• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05a
• /
• pp.281-284
• /
• 2003

본 연구는 웨이블릿 변환을 통하여 객체 영상에서 질감 특징 값을 추출하고, 신경망을 계층적으로 구성하여 분류하는 방법을 제안한다. 기존의 신경망을 이용한 영상의 분류는 단일 신경망을 이용하는 것이 대부분이었다. 하지만 단일 신경망은 분류하고자 하는 클래스의 수가 많거나 분류하고자 하는 대상이 유사한 입력패턴을 가질 경우 학습시간이 오래 걸리고, 인식률이 크게 떨어지는 문제를 가지고 있다. 그래서 본 연구에서는 효과적인 객체 영상 분류를 위해서 여러 개의 단일 신경망을 계층적으로 결합하는 방법을 제안한다. 실험결과 분류 대상 클래스가 증가함에도 불구하고 단일 신경망에 비해 학습시간이 단축되고, 높은 인식률을 보여주었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07a
• /
• pp.433-435
• /
• 2005

현재 무선 센서 네트워크에서 에너지 효율적인 라우팅을 위해 않은 알고리즘들이 발표 되고 있다. 그 중 클러스터링을 기반으로 하는 라우팅 알고리즘들은 싱크노드가 클러스터 내의 클러스터 헤드와 통신함으로써 센서노드들과 싱크노드 사이의 통신 횟수를 줄여 에너지 효율을 얻을 수 있다. 클러스터링 기반의 라우팅 알고리즘에서는 클러스터 내의 클러스터 헤드 선정이 무엇보다 중요하다. 그래서 본 논문에서는 효율적인 클러스터 헤드 선정 방안을 제안한다. 제안된 방안은 클러스터 내에서 노드의 잔존 에너지와 트래픽 로드를 가지고 클러스터 헤드를 효율적으로 결정함으로써 센서 네트워크의 생존시간을 최대화 한다.

• Industrial Engineering and Management Systems
• /
• v.12 no.2
• /
• pp.161-170
• /
• 2013

Deployment of green transportation in reverse logistics is a key issue for low carbon technologies. To cope with such logistic innovation, this paper proposes a hybrid approach to solve practical vehicle routing problem (VRP) of pickup type that is common when considering the reverse logistics. Noticing that transportation cost depends not only on distance traveled but also on weight loaded, we propose a hierarchical procedure that can design an economically efficient reverse logistics network even when the scale of the problem becomes very large. Since environmental concerns are of growing importance in the reverse logistics field, we need to reveal some prospects that can reduce $CO_2$ emissions from the economically optimized VRP in the same framework. In order to cope with manifold circumstances, the above idea has been deployed by extending the Weber model to the generalized Weber model and to the case with an intermediate destination. Numerical experiments are carried out to validate the effectiveness of the proposed approach and to explore the prospects for future green reverse logistics.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.04a
• /
• pp.263-266
• /
• 2001

상호 연결망에서 임의의 두 노드 사이에 존재하는 노드 중복 없는 경로들의 집합을 Container라고 하는데, 본 논문에서는 계층적 하이퍼큐브 연결망의 Container가 n+1임을 보이고, 그 결과를 통하여 계층적 하이퍼큐브 연결망의 고장지름이 dia(HCN(n,n))+4 이하임을 보인다. 이러한 Container는 노드간에 메시지를 전송하는 시간을 줄일 수 있으며, 연결망의 노드 몇 개가 고장이 발생해도 통신지연시간이 발생하지 않음을 의미한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.71-72
• /
• 2019

본 논문에서는 계층구조 합성곱 신경망 기반의 고해상도 동영상 프레임 고속 보간 방법을 제안한다. 기존의 고해상도 동영상 프레임 보간 방법은 시간 해상도와 공간 해상도를 분리하여 보간 하기 때문에, 예측된 보간 프레임이 블러(blur) 열화를 갖는 문제를 보인다. 제안하는 방법에서는 이러한 문제를 해결하기 위하여 계층구조 합성곱 신경망 기반의 보간 방법을 이용한다. 제안하는 계층구조 합성곱 신경망은 우선 저해상도의 광학 흐름 추정지도를 생성하고 이를 고해상도로 복원하여 프레임 보간을 수행한다. 이때, 저해상도 광학 흐름 지도를 추정할 때 사용된 특징 정보들을 활용하여 고품질의 고해상도 광학 흐름 지도를 추정한다. 실험을 통하여 제안하는 방법이 고해상도 프레임을 고속으로 보간하며, 동시에 블러 열화에 대한 성능 향상을 가짐을 보였다.

