• Journal of KIISE:Software and Applications
• /
• v.32 no.7
• /
• pp.663-673
• /
• 2005

An analysis model for the dynamics information of two-dimensional time-series patterns is described. In the proposed model, two novel transforms that visualize the dynamic characteristics are proposed. The first transform, referred to as speed equalization, reproduces a time-series pattern assuming a constant linear velocity to effectively model the temporal characteristics of the signing process. The second transform, referred to as velocity transform, maps the signal onto a horizontal vs. vertical velocity plane where the variation oi the velocities over time is represented as a visible shape. With the transforms, the dynamic characteristics in the original signing process are reflected in the shape of the transformed patterns. An analysis in the context of these shapes then naturally results in an effective analysis of the dynamic characteristics. The proposed transform technique is applied to an online signature verification problem for evaluation. Experimenting on a large signature database, the performance evaluated in EER(Equal Error Rate) was improved to 1.17$\%$ compared to 1.93$\%$ of the traditional signature verification algorithm in which no transformed patterns are utilized. In the case of skilled forgery experiments, the improvement was more outstanding; it was demonstrated that the parameter set extracted from the transformed patterns was more discriminative in rejecting forgeries

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.1369-1370
• /
• 2015

본 논문에서는 얼굴 인식을 위하여 인공 신경망의 일종인 Extreme Learning Machine의 학습 알고리즘을 기반으로 하여 지능형 알고리즘인 퍼지 집합 이론을 이용하여 주변 노이즈에 매우 강한 특성을 보이며 학습 속도가 매우 빠른 새로운 패턴 분류기를 제안한다. 제안된 퍼지 패턴 분류기는 기존 신경회로망의 학습 속도에 비해 매우 빠른 학습 속도를 보이며, 패턴 분류기의 일반화 성능이 우수하다고 알려진 Extreme Learning Machine의 특성을 퍼지 집합 이론과 결합하여 퍼지 패턴 분류기의 일반화 성능을 개선하였다. 제안된 퍼지 패턴 분류기는 얼굴 인식 데이터를 이용하여 성능을 평가 하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.04a
• /
• pp.390-393
• /
• 2012

H.264/AVC에서 움직임 추정에 소요되는 시간을 줄이면서 보다 나은 화질을 유지하기 위하여 본 논문에서는 정화소 움직임 추정 기법을 제안하였다. 본 논문에서는 정화소 움직임 추정을 위하여 대칭적인 탐색패턴을 이용한 계층적인 탐색 기법을 사용하였다. 제안한 정화소 움직임 추정 탐색 기법은 십자가 탐색 패턴, 다중 사각형 탐색 패턴, 작은 사각형 탐색 패턴, 다이아몬드 탐색 패턴들로 이루어져 있다. 제안한 움직임 추정 탐색 기법에서 사용한 탐색 패턴들은 블록 움직임이 수직으로 크거나 블록 움직임이 크면서 규칙적인 영상에서 국부적 최소화 문제를 해결하고 움직임 추정에 소요되는 시간을 줄이기 위하여 탐색 영역 내에 탐색 점들을 규칙적, 대칭적으로 배치하였다. 제안한 기법의 성능을 전역 탐색 기법의 성능과 비교하였을 때 움직임 추정에 소요되는 시간에 있어서 약 4~5.5 배의 속도 향상을 가져왔으며, 영상 화질에 있어서 전역 탐색 기법의 화질과 같거나 약간의 화질 저화를 보였다. 반면에, 비대칭 다중 육각형 탐색 기법의 성능과 비교하였을 때 움직임 추정 속도면에 있어서 약간의 성능 향상과 화질에 있어서 비슷하거나 최대 0.05 (dB)정도 향상을 보였다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.7
• /
• pp.919-928
• /
• 2010

Four patterns for width adjustment were studied with an aim to increase the width-adjustment speed in continuous casting. The main goals are to minimize the actuating force of a WAM actuator, to develop a deformation analysis model of a solidified shell in the mold, and to induce the main limit factor for the speedup of width adjustment. On the basis of the width-adjustment experiment, the notable features of four patterns types were considered, and we compared the corresponding actuating forces. For comparing the driving forces of the patterns, during the experiment, the same casting speed was maintained for each pattern. To optimize the parameter of the deformation analysis model of the solidified shell, the experiment results were applied to them. To speed up width adjustment and to reduce the driving force, we controlled the pattern parameters. The most effective pattern was the fast-mode pattern, and the taper was the main parameter that helped reduce the driving forces during the motion of the actuator.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.13 no.2
• /
• pp.1-11
• /
• 2014

In this paper, travel speed patterns were deducted based on historical DSRC travel speed data using Decision Tree technique to improve availability of the massive amount of historical data. These patterns were designed to reflect spatio-temporal vicissitudes in reality by generating pattern units classified by months, time of day, and highway sections. The study area was from Seoul TG to Ansung IC sections on Gyung-bu highway where high peak time of day frequently occurs in South Korea. Decision Tree technique was applied to categorize travel speed according to day of week. As a result, five different pattern groups were generated: (Mon)(Tue Wed Thu)(Fri)(Sat)(Sun). Statistical verification was conducted to prove the validity of patterns on nine different highway sections, and the accuracy of fitting was found to be 93%. To reduce travel pattern errors against individual travel speed data, inclusion of four additional variables were also tested. Among those variables, 'traffic condition on previous month' variable improved the pattern grouping accuracy by reducing 50% of speed variance in the decision tree model developed.

