• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.3
• /
• pp.209-219
• /
• 2004

In order to implement a real time hardware for keyword spotting, we propose a Single-End-Point DTW(SEP-DTW) algorithm which is simple and less complex for computation. The SEP-DTW algorithm only needs a single end point which enables efficient applications, and it has a small wont of computations because the global search area is divided into successive local search areas. Also, we adopt new local constraints and a new distance measure for a better performance of the SEP-DTW algorithm. Besides, we make a normalization of feature same vectors so that they have the same variance in each frequency bin, and each frame has the same energy levels. To construct several reference patterns for each keyword, we use a clustering algorithm for all training patterns, and mean vectors in every cluster are taken as reference patterns. In order to detect a key word for input streams of speech, we measure the distances between reference patterns and input pattern, and we make a decision whether the distances are smaller than a pre-defined threshold value. With isolated speech recognition and keyword spotting experiments, we verify that the proposed algorithm has a better performance than other methods.

• Journal of Korea Multimedia Society
• /
• v.16 no.3
• /
• pp.302-308
• /
• 2013

In this research, we have explored personal authentication system through multimodal biometrics for mobile computing environment. We have selected face and speaker recognition for the implementation of multimodal biometrics system. For face recognition part, we detect the face with Modified Census Transform (MCT). Detected face is pre-processed through eye detection module based on k-means algorithm. Then we recognize the face with Principal Component Analysis (PCA) algorithm. For speaker recognition part, we extract features using the end-point of voice and the Mel Frequency Cepstral Coefficient (MFCC). Then we verify the speaker through Dynamic Time Warping (DTW) algorithm. Our proposed multimodal biometrics system shows improved verification rate through combining two different biometrics described above. We implement our proposed system based on Android environment using Galaxy S hoppin. Proposed system presents reduced false acceptance ratio (FAR) of 1.8% which shows improvement from single biometrics system using the face and the voice (presents 4.6% and 6.7% respectively).

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.12a
• /
• pp.173-176
• /
• 2000

음성은 인간이 가진 가장 편리한 제어전송수단으로 이를 통한 제어는 인간에게 많은 편리함을 제공할 것이다. 본 논문에서는 다층구조 신경망(Multi-Layer Perceptron)을 이용하여 간단한 음성인식 명령처리시스템을 Matlab 상에서 구성해 보았다. 음성인식을 통한 제어의 목적을 위해 화자종속, 고립단어인식기를 목표로 설정하여 연구를 수행하였다. 음성의 시작점과 끝점을 검출하기 위해 단구간 에너지와 영교차율(ZCR)을 이용하였고 인식기의 특징파라미터로는 12차 LPC켑스트럼 계수를 사용하였다. 그리고 신경망의 출력값을 기동, 정지시에 활성화되도록 3개의 계층으로 하였고, 신경망의 뉴런의 개수를 각각 12, 12, 2으로 설정하였다. 먼저 기준음성패턴으로 학습시킨 후에 Matlab 환경하에 동작하는 dSPACE 실시간처리보드에 변환된 C프로그램을 다운로드하고, 음성을 입력하여 인식 후 dSPACE보드의 D/A컨버터의 출력단에 연결된 DC모터를 기동, 정지제어를 수행하였다. 실시간 음성인식 명령처리 시스템 구현을 통하여 원격제어와 같은 음성명령을 통한 제어가 가능함을 확인할 수 있었다.

