• Journal of Internet Computing and Services
• /
• v.20 no.1
• /
• pp.39-46
• /
• 2019

This paper investigates the importance of various environmental factors that have a strong influence on strawberry yields grown in greenhouse using the pattern recognition methods. The environmental factors influencing the production of strawberries were six factors such as average inside temperature, average inside humidity, average $CO_2$ level, average soil temperature, cumulative solar radiation, and average illumination. The results of analyzing the observed data using Dynamic Time Warping (DTW) showed that the most significant factor influencing the strawberry production was average soil temperature, average inside humidity, and cumulative solar radiation. Second, the results of analyzing the observed data using Multidimensional Scaling (MDS) showed that the most influential factors on the strawberry yields, such as average $CO_2$ level, average inside humidity, and average illumination were differently given for each farms. However, these results are based on the distance in 3D space and can be deduced from the fact that there is not a large difference between these distances. Therefore, in order to increase the harvest of strawberries cultivated in the farms, it is necessary to manage the environmental factors such as thoroughly controlling the humidity and maintaining the concentration of $CO_2$ constantly by ventilation of the greenhouse.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.3
• /
• pp.175-182
• /
• 2004

There is a growing interest in speaker verification, which verifies someone by his/her voices. There are many speaker vitrification algorithms such as HMM and DTW. However, it is impossible to apply these algorithms to memory limited applications because of large number of feature vectors to register or verify users. In this paper we introduces a speaker verification system using SVM, which needs a little memory usage and computation time. Also we proposed hardware architecture for SVM. Experiments were conducted with Korean database which consists of four-digit strings. Although the error rate of SVM is slightly higher than that of HMM, SVM required much less computation time and small model size.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.307-309
• /
• 2004

In this study, we have evaluated and classified arthritic pathology using the auscultation of knee joint sound. Six normal persons and 11 patients with knee problem were enrolled. Six patients of Group 1 needed an orthopeadic surgery because of the ruptured wounds of meniscus or ACL(Anterior Cruciate Ligament) and 5 patients of Group 2 diagnosed as osteoarthritis. Subjects were taken knee flexion and extension being seated in a chair for 20 seconds which repeated 3 times. Also subjects stood up and sit down repeatedly in the same way. After the movement of knee was divided into 18 degrees, the pitch perturbation according to partial degrees was analyzed and the DTW(Dynamic Time Warping) method was applied for normalizing a time-axis and unpaired t-test was used for statistic results among groups. As a result, the amplitude and frequency perturbations of group 2 was higher than group 1(p<0.05) and showed a characteristic 'w-shape' in angle-amplitude graph. These results suggest that the analysis of knee joint sound might assist in early diagnosis of knee joint disease.

• The Journal of the Acoustical Society of Korea
• /
• v.17 no.4
• /
• pp.14-22
• /
• 1998

본 연구에서는 Texas Instruments 사의 저가형 부동소수점 디지털 신호 처리기 (Digital Singnal Processor, DSP)인 TMS320C32를 이용하여 실시간 화자종속 음성인식 하 드웨어 모듈(VR32)을 개발하였다. 하드웨어 모듈의 구성은 40MHz의 TMS320C32 DSP, 14bit 코덱인 TLC32044(또는 8bit μ-law PCM 코덱), EPROM과 SRAM 등의 메모리와 호 스트 인터페이스를 위한 로직 회로로 이루어졌다. 뿐만 아니라 이 하드웨어 모듈을 PC사에 서 평가해보기 위한 PC 인터페이스용 보드 및 소프트웨어도 개발하였다. 음성인식 알고리 즘의 구성은 에너지와 ZCR을 기반으로 한 끝점검출(Endpoint Detection) 침 10차 가중 LPC 켑스터럼(Weighted LPC Cepstrum) 분석이 실시간으로 이루어지며 이후 Dynamic Time Warping(DTW)를 통하여 최고 유사 단어를 결정하고 다시 검증과정을 거쳐 최종 인식을 수행한다. 끝점검출의 경우 적응 문턱값(Adaptive threshold)을 이용하여 잡음에 강인한 끝 점검출이 가능하며 DTW 알고리즘의 경우 C 및 어셈블리를 이용한 최적화를 통하여 계산 속도를 대폭 개선하였다. 현재 인식률은 일반 사무실 환경에서 통상 단축다이얼 용도로 사 용할 수 있는 30 단어에 대하여 95% 이상으로 매우 높은 편이며, 특히 배경음악이나 자동 차 소음과 같은 잡음환경에서도 잘 동작한다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.5
• /
• pp.109-119
• /
• 2017

In the present study, to determine walking imbalance using the walking analysis method, where limitations in the existing walking analysis have been minimized, we propose a new walking analysis method that adopts the following: self-developed equipment to measure the angles of left-right hip joints and knee joints; a determination system using symmetry index (SI); and dynamic time warping (DTW) similarity analysis algorithm to analyze individual walking styles. Normal and imbalanced walking tests were conducted for 12 subjects without walking disorder. From the SI calculation to determine imbalanced walking, both the normal and imbalanced walking styles can be determined using the angle measurements of the left-right hip joints and knee joints. In the analysis of the individual walking styles, the similarities at the center of the lower back, left-right thighs, and dorsum of the feet of the 12 subjects in both normal and imbalanced walking cases were compared. From the similarity analysis of the measured values during the normal and imbalanced walking tests, I determined that the walking pattern does not maintain the same stance when the body parts move during walking.

