• Title/Summary/Keyword: Minima

Search Result 452, Processing Time 0.037 seconds

Bilateral Filtering-based Mean-Shift for Robust Face Tracking (양방향 필터 기반 Mean-Shift 기법을 이용한 강인한 얼굴추적)

  • Choi, Wan-Yong;Lee, Yoon-Hyung;Jeong, Mun-Ho
    • The Journal of the Korea institute of electronic communication sciences
    • /
    • v.8 no.9
    • /
    • pp.1319-1324
    • /
    • 2013
  • The mean shift algorithm has achieved considerable success in object tracking due to its simplicity and robustness. It finds local minima of a similarity measure between the color histograms or kernel density estimates of the target and candidate image. However, it is sensitive to the noises due to objects or background having similar color distributions. In addition, occlusion by another object often causes a face region to change in size and position although a face region is a critical clue to perform face recognition or compute face orientation. We assume that depth and color are effective to separate a face from a background and a face from objects, respectively. From the assumption we devised a bilateral filter using color and depth and incorporate it into the mean-shift algorithm. We demonstrated the proposed method by some experiments.

Customer Classification System Using Incrementally Ensemble SVM (점진적 앙상블 SVM을 이용한 고객 분류 시스템)

  • Park, Sang-Ho;Lee, Jong-In;Park, Sun;Kang, Yun-Hee;Lee, Ju-Hong
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2003.10a
    • /
    • pp.190-192
    • /
    • 2003
  • 소비자의 신용 대출 규모가 점차 증가하면서 기업에서 고객의 신용 등급에 의한 정확한 고객 분류를 필요로 하고 있다 이를 위해 판별 분석과 신경망의 역전파(BP: Back Propagation)를 이용한 고객 분류 시스템이 연구되었다. 그러나, 판별 분석을 사용한 방법은 불규칙한 신용 거래의 성향을 보이는 비정규 분포의 고객 데이터의 영향으로 여러 개의 판별 함수와 판별점이 존재하여 분류 정확도가 떨어지는 단점이 있다. 신경망을 이용한 방법은 불규칙한 신용 거래의 성향을 보이는 고객 데이터에 의해서, 지역 최소점(Local Minima)에 빠져 최대의 분류 정확률을 보이는 분류자를 얻지 못하는 경우가 발생할 수 있다. 본 논문에서는 이러한 기존 연구의 분류 정확률을 저하시키는 단점을 해결하기 위해 SVM(Support Vector Machine)을 사용하여 고객의 신용 등급을 분류하는 방법을 제안한다. SVM은 SV(Support Vector)의 수에 의해서 학습 성능이 좌우되므로, 불규칙한 거래 성향을 보이는 고객에 대해서도 높은 차원으로의 매핑을 통하여, 효과적으로 학습시킬 수 있어 분류의 정확도를 높일 수 있다 하지만, SVM은 근사화 알고리즘(Approximation Algorithms)을 이용하므로 분류 정확도가 이론적인 성능에 미치지 못한다. 따라서, 본 논문은 점진적 앙상블 SVM을 사용하여, 기존의 고객 분류 시스템의 문제점을 해결하고 실제적으로 SVM의 분류 정확률을 높인다. 실험 결과는 점진적 앙상블 SVM을 이용한 방법의 정확성이 기존의 방법보다 높다는 것을 보여준다.

  • PDF

Distribution System Reconfiguration Using the PC Cluster based Parallel Adaptive Evolutionary Algorithm

  • Mun Kyeong-Jun;Lee Hwa-Seok;Park June Ho;Hwang Gi-Hyun;Yoon Yoo-Soo
    • KIEE International Transactions on Power Engineering
    • /
    • v.5A no.3
    • /
    • pp.269-279
    • /
    • 2005
  • This paper presents an application of the parallel Adaptive Evolutionary Algorithm (AEA) to search an optimal solution of a reconfiguration in distribution systems. The aim of the reconfiguration is to determine the appropriate switch position to be opened for loss minimization in radial distribution systems, which is a discrete optimization problem. This problem has many constraints and it is very difficult to find the optimal switch position because of its numerous local minima. In this investigation, a parallel AEA was developed for the reconfiguration of the distribution system. In parallel AEA, a genetic algorithm (GA) and an evolution strategy (ES) in an adaptive manner are used in order to combine the merits of two different evolutionary algorithms: the global search capability of GA and the local search capability of ES. In the reproduction procedure, proportions of the population by GA and ES are adaptively modulated according to the fitness. After AEA operations, the best solutions of AEA processors are transferred to the neighboring processors. For parallel computing, a PC-cluster system consisting of 8 PCs·was developed. Each PC employs the 2 GHz Pentium IV CPU, and is connected with others through switch based fast Ethernet. The new developed algorithm has been tested and is compared to distribution systems in the reference paper to verify the usefulness of the proposed method. From the simulation results, it is found that the proposed algorithm is efficient and robust for distribution system reconfiguration in terms of the solution quality, speedup, efficiency, and computation time.

