• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.6
• /
• pp.15-29
• /
• 2018

This paper proposes an enhanced object tracking algorithm to compensate the lack of temporal information in existing particle swarm optimization based object trackers using the trajectory of the target object. The proposed scheme also enables the tracking and documentation of the location of an online updated set of distractions. Based on the trajectories information and the distraction set, a rule based approach with adaptive parameters is utilized for occlusion detection and determination of the target position. Compare to existing algorithms, the proposed approach provides more comprehensive use of available information and does not require manual adjustment of threshold values. Moreover, an effective weight adjustment function is proposed to alleviate the diversity loss and pre-mature convergence problem in particle swarm optimization. The proposed weight function ensures particles to search thoroughly in the frame before convergence to an optimum solution. In the existence of multiple objects with similar feature composition, this algorithm is tested to significantly reduce convergence to nearby distractions compared to the other existing swarm intelligence based object trackers.

• The Journal of the Korea Contents Association
• /
• v.6 no.10
• /
• pp.107-113
• /
• 2006

Error Concealment method for Intra frames in H.264 reconstructs the lost block by computing weighted average value of the boundary pixels of the neighboring blocks; up, bottom, left and right blocks. However a simple average of pixel values of the neighboring blocks for Intra frames in H.264 leads to excessive blurring and degrades the picture quality severely. To solve this problem, in this paper we estimate the dominant edge of lost block using the pixel values of the neighboring blocks and reconstruct the pixel values by choosing adaptive interpolation between directional interpolation and weighted average interpolation considering the result value of the interference function based on statistics. Finally directional interpolation method improves by determining the dominant edge direction considering the relation of the dominent edge and the edges of neighboring blocks. Experiments show improvement of picture quality of about $0.5{\sim}2.0dB$ compared with the method of H.264.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.563-564
• /
• 2011

본 논문에서 우리는 unequal loss protection(ULP) 알고리즘을 기반으로 패킷이 손실될 수 있는 망 환경에서 인지적으로 재구성된 영상의 왜곡을 최소화하는 방법을 제안한다. 알고리즘에는 2가지의 주요 요인이 있다. 첫째, 인간 시각 체계의 균일하지 않은 분포의 함수로 압축된 영상에 가중치를 준다. 둘째, 패킷은 오류 전파가 일어나지 않도록 하면서 각각의 group of picture(GOP)내에서 시간적인 중요성이 할당된다. 프레임의 인지적인 중요성과 GOP의 계층적인 중요성을 동시에 고려하여, 제안하는 ULP알고리즘은 인간 시각적으로 가장 중요한 지역의 크기를 식별하여 효율적인 forword error correction(FEC) 알고리즘을 수행한다.

• Journal of Advanced Navigation Technology
• /
• v.13 no.6
• /
• pp.901-906
• /
• 2009

This paper proposes a call admission control(CAC) method for wireless networks, which is based on the upper bound of a possibility distribution of handoff calls dropping rates. The possibility distribution is estimated in a fuzzy inference and a learning algorithm in neural network. The learning algorithm is considered for tuning the membership functions(then parts)of fuzzy rules for the inference. The fuzzy inference method is based on a weighted average of fuzzy sets. The proposed method can avoid estimating excessively large handoff calls dropping rates, and makes possibile self-compensation in real time for the case where the estimated values are smaller than real values. So this method makes secure CAC, thereby guaranteeing the allowed CDR. From simulation studies we show that the estimation performance for the upper bound of call dropping rate is good, and then handoff call dropping rates in CAC are able to be sustained below user's desired value.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.310-310
• /
• 2017

