• Journal of KIISE
• /
• v.44 no.12
• /
• pp.1282-1289
• /
• 2017

Since the study of deep convolutional neural network became prevalent, one of the important discoveries is that a feature map from a convolutional network can be extracted before going into the fully connected layer and can be used as a saliency map for object detection. Furthermore, the model can use features from each different layer for accurate object detection: the features from different layers can have different properties. As the model goes deeper, it has many latent skip connections and feature maps to elaborate object detection. Although there are many intermediate layers that we can use for semantic segmentation through skip connection, still the characteristics of each skip connection and the best skip connection for this task are uncertain. Therefore, in this study, we exhaustively research skip connections of state-of-the-art deep convolutional networks and investigate the characteristics of the features from each intermediate layer. In addition, this study would suggest how to use a recent deep neural network model for semantic segmentation and it would therefore become a cornerstone for later studies with the state-of-the-art network models.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2020.06a
• /
• pp.47-47
• /
• 2020

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2019.09a
• /
• pp.112-112
• /
• 2019

• Convergence Security Journal
• /
• v.19 no.2
• /
• pp.73-81
• /
• 2019

In this paper, we propose a user-dependent mid-point navigation system using a time weighted mid-point navigation algorithm and a user preference based mid-point neighborhood recommendation system. The proposed system consists of a mid-point navigation module for calculating an mid-point by applying a time weight of each user based on a departure point between users, and a search module for providing a search for a route to the calculated mid-point. In addition, based on the mid-point search result, it is possible to increase the utilization rate of users by including a place recommending function based on user's preference. Experimental results show that the proposed system can increase the efficiency of using by the user-dependent mid-point navigation and place recommendation function.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05b
• /
• pp.158-161
• /
• 2004

RBF 네트워크의 중간층은 클러스터링하는 층이다. 즉, 이 충의 목적은 주어진 자료 집합을 유사한 클러스터들(homogenous cluster)로 분류하는 것이다. 여기서 유사하다는 것은 입력 데이터들에 대한 특징 벡터 공간사이에서 한 클러스터내의 벡터들 간에 거리를 측정하여 정해진 반경 내에 존재하면 같은 클러스터로 분류하고 정해진 반경 내에 존재하지 않으면 다른 클러스터로 분류한다. 그러나 정해진 반경 내에서 클러스터링하는 것은 잘못된 클러스터를 선택하는 단점을 가지게 된다. 그러므로 중간층을 결정하는 .것은 RBF 네트워크의 전반적인 효율성에 큰 영향을 준다. 따라서 본 논문에서는 효율적으로 중간층을 결정하기 위한 방법으로 퍼지 C-Means 클러스터링 알고리즘을 적용한 퍼지 RBF 네트워크를 제안한다. 제안된 퍼지 RBF 네트워크의 학습은 크게 두 단계로 구분된다. 첫 번째 단계는 입력층과 중간층 사이에 퍼지 C-Means 알고리즘이 수행되고, 두 번째 단계는 중간층과 출력층 사이에 지도학습이 수행된다. 제안된 방법의 학습 성능을 평가하기 위하여 실제 주민등록증에서 추출한 숫자패턴에 적용한 결과, 기존의 RBF네트워크 보다 학습 성능이 개선된 것을 확인하였다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.5
• /
• pp.294-304
• /
• 2016

This study aims at identifying the development strategies for capacity building of intermediary agencies from the survey and analysis of intermediary agencies in the private sector which play an important role in the economic development of Chungnam province. From the review of the literature, we defined the concept of intermediaries as an institute or program which builds and maintains the proper relationship among the various actors. In order to determine the current situation of intermediary agencies and their roles in Chungnam province, we selected nine private industrial institutes and carried out a questionnaire and interview survey. It was identified that they have very limited knowledge of the role of intermediaries, while mainly focusing on the traditional function of lobbying groups. Therefore, a policy needs be developed to allow them to participate in regional development projects, in order to improve their capability to facilitate network activities for regional economic development.

• The Journal of the Korea Contents Association
• /
• v.3 no.3
• /
• pp.98-102
• /
• 2003

For elucidating the key role of hidden neurons in information processing of Multilayer perceptrons(MLPs), we prove that the correlation coefficient between weighted sums to hidden neurons decreases under element-wise nonlinear transformations. This is verified through training of MLPs for an isolated word recognition problem. From this result, we can say that the element-wise nonlinear functions reduces redundancy in the information contents of hidden neurons.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.7B
• /
• pp.891-894
• /
• 2001

본 논문에서는 능동 배열 안테나에서 RF 대신 중간주파수를 이용하여 빔 추적을 하는 방법이 연구되었다. 안테나의 각 배열은 전압제어 발진기, 위상추적기, 혼합기와 결합되어 있으며 혼합기는 안테나 상에서 직접 RF 신호를 직접 중간주파수 신호로 변환시킨다. 전압제어 발진기 입력은 위상추적기에 의하여 조절되며 배열 안테나의 주사범위는 위상추적기와 전압제어발진기에 의하여 결정되었다.

• Journal of the Korea Convergence Society
• /
• v.11 no.6
• /
• pp.183-189
• /
• 2020

The objective of this research was to provide an objective and scientific basis for the effect of mid-advertising on viewers' rights by conducting an empirical study on how mid-program advertising affects viewer satisfaction and interest from the viewers' perspective. The experiment was conducted on 210 subjects to investigate the difference between viewers' interest in the program and purchase intention price. The results did not support the hypothesis that advertisements inserted in the middle of television programs would affect the dependent variables. The theoretical and practical implications of the mid-program advertisements on the interests of viewers were discussed.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.5
• /
• pp.435-441
• /
• 2017

Detecting an inter-harmonic accurately is not easy work, because it has small magnitude, and its frequency which can be observed is not an integer multiple of fundamental frequency. In this paper, a new method using filter bank system and adaptive predictor is proposed. Filter bank system decomposes input signal to sub bands. In adaptive predictor, inter-harmonic is detected with decomposed sub band signal as input, and error signal as output. In this scheme, input-output characteristic of adaptive predictor is notch filter, as predicted harmonic is canceled in error signal, so detecting an inter-harmonic can be possible. Magnitude and frequency of detected inter-harmonic is estimated by recursive algorithm. The performances of proposed method are evaluated to sinusoidal signal model synthesized with harmonics and inter-harmonics. And validity of the method is proved as comparing the inter-harmonic detection results to MUSIC and ESPRIT.