• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.321-323
• /
• 2012

스마트폰 사용의 보편화와 센서기술의 발달로 이를 응용하는 다양한 연구가 진행되고 있다. 특히 가속도, GPS, 조도, 방향센서 등의 센서들이 스마트폰에 부착되어 출시되고 있어서, 이를 이용한 상황인지, 행동인식 등의 관련 연구들이 활발하다. 하지만 다양한 클래스를 분류하면서 높은 인식률을 유지하는 것은 어려운 문제이다. 본 논문에서는 인식률 향상을 위해 계층적 구조의 순환 신경망을 이용하여 제스처를 인식한다. 스마트폰의 가속도 센서를 이용하여 사용자의 제스처 데이터를 수집하고 BLSTM(Bidirectional Long Short-Term Memory) 구조의 순환신경망을 계층적으로 사용하여, 20가지 사용자의 제스처와 비제스처를 분류한다. 약 24,850개의 시퀀스 데이터를 사용하여 실험한 결과, 기존 BLSTM은 평균 89.17%의 인식률을 기록한 반면 계층적 BLSTM은 평균 91.11%의 인식률을 나타내었다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.360-363
• /
• 2018

본 논문에서는 계층적 RNN의 성능 향상을 위하여 강화학습을 통한 계층적 RNN 내 파라미터를 효율적으로 찾는 방법을 제안한다. 계층적 RNN 내 임의의 파라미터에서 학습을 진행하고 얻는 분류 정확도를 보상으로 하여 간소화된 강화학습 네트워크에서 보상을 최대화하도록 강화학습 내부 파라미터를 수정한다. 기존의 강화학습을 통한 내부 구조를 찾는 네트워크는 많은 자원과 시간을 소모하므로 이를 해결하기 위해 간소화된 강화학습 구조를 적용하였고 이를 통해 적은 컴퓨터 자원에서 학습속도를 증가시킬 수 있었다. 간소화된 강화학습을 통해 계층적 RNN의 파라미터를 수정하고 이를 행동 인식 데이터 세트에 적용한 결과 기존 알고리즘 대비 높은 성능을 얻을 수 있었다.

• Journal of Industrial Convergence
• /
• v.21 no.9
• /
• pp.57-66
• /
• 2023

This study aims to examine how subjective class perception of children from single-parent families affects suicidal thoughts and to verify the mediated effects of depression and subjective health perception. To this end, the analysis data used the 2020 Korean Children and Youth Human Rights Survey conducted by the Korea Youth Policy Institute, and 618 children from single-parent families who responded to the survey were selected and analyzed as study subjects. As a result of the analysis, first, it was found that the higher the subjective class perception, the lower the suicidal impulse. Second, depression was found to be completely mediated in the relationship between subjective class perception and suicide impulse. Third, subjective health awareness was found to be completely mediated in the relationship between subjective class perception and suicidal thoughts. Based on these research results, we proposed policy and practical measures to reduce suicidal impulses according to the subjective class perception of children of single-parent families.

• Journal of KIISE:Software and Applications
• /
• v.36 no.12
• /
• pp.1028-1033
• /
• 2009

This paper presents a real-time hand gesture recognition approach for controlling a computer. We define hand gestures as continuous hand postures and their movements for easy expression of various gestures and propose a Two-layered Bayesian Network (TBN) to recognize those gestures. The proposed method can compensate an incorrectly recognized hand posture and its location via the preceding and following information. In order to vertify the usefulness of the proposed method, we implemented a Virtual Mouse interface, the gesture-based interface of a physical mouse device. In experiments, the proposed method showed a recognition rate of 94.8% and 88.1% for a simple and cluttered background, respectively. This outperforms the previous HMM-based method, which had results of 92.4% and 83.3%, respectively, under the same conditions.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.10
• /
• pp.1977-1985
• /
• 2007

The character recognition technique is one of the artificial intelligence and has been widely applied in the automated system robot HCI(Human Computer Interaction), etc. This paper introduces the character set and the representative character that can be used in the recognition of the mage ROI. The character codes in this ROI include the digit, symbol, English and Hereat etc. We proposed the efficient multi-classifier structure by combining the small-size classifiers hierarchically. Moreover, we generated each small-size classifiers by delta-bar-delta learning algorithm. We tested the performance with various kinds of images and achieved the accuracy of 99%. The proposed multi-classifier showed the efficiency and the reliability for the mixed character code set.

• The Journal of the Korea Contents Association
• /
• v.17 no.12
• /
• pp.426-436
• /
• 2017

The purpose of this study was to determine the moderating effect of subjective health state of elder who lives alone on the influence of those people's stratum consciousness on their depression. For this purpose, the study utilized the 5th version of Korea Longitudinal Study on Aging 2014 and analyzed data concerning 774 elder who lives alone. The findings of this study can be summarized as follows. First, the higher elder who lives alone were in subjective stratum consciousness, the lower they were in depression. Second, elder who lives alone were lower in depression when perceiving they were higher in health state. Third, the elder who lives alone were lower in depression when their perceived subjective health state was higher even if they were lower in stratum consciousness. All these findings clearly indicate that the stratum consciousness and depression of elder who lives alone are moderated by their perceived health state of their own. Lastly, the implications, limitations, and suggestion for further research were discussed.

• 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.

• 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 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.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.513-515
• /
• 2023

본 논문에서는 그리드 탐색과 트랜스포머를 사용한 그룹 행동 인식 모델을 제안한다. 추출된 여러 사람의 스켈레톤 정보를 차분 벡터, 변위 벡터, 관계 벡터로 변환하고 사람별로 묶어 이를 TimeDistributed 함수에 넣고 풀링을 한다. 이를 트랜스포머 모델의 입력으로 넣고 그룹 행동 인식 분류를 출력하였다. 논문에서 3가지 벡터를 입력으로 하여 합치고 트랜스포머 계층을 거친 모델과 3가지 벡터를 입력으로 하고 계층적으로 트랜스포머 모델을 거쳐 행동 인식 분류를 출력하는 두 가지 모델을 제안한다. 3가지 벡터를 합친 모델에서 클래스 분류 정확도는 CAD 데이터 세트 96.6%, Volleyball 데이터 세트 91.4%, 계층적 트랜스포머 모델은 CAD 데이터 세트 96.8%, Volleyball 데이터 세트 91.1%를 얻었다