• 한국컴퓨터정보학회논문지
• /
• 제15권2호
• /
• pp.65-74
• /
• 2010

본 연구에서는 비행슈팅게임을 플레이하는 피험자의 긴장 또는 이완상태를 자동으로 인식하는 시스템을 제안한다. 기존 연구에서는 피험자에게 자극원을 제시하여 나타난 변화 값을 비교하기 때문에 자동으로 분류하는데 한계가 있었다. 본 연구에서는 피험자의 상태 변화를 자동으로 분류하여 인식할 수 있도록 비지도학습의 SOM을 적용한다. 긴장과 이완상태의 자동인식을 위한 SOM의 적용은 두 가지 단계로 구성된다. 첫 번째 단계는 ECG측정 및 분석으로 피험자에게 게임을 플레이하게 한 후 ECG를 측정하여 HRV 분석으로 특징벡터를 추출한다. 두 번째 단계는 SOM 학습 및 인식으로 특징이 추출된 심박신호의 입력벡터들을 SOM으로 학습하여 피험자의 긴장과 이완상태를 분류하여 인식 한다. 실험 결과는 세 가지로 나누어진다. 첫 번째, HRV의 주파수변화와 두 번째 심박신호의 SOM 학습결과를 나타냈다. 세 번째 단계는 SOM학습의 성능을 알기 위해서 매칭율을 분석했다. HRV의 주파수분석의 LF/HF 비율을 1.5 기준으로 SOM의 승자뉴런 거리와 매칭한 결과 평균 72%의 매칭율을 보였다.

• Nutrition Research and Practice
• /
• 제1권2호
• /
• pp.150-157
• /
• 2007

This study analyzed Kimchi eating culture in 178 households with female middle school children located in Incheon and Seosan areas, investigated the Kimchi eating patterns of female middle school students, and also analyzed the differences in value recognition for Kimchi between mothers and their female middle school students. Results showed that 23.0% of subject households answered eat Kimchi at every meal and the main reason for eating Kimchi in most households was good for taste. Most households made their own Kimchi, and only 12.3% of households bought Kimchi. Subject households preferred hot and spicy taste (34.8%) and pleasing taste (20.2%), and 44.4% of middle school children answered as eating Kimchi at every meal, and the source for information on Kimchi was home in 51.6% and mass media in 33.7%, suggesting the lack of school education. Both mothers and their female middle school students placed high value on Kimchi for its nutritional aspect and on Kimchi from the market for its convenience. Mothers showed significantly higher value (p<0.05) on the storage aspect of Kimchi compared to their middle school students, and female middle school students showed significantly higher value (p<0.05) on the value recognition for Kimchi as an international food compared to their mothers. Also, the value for hot pepper powder was high among other additional ingredients, and both mothers and middle school students had high values for Kimchi stew among other food dishes using Kimchi, and middle school students showed higher values (p<0.001) on foreign dishes using Kimchi such as Kimchi pizza and Kimchi spaghetti compared to the mothers group. Therefore, based on these results, the development of educational programs on Kimchi is needed not only at home but also at schools, by re-emphasizing the importance of value recognition for Klmchi in our food culture.

• 한국게임학회 논문지
• /
• 제9권5호
• /
• pp.63-72
• /
• 2009

아이폰은 동작인식센서를 도입하여 새로운 모바일 조작형태를 제시하였고, 이는 게임 어플리케이션 개발에 영향을 미쳐 다양한 센서가 적용된 게임이 수 없이 나타나게 된 원인이 되었다. 이를 이용한 게임의 진행이 전체적인 재미에 어떤 방향으로 영향을 끼치는지 구체화하기 위해 본 논문은 재미를 5요소로 구분하였고, 각 요소를 한 게임을 동작인식센서와 터치센서의 조작방식으로 각각 실험하여 요소의 정도차이를 유도, 추출하였다. 본 실험에는 게임으로는 '쿠킹마마', 기기로는 아이팟 터치와 NDS를 이용하였다. 분석 내용을 보면 동작인식을 통한 조작에 대한 즐거움이 압도적으로 나타났다. 각 5개 요소, 즉 자극, 몰입, 감정이입, 성취, 변화와 확장의 요소 모두에서 동작인식센서가 높은 점수를 얻었고, 특히 자극과 감정이입부분에서 많은 차이를 보였다. 이에 자신과 디바이스와의 확장된 소통형태에서 즐거움을 얻었다는 사실을 알 수 있었다.

