• 제목/요약/키워드: Problem features

검색결과 1,863건 처리시간 0.024초

A comparative study of filter methods based on information entropy

  • Kim, Jung-Tae;Kum, Ho-Yeun;Kim, Jae-Hwan
    • Journal of Advanced Marine Engineering and Technology
    • /
    • 제40권5호
    • /
    • pp.437-446
    • /
    • 2016
  • Feature selection has become an essential technique to reduce the dimensionality of data sets. Many features are frequently irrelevant or redundant for the classification tasks. The purpose of feature selection is to select relevant features and remove irrelevant and redundant features. Applications of the feature selection range from text processing, face recognition, bioinformatics, speaker verification, and medical diagnosis to financial domains. In this study, we focus on filter methods based on information entropy : IG (Information Gain), FCBF (Fast Correlation Based Filter), and mRMR (minimum Redundancy Maximum Relevance). FCBF has the advantage of reducing computational burden by eliminating the redundant features that satisfy the condition of approximate Markov blanket. However, FCBF considers only the relevance between the feature and the class in order to select the best features, thus failing to take into consideration the interaction between features. In this paper, we propose an improved FCBF to overcome this shortcoming. We also perform a comparative study to evaluate the performance of the proposed method.

움직임 벡터와 빛의 특징을 이용한 비디오 인덱스 (Video Indexing using Motion vector and brightness features)

  • 이재현;조진선
    • 한국컴퓨터정보학회논문지
    • /
    • 제3권4호
    • /
    • pp.27-34
    • /
    • 1998
  • 본 논문에서는 움직임 벡터와 빛의 세기를 이용하여 비디오의 인덱싱과 검색 기법에 대하여 제안한다. 본 논문에서는 움직임 벡터의 특징과 빛의 세기를 계산하여 각 샷 당하나의 대표프레임을 추출하였다. 각각의 대표프레임은 빛의 흐름을 계산하였다. 즉 움직임벡터의 특징은 빛의 흐름으로부터 얻어냈고, BMA 는 움직임 벡터를 찾기 위해 사용했다. 그리고 빛의 세기 값을 히스토그램으로 변환 한 후 컷 검출에 사용하였다. 비디오 프레임의움직임 벡터와 빛의 세기 특징을 기반으로 비디오 데이터를 구성하고 인덱싱 하였다. 비디오 데이터베이스는 비디오의 접근을 위해 내용기반을 제공하고, 인덱스 특징은 B+ 트리 검색을 사용했고, 내부적으로 구성되어 단 노드 방식으로 저장되어 컴퓨터 저장장치에 직접 접근할 수 있게 했다. 본 논문에서는 비디오 데이터 모델을 기반으로 한 비디오 인덱스의 문제를 정의하였다.

  • PDF

변곡점과 필자고유특징을 이용한 온라인 서명 인증 (Online Signature Verification using Extreme Points and Writer-dependent Features)

  • 손기형;박재현;차의영
    • 한국멀티미디어학회논문지
    • /
    • 제10권9호
    • /
    • pp.1220-1228
    • /
    • 2007
  • 본 논문에서는 기존의 서명 비교방법인 픽셀비교 (point-to-point) 방식과 부분비교(segment-to-segment) 방식의 단점을 보완한 효율적인 온라인 서명 인증 방법을 제안한다. 기존의 연구에서는 각각의 비교 방식에 알맞은 특징들이 추출되어서 서명 인증 시스템이 구현되어 왔었다. 본 논문에서는 두 비교방식의 장점을 결합하였다. 제안된 기법은 서명의 제적방향이 변화되는 지점인 변곡점을 이용해서 서명을 비교하고, 학습을 통하여 진서명간의 유사도는 높이고 진서명과 위조서명간의 상이도를 높이는 필자고유특징을 찾아낸다. 본 논문에서 제안된 방식을 사용한 경우, 필자고유특징을 사용하지 않는 경우와 비교해서 서명 인증율이 96.33%로 향상되었다.

  • PDF

Video Expression Recognition Method Based on Spatiotemporal Recurrent Neural Network and Feature Fusion

  • Zhou, Xuan
    • Journal of Information Processing Systems
    • /
    • 제17권2호
    • /
    • pp.337-351
    • /
    • 2021
  • Automatically recognizing facial expressions in video sequences is a challenging task because there is little direct correlation between facial features and subjective emotions in video. To overcome the problem, a video facial expression recognition method using spatiotemporal recurrent neural network and feature fusion is proposed. Firstly, the video is preprocessed. Then, the double-layer cascade structure is used to detect a face in a video image. In addition, two deep convolutional neural networks are used to extract the time-domain and airspace facial features in the video. The spatial convolutional neural network is used to extract the spatial information features from each frame of the static expression images in the video. The temporal convolutional neural network is used to extract the dynamic information features from the optical flow information from multiple frames of expression images in the video. A multiplication fusion is performed with the spatiotemporal features learned by the two deep convolutional neural networks. Finally, the fused features are input to the support vector machine to realize the facial expression classification task. The experimental results on cNTERFACE, RML, and AFEW6.0 datasets show that the recognition rates obtained by the proposed method are as high as 88.67%, 70.32%, and 63.84%, respectively. Comparative experiments show that the proposed method obtains higher recognition accuracy than other recently reported methods.

