• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.42 no.3
• /
• pp.31-38
• /
• 2005

This paper proposes an implementation method of intelligent characters that can properly adapt to action patterns of opponent characters in fighting games by using genetic algorithm. For this intelligent characters, past actions patterns of opponent characters should be included in the learning process. To verify the effectiveness of the proposed method, two types of experiments are performed and their results are compared. In first experiment(exp-1), intelligent characters consider current action and its step of an opponent character. In second experiment (exp-2), on the other hands, they take past actions of an opponent characters into account additionally. As a performance index, the ratio of score obtained by an intelligent character to that of an opponent character is adopted. Experimental results shows that even if the performance index of exp-1 is better than that of exp-2 at the beginning of stages, but the performance index of exp-2 outperforms that of exp-1 as stages go on. Moreover, optimum solutions are always found in all experimental cases in exp-2. Futhermore, intelligent characters in exp-2 could learn moving actions (forward and backward) and waiting actions for getting more scores through self evolution.

• Journal of Software Assessment and Valuation
• /
• v.17 no.1
• /
• pp.83-92
• /
• 2021

There are continuous and tremendous attempts to apply various sensor systems and ICTs into the dairy science for data accumulation and improvement of dairy productivity. However, these only concerns the fields which directly affect to the dairy productivity such as the number of individuals and the milk production amount, while researches on the physiology aspects of dairy cows are not enough which are fundamentally involved in the dairy productivity. This paper proposes the basic approach for extraction of daily behavior pattern from hourly behavioral data of dairy cows to identify the health status and stress. Total four clusters were grouped by k-means clustering and the reasonability was proved by visualization of the data in each groups and the representatives of each groups. We hope that provided results should lead to the further researches on catching abnormalities and disease signs of dairy cows.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.892-895
• /
• 2017

본 논문에서는 비분할 비디오로부터 이 비디오에 담긴 사람의 행동을 효과적으로 탐지해내기 위한 심층 신경망 모델을 제안한다. 일반적으로 비디오에서 사람의 행동을 탐지해내는 작업은 크게 비디오에서 행동 탐지에 효과적인 특징들을 추출해내는 과정과 이 특징들을 토대로 비디오에 담긴 행동을 탐지해내는 과정을 포함한다. 본 논문에서는 특징 추출 과정과 행동 탐지 과정에 이용할 심층 신경망 모델을 제시한다. 특히 비디오로부터 각 행동별 시간적, 공간적 패턴을 잘 표현할 수 있는 특징들을 추출해내기 위해서는 C3D 및 I-ResNet 합성곱 신경망 모델을 이용하고, 시계열 특징 벡터들로부터 행동을 자동 판별해내기 위해서는 양방향 BI-LSTM 순환 신경망 모델을 이용한다. 대용량의 공개 벤치 마크 데이터 집합인 ActivityNet 비디오 데이터를 이용한 실험을 통해, 본 논문에서 제안하는 심층 신경망 모델의 성능과 효과를 확인할 수 있었다.

• Proceedings of KOSOMES biannual meeting
• /
• 2018.06a
• /
• pp.68-68
• /
• 2018

• Proceedings of the Korea Society of Costume Conference
• /
• 2004.05a
• /
• pp.61-61
• /
• 2004

현대 사회에 들어와서는 소비자의 성향이나 소비패턴의 다양화로 인하여 소비자 행동을 예측할 수 있는 보다 중요한 변수가 무엇인가에 대한 연구가 필요하여 알아보고자 한다. 특히 자녀를 둔 주부들의 경우 자녀의 의복 소비성향에서 다양한 성향들을 나타내는데, 이는 사회구조나 가족구조의 변화에 따라 소득의 향상, 주부의 사회진출이나 낮은 출산율 등의 영향으로 유아복에 대한 소비자들의 관심이 커지고 있기 때문이다. (중략)

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2011.11a
• /
• pp.39-40
• /
• 2011

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2003.10a
• /
• pp.367-373
• /
• 2003

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.16 no.1
• /
• pp.39-51
• /
• 2011

Acute toxicity test and behavioral change analysis of seawater acclimated Japanese medaka were conducted to identify the brine effects on fish by seawater desalination. 7 day acute toxicity test of brine revealed linear concentration-response relationship from 40.0~80.0 psu treatment groups. There was no significant brine effect for 30-40 psu groups and mass mortality was observed from >50 psu exposure (7-day $LC_{50}$=51.4 psu). Images from the real time camera system were analyzed to observe the changes in behavioral patterns of medaka exposed to various salinity. 40.0 and 50.0 psu exposed groups were stabilized in behavioral patterns after 3.1 and 4.6 hours, respectively and 60.0 psu group showed sharp increase in activity during first 12 hours and 50% mortality thereafter. Similar patterns were observed to 70 and 80 psu groups and both experimental groups showed 100% mortality within 12 hours. Acute toxicity test and behavioral patterns showed very similar toxicity results which revealed the increases in mortality and behavioral activities from 50.0 psu. This critical salinity for fish impacts must be implemented to brine discharge strategy by seawater desalination into the coastal area. Also, we recommend that real time camera monitoring system must be a useful tool for early warning of fish toxicity for other applications. This research was funded by Ministry of Land, Transport and Maritime Affairs, Korea.

• Journal of Internet Computing and Services
• /
• v.20 no.6
• /
• pp.95-103
• /
• 2019

The number of one person households has grown steadily over the recent past and the population of lonely and unnoticed death are also observed. The phenomenon of one person households has been occurred. In the dark side of society, the remarkable number of lonely and unnoticed death are reported among different age-groups. We propose an unusual event detection method which may give a remarkable solution to reduce the number of the death rete for people dying alone and remaining undiscovered for a long period of time. The unusual event detection method we suggested to identify abnormal user behavior in their lives using vision pattern, audio pattern, and dust pattern algorithms. Individually proposed pattern algorithms have disadvantages of not being able to detect when they leave the coverage area. We utilized a fusion method to improve the accuracy performance of each pattern algorithm and evaluated the technique with multiple user behavior patterns in indoor areas.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.39 no.6
• /
• pp.603-610
• /
• 2015

This paper presents a multimodal sensor system that can determine the location of house space by analyzing the postures and heights of the residents. It consists of two sensors: a tilt sensor and an altimeter sensor. The tilt sensor measures the static and dynamic postures of the residents, and the altimeter sensor measures their heights. The sensor system includes a Bluetooth transmitter, and the server receives the measured data and determines the location in the house. We describe the process determining the locations of the residents after analyzing their postures and behaviors from the measured data. We also demonstrate the usefulness of the proposed system by applying it to a real environment.