• Asian Journal for Public Opinion Research
• /
• v.10 no.3
• /
• pp.178-199
• /
• 2022

Two surveys for exploring communicative paths toward political participation were conducted with relatively large samples of Americans (N = 1001) and South Koreans (N = 1166). Hierarchical regression modeling of the relationships among demographics, personal networks, news consumption, and cross-cutting discussion and political participation demonstrated mostly commonalities between the two samples, including the interaction between political diversity and Twitter usage for news access but with distinct effect sizes of cross-cutting discussion on political participation. We attribute the differences to the two countries' distinct histories of democracy and culture, and the commonalities to the general relationships between cross-cutting discussion and political participation moderated by strong ties political homogeneity.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.1288-1290
• /
• 2007

Congestion in WSN increases energy dissipation rates of sensor nodes as well as loss of packets and thereby hinders fair and reliable event detections. We find that one of the key reasons of congestion in WSN is allowing sensing nodes to transfer as many packets as possible. This is due to the use of CSMA/CA that gives opportunistic media access control. In this paper, we propose an energy efficient congestion avoidance protocol that includes source count based hierarchical and load adaptive medium access control. Our proposed mechanism ensures load adaptive media access to the nodes and thus achieves fairness in event detection. The results of simulation show our scheme exhibits more than 90% delivery ratio with retry limit 1, even under bursty traffic condition which is good enough for reliable event perception.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.11A
• /
• pp.903-911
• /
• 2011

In this paper we proposed an energy adaptive data aggregation and transmission mechanism to solve the problem of energy limitation in wireless sensor networks (WSNs). Hierarchical structure methods are wildly used in WSNs to improve the energy efficiency. LEACH and TEEN protocols are the typical techniques. In these methods, all nodes, including nodes who have sensed data to transmit and nodes who haven't, are set frame timeslots in every round. MNs (member nodes) without sensed data keep active all the time, too. These strategies caused energy waste. Furthermore, if data collection in MNs is same to the previous transmission, it increases energy consumption. Most hierarchical structure protocols are developed based on LEACH. To solve the above problems, this paper proposed a method in which only MNs with sensed data can obtain allocated frame to transmit data. Moreover, if the MNs have same sensed data with previous, MNs turn to sleep mode. By this way redundant data transmission is avoided and aggregation in CH is lightened, too.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.41 no.5
• /
• pp.57-64
• /
• 2004

We proposed the eye gaze tracking system under natural head movements, which consists of one narrow-view field CCD camera, two mirrors which of reflective angles are controlled and active infra-red illumination. The mirrors' angles were computed by geometric and linear algebra calculations to put the pupil images on the optical axis of the camera. Our system allowed the subjects head to move 90cm horizontally and 60cm vertically, and the spatial resolutions were about 6$^{\circ}$ and 7$^{\circ}$, respectively. The frame rate for estimating gaze points was 10～15 frames/sec. As gaze mapping function, we used the hierarchical generalized regression neural networks (H-GRNN) based on the two-pass GRNN. The gaze accuracy showed 94% by H-GRNN improved 9% more than 85% of GRNN even though the head or face was a little rotated. Our system does not have a high spatial gaze resolution, but it allows natural head movements, robust and accurate gaze tracking. In addition there is no need to re-calibrate the system when subjects are changed.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.5
• /
• pp.174-180
• /
• 2015

In this paper, we propose the passive sonar signal processing technique for estimating target information using proximity sensor. This algorithm is performed by single sensor which is constituted underwater sensor network and has a hierarchical structure. The estimated parameter is the velocity, the depth, the distance and bearing at CPA situations and we can improve the accuracy of signal processing techniques through having a hierarchical structure. We verify the performance of the proposed method by computer simulation and then we check the result that 20% error can be occurred in maximum detectable range. We also confirm that proposed method has the reliability in the actual sea environment through the sea experiment.