• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.39 no.1
• /
• pp.16-23
• /
• 2002

In this paper, we propose the growing and pruning algorithm to design the optimal structure of modular wavelet neural network(MWNN) with F-projection and geometric growing criterion. Geometric growing criterion consists of estimated error criterion considering local error and angle criterion which attempts to assign wavelet function that is nearly orthogonal to all other existing wavelet functions. These criteria provide a methodology which a network designer can construct MWNN according to one's intention. The proposed growing algorithm increases in number of module or the size of modules of MWNN. Also, the pruning algorithm eliminates unnecessary node of module or module from constructed MWNN to overcome the problem due to localized characteristic of wavelet neural network which is used to modules of MWNN. We apply the proposed constructing algorithm of the optimal structure of MWNN to approximation problems of 1-D function and 2-D function, and evaluate the effectiveness of the proposed algorithm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.9
• /
• pp.782-787
• /
• 2001

In this paper, we propose an growing and pruning algorithm to design the adaptive structure of modular wavelet neural network(MWNN) with F-projection and geometric growing criterion. Geometric growing criterion consists of estimated error criterion considering local error and angel criterion which attempts to assign wavelet function that is nearly orthogonal to all other existing wavelet functions. There criteria provide a methodology that a network designer can constructs wavelet neural network according to one s intention. The proposed growing algorithm grows the module and the size of modules. Also, the pruning algorithm eliminates unnecessary node of module or module from constructed MWNN to overcome the problem due to localized characteristics of wavelet neural network which is used to modules of MWNN. We apply the proposed constructing algorithm of the adaptive structure of MWNN to approximation problems of 1-D function and 2-D function, and evaluate the effectiveness of the proposed algorithm.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.2
• /
• pp.77-86
• /
• 2004

In general, small-sized neural networks, even though they show good generalization performance, tend to fail to team the training data within a given error bound, whereas large-sized ones learn the training data easily but yield poor generalization. Therefore, a way of achieving good generalization is to find the smallest network that can learn the data, called the optimal-sized neural network. This paper proposes a new scheme for network pruning with ‘impact factor’ which is defined as a multiplication of the variance of a neuron output and the square of its outgoing weight. Simulation results of function approximation problems show that the proposed method is effective in regression.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39A no.12
• /
• pp.756-763
• /
• 2014

In this paper, we introduce a new sparse signal recovery algorithm referred to as the matching pursuit with greedy tree search (GTMP). The tree search in our proposed method is implemented to minimize the cost function to improve the recovery performance of sparse signals. In addition, a pruning strategy is employed to each node of the tree for efficient implementation. In our performance guarantee analysis, we provide the condition that ensures the exact identification of the nonzero locations. Through empirical simulations, we show that GTMP is effective for sparse signal reconstruction and outperforms conventional sparse recovery algorithms.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.06a
• /
• pp.123-126
• /
• 2013

High Efficiency Video Coding 비디오 표준은 다양한 분할방식 및 35가지 예측모드를 허용하기 때문에 최적의 분할 및 예측모드를 결정하기 위한 연산량이 많다. 이를 줄이기 위하여 본 논문에서는 CU분할의 결정에 있어 가설검정을 이용하여 early splitting 및 early pruning을 위한 임계값을 설정하고, early splitting의 경우 연산의 결과값이 임계값보다 클 경우, early pruning의 경우 연산의 결과값보다 임계값보다 작을 경우 CU의 분할을 조기에 결정하는 논문[1]의 방법을 차용하여 CU의 분할을 조기에 결정하며, 추가로 비트율 및 왜곡을 연산하는 예측모드의 개수를 줄임으로써 인코더의 성능을 향상시켰다. 또한 예측모드를 결정할 때 RDOQ를 수행하지 않음으로써 예측모드를 빠르게 결정하며, TU의 분할에 있어서도 CBF의 값 및 임계값을 이용한 early pruning 방법을 수행하여 인코더의 성능을 향상시켰다. 실험결과 5.9%의 luma BDRate의 증가가 있었으나, 63.7%의 인코딩 시간이 절감되었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.11a
• /
• pp.51-53
• /
• 2015

