• Annual Conference of KIPS
• /
• 2015.10a
• /
• pp.1439-1441
• /
• 2015

본 연구는 비디오 이해를 위해 비디오에 등장하는 주요 객체들의 행동이나 상태를 시각 동사라고 명명하고, 도메인 확장성 있는 계층적 시각 동사의 인식을 위해 온톨로지와 규칙을 기반으로 도메인 독립적인 시각 동사를 계층적으로 인식하는 방법과 특정 도메인에 관련된 시각 동사를 도메인 독립적 시각 동사를 기반으로 확장하여 인식하는 방법을 제안하고, CCTV 감시 비디오에서 인식 시뮬레이션 결과를 보여준다.

• Journal of KIISE:Software and Applications
• /
• v.36 no.8
• /
• pp.633-641
• /
• 2009

In this paper, we proposed a new pattern classifier which can be incrementally learned, be added new class in learning time, and handle with analog data. Proposed pattern classifier has hierarchical structure and the classification rate is improved by using different metric for each levels. Proposed model is based on the Gaussian ARTMAP which is an artificial neural network model for the pattern classification. We hierarchically constructed the Gaussian ARTMAP and proposed the Principal Component Emphasis(P.C.E) method to be learned different features in each levels. And we defined new metric based on the P.C.E. P.C.E is a method that discards dimensions whose variation are small, that represents common attributes in the class. And remains dimensions whose variation are large. In the learning process, if input pattern is misclassified, P.C.E are performed and the modified pattern is learned in sub network. Experimental results indicate that Hierarchical Gaussian ARTMAP yield better classification result than the other pattern recognition algorithms on variable data set including real applicable problem.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.06a
• /
• pp.173-176
• /
• 2001

본 논문에서는 저차원 제스처 특징 공간에서 연속적인 인간의 제스처 영상을 계층적 클러스터링을 이용하여 인식할 수 있는 방법에 대해 소개한다. 일반적으로 제스처 공간에서 모델 패턴들과 매칭하기 위해서는 모든 모델 영상과 연속적인 입력영상들간의 거리평가로 인식을 수행하게 된다. 여기서 제안한 방법은 모델영상들을 연속성을 가진 클러스터로 분류하여 입력 영상과 계층적으로 비교할 수 있으며 동작에 관한 구체적 정보를 얻을 수 있다. 이 방법은 매칭 속도와 인식률을 개선하고 인식결과를 학습에 이용할 수 있는 장점이 있다.

• Journal of KIISE:Software and Applications
• /
• v.31 no.1
• /
• pp.1-7
• /
• 2004

For the handwritten digit recognition, this paper Proposes a hierarchical Gator features extraction method and a Bayesian network for them. Proposed Gator features are able to represent hierarchically different level information and Bayesian network is constructed to represent hierarchically structured dependencies among these Gator features. In order to extract such features, we define Gabor filters level by level and choose optimal Gabor filters by using Fisher's Linear Discriminant measure. Hierarchical Gator features are extracted by optimal Gabor filters and represent more localized information in the lower level. Proposed methods were successfully applied to handwritten digit recognition with well-known naive Bayesian classifier, k-nearest neighbor classifier. and backpropagation neural network and showed good performance.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.7
• /
• pp.685-692
• /
• 2016

In this paper, we not only take advantage of the SIFT features in banknote recognition, which has robustness to illumination changes, geometric rotation as well as scale changes, but also propose the hierarchical banknote recognition algorithm, which comprised of feature vector extraction from the frame grabbed image of the banknotes, and matching to the prepared data base of multinational banknotes by ANN algorithm. The images of banknote under the developed UV, IR and white illumination are used so as to extract the SIFT features peculiar to each banknotes. These SIFT features are used in recognition of the nationality as well as face value. We confirmed successful function of the proposed algorithm by applying the proposed algorithm to the banknotes of Korean and USD as well as EURO.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.4
• /
• pp.479-485
• /
• 2005

Recently, computing technology requires intelligent system structures for context-awareness in ubiquitous computing environment. An intelligent system for context-awareness is based on agents, and need sensor information to recognize users and frames to support service. Therefore, this paper proposes the structure of 3-tier context-awareness processing server/client that can connect dynamically with each sensor and service, and support various context stably The structure of a proposal system is composed of a client class that recognizes uses' context information, a server class that processes realized context information by an application processing agent, and a management server that manages these two classes. Also, in this structure users information is composed of dynamic profile to support exquisite service.