홍수추적 모형의 적절성을 결정하는 중요한 요소 중 하나는 모형의 매개변수이다. 특히 자연하천에 관한 부정류 계산모형의 매개변수인 조도계수는 하상재료의 특성에 따라 좌우되는 표피마찰뿐만 아니라 하상의 굴곡 등 단면형의 변화에 따른 형상손실 및 하천의 사행에 따른 손실 효과 등을 포괄적으로 내포하고 있기 때문에 모든 하천구간에 대하여 일반적으로 적용할 수 있는 조도계수의 값을 하나로 결정하기는 어렵다. 또한 조도계수는 흐름조건, 즉 유량 또는 수위의 변화에 따른 가변성을 갖고 있기 때문에, 흐름이 시간 및 공간적으로 변화하는 부정류 계산모형에 있어서는 더욱 그러하다. 그러므로 본 연구에서는 조도계수의 가변성과 다수 지점의 관측치를 고려한 모형보정의 결과로부터 얻은 파레토 최적화와 최소최대 후회도 방법(Minimax regret approach, MRA)을 결합하여 부정류 계산모형의 안정적인 매개변수를 선정할 수 있는 방법을 제안하였다. 여러 지점의 관측치를 고려한 모형의 보정은 다목적 최적화 문제로서, 여러 지점에 대한 가중치를 결합하여 얻은 하나의 목적함수에 대하여 여러 번의 개별 최적화를 수행함으로써 다수의 파레토 최적해들을 구할 수 있는 통합접근법을 적용하였다. 이때 유량에 따른 조도계수의 가변성을 나타내는 두 개의 매개변수로 구성된 관계식을 이용하여 두 구간에 대한 매개변수들을 모형의 추정 대상 매개변수로서 최적화하였다. 이 후 각기 다른 홍수사상에 대해 보정과 검증을 수행하였으며 각각에 대한 평가지표의 후회도를 정량화하였고 최종 안정적인 매개변수를 추정하기 위해 MRA를 이용하여 종합적인 순위를 도출하였다. MRA는 완전히 불확실한 의사결정 상황에서 유용한 방법으로 알려져 있는데 가장 나쁜 순위가 가장 좋은 것을 선택할 수 있게 하는 보수적인 의사결정기법이다. 계산결과 추정된 모형의 가변조도계수와 그로부터 얻은 두 개 지점에서의 평가지표인 RMSE는 두 지점에 대한 가중치의 조합에 따라 선택되는 매개변수 값에 따라 달라짐을 알 수 있었다. 본 연구에서 제시한 방법은 수문 및 수리모형의 다수의 관측지점의 자료를 이용한 매개변수 산정문제에 있어서 안정적인 해를 도출할 수 있다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.735-740
• /
• 2012

In this paper, we introduce design methodologies of polynomial radial basis function neural network classifier with the aid of Principal Component Analysis(PCA) and Linear Discriminant Analysis(LDA). By minimizing the information loss of given data, Feature data is obtained through preprocessing of PCA and LDA and then this data is used as input data of RBFNNs. The hidden layer of RBFNNs is built up by Fuzzy C-Mean(FCM) clustering algorithm instead of receptive fields and linear polynomial function is used as connection weights between hidden and output layer. In order to design optimized classifier, the structural and parametric values such as the number of eigenvectors of PCA and LDA, and fuzzification coefficient of FCM algorithm are optimized by Artificial Bee Colony(ABC) optimization algorithm. The proposed classifier is applied to some machine learning datasets and its result is compared with some other classifiers.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.04a
• /
• pp.182-183
• /
• 2022

In this study, compared and analyzed various loss function minimization techniques to present a methodology for developing a natural intelligence-based prediction system. As a result of the analysis, He Initialization was the best with RMSE: 3.78, R2: 0.94, and the error rate was 6%. However, it is considered desirable to construct a prediction system by combining each technique for optimization.

• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.980-993
• /
• 2020

Deep-learning based style transfer has recently attracted great attention, because it provides high quality transfer results by appropriately reflecting the high level structural characteristics of images. This paper deals with the problem of providing more stable and more diverse style transfer results of such deep-learning based style transfer method. Based on the investigation of the experimental results from the wide range of hyper-parameter settings, this paper defines the problem of the stability and the diversity of the style transfer, and proposes a partial loss normalization method to solve the problem. The style transfer using the proposed normalization method not only gives the stability on the control of the degree of style reflection, regardless of the input image characteristics, but also presents the diversity of style transfer results, unlike the existing method, at controlling the weight of the partial style loss, and provides the stability on the difference in resolution of the input image.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.6
• /
• pp.647-654
• /
• 2022

Although the fields in which is utilized children's speech recognition is on the rise, the lack of quality data is an obstacle to improving children's speech recognition performance. This paper proposes a new method for improving children's speech recognition performance by additionally using adult speech data. The proposed method is a transformer based domain adversarial training using dynamically weighted loss to effectively address the data imbalance gap between age that grows as the amount of adult training data increases. Specifically, the degree of class imbalance in the mini-batch during training was quantified, and the loss function was defined and used so that the smaller the data, the greater the weight. Experiments validate the utility of proposed domain adversarial training following asymmetry between adults and children training data. Experiments show that the proposed method has higher children's speech recognition performance than traditional domain adversarial training method under all conditions in which asymmetry between age occurs in the training data.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.12C
• /
• pp.1004-1009
• /
• 2010

ost digital cameras use single sensor array with color filter array to reduce size and cost. However images taken by single sensor array have only one color component per pixel, to obtain a color image missing two color components need to be reconstructed. This reconstructing process is called as demosaicking. This paper propose a new directional demosaicking method and proposed method achieves better image quality with enhanced weighting function. With comparing objective and subjective performance, we show proposed method achieves better performance than the conventional methods.