• Proceedings of the KIEE Conference
• /
• 2007.10c
• /
• pp.244-246
• /
• 2007

본 논문에서는 완전 자동화된 개인고속이동 시스템의 원활한 차량운행 제어를 위한 운행속도 패턴과 차량간의 충돌을 방지하기 위한 알고리즘의 설계 및 설계된 알고리즘의 검증을 위한 하드웨어 구성에 대해서 다룬다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.6
• /
• pp.682-687
• /
• 2005

Behavioral sequences of the medaka(Oryzias latipes) were investigated through an image system in response to medaka treated with the insecticide and medaka not treated with the insecticide, diazinon(0.1 mg/1). After much observation, behavioral patterns could be divided into 4 patterns: active smooth, active shaking, inactive smooth, and inactive shaking. These patterns were analyzed by 5 features: speed ratio, x and y axes projection, FFT to angle transition, fractal dimension, and center of mass. Each pattern was classified using decision tree. It provide a natural way to incorporate prior knowledge from human experts in fish behavior, The main focus of this study was to determine whether the decision tree could be useful in interpreting and classifying behavior patterns of the animal.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.1B
• /
• pp.47-55
• /
• 2009

In recent network intrusion detection systems, regular expressions are used to represent malicious packets. In order to process incoming packets through high speed networks in real time, we should perform hardware-based pattern matching using the configurable device such as FPGAs. However, operating speed of FPGAs is slower than giga-bit speed network and so, multi-byte processing per clock cycle may be needed. In this paper, we propose a hardware architecture of multi-byte based regular expression pattern matching and implement the pattern matching circuit generator. The throughput improvements in four-byte based pattern matching circuit synthesized in FPGA for several Snort rules are $2.62{\sim}3.4$ times.

• Culinary science and hospitality research
• /
• v.9 no.3
• /
• pp.169-181
• /
• 2003

안면 특정 근육의 움직임으로부터 기록되는 Electronic Sensing System(ESS)신호는 인간의 관능검사에 사용할 수 있다. 본 연구는 ESS를 이용하여 저작패턴에 따라 나타나는 결과들을 분석, 분류하고 각 그룹별로 같은 식품에 대한 관능 감지도의 차이를 검사하기 위하여 각 그룹별 씹는 특성을 파악하여 이에 따라 패널요원들을 선발하였다. 패널들을 젊은 남$.$여 및 노년 남$.$여 총 4그룹으로 구분하여 껌 및 당근의 저작과정에 대한 패턴 즉 속도, 시간 및 총 에너지를 비교한 결과, 젊은 남$.$여 그룹(n=47, 18∼42세, 남성 27명, 여성 20명) 및 노년 남$.$여 그룹((n=44, 65세 이상, 남성 33명, 여성 31명)은 저작 특성들이 서로 달라 같은 식품에 대하여 서로 관능감지도가 달라질 수 있음을 나타내었다. 또한 ESS에 의한 각 패널들의 검사치를 분석한 결과 껌을 씹을 때의 에너지에 대한 표준편차는 2.0 이하(n=71)그리고 씹는 속도의 경우는 0.1 이하로 반복실험의 재현성이 있었다. 91명의 패널들을 저작 에너지 및 씹는 속도에 따라 4그룹(낮은 에너지를 사용하며 천천히 씹는 그룹, 낮은 에너지를 사용하면서 빨리 씹는 그룹, 높은 에너지를 사용하며 천천히 씸는 그룹, 그리고 높은 에너지를 사용하며 빨리 씹는 그룹)으로 분류하고 각 그룹별 평균값에 가장 비슷한 양상을 나타내는 6명씩 총 24명의 관능검사 요원들을 선발하였다.

• The Journal of the Korea Contents Association
• /
• v.8 no.10
• /
• pp.251-258
• /
• 2008

This study was to investigate the effects of the combined patterns of PNF(proprioceptive neuromuscular facilitation) on the static balance ability by 20 subjects for 6 weeks. The combined patterns of PNF were carried out by Sprinter and Skater suggested by Dietz which were practiced once a day, 3 times a week. This study were measured normal standing, one leg left and one leg right standing when eye open and close on GOOD BALANCE system. These result lead us to the conclusion that mean velocity of X,Y direction, COP velocity moment were showed a statically decrease applying post-exercise on Normal Standing Eye Open(NSEO), Normal Standing Eye Close(NSEC), One Leg Right Standing Eye Close(OLRSEC) and Just velocity of X direction were showed a statically decrease applying post-exercise on One Leg Right Standing Eye Close(OLRSEC). The above results from this study indicated that combined patterns of PNF have improved the static balance ability. However the used self-exercise ca be applied to normal people, i.e., the exercise is difficult to apply into clinical patients. The further study should be focused at development of various modified forms of the combined patterns of PNF in keeping up the improvement effect of the exercise.