "purchasing product", "adding product to shopping cart", and "viewing the product information". We implicitly track customer attitude to estimate the rating of products for recommending products. We classified user groups which have similar preference for each item using implicit user behavior. The preference similarity is estimated using the Cross Correlation Coefficient. Our recommendation technique shows a high degree of accuracy as we use age and gender to group the customers with similar preference. In the experimental section, we show that our method can provide better performance than other traditional recommender system in terms of accuracy.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.493-496
• /
• 2018

추천 시스템은 다양한 분야에 적용되는 기술로서 활발한 연구가 진행되고 있고 기존 추천 시스템의 성능을 높이기 위해서 더욱 개인화된 차세대 추천 시스템의 필요성이 대두되고 있다. 본 논문은 하이퍼 개인화 범주에 속하는 사후 필터링기법을 사용한 실시간 상황 인식 추천 시스템을 제안한다. 실시간 상황 인식 추천 시스템은 사용자 행동과 계속적인 동기화로 현재 상황에 가장 적합한 추천 목록을 생성하기 때문에 사용자 기반 협업 필터링 (User Based Collaborative Filtering), 콘텐츠 기반 필터링(Content-based Filtering), 특이값 분해(Singular Value Decomposition)보다 훨씬 미래 지향적인 추천 시스템이다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.2
• /
• pp.334-343
• /
• 2003

This paper suggests the education method of information communication ethics by harmful word filtering on web boards as a way to solve the malfunctioning problem occurring in making informations at the step of their positive activities of information offers. The harmful word filtering system for the education of information communication ethics describes the method to construct a harmful word dictionary by extracting harmful words related with improper doing of writing, sexual insult, abusive language and expressions of criticizing others shown in web boards. Decrease by more than 90% in writing with harmful words and inappropriate writing was shown as the result of application of the harmful word filtering system on school home pages.