• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.335-339
• /
• 2005

본 논문에서는 퍼지 RBF 네트워크의 학습 성능을 개선하기 위하여 Delta-bar-Delta 알고리즘을 적용하여 학습률을 동적으로 조정하는 개선된 퍼지 RBF 네트워크를 제안한다. 제안된 학습 알고리즘은 일반화된 델타 학습 방법에 퍼지 C-Means 알고리즘을 결합한 방법으로, 중간층의 노드를 자가 생성하고 중간층과 출력충의 학습에는 일반화된 델타 학습 방법에 Delta-bar-Delta 알고리즘을 적용하여 학습률을 동적으로 조정하여 학습 성능을 개선한다. 제안된 RBF 네트워크의 학습 성능을 평가하기 위하여 컨테이너 영상에서 추출한 40개의 식별자를 학습 데이터로 적용한 결과, 기존의 ART2 기반 RBF 네트워크와 기존의 퍼지 RBF 네트워크 보다 학습 시간이 적게 소요되고, 학습의 수렴성이 개선된 것을 확인하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10a
• /
• pp.226-228
• /
• 2004

베이지안 네트워크는 불확실한 상황을 모델링하기 위한 확률 기반의 모델이다. 베이지안 네트워크의 구조를 자동 학습하기 위한 연구가 많이 있었고, 최근에는 진화 알고리즘을 이용한 연구가 많이 진행되고 있다. 그러나 대부분은 마지막 세대의 가장 좋은 개체만을 이용하고 있다. 시스템이 요구하는 다양한 요구조건을 하나의 적합도 평가 수식으로 나타내기 어렵기 때문에, 마지막 세대의 가장 좋은 개체는 종종 편향되거나 변화하는 환경에 덜 적응적일 수 있다. 본 논문에서는 적합도 공유 방법으로 다양한 베이지안 네트워크를 생성하고, 이를 베이즈 규칙을 통해 결합하여 변화하는 환경에 적응적인 추론 모델을 구축할 수 있는 방법을 제안한다. 성능 평가를 위해 ALARM 네트워크에서 인공적으로 생성한 데이터를 이용한 구조 학습 및 추론 실험을 수행하였다. 다양한 조건에서 학습된 네트워크를 실험한 결과, 제안한 방법이 변화하는 환경에서 더욱 강건하고 적응적인 모델을 생성할 수 있음을 확인한 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.615-617
• /
• 2022

본 논문에서는 얼굴사진 기반 감정인식 심층망, 음성사운드를 기반한 감정인식 심층망을 결합한 앙상블 네트워크 구축을 위한 사전연구로서 얼굴사진 기반 감정을 인식하는 기존 딥뉴럴 네트워크 모델들을 입력 데이터 처리 방법에 따라 분류하고, 각 방법의 특성을 분석한다. 또한, 얼굴사진 외관 특성을 기반한 감정인식 네트워크를 여러 구조로 구성하고, 구성된 방법의 성능을 비교하여, 우수 성능을 보이는 네트워크를 선정하여 추후 앙상블 네트워크의 구성 네트워크로 사용하고자 한다.

• Journal of Korean Society of Transportation
• /
• v.26 no.2
• /
• pp.89-100
• /
• 2008

In an urban network controlled by traffic signals, there is an interaction between the signal timing and the routes chosen by individual road users. This study develops a bi level programming model for traffic signal optimization in networks with path based traffic assignment. In the bi level programming model, genetic algorithm approach has been proposed to solve upper level problem for a signalized road network. Path based traffic assignment using column generation technique which is proposed by M.H. Xu, is applied at the lower-level. Genetic Algorithm provieds a feasible set of signal timings within specified lower and upper bounds signal timing variables and feeds into lower level problem. The performance of this model is investigated in numerical experiment in a sample network. In result, optimal signal settings and user equilibrium flows are made.

• The Journal of the Korea Contents Association
• /
• v.20 no.2
• /
• pp.96-104
• /
• 2020

As consumers' consumption activities become more active due to the activation of online shopping malls, companies are conducting item trend analyses to boost sales. The existing item trend analysis methods are analyzed by considering only the activities of users in online shopping mall services, making it difficult to identify trends for new items without purchasing history. In this paper, we propose a trend analysis method that combines data in online shopping mall services and social network data to analyze item trends in users and potential customers in shopping malls. The proposed method uses the user's activity logs for in-service data and utilizes hot topics through word set extraction from social network data set to reflect potential users' interests. Finally, the item trend change is detected over time by utilizing the item index and the number of mentions in the social network. We show the superiority of the proposed method through performance evaluations using social network data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.12
• /
• pp.2826-2834
• /
• 2013

In mobile ad hoc networks (MANET), power-saving technology of mobile nodes is divided into transmit power control (TPC), power-saving mode (PSM), and routing. TPC and PSM are operated in physical layer but the routing is managed in network layer, so the design of a joint algorithm is needed to provide better performance. Therefore, in this paper, we propose a joint power-saving and routing algorithm for maximizing the network lifetime while satisfying the end-to-end data rate in ad hoc networks. The proposed algorithm first applies the TPC or PSM to reduce the power consumption of mobile nodes and then performs the routing by considering the decided node lifetime in order to maximize the path lifetime. Simulation results show that the proposed algorithm maximize the lifetime while satisfying the required rate according to the number of mobile nodes and the level of interference.