Screening of Biologically Active Compounds from various weeds (다양한 잡초로부터 생리활성물질의 탐색)

  • Kang, Byeong-Hoa;Ryoo, In-Ja;Park, Dong-Jin;Lee, Hyun-Sun;Kim, Young-Ho;Yoo, Ick-Dong;Kim, Chang-Jin
    • Applied Biological Chemistry
    • /
    • v.39 no.5
    • /
    • pp.409-413
    • /
    • 1996
  • To search for bioactive compounds from plant resources, 80% methanol extracts of 46 species of weeds were screened for their activities of antimicrobial, antioxidative, antiblebing, antitumor and herbicidal. Among extracts tested, some showed activities at the concentration of $50\;to\;100\;{\mu}g/ml$. Phryma leptostachya var. asiatica, Aster ageratoides, Centipeda minima, Cirsium pendulum, Lythrum anceps showed antibacterial activity. Penthorum chinense, Lindernia procumbens, Aster ageratoides, Dianthus superbus var. longicalycinus showed antiblebing activity. Phyma leptostachya var. asiatica, Juncus effusus var. decipiens, Lindernia procumbens, Aster ageratoides, Dianthus superbus var. longicalycinus, Viscum album var. coloratum showed antitumor activity. Juncus effusus var. decipiens, Hypericum ascyron, Juncus papillosus, Inula britannicar var. chinensis, Scirpus wichurae, Hypericum laxum showed antioxidant activity.

  • PDF

Theoretical Studies on Conformation of Cyclic Hexapeptides and Blocking for the Cation Transport by 5,5-diphenylhydantoin (고리형 헥사펩티드의 형태 및 5,5-디페닐하이덴토인에 의한 양이온 전달방해에 관한 이론적 연구)

  • Kiyull Yang;In Sun Koo;Ikchoon Lee;Chang-Kook Sohn
    • Journal of the Korean Chemical Society
    • /
    • v.36 no.4
    • /
    • pp.523-535
    • /
    • 1992
  • The conformations of hexapeptides, their complexation with alkali cations and the inhibition of the cation transport by 5,5-diphenylhydantoin(DPH) were studied theoretically using ECEPP/2 and MM2 force field. Several low energy conformations of uncomplexed cyclic hexapepides are obtained, and they adopt compact conformations in which most amide hydrogens form intramolecular hydrogen bond to amide carbonyl oxygens. The complexation energy of the peptide with $Na^+$ ion and DPH is -60 kcaal/mol and -18 kcal/mol, respectively. However, no suitable cavity to bind metal cation exists for the local minima of the peptide, and the internal energy of the uncomplexed hexapeptide having cavity is higher than that of the uncomplexed global minimum of this work by 10 kcal/mol. Also, one of the most important amino acid residue to bind DPH is Glycine, and this can explain experimental observation that the replacement of Gly by Sarcosine (N-methyl Glycine) reduce the inhibition ability of the cation transport.

  • PDF

Thickness and Surface Measurement of Transparent Thin-Film Layers using White Light Scanning Interferometry Combined with Reflectometry

  • Jo, Taeyong;Kim, KwangRak;Kim, SeongRyong;Pahk, HeuiJae
    • Journal of the Optical Society of Korea
    • /
    • v.18 no.3
    • /
    • pp.236-243
    • /
    • 2014
  • Surface profiling and film thickness measurement play an important role for inspection. White light interferometry is widely used for engineering surfaces profiling, but its applications are limited primarily to opaque surfaces with relatively simple optical reflection behavior. The conventional bucket algorithm had given inaccurate surface profiles because of the phase error that occurs when a thin-film exists on the top of the surface. Recently, reflectometry and white light scanning interferometry were combined to measure the film thickness and surface profile. These techniques, however, have found that many local minima exist, so it is necessary to make proper initial guesses to reach the global minimum quickly. In this paper we propose combing reflectometry and white light scanning interferometry to measure the thin-film thickness and surface profile. The key idea is to divide the measurement into two states; reflectometry mode and interferometry mode to obtain the thickness and profile separately. Interferogram modeling, which considers transparent thin-film, was proposed to determine parameters such as height and thickness. With the proposed method, the ambiguity in determining the thickness and the surface has been eliminated. Standard thickness specimens were measured using the proposed method. Multi-layered film measurement results were compared with AFM measurement results. The comparison showed that surface profile and thin-film thickness can be measured successfully through the proposed method.