• 한국정보시스템학회지:정보시스템연구
• /
• 제11권1호
• /
• pp.29-49
• /
• 2002

Recently the paradigm of business management has changed. The businesses have restored to ERP or BPR to integrate their information system. But now they are trying to find out a new competitiveness in tacit knowledge of individuals. The creative company has come to put much weigh on the value of their employee′s "non-patternized" knowledge. And this trend has seen a development into a theory of knowledge management in which "non-patternized" knowledge, along with explicit knowledge, is also considered as a source of competitiveness. With the hypothesis that the recognition of the knowledge management and the utilization of the information technology will have influence on the integration of the integrating the information system information system into a new phase, this study carries out a research on the effects of knowledge management and information technology on management achievement. According to this study the distribution of knowledge has an effect on the integration of information system and management achievement. The asset of knowledge, however, has little effect on them. This means that the recognition of the asset of knowledge alone can't affect the management achievement, but when combined with the recognition of the distribution of knowledge, it can have influence on the management achievement. Thus, a company has to enhance the recognition of the distribution of knowledge. And with this, a company can have a business management based on management achievement and the integration of information system utilizing information technology and the recognition of knowledge management. A company has to promote it business achievement by integrating the information system utilizing information technology and recognizing knowledge management.

• 한국식품조리과학회지
• /
• 제33권2호
• /
• pp.237-245
• /
• 2017

Purpose: This research was conducted to provide basic data on Kimchi consumption of high school students by determining their recognition and preferences related to Kimchi. Methods: Our survey was administered to 450 high school students in the Incheon area from September 1 to October 30, 2015. A total of 412 questionnaires were used for the final analysis. Results: Most students (42.6%) consumed Kimchi every meal (more than 3 meals/day), and only 3.6% did not consume Kimchi at all. The most common reason for consuming Kimchi was 'tasty' (46.4%). On the other hand, those who did not consume Kimchi cited 'preference for other side dishes' (50.0%). 'Home-made Kimchi' was the most common source of consumed Kimchi (63.0%). With respect to recognition of Kimchi, most cited terms were 'traditional' ($4.64{\pm}0.58$), followed by 'healthy' ($4.30{\pm}0.77$) and 'prefer home-made' ($3.88{\pm}0.93$) (p<0.001). The average preference for Kimchi was $3.71{\pm}1.07$. The most common reason for preferences was 'crisp texture' (37.6%). The most popular flavor was 'spicy' (33.6%), and the most popular fermentation level was 'appropriate' (55.6%). When preferences for Kimchi were further analyzed, 'baechu Kimchi' (4.18) was the most popular. Further, Kimchi is a popular ingredient for many dishes, and the most popular dish was 'stir-fried pork with Kimchi' (4.50). Conclusion: In the future, positive recognition of Kimchi consumption can be promoted through nutrition education and various advertisements. Furthermore, efforts should be made to establish the principles of traditional Korean food for students.

• 제어로봇시스템학회논문지
• /
• 제7권8호
• /
• pp.656-663
• /
• 2001

This paper presents a sensor fusion method to recognize a cylindrical object a CCD camera, a laser slit beam and ultrasonic sensors on a pan/tilt device. For object recognition with a vision sensor, an active light source projects a stripe pattern of light on the object surface. The 2D image data are transformed into 3D data using the geometry between the camera and the laser slit beam. The ultrasonic sensor uses an ultrasonic transducer array mounted in horizontal direction on the pan/tilt device. The time of flight is estimated by finding the maximum correlation between the received ultrasonic pulse and a set of stored templates - also called a matched filter. The distance of flight is calculated by simply multiplying the time of flight by the speed of sound and the maximum amplitude of the filtered signal is used to determine the face angle to the object. To determine the position and the radius of cylindrical objects, we use a statistical sensor fusion. Experimental results show that the fused data increase the reliability for the object recognition.

