• 음성과학
• /
• 제10권1호
• /
• pp.71-84
• /
• 2003

In the acoustic modeling for large vocabulary speech recognition, a sparse data problem caused by a huge number of context-dependent (CD) models usually leads the estimated models to being unreliable. In this paper, we develop a new clustering method based on the C45 decision-tree learning algorithm that effectively encapsulates the CD modeling. The proposed scheme essentially constructs a supervised decision rule and applies over the pre-clustered triphones using the C45 algorithm, which is known to effectively search through the attributes of the training instances and extract the attribute that best separates the given examples. In particular, the data driven method is used as a clustering algorithm while its result is used as the learning target of the C45 algorithm. This scheme has been shown to be effective particularly over the database of low unknown-context ratio in terms of recognition performance. For speaker-independent, task-independent continuous speech recognition task, the proposed method reduced the percent accuracy WER by 3.93% compared to the existing rule-based methods.

• Journal of Communications and Networks
• /
• 제5권1호
• /
• pp.7-18
• /
• 2003

In this paper, a decision feedback recurrent neural network equalizer and a modified real time recurrent learning algorithm are proposed, and an adaptive adjusting of the learning step is also brought forward. Then, a complex case is considered. A decision feedback complex recurrent neural network equalizer and a modified complex real time recurrent learning algorithm are proposed. Moreover, weights of decision feedback recurrent neural network equalizer under burst-interference conditions are analyzed, and two anti-burst-interference algorithms to prevent equalizer from out of working are presented, which are applied to both real and complex cases. The performance of the recurrent neural network equalizer is analyzed based on numerical results.

• International Journal of Computer Science & Network Security
• /
• 제24권6호
• /
• pp.83-88
• /
• 2024

In this paper we used classification algorithms on social networking. We are proposing, a new classification algorithm called the improved Decision Tree (IDT). Our model provides better classification accuracy than the existing systems for classifying the social network data. Here we examined the performance of some familiar classification algorithms regarding their accuracy with our proposed algorithm. We used Support Vector Machines, Naïve Bayes, k-Nearest Neighbors, decision tree in our research and performed analyses on social media dataset. Matlab is used for performing experiments. The result shows that the proposed algorithm achieves the best results with an accuracy of 84.66%.

• International Journal of Control, Automation, and Systems
• /
• 제1권3호
• /
• pp.358-367
• /
• 2003

We consider discrete-time factorial Markov Decision Processes (MDPs) in multiple decision-makers environment for infinite horizon average reward criterion with a general joint reward structure but a factorial joint state transition structure. We introduce the "localization" concept that a global MDP is localized for each agent such that each agent needs to consider a local MDP defined only with its own state and action spaces. Based on that, we present a gradient-ascent like iterative distributed algorithm that converges to a local optimal solution of the global MDP. The solution is an autonomous joint policy in that each agent's decision is based on only its local state.cal state.

• 대한산업공학회지
• /
• 제26권2호
• /
• pp.171-182
• /
• 2000

For the last five years, data mining has drawn much attention by researchers and practitioners because of its many applicable domains. This article presents an adaptive decision tree algorithm for dynamically reasoning machine failure cause out of real-time, large-scale machine status database. Among many data mining methods, intelligent decision tree building algorithm is especially of interest in the sense that it enables the automatic generation of decision rules from the tree, facilitating the construction of expert system. On the basis of experiment using semiconductor etching machine, it has been verified that our model outperforms previously proposed decision tree models.

• 한국통신학회논문지
• /
• 제36권12C호
• /
• pp.753-758
• /
• 2011

The constant modulus algorithm (CMA) widely used in blind equalization applications minimizes the averaged power of constant modulus error (CME) defined as the difference between an instant output power and a constant modulus. In this paper, a decision feedback version of the linear blind algorithm based on maximization of the zero-error probability for CME is proposed. The Gaussian kernel of the maximum zero-error criterion is analyzed to have the property to cut out excessive CMEs that may be induced from severely distorted channel characteristics. Decision feedback approach to the maximum zero-error criterion for CME is developed based on the characteristic that the Gaussian kernel suppresses the outliers and this prevents error propagation to some extent. Compared to the linear algorithm based on maximum zero-error probability for CME in the simulation of blind equalization environments, the proposed decision feedback version has superior performance enhancement particularly in cases of severe channel distortions.