In this paper, we propose an efficient sparse signal recovery algorithm referred to as the matching pursuit with a tree pruning (TMP). Two key ingredients of TMP are the pre-selection to put a restriction on columns of the sensing matrix to be investigated and the tree pruning to eliminate unpromising paths from the search tree. In our analysis, we show that the sparse signal is accurately reconstructed when the sensing matrix satisfies the restricted isometry property. In our simulations, we confirm that TMP is effective in recovering sparse signals and outperforms conventional sparse recovery algorithms.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.663-667
• /
• 2004

This paper presents new pruning and learning methods for the fuzzy rule-based classifier. The structure of the proposed classifier is framed from the fuzzy sets in the premise part of the rule and the Bayesian classifier in the consequent part. For the simplicity of the model structure, the unnecessary features for each fuzzy rule are eliminated through the iterative pruning algorithm. The quality of the feature is measured by the proposed correctness method, which is defined as the ratio of the fuzzy values for a set of the feature values on the decision region to one for all feature values. For the improvement of the classification performance, the parameters of the proposed classifier are finely adjusted by using the gradient descent method so that the misclassified feature vectors are correctly re-categorized. The cost function is determined as the squared-error between the classifier output for the correct class and the sum of the maximum output for the rest and a positive scalar. Then, the learning rules are derived from forming the gradient. Finally, the fuzzy rule-based classifier is tested on two data sets and is found to demonstrate an excellent performance.

• Journal of applied mathematics & informatics
• /
• v.29 no.5_6
• /
• pp.1337-1349
• /
• 2011

So far as a solution of the given consistent linear system is concerned many numerical methods - both mathematically non-iterative as well as iterative - have been reported in the literature over the last couple of centuries. Most of these methods consider all the equations including linearly dependent ones in the system and obtain a solution whenever it exists. Since linearly dependent equations do not add any new information to a system concerning a solution we have proposed an algorithm that identifies them and prunes them in the process of solving the system. The pruning process does not involve row/column interchanges as in the case of Gauss reduction with partial/complete pivoting. We demonstrate here that the use of pruning as an inbuilt part of our solution process reduces computational and storage complexities and also computational error.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.260-262
• /
• 2004

Spatial database system provides many query types and most of them are required frequent disk I/O and much CPU time. k-NN search is to find k-th closest object from the query point and up to now, several k-NN search methods have been proposed. Among these, MINMAX distance method has an aim not to visit unnecessary node by applying pruning technique. But this method access more disk than necessary while pruning unnecessary node. In this paper, we propose new k-NN search algorithm based on density of object. With this method, we predict the radius to be expected to contain k-NN object using density of data set and search those objects within this radius and then adjust radius if failed. Experimental results show that this method outperforms the previous MINMAX distance method. This algorithm visit fewer disks than MINMAX method by the factor of maximum $22\%\;and\;average\;6\%.$

• Journal of Communications and Networks
• /
• v.18 no.5
• /
• pp.699-712
• /
• 2016

Recently, greedy algorithm has received much attention as a cost-effective means to reconstruct the sparse signals from compressed measurements. Much of previous work has focused on the investigation of a single candidate to identify the support (index set of nonzero elements) of the sparse signals. Well-known drawback of the greedy approach is that the chosen candidate is often not the optimal solution due to the myopic decision in each iteration. In this paper, we propose a tree search based sparse signal recovery algorithm referred to as the tree search matching pursuit (TSMP). Two key ingredients of the proposed TSMP algorithm to control the computational complexity are the pre-selection to put a restriction on columns of the sensing matrix to be investigated and the tree pruning to eliminate unpromising paths from the search tree. In numerical simulations of Internet of Things (IoT) environments, it is shown that TSMP outperforms conventional schemes by a large margin.