• 한국정밀공학회지
• /
• 제16권2호통권95호
• /
• pp.39-49
• /
• 1999

This paper describes the development of a vision-aided position and orientation recognition system for automatically adjusting electronic tuners which control the waveform by rotating variable resisters. The position and orientation recognition system estimates the center and the angle of the tuner grooves so that the main controller may correct the difference from the ideal position and thereby manipulate the variable resisters automatically. In this paper a robust algorithm is suggested which estimates the center and the angle of the tuner grooves fast and precisly from the source image with lighting variance and video noise. In the algorithm morphological filtering, 8-chain coding, and invariant moments are sequentially used to figure out image segments concerned. The performance of the proposed system was evaluated using a set of real specimens. The results indicate the system works well enough to be used practically in real manufacturing lines. If the system adopts a high speed frame grabber which enables real time image processing, it can also be applied to positioning of robot manipulators as well as automated PCB adjusters.

• 한국정보처리학회논문지
• /
• 제7권11호
• /
• pp.3584-3591
• /
• 2000

본 논문에서는 국내의 대표적인 상용인식기들의 성능을 평가하기 위한 평가 방법과 평가 기준을 제안한다. 제안한 평가 기준으로 상용화된 오프라인 문자인식기들과 실험실 인식기를 비교해본 후 각각의 특성을 분석해 보았다. 인식에 필요한 대상 문서는 400 DPI로 스캔한 1000여개의 문서영상과 수작업으로 작성한 원문이 존재하는 KT 테스트 컬렉션을 사용하였다. 본 논문에서 인식기의 성능을 평가하기 위해 문자단위 인식률 측정 방법을 제안하였다. 비교를 위한 문서의 유형을 제안하여, 단일 특성을 가지는 문서, 복합 특성을 가지는 문서 등으로 비교·분석하였다.

• International Journal of Contents
• /
• 제15권4호
• /
• pp.8-15
• /
• 2019

This paper presents a solution of the 'Quick, Draw! Doodle Recognition Challenge' hosted by Google. Doodles are drawings comprised of concrete representational meaning or abstract lines creatively expressed by individuals. In this challenge, a doodle is presented as a sequence of sketches. From the view of at the sketch level, to learn the pattern of strokes representing a doodle, we propose a sequential model stacked with multiple convolution layers and Long Short-Term Memory (LSTM) cells following the attention mechanism [15]. From the view at the image level, we use multiple models pre-trained on ImageNet to recognize the doodle. Finally, an ensemble and a post-processing method using the minimum cost flow algorithm are introduced to combine multiple models in achieving better results. In this challenge, our solutions garnered 11th place among 1,316 teams. Our performance was 0.95037 MAP@3, only 0.4% lower than the winner. It demonstrates that our method is very competitive. The source code for this competition is published at: https://github.com/ngxbac/Kaggle-QuickDraw.

• 한국전기전자재료학회논문지
• /
• 제11권10호
• /
• pp.940-945
• /
• 1998

In this paper, we obtained the data, which is required in training the neural network and diagnosing the degradation degree, by introducing the AE detection that is effective method in ordinary degradation diagnosis on activation. Aa the results of generalization tests by appling neural network to the unknown AE patterns obtained from two kinds of specimen, firstly as to evaluate an objective performance of neural network, the recognition ration for no-void specimen and 1[mm] -void specimen are appeared to be 98.9% and 92.5%, respectively. Also, in the evaluation of the adaptability of neural network with a new type of 0.2[mm] -void specimen, it is confirmed that the result appears to be 64% of recognition ratio at 94% of confidence interval coefficient in expectation output 0.2. On the other hand, the recognition capability of the neural network was confirmed by data from no-void and 1[mm] void specimen. The results prove the promising possibility of the application of ANN to discriminate specific void affecting as main degradation source at partial discharge condition in insulator containing multi-void by accummulated data base.