• Korean Journal of Environment and Ecology
• /
• v.34 no.3
• /
• pp.259-270
• /
• 2020

Plants Social Network (PSN) was first used in recent studies to incorporate the plant sociology methods for the understanding of plant society with the social network analysis methods that have recently attracted attention in the social science and visualize and analyze a PSN. The process of construction and analysis on PSN proceeds in the order of setting up the survey area, investigating the appearance plants species on plots of 100㎡, analyzing the interspecific association, building the sociogram, and analyzing the network structure and centrality. This study established a PSN by investigating the appearance species after installing 708 plots to include various dominant vegetational physiognomies in Busan Metropolitan City, where coastal and inland vegetation could be observed simultaneously. The survey found a total of 195 species, including 42 species of evergreen, 151 species of deciduous trees, and 2 species of semi-evergreen trees. The interspecies binding analysis was performed with the focus on the total number of species. It showed the number of friendly species in the order of Eurya japonica (47 species), Trachelospermum asiaticum (46 species), Linder glauca (44 species), Sorbus alnifolia (44 species), and Ligustrum japonicum (41 species). Based on it, we generated a sociogram using Gephi 0.9.2 program. The sociogram was divided into groups that appeared mostly on the coast and those that did not, reflecting the geographical distribution characteristics of forest vegetation in Busan. The analysis of the network structured showed 1,709 links and an average of 17.5 species having interspecies binding with a species. The density was 0.09, the diameter was 5, and the average path distance was 2.268. We concluded that various PSNs should be established in the future for precise comparative analysis of network characteristics in the social science field. In the PSN of Busan Metropolitan City, Eurya japonica, Linder glauca, Ligustrum japonicum, and Trachelospermum asiaticum showed high centrality.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06a
• /
• pp.277-281
• /
• 2007

광 기반 네트워크 기술의 발전에 따라 Gbps 급의 대역폭을 요구하는 비입축 HD (high definition) 영상을 낮은 지연으로 전송하고 재생하는 것이 가능해지고 있다. 이를 위하여 다양한 비압축 HD 미디어 전송 시스템이 소개되어 왔으며, 이들은 일반적으로 RTP(Real-time Transport Protocol)에 기반으로 한 실시간 데이터 전송과 비압축 미디어 인터페이스를 효과적으로 결합하여 대화형으로 사용함에도 지장이 없는 저지연의 실감형 시스템을 지원하고 있다. 본 논문에서는 [4,5]에서 제안된 비압축 HD 미디어 시스템의 실감성을 향상시키기 위하여 9600 $\times$ 4800 해상도의 타일드 디스플레이를 통해 전송된 비압축 HD 영상을 재생할 수 있는 기법을 제시한다. 또한 실제 구현된 비압축 HD 영상과 타일드 디스플레이 간의 연동 실험을 통하여 제안된 결합 방식의 타당성을 확인하고, 그 결과로 얻어진 실감성 있는 미디어 서비스의 효용성을 입증한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.8A
• /
• pp.769-774
• /
• 2006

Based on the performance of a cooperative diversity with selection combining in Rayleigh fading, the power control range of a relay node is investigated. Also the effect of the power-limited relay node to the system performance is investigated. If the average signal-to-noise ratio(SNR) of each signal path is equal, the single relay cooperative diversity is obtained 13.5dB gain at the outage probability of $1{\times}10^{-3}$ in Rayleigh fading. We noticed that the limited power of a relay node severely degrades the system performance. Therefore the node with limited power in ad-hoc network is not recommended as a relay node in cooperative diversity system.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.21 no.7
• /
• pp.815-822
• /
• 2010

Two-way relaying scheme based on relay selection can not only achieve higher rate but also get the selection diversity gain according to the number of relays. However the scheme can not achieve combining gain because it does not consider the direct link between users. In this paper, we propose, with multiple relays, opportunistic cooperative two-way relaying scheme and incremental cooperative two-way relaying scheme which can achieve both selection diversity gain and combining gain. Simulation results show that proposed scheme outperform the conventional scheme by achieving both combining gain and selection diversity gain according to the number of relays.