• 한국컴퓨터정보학회논문지
• /
• 제5권3호
• /
• pp.51-57
• /
• 2000

본 논문에서는 피치와 퍼지를 포함한 화자 인식 알고리즘을 제안한다. 음의 시간적인 특징을 이용하여 시간 영역에서 분해력을 높이고 주파수 영역에서 잡음에 강인함을 갖는 국부 봉우리와 골에 의한 피치 검출법을 제안하여 피치를 검출한다. 또한 화자 인식에서 음성 신호의 애매성을 보완할 수 있는 퍼지의 소속함수를 이용하여 표준 패턴을 작성하고 퍼지 패턴 매칭을 이용하여 인식을 수행한다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권2호
• /
• pp.131-139
• /
• 2016

Recognition of human motions has become a main area of computer vision due to its potential human-computer interface (HCI) and surveillance. Among those existing recognition techniques for human motions, head detection and tracking is basis for all human motion recognitions. Various approaches have been tried to detect and trace the position of human head in two-dimensional (2D) images precisely. However, it is still a challenging problem because the human appearance is too changeable by pose, and images are affected by illumination change. To enhance the performance of head detection and tracking, the real-time three-dimensional (3D) data acquisition sensors such as time-of-flight and Kinect depth sensor are recently used. In this paper, we propose an effective feature extraction method, called adaptive local binary pattern (ALBP), for depth image based applications. Contrasting to well-known conventional local binary pattern (LBP), the proposed ALBP cannot only extract shape information without texture in depth images, but also is invariant distance change in range images. We apply the proposed ALBP for head detection and tracking in depth images to show its effectiveness and its usefulness.

• 재무관리연구
• /
• 제15권2호
• /
• pp.369-399
• /
• 1998

주가가 과연 예측가능한가의 여부는 이론적으로나 실무적으로 매우 중요한 의미를 가져 이 부분에 대해 많은 연구가 이루어져 왔으나 많은 기존연구들은 주가가 예측 가능하다는 결론을 얻지 못하고 있으며, 예측 가능하다는 연구에서도 예측력이 크지 않게 나타나고 있다. 이러한 실증결과는 실증모형의 선택이 적절하지 못한데서 나타날 수 있다는 가능성을 배제할 수 없다. 기존연구들이 실증분석에서 선형모형을 사용했는데, 선형모형으로는 주가의 예측가능성을 정확히 검증하기 어려운 현실적 요인들이 존재할 수 있다. 증권시장에는 시장실패를 방지하기 위한 규제나 제도 및 시장의 불완전성으로 인해 주가움직임에 선형모형으로 추정하기 어려운 특이패턴이 발생할 수 있기 때문이다. 이 논문에서는 이러한 특이패턴이 존재한다는 가능성을 전제로 비모수적 모형, 그 중에서도 인공신경망모형을 이용하여 주가예측 가능성을 재검증해 보고자 한다. 특히 인공신경망모형을 이용한 예측성과를 동일한 구조를 가지는 선형모형의 성과와 비교함으로써 특이패턴의 고려가 주가예측에 어떤 개선을 제공할 수 있는지를 검증해 보고자 한다. 분석결과를 요약하면, 인공신경망모형이 예측력을 가질 수 있으며, 특히 유사한 구조를 가지는 선형모형보다 우월한 성과를 제공할 수 있다는 가능성을 발견하였다. 이는 선형모형으로 추정하기 어려운 특이패턴이 주가움직임에 존재하며, 따라서 이러한 패턴을 반영할 수 있는 인공신경망모형이 주가예측에 유용하게 사용될 수 있다는 것을 보이는 결과라 볼 수 있다.

• 한국소음진동공학회논문집
• /
• 제15권1호
• /
• pp.53-62
• /
• 2005

This study presents the NDE (non-destructive evaluation) technique for detecting the loosened bolts on joint steel structures on the basis of TOF (time of flight) and amplitudes of Lamb waves. Probabilistic neural network (PNN) technique which is an effective tool for pattern classification problem was applied to the damage estimation using PZT induced Lamb waves. Two kinds of damages were introduced by dominant damages (DD) which mean loosened bolts within the Lamb waves beam width and minor damages (MD) which mean loosened bolts out of the Lamb waves beam width. They were investigated for the establishment of the optimal decision boundaries which divide each damage class's region including the intact class. In this study, the applicability of the probabilistic neural networks was identified through the test results for the damage cases within and out of wave beam path. It has been found that the present methods are very efficient and reasonable in predicting the loosened bolts on the joint steel structures probabilistically.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2004년도 추계학술대회논문집
• /
• pp.625-632
• /
• 2004

This study presents the NDE (non-destructive evaluation) technique for detecting the loosened bolts on joint steel structures on the basis of TOF (time of flight) and amplitudes of Lamb waves. Probabilistic neural network (PNN) technique which is an effective tool for pattern classification problem was applied to the damage estimation using PZT induced Lamb waves. Two kinds of damages were introduced by dominant damages (DD) which mean loosened bolts within the Lamb waves beam width and minor damages (MD) which mean loosened bolts out of the Lamb waves beam width. They were investigated for the establishment of the optimal decision boundaries which divide each damage class's region including the intact class. In this study, the applicability of the probabilistic neural networks was identified through the test results for the damage cases within and out of wave beam path. It has been found that the present methods are very efficient and reasonable in predicting the loosened bolts on the joint steel structures probabilistically.