• 한국경영과학회지
• /
• 제8권1호
• /
• pp.31-40
• /
• 1983

An uncertain dynamic evolving process has been a continuing challenge to decision problems. The dynamic random variable (drv) changes which characterize such a process are very important for the decision-maker in selecting a course of action in a world that is perceived as uncertain, complex, and dynamic. Using this subjective point prediction algorithm based on a modified recursive filter, the decision-maker becomes to have periodically changing plausible points with the passage of time.

• 한국정보통신학회논문지
• /
• 제8권7호
• /
• pp.1405-1409
• /
• 2004

본 논문은 H.264/AVC의 전체 부호화 과정의 큰 부분을 차지하는 블록 모드 결정의 연산량을 효율적으로 줄이면서도 영상의 화질을 감소시키지 않는 블록 모드 결정 알고리즘을 연구한다. 움직임 추정의 연산량 감소를 위해 매크로블록을 8$\times$8 보다 큰 블록 모드와 8$\times$8 보다 작은 블록 모드로 영역을 예측하여 모든 블록 모드 결정의 연산량을 줄인다. 여기서 8$\times$8 보다 작은 블록은 중요한 움직임 정보나 급격한 외각선의 경계를 포함 가능성이 높으므로 정확한 움직임 추정이 필요하다. 이를 위하여 8$\times$8 블록내 모든 블록 크기에 대해서 $RDC_{M\timesN}$를 구하고 가장 작은 $RDC_{M\timesN}$를 갖는 블록을 선택한다. 이때 $RDC_{M\timesN}$의 결정을 위하여 SATD와 이웃하는 탐색 블록의 화소값 평균의 차이를 이용한 움직임 강도를 사용하는 방식을 제안한다. 제안된 알고리즘은 매크로블록 내에서 블록 모드의 결정을 고속으로 수행하면서도 정확한 움직임 추정 및 보상을 가능하게 한다.

• 한국전자파학회논문지
• /
• 제22권7호
• /
• pp.705-710
• /
• 2011

본 논문에서는 Chase 알고리즘 기반의 연판정 e-BCH 복호시 계산량을 감소하는 알고리즘을 제시하였다. Chase 알고리즘 기반의 연판정 e-BCH 복호 방식은 test pattern을 만들기 위해 수신 데이터 중 신뢰성이 낮은 데이터를 순서대로 찾기 위해 ordering을 한다. 데이터를 ordering하는 과정과 test pattern 수 만큼을 수신 데이터와 비교함으로써 최적의 복호 열을 찾는 과정에서 높은 복잡도가 요구되며, 본 논문에서는 이러한 복잡도를 줄이는 방안을 제시하여 계산량 및 성능 관점에서 비교 분석하였다.

• 한국멀티미디어학회논문지
• /
• 제7권1호
• /
• pp.73-79
• /
• 2004

본 논문에서는 선형 블록 부호에 대한 효율적인 연판정 복호 알고리듬을 제안하였다. 종래 의 연판정 복호기는 그 연판정 값을 추정하기 위하여 경판정 복호를 여러 번 수행해야 한다. 그러나 종래의 방법으로는 후보 부호어들이 구해지지 않을 수도 있으며, 그렇게 되면 연판정 값을 얻기가 매우 어려워진다. 본 논문에서는 후보 부호어들을 탐색하는 효율적인 알고리듬을 도입하여 이 문제를 해결하였다. 이 방법을 사용하면 후보 부호어가 찾아지지 않을 가능성을 대폭 감소시킬 수 있다. 시뮬레이션을 통하여 제안된 알고리듬의 성능을 확인할 수 있었다. 페이딩 채널에서 2진 (63, 36) BCH 부호에 대하여 시뮬레이션을 수행하였다.