The Study on the Application of RE-CAT and Effectiveness (Wake Turbulence RE-CAT 적용과 효과성에 관한 연구)

  • Choi, Sang Il;Choi, Ji Ho;Yu, Soo Jeong;Lim, Min Sung;Oh, Min Ha;Lee, Soo Jung;Kim, Hyeon Mi;Kim, Hui Yang
    • Journal of the Korean Society for Aviation and Aeronautics
    • /
    • v.29 no.3
    • /
    • pp.34-43
    • /
    • 2021
  • Wake turbulence generated by the lead aircraft has a significant impact on the following aircraft and it is has been considered a key factor to consider whenin determining the longitudinal separation between the aircraft. ICAO classifies aircraft into four wake turbulence categories based on the maximum takeoff weight and provides the longitudinal separation minima for each category. Due to richer measured data and better understanding of physical processes, it is raised that classifying aircraft with only four wake turbulence grades is imprecise and leads to over-separation in many instances. In this regards, much research on a new method of classifying Wake Turbulence Category(Re-CAT) has been done by EURO-CONTROL, FAA, and ICAO. The main purpose of this study is to conduct a comparative analysis of the existing wake turbulence separation standards with Re-CAT in terms of departure capacity and the resulting benefits of Re-CAT using the data from the Incheon International Airport. The results show that EUROCONTROL and new ICAO standards have the greater effect on reducing wake turbulence separation, compared to the FAA RE-CAT standards. It is also concluded that Re-CAT presents different results of wake turbulence separation depending on the flight characteristics of each airport.

Theoretical Study for Thermally Activated Delayed Fluorescence (TADF) Property in Organic Light-Emitting Diode (OLED) Candidates (유기발광소재(OLED) 후보물질의 지연형광(TADF) 성질에 대한 이론적 연구)

  • Seo, Hyun-il;Jeong, Hyeon Jin;Yoon, Byung Jin;Kim, Seung-Joon
    • Journal of the Korean Chemical Society
    • /
    • v.63 no.3
    • /
    • pp.151-159
    • /
    • 2019
  • The TADF properties for carbazol-dicyanobenzene, carbazol-diphenyl sulfone, carbazol-benzonitrile derivatives as OLED candidate materials are theoretically investigated using density functional theory (DFT) with $6-31G^{**}$, cc-pVDZ, and cc-pVTZ basis sets. The optimized geometries, harmonic vibrational frequencies, and HOMO-LUMO energy separations are predicted at the B3LYP/$6-31G^{**}$ level of theory. The harmonic vibrational frequencies of the molecules considered in this study show all real numbers implying true minima. The time dependent density functional theory (TD-DFT) calculations have been also applied to investigate the absorption and emission wavelength (${\lambda}_{max}$), energy differences (${\Delta}E_{ST}$) between excited singlet ($S_1$) and triplet ($T_1$) states of candidate materials.

Investigation of the Light Reflection from Dielectric Thin Films Coated on Substrates (기판 위에 입혀진 유전체 박막의 빛 반사에 관한 연구)

  • Kim, Deok Woo;Kim, Jiung;Kim, Byoung Joo;Cha, Myoungsik
    • Korean Journal of Optics and Photonics
    • /
    • v.31 no.6
    • /
    • pp.321-327
    • /
    • 2020
  • We investigated the light reflection from thin films coated on substrates. Using a prism with a high refractive index as the incident medium, the phenomena of the total internal reflection (TIR) of the prism/film/substrate system and the light coupling into the optical waveguide formed by the air/film/substrate system were comprehensively studied and compared. If the refractive index of the thin film is greater than that of the substrate, within the TIR region of the substrate, sharp reflection minima occur at specific angles where the waveguide modes are excited, that can be used to accurately measure the refractive index and thickness of a thin film. On the other hand, if the refractive index of the thin film is smaller than that of the substrate, such waveguide modes do not exist. In this case, although not so distinct as a bulk medium, the TIR effect of the thin film is still observable, accompanied by an interference pattern. In this study we analyzed the overall reflection phenomena occurring from prism/film/substrate structures, to investigate the possibility of measuring the refractive index of a thin film in both cases.

Power Disturbance Detection using the Inflection Point Estimation (변곡점 추정을 이용한 전력선 신호의 이상현상 검출)

  • Iem, Byeong-Gwan
    • Journal of IKEEE
    • /
    • v.25 no.4
    • /
    • pp.710-715
    • /
    • 2021
  • Power line signal can show disturbances due to various causes. Typical anomalies are temporary sag/swell of the amplitude, flat topped signal, and harmonic distortions. The disturbances need to be detected and treated properly for the quality of the power signal. In this study, the power disturbances are detected using the inflection points (IP). The inflection points are defined as points where local maxima/minima or the slope changes occur. The power line signal has a fixed IP pattern since it is basically sinusoidal, and it may have additional inflection points if there is any disturbance. The disturbance is detected by comparing the IP patterns between the normal signal and distorted signal. In addition, by defining a cost function, the time instant where the disturbance happens can be decided. The computer simulation shows that the proposed method is useful for the detection of various disturbances. The simple sag or swell signal only shows the amplitude changes at the detected inflection points. However, the flat top signal and harmonically distorted signal produce additional inflection points and large values in the cost function. These results can be exploited for the further processing of disturbance classification.