• Journal of Multimedia Information System
• /
• 제4권4호
• /
• pp.219-224
• /
• 2017

This paper is to introduce an application of face recognition algorithm in parallel. We have experiments of 25 images with different motions and simulated the image recognitions; grouping of the image vectors, image normalization, calculating average image vectors, etc. We also discuss an analysis of the related eigen-image vectors and a parallel algorithm. To develop the parallel algorithm, we propose a new type of initial matrices for eigenvalue problem. If A is a symmetric matrix, initial matrices for eigen value problem are investigated: the "optimal" one, which minimize ${\parallel}C-A{\parallel}_F$ and the "super optimal", which minimize ${\parallel}I-C^{-1}A{\parallel}_F$. In this paper, we present a general new approach to the design of an initial matrices to solving eigenvalue problem based on the new optimal investigating C with preserving the characteristic of the given matrix A. Fast all resulting can be inverted via fast transform algorithms with O(N log N) operations.

• ETRI Journal
• /
• 제35권6호
• /
• pp.1168-1171
• /
• 2013

We propose an improvement of particle swarm optimization (PSO) based on the stabilization of particle movement (PM). PSO uses a stochastic variable to avoid an unfortunate state in which every particle quickly settles into a unanimous, unchanging direction, which leads to overshoot around the optimum position, resulting in a slow convergence. This study shows that randomly located particles may converge at a fast speed and lower overshoot by using the proportional-integral-derivative approach, which is a widely used feedback control mechanism. A benchmark consisting of representative training datasets in the domains of function approximations and pattern recognitions is used to evaluate the performance of the proposed PSO. The final outcome confirms the improved performance of the PSO through facilitating the stabilization of PM.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(3)
• /
• pp.215-218
• /
• 2002

Gesture recognitions needed for various applications and is now gaining in importance as one method of enabling natural and intuitive human machine communication. In this paper, we propose a real time hand-signal recognition system in 3-dimensional space performs robust, real-time tracking under varying illumination. As compared with the existing method using classical pattern matching, this system is efficient with respect to speed and also presents more systematic way of defining hand-signals and developing a hand-signal recognition system. In order to verify the proposed method, we developed a virtual driving system operated by hand-signals.

• 비파괴검사학회지
• /
• 제36권4호
• /
• pp.300-307
• /
• 2016

차량 부품의 고장은 운용 중단과 탈선 결과로 나타날 수 있으며 차량 주요부품의 이상상태를 진단하는 것은 중요하다. 온도를 이용한 진단 방법은 철도차량 회전기기의 -예를 들면, 베어링, 감속기, 견인전동기, 디스크- 비정상 상태를 진단하는 기본적인 방법이다. 본 연구에서는 적외선열화상과 패턴 이미지법을 이용하여 차량 하부의 회전기기의 이상 진단시스템을 구축하여 현장시험을 수행하였다. 그 이상상태 진단시스템은 차량 하부 회전기기의 이상발열 상태를 진단할 수 있었으며 비정상 상태를 평가할 수 있었다.

• 한국IT서비스학회지
• /
• 제11권sup호
• /
• pp.177-189
• /
• 2012

We developed the ocean disaster detection system(OD2S) which copes with the occurrences of ocean disasters (e. g. the red and green tide, the oil spill, the typhoon, and the sea ice) by converging and integrating the ocean color remote sensing using the satellite and the information technology exploiting the mass data processing and the pattern recognitions. This system which is based on the cosine similarity detects the ocean disasters in real time. The existing ocean color sensors which are operated in the polar orbit platforms cannot conduct the real time observation of ocean environments because they support the low temporal resolutions of one observation a day. However, geostationary ocean color imager(GOCI), the first geostationary ocean color sensor in the world, produces the ocean color images(e. g. the chlorophyll, the colored dissolved organic matter(CDOM), and the total suspended solid(TSS)), with high temporal resolutions of hourly intervals up to eight observations a day. The evaluation demonstrated that the OD2S can detect the excessive concentration of chlorophyll, CDOM, and TSS. Based on these results, it is expected that OD2S detects the ocean disasters in real time.