• 대한전자공학회논문지
• /
• 제25권4호
• /
• pp.356-365
• /
• 1988

In this paper, we describe an isolated words recognition system for Korean isolated digits based on a voiced -unvoiced decision algorithm and a frequency domain analysis. The algorithm first performs a voiced-unvoiced decision procedure for the begtinning part of each uttered work using the normalized log energy and zero crossing rate as decision parameters. Based on this decision,. each word is assigned to one of two classes. In order to identify the uttered word within each class, a dynamic time warping algorithm is applied using formant frequencies as the basis for the distance measure. We exploit a pole-zero analysis to measure formant frequencies in each frame. We have observed that pole-zero analysis can provide more accurate estimation of formant frequencies than analysis based on poles only. Experimental recognition rates of 97.3% illustrating the performance of the recognition system was achieved.

• International journal of advanced smart convergence
• /
• 제6권3호
• /
• pp.22-28
• /
• 2017

With the recent development of technologies to manage vast amounts of data, data mining technology has had a major impact on all industries.. Data mining is the process of discovering useful correlations hidden in data, extracting executable information for the future, and using it for decision making. In other words, it is a core process of Knowledge Discovery in data base(KDD) that transforms input data and derives useful information. It extracts information that we did not know until now from a large data base. In the decision tree, c4.5 algorithm was used. In addition, the C4.5 algorithm was used in the decision tree to analyze the difference between frequency and mortality in the region. In this paper, the frequency and mortality of percutaneous coronary intervention for patients with heart disease were divided into regions.

• 한국화재소방학회:학술대회논문집
• /
• 한국화재소방학회 2008년도 춘계학술논문발표회 논문집
• /
• pp.135-138
• /
• 2008

Many Victims and property damage are caused in fires. In this paper, an flame detection algorithm is proposed to early alarm fires. The proposed flame detection algorithm is based on 2-stage decision strategy of video processing. The first decision is to check with color distribution of input vidoe. In the second, the candidated region is settled as fire region with activity. As a result of simulation, it is shown that the proposed algorithm is useful for fire recognition.

• Journal of Power Electronics
• /
• 제8권1호
• /
• pp.101-107
• /
• 2008

In this paper, the features extracted from vibration time signals are used to detect the bearing fault condition. The decision tree is applied to diagnose the bearing status, which has the benefits of being an expert system that is based on knowledge history and is simple to understand. This paper also suggests a genetic algorithm (GA) as a method to reduce the number of features. In order to show the potentials of this method in both aspects of accuracy and simplicity, the reduced-feature decision tree is compared with the non reduced-feature decision tree and the PCA-based decision tree.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2017년도 춘계학술발표대회
• /
• pp.787-790
• /
• 2017

Data quality is the main issue in the classification problems; generally, the presence of noisy instances in the training dataset will not lead to robust classification performance. Such instances may cause the generated decision tree to suffer from over-fitting and its accuracy may decrease. Decision trees are useful, efficient, and commonly used for solving various real world classification problems in data mining. In this paper, we introduce a preprocessing technique to improve the classification accuracy rates of the C4.5 decision tree algorithm. In the proposed preprocessing method, we applied the naive Bayes classifier to remove the noisy instances from the training dataset. We applied our proposed method to a real e-commerce sales dataset to test the performance of the proposed algorithm against the existing C4.5 decision tree classifier. As the experimental results, the proposed method improved the classification accuracy by 8.5% and 14.32% using training dataset and 10-fold crossvalidation, respectively.

• 한국컴퓨터산업학회논문지
• /
• 제2권2호
• /
• pp.195-202
• /
• 2001

본 논문에서는 한국어 음소가 좌, 우 음소에 따라 발음 방식이 달라질 때 매 음소를 모델링 하는 방법에 관한 연구를 수행한다. 이를 위해 유니트 감소 알고리즘과 결정 트리(Decision Tree)를 사용하는 방법을 사용하여 비교 연구한다. 유니트 감소 알고리즘은 통계적 특성만을 이용한 알고리즘이며 결정 트리 모델링 방식은 한국어 음운정보와 통계적 정보를 이용하여 문맥종속 음소를 분류하는 방식이다. 특히 본 논문에서는 결정 트리를 사용하여 문맥종속 음소를 분류하는 것에 대하여 상세히 기술한다. 마지막으로 결정 트리를 사용하여 분류된 문맥종속 음소의 성능을 실험하였다.

• 한국경영과학회지
• /
• 제27권2호
• /
• pp.15-31
• /
• 2002

This research suggests an interactive methodology for multiple objective linear programming problems to help the group select a compromising solution in the World Wide Web environment. Our methodology lessens the burden of group decision makers, which is one of necessary conditions of the web environment. Only the partial weak order of variables and objectives from the group decision makers are enough for searching the best compromising solution. For such a purpose, we expand the Dror and Gass algorithm to the group decision context. And we suggest the system architecture of a web-based GDSS for the Implementation of our methodology.

• 한국통신학회논문지
• /
• 제21권6호
• /
• pp.1447-1452
• /
• 1996

In this papre, a complex fuzzy adaptive decision feedback equalizer using the RLS algorithm is proposed. The proposed equalizer is based on the complex fuzzy adaptive equalizer. The 'IF'-part of the complex fuzzy adaptive decision feedback equalizer has membership functions which are characterized by the sate of decision feedback. The role of decision feedback is to reduce the computational complexity. Computer simulation shows that the proposed equalizer not only reduces the computational complexity but also improves the performance compared with the conventional complex fuzzy adaptive equalizers under the assumption of perfect knowledge of the linear and nonlinear channels. The effects of error propagation due to wrong decision feedback is also shown.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1996년도 추계학술대회 학술발표 논문집
• /
• pp.271-274
• /
• 1996

In this paper a new determination scheme of linear decision function is proposed. In this scheme, the weights in linear decision function is obtained by genetic algorithm. The result considering balance between clusters as well as classification error can be obtained by properly selecting the fitness function of genetic algorithm in determination of linear decision function and this has the merit in applying this scheme to the construction of binary decision tree. The proposed scheme is applied to the artificial two dimensional data and real multi dimensional data. Experimental results show the usefulness of the proposed scheme.

• 대한전자공학회논문지SP
• /
• 제43권6호
• /
• pp.11-19
• /
• 2006

최근에 만들어진 비디오 압축 표준인 H.264는 매크로블록당 최적의 부호화 모드를 결정하기 위해 비트율-왜곡 (rate-distortion) 기법을 사용하지만, 그 복잡성으로 인해 부호화하는 데 많은 시간이 걸린다. 따라서, H.264의 부호화 시간을 단축하기 위해 고속 모드결정 방법이 필요하다. 본 논문에서는 양자화 계수에 따라 발생 모드가 변하는 특성에 기반하여 불필요한 움직임 예측 및 모드결정 과정을 생략하는 새로운 고속 모드결정 방법을 제안한다. 양자화 계수에 따라 최적모드의 발생 빈도가 변하게 되는데, 제안한 방법에서는 매크로블록의 양자화된 이산 여현변환 계수들이 모두 0일 때, 0의 값을 가지는 CBP(coded block pattern)를 고려하여 이러한 특성을 반영하며, 조기 SKIP 모드 결정방법과 조기 $16{\times}16$ 모드 결정방법을 이용한다. 컴퓨터 모의실험을 통해, 본 논문에서 제안한 고속 인터모드 결정방법이 H.264의 참조 소프트웨어에 구현된 고속 인터모드 결정방법에 비해, Baseline 프로파일의 경우 19.6%, Main 프로파일의 경우 18.8%의 부호화 시간을 감소시키는 것을 확인했다.