• Annual Conference of KIPS
• /
• 2016.10a
• /
• pp.262-264
• /
• 2016

본 논문에서는 스마트폰 사용자의 고유한 행동패턴에 따른 인증 기법을 제안하였다. 이를 위해 특정 행동패턴의 센서 데이터만을 수집할 수 있는 센서 데이터 추출앱을 개발하고 DTW (Dynamic Time Warping)[2] 알고리즘을 활용하여, 수집된 사용자 행동 패턴 데이터의 유사성을 판단한다. 또한 사용자의 특징점 패턴이 일치하는 지를 판단하여 사용자 인증을 수행한다.

• Annual Conference of KIPS
• /
• 2012.11a
• /
• pp.1732-1735
• /
• 2012

인간은 일주일 단위로 유사한 행동 패턴을 가진다고 한다. 이런 점에서 일주일 단위의 시간-공간 기록의 형태인 인간 이동 데이터를 이용하면, 인간의 행동 패턴을 유추해 낼 수 있다. 본 논문에서 인간의 행동을 유추하기 위해 BPN알고리즘을 사용하였다. BPN알고리즘에 대해 설명하고, 인간 이동의 예측에 관한 적용에 관한 BPN알고리즘의 설계 과정을 논의한다. 그리고 해당 실험의 결과와 분석을 제시한다.

• Korean Journal of Culture and Social Issue
• /
• v.22 no.1
• /
• pp.19-39
• /
• 2016

Though research has shown that public transportation drivers experience greater burnout than other drivers, the sources of their burnout and possible mediators remain largely unknown. In response, in this study we investigate the relationships among sensation seeking, Type A driving behavior, and meaning of work to elucidate the burnout experienced by bus drivers in Gyeonggi-do, South Korea. To collect data regarding these relationships, 188 bus drivers answered a questionnaire involving the sensation seeking scale, burnout scale, and meaning of work scale. Results showed that Type A driving behavior mediated the relationship between sensation seeking and burnout, while meaning of work moderated the mediated model. These findings demonstrate that sensation-seeking bus drivers tend to experience greater burnout given their tendency to exhibit Type A driving behavior, and this relationship depends on perceived meaning of work. This study therefore contributes meaningful information and outlines significant implications in understanding drivers' burnout.

• Journal of Digital Convergence
• /
• v.10 no.2
• /
• pp.293-297
• /
• 2012

In order to provide with personalized recommendation service in context-awareness environment, the collected context data should be analyzed fast and the objective of user should be able to inferred effectively. But, the context collected from the mobile devices is not suitable for applying the existing inference algorithms as they are due to the omission or uncertainty of information and the efficient algorithms are required for mobile environment. In this paper, the behavior pattern was classified using naive bayes classification for minimize the loss caused by the omission or error of information. And pattern matching was used to effectively learn of the users inclination and infer the behavior purpose. The accuracy of the suggested inference model was evaluated by applying to the application recommendation service in the smart phones.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.11a
• /
• pp.475-478
• /
• 2000

사람의 몸 동작을 인식해야하는 여러 응용분야에서의 필요성이 대두되면서 이 분야로의 연구가 활발해지고 있다. 이 논문은 사람의 비언어적 행동을 자동적으로 분석할 수 있는 인식기 개발에 관한 것으로 실세계 3 차원 좌표값을 입력으로 하는 사람 몸 동작 패턴 분류기의 구현방법을 소개한 것이다. 하나의 사람 몸 동작은 각 몸 구성 성분(손, 아래팔, 위팔, 어깨, 머리, 몸통 등)의 움직임을 조합해서 정의한 수가 있기 때문에 개별적인 각 몸 구성성분의 움직임을 인식하여 조합해서 임의의 동작을 판별하려는 방법을 적용한다. 사람 몸 동작 패턴 분류기는 측정된 실세계 3 차원 좌표 자료를 양자화한 후 xy, zy 평면에 투영한 값을 자자 구한다. 이 결과를 각각 8 방향 체인 코드로 바꾸고 2 단계 체인 코드 평활화 사업을 하여, 4 방향 코드 체적화 및 대표 코드로의 압축단계를 거친다. 이로서 생성된 프리미티브 패턴나열들을 동작 클래스별로 분류하여 프리미티브 패턴나열의 확장으로 각각의 식별기를 구축하여 각 몸 구성 성분별 동작들을 분류한다. 일련의 실험이 행해져 그 타당성을 확인하였으며, 차후에 이 분류기는 비언어적 행동 분석을 위한 사람 몸 동작 인식기의 전처리 단계로 사용되어진 것이다.