• Journal of Family Resource Management and Policy Review
• /
• v.27 no.3
• /
• pp.39-52
• /
• 2023

In this study, based on survey data from Japan, I analyzed the differences between the expectations for social security and the perception of life in old age by age group. The analysis data used in this study are from the "Survey on Life Security, 2019" conducted by the Japan Life Insurance Cultural Center, which surveyed men and women aged 18 to 69. The results of the analysis are as follows. First, expectations about health insurance are higher than expectations about other forms of social security in all age groups. Second, when it comes to expectations for public pensions, both men and women have the highest average scores in their 60s. Third, the age group with the lowest average score for public health insurance, public pension, public care insurance, and survivors' pension was found to be those in their 40s. In addition, men in their 20s had a higher average score on their perception of life in old age. Fourth, the effect of social security expectations on perception of life in old age was found to be somewhat different for gender and age groups, but overall, it was found that public health insurance expectations were an important factor that had a positive impact on the perception of life in old age.

• Journal of Digital Convergence
• /
• v.15 no.3
• /
• pp.201-209
• /
• 2017

This paper is a smartphone object recognition system using hierarchical convolutional neural network. The overall configuration is a method of communicating object information to the smartphone by matching the collected data by connecting the smartphone and the server and recognizing the object to the convergence neural network in the server. It is also compared to a hierarchical convolutional neural network and a fractional convolutional neural network. Hierarchical convolutional neural networks have 88% accuracy, fractional convolutional neural networks have 73% accuracy and 15%p performance improvement. Based on this, it shows possibility of expansion of T-Commerce market connected with smartphone and broadcasting media.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.251-256
• /
• 2021

개체명 인식은 정보 추출의 하위 작업으로, 문서에서 개체명에 해당하는 단어를 찾아 알맞은 개체명을 분류하는 자연어처리 기술이다. 질의 응답, 관계 추출 등과 같은 자연어처리 작업에 대한 관심이 높아짐에 따라 세부 분류 개체명 인식에 대한 수요가 증가했다. 그러나 기존 개체명 인식 성능에 비해 세부 분류 개체명 인식의 성능이 낮다. 이러한 성능 차이의 원인은 세부 분류 개체명 데이터가 불균형하기 때문이다. 본 논문에서는 이러한 데이터 불균형 문제를 해결하기 위해 대분류 개체명 정보를 활용하여 세부 분류 개체명 인식을 수행하는 방법과 대분류 개체명 인식의 오류 전파를 완화하기 위한 2단계 학습 방법을 제안한다. 또한 레이블 주의집중 네트워크 기반의 구조에서 레이블의 공통 요소를 공유하여 세부 분류 개체명 인식에 효과적인 레이블 임베딩 구성 방법을 제안한다.

• 한국사회정책
• /
• v.24 no.2
• /
• pp.157-179
• /
• 2017

In Korea, 'spoon class discourse' has attracted public attention in the press and among young people, which reflects that mass awareness that the class status structure is clearly rooted in the society becomes widespread. Although income distribution has been improved since late 2000s, it is interesting that Korean people's subjective perception concerning class mobility and social justice has been worsemed. By using the survey data on people's perception of opportunity inequality, this study finds that Korean people have by and large negative subjective awareness regarding socio-economic opportunity inequality, magnitude of opportunity inequality, and achievement by efforts, and that the degree of the negative perception is greater in accordance with the people's subjective identification. The regression analysis reveals that the social status of respondents and their parents(-), experience of discrimination(+), age(-), and high education of college and above (+) have consistent effect over socio-economic opportunity inequality, magnitude of opportunity inequality, and achievement by efforts with statistical significance. More concretely, as people have lower subjective status identification at the time of parent generation and their own generation, as they have the experience of discriminatory misconduct, and as they are young and highly educated, they have negative or pessimistic perception regarding opportuinity inequality. In addition, it is revealed that the unemployed and non-regular workers have significantly negative perception on socio-economic opportunity inequality, magnitude of opportunity inequality, while negative perception on the magnitude of opportunity inequality and achievement by efforts is noticeable among high and middle income households.