An Automatic Construction for Class Diagram from Problem Statement using Natural Language Processing

  • Utama, Ahmad Zulfiana;Jang, Duk-Sung
    • 한국멀티미디어학회논문지
    • /
    • 제22권3호
    • /
    • pp.386-394
    • /
    • 2019
  • This research will describe algorithm for class diagram extraction from problem statements. Class diagram notation consist of class name, attributes, and operations. Class diagram can be extracted from the problem statement automatically by using Natural Language Processing (NLP). The extraction results heavily depends on the algorithm and preprocessing stage. The algorithm obtained from various sources with additional rules that are obtained in the implementation phase. The evaluation features using five problem statement with different domains. The application will capture the problem statement and draw the class diagram automatically by using Windows Presentation Foundation(WPF). The classification accuracy of 100% was achieved. The final algorithm achieved 92 % of average precision score.

측정치 융합기법을 이용한 다중표적 방위각 추적 알고리즘 (Multiple Target DOA Tracking Algorithm Using Measurement Fusion)

  • 신창홍;류창수;이균경
    • 대한전자공학회:학술대회논문집
    • /
    • 대한전자공학회 2003년도 신호처리소사이어티 추계학술대회 논문집
    • /
    • pp.493-496
    • /
    • 2003
  • Recently, Ryu et al. proposed a multiple target DOA tracking algorithm, which has good features that it has no data association problem and simple structure. But its performance is seriously degraded in the low signal-to-noise ratio. In this paper, a measurement fusion method is presented based on ML(Maximum Likelihood), and the new DOA tracking algorithm is proposed by incorporating the presented fusion method into Ryu's algorithm. The proposed algorithm has a better tracking performance than that of Ryu's algorithm, and it sustains the good features of Ryu's algorithm.

  • PDF

A Study on Data Mining Application Problem in the TFT-LCD Industry

  • Lee, Hyun-Woo;Nam, Ho-Soo;Kang, Jung-Chul
    • Journal of the Korean Data and Information Science Society
    • /
    • 제16권4호
    • /
    • pp.823-833
    • /
    • 2005
  • This paper deals the TFT-LCD process and quality, process control problems of the process. For improvement of the process quality and yield, we apply a data mining technique to the LCD industry. And some unique quality features of the LCD process are also described. We describe some preceding researches first and relate to the TFT-LCD process and the problems of data mining in the process. Also we tried to observe the problems which need to solve first and the features from description below hazard must be considered a quality mining in LCD industry.

  • PDF

양방향 사진트리 기반 변이 추정을 이용한 중간 시점 영상 합성 (IVS using disparity estimation based on bidirectional quadtree)

  • 김재환;임정은;손광훈
    • 대한전자공학회:학술대회논문집
    • /
    • 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
    • /
    • pp.2295-2298
    • /
    • 2003
  • The correspondence problem for stereo image matching plays an important role in expanding view points as multi view video applications become more popular. The conventional disparity estimation algorithms have limitation to find exact disparities because they consider not image features but similiar intensity points. Thus we propose an efficient disparity estimation algorithm considering features of stereo image pairs. As simulation results, our proposed method confirms better intermediate views than the existing block-matching methods.

  • PDF

속성추출을 이용한 협동적 추천시스템의 성능 향상 (Performance Improvement of a Collaborative Recommendation System using Feature Selection)

  • 유상종;권영식
    • 산업공학
    • /
    • 제19권1호
    • /
    • pp.70-77
    • /
    • 2006
  • One of the problems in developing a collaborative recommendation system is the scalability. To alleviate the scalability problem efficiently, enhancing the performance of the recommendation system, we propose a new recommendation system using feature selection. In our experiments, the proposed system using about a third of all features shows the comparable performances when compared with using all features in light of precision, recall and number of computations, as the number of users and products increases.

시간전개형 네트워크 접근법을 이용한 기존 열차시각표를 고려한 추가적 철도화물 최대수송량 결정에 관한 연구 (A Study on Time-Expanded Network Approach for Finding Maximal Capacity of Extra Freight on Railway Network)

  • 안재근
    • 한국산학기술학회논문지
    • /
    • 제12권8호
    • /
    • pp.3706-3714
    • /
    • 2011
  • 본 연구는 주어진 시간 내에 현재의 열차운행계획을 바꾸지 않고 추가적으로 수송할 수 있는 화물의 최대량과 수송 일정을 찾고자 하는 알고리즘에 관한 것이다. 이를 위해 시간전개형 네트워크로 주어진 문제를 표현한 후, 전처리 절차를 통해 불필요한 호들을 제거하는 방법으로 정적네트워크에 반복적인 최대유통문제를 적용하여 기존 열차운행계획을 고려한 화물의 최대량과 수송일정을 제시하는 절차를 예시와 함께 제시하였다.