• Annual Conference of KIPS
• /
• 2003.05c
• /
• pp.1555-1558
• /
• 2003

침입탐지란 컴퓨터와 네트워크 자원에 대한 유해한 침입 행동을 식별하고 대응하는 과정이다. 점차적으로 시스템에 대한 침입의 유형들이 복잡해지고 전문적으로 이루어지면서 빠르고 정확한 대응을 필요로 하는 시스템이 요구되고 있다. 이에 대용량의 데이터를 분석하여 의미 있는 정보를 추출하는 데이터 마이닝 기법을 적용하여 지능적이고 자동화된 탐지 및 경보데이터 분석에 이용할 수 있다. 마이닝 기법중의 하나인 순차 패턴 탐사 방법은 일정한 시퀸스 내의 빈발한 항목을 추출하여 순차적으로 패턴을 탐사하는 방법이며 이를 이용하여 시퀸스의 행동을 예측하거나 기술할 수 있는 규칙들을 생성할 수 있다. 이 논문에서는 대량의 경보 데이터를 효율적으로 분석하고 반복적인 공격 패턴에 능동적인 대응을 위한 방법으로 확장된 순차패턴 알고리즘인 PrefixSpan 알고리즘에 대해 제안하였고 이를 적용하므로써 침입탐지 시스템의 자동화 및 성능의 향상을 얻을 수 있다.

• Journal of Korea Game Society
• /
• v.10 no.4
• /
• pp.15-22
• /
• 2010

The purpose of this research is to analyze players' emotion pattern for conducting a quest in Role Playing Game(RPG). We have rebuilt up the action and content of gameplay related to category to set up five action classes of game players based on the literature review about the human behavior classification. Moreover, Mabinogi game includes the composition of various quests by story-centered expanse. We classified the quest structure of the tutorial mode, initial state, of its game into the cognitive action. We build the model of the correlation between cognitive behavior patterns of gameplay and emotions derived from targeting ten novices. The result of this research reveals that gameplayers' stimulus levels are identified to emotion pattern. It is enable to grope to concrete the design of the quest and the level in a specified state. Moreover, players' emotion variation is indicated to the type of expression of fun elements. We expect to use a device to induce the curiousness and the challenge for conducting the higher goal of game in the whole.

• The Journal of the Korea Contents Association
• /
• v.8 no.9
• /
• pp.19-26
• /
• 2008

With the development of ubiquitous computing and the construction of infrastructure for one-to-one personalized services, the importance of context-aware services based on user's situation and environment is being spotlighted. The smart home technology connects real space and virtual space, and converts situations in reality into information in a virtual space, and provides user-oriented intelligent services using this information. In this paper, we proposed the discovery of the behavior sequence pattern using the mining in the smart home. We discovered the behavior sequence pattern by using mining to add time variation to the association rule between locations that occur in location transactions. We can predict the path or behavior of user according to the recognized time sequence and provide services accordingly. To evaluate the performance of behavior consequence pattern using mining, we conducted sample t-tests so as to verify usefulness. This evaluation found that the difference of satisfaction by service was statistically meaningful, and showed high satisfaction.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.24 no.6
• /
• pp.701-708
• /
• 2018

Human error is an important cause of maritime accidents and the identification of human error is fundamental to maritime-accident preventions. In particular, the pattern of technical behavior taken in the circumstance of bridge teams(navigator & helmsman) provides important information to identify human error. The purpose of this study is to identify and analyze technical behavior pattern of bridge teams using Williamson's turn for rescue of persons overboard. The focus of this study is to build and analyze a cognitive model of the human behavior factors of the bridge teams in the process of implementing the experiments. The experimental environment was constructed using a ship-handling simulator and conducted an experiment on participants from 24 bridge teams. As a result of the experiment, it was able to identify the behavior pattern of the ship's maneuvering and maintain trajectory using the rudder and engine. This study is expected to correct human error in the bridge teams application to the certification and training of seafarers.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.571-575
• /
• 2015

This paper propose a temporal histogram -based behavior pattern analysis algorithm to analyze the movement features of moving objects from the image inputted in real-time. For the purpose of tracking and analysis of moving objects, it needs to be performed background learning which separated moving objects from the background. Moving object is extracted as a background learning after identifying the object by using the center of gravity and the coordinate correlation is performed by the object tracking. The start frame of each of the tracked object, the end frame, the coordinates information and size information are stored and managed by the linked list. Temporal histogram defines movement features pattern using x, y coordinates based on time axis, it compares each coordinates of objects for understanding its movement features and behavior pattern. Behavior pattern analysis system based on temporal histogram confirmed high tracking rate over 95% with sustaining high processing speed 45~50fps through the demo experiment.