• Journal of Korea Multimedia Society
• /
• v.17 no.2
• /
• pp.124-131
• /
• 2014

In this paper, we propose the non-contact gesture recognition algorithm using 4- channel electrometer sensor array. ELF(Extremely Low Frequency) EMI and PLN are minimized because ambient electromagnetic noise around sensors has a significant impact on entire data in indoor environments. In this study, we transform AC-type data into DC-type data by applying a 10Hz LPF as well as a maximum buffer value extracting algorithm considering H/W sampling rate. In addition, we minimize the noise with the Kalman filter and extract 2-dimensional movement information by taking difference value between two cross-diagonal deployed sensors. We implemented the DTW gesture recognition algorithm using extracted data and the time delayed information of peak values. Our experiment results show that average correct classification rate is over 95% on five-gesture scenario.

• The KIPS Transactions:PartD
• /
• v.11D no.3
• /
• pp.709-716
• /
• 2004

This paper describes an intelligent real-time monitoring system of a semiconductor processing equipment, which determines normal or not for a wafer in processing, using multiple time-series pattern recognition. The proposed system consists of three phases, initialization, learning and real-time prediction. The initialization phase sets the weights and tile effective steps for all parameters of a monitoring equipment. The learning phase clusters time series patterns, which are producted and fathered for processing wafers by the equipment, using LBG algorithm. Each pattern has an ACI which is measured by a tester at the end of a process The real-time prediction phase corresponds a time series entered by real-time with the clustered patterns using Dynamic Time Warping, and finds the best matched pattern. Then it calculates a predicted ACI from a combination of the ACI, the difference and the weights. Finally it determines Spec in or out for the wafer. The proposed system is tested on the data acquired from etching device. The results show that the error between the estimated ACI and the actual measurement ACI is remarkably reduced according to the number of learning increases.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.3
• /
• pp.15-23
• /
• 2001

This paper presents a voice conversion technique that modifies the utterance of a source speaker as if it were spoken by a target speaker. Feature parameter conversion methods to perform the transformation of vocal tract and prosodic characteristics between the source and target speakers are described. The transformation of vocal tract characteristics is achieved by modifying the LPC cepstral coefficients using Linear Multivariate Regression (LMR). Prosodic transformation is done by changing the average pitch period between speakers, and it is applied to the residual signal using the LP-PSOLA scheme. Experimental results show that transformed speech by LMR and LP-PSOLA synthesis method contains much characteristics of the target speaker.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.241-243
• /
• 2003

일반적으로 사용되는 반도체 공정에 대한 진단 기법은 한 공정을 진행하기 전에 테스트 공정을 수행하여 공정의 진행 여부를 결정하고, 한 공정의 진행을 완료한 후에 다시 테스트 공정을 수행하여 공정의 결과를 진단하는 방법이다. 본 논문에서 제안하는 실시간 자동 진단 시스템은 기존 방법의 문제점인 자원의 낭비를 막고, 실시간으로 진단함으로써 시간의 낭비를 막는 진단 시스템을 제안한다. 실시간 자동 진단 시스템은 크게 시스템 초기화 단계, 학습 단계 그리고 예측 단계로 나누어진다. 초기화 단계는 진단할 공정에 대한 사전 입력값을 받아 시스템을 초기화하는 과정으로 공정장비 파라미터별 중요도 자동 설정 과정과 초기화 클러스터링으로 이루어진다. 학습 단계는 실시간으로 저장된 공정장치별 데이터와 계측기로부터 획득된 데이터를 이용하여 최적의 유사 클래스를 결정하는 단계와 결정된 유사 클래스를 이용하여 가중치를 학습하는 단계로 나누어진다. 예측 단계는 공정 진행 중 획득된 실시간 데이터를 학습 단계에서 결정된 파라미터별 가중치를 사용하여 공정에 대한 진단을 한다. 본 시스템에서 사용하는 클러스터링 알고리즘은 DTW(Dynamic Time Warping)를 이용하여 파라미터 데이터에 대한 특징을 추출하고 LBG(Linde, Buzo and Gray) 알고리즘을 사용하여 데이터를 군집화 한다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.8 no.6
• /
• pp.111-117
• /
• 2008

In this paper, we describes the boxing motion recognition which is used in the part of games, animation. To recognize the boxing motion, we have used two algorithms, one is principle component analysis, the other is dynamic time warping algorithm. PCA is the simplest of the true eigenvector-based multivariate analyses and often used to reduce multidimensional data sets to lower dimensions for analysis. DTW is an algorithm for measuring similarity between two sequences which may vary in time or speed. We introduce and compare PCA and DTW algorithms respectively. We implemented the recognition of boxing motion on the motion capture system which is developed in out research, and depict the system also. The motion graph will be created by boxing motion data which is acquired from motion capture system, and will be normalized in a process. The result has implemented in the motion recognition system with five actors, and showed the performance of the recognition.