• Korean Journal of Food Science and Technology
• /
• v.22 no.6
• /
• pp.711-715
• /
• 1990

Continuous column chromatographic separation of lysozyme from egg white was investigated. A weak acid type cation exchange resin, Duolite C-464, was used because of high lysozyme recovery and ease of column operation in this experiment. The resin was equilibrated at $pH\;7.9{\pm}0.1$ in Na+form. Continuous lysozyme separation was processed by repeating cycles(one cycle : resin equilibration, flow egg white, rinse, lysozyme elution) in automated preparative Liquid Chromatography(LC) system(column size ; i.d. 50 mm, resin bed volumn ; 1020 ml). At comparison of UV levels in rinse end point and elution end point of every cycle, the UV levels of rinse end point are maintained below 30% for 19 cycles and that of elution end point are also maintained below 30% for 17 cycles, stably, but was increased above 50% after 18 cycle. That indicated the eluting ability of lysozyme was reduced conspicuously after 18 cycle in continuous cycling process. The recovery of lysozyme was maintained above 90% from one to 17 cycle, but was decreased to 72% and 65% in 18 cycle and 19 cycle, respectively.

• Journal of the Institute of Convergence Signal Processing
• /
• v.15 no.2
• /
• pp.42-47
• /
• 2014

A finger-gesture game controller using the single camera is implemented in this paper, which is based on the recognition of the number of fingers and the index finger moving direction. Proposed method uses the CAMShift algorithm to trace the end-point of index finger effectively. The number of finger is recognized by using a double circle tracing method. Then, HSI color mode transformation is performed for the CAMShift algorithm, and YCbCr color model is used in the double circle tracing method. Also, all processing tasks are implemented by using the Intel OpenCV library and C++ language. In order to evaluate the performance of the proposed method, we developed a shooting game simulator and validated the proposed method. The proposed method showed the average recognition ratio of more than 90% for each of the game command-mode.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.12
• /
• pp.32-40
• /
• 2018

In order to avoid excessive vibration, it is required to carry out a vibration analysis of heat-exchanger/nuclear-reactor at the design stage. Information of eigen-frequency in the vibration problem is required to evaluate safety of heat-exchange/nuclear reactor. This paper describes a numerical method, Galerkin's method, to solve the eigenvalue problem occurred in a cantilever beam. The beam is restrained with added mass and spring at the free end or a node point of a mode shape. The numerical results of eigen-frequency were compared with simple analytical and experimental results given by simple approach and simple test, respectively. It is found that Galerkin's method is applicable to estimate the eigen-frequency of the cantilever beam. The frequencies become lower with increasing the added mass and the frequencies increase with the spring force. It is shown the heavy added mass has a role of support on the flexible tube. The eigen-frequency of the first mode, for the system with the added mass mounted at the free end, can be calculated by the approximate analytical method existing with more or less accuracy.

• Proceedings of the Korea Society of Costume Conference
• /
• 2003.05a
• /
• pp.34-34
• /
• 2003

본 연구는 체형의 특성이 현저히 나타나는 40~50대의 Plus-size 여성을 대상으로 체형의 특징이 고려된 치수체계에 대해 맞음새가 우수한 재킷을 개발하고, 이 원형을 토대로 하여 체형의 단점을 보완할 시각적 효과를 연구하기 위해 Plus-size에 해당하는 여성을 선정하여 수트(suit)를 제작한 후 착의 평가하여 Plus-size에 적합한 수트를 제안하는데 목적을 두고 있다. 결과를 요약하면 다음과 같다. 1. Plus-size 여성의 착용실태를 파악하기 위해 실시한 착용실태 조사는 판매자의 측면의 심층면접과 소비자 측면의 착장조사로 구분하여 조사하고 분석하였다. 착용실태조사 결과, Plus-size 여성은 의복구매시 맞음새와 편안함을 중시하고 상완부와 어깨의 두께, 가슴둘레와 복부의 비만등의 체형단점을 갖게 되므로 판매자측에서는 의복제도 시에 등품, 앞품, 상완부, 복부의 여유분을 고려하고 있었다. 시각적 효과로는 세미피트 스타일의 프린세스 라인과 허리선+20, 30cm의 재킷길이, 그리고 테일러드 칼라, 스테인 칼라, 라운드 네크라인이 판매자과 소비자의 양측면에서 선호되고 있었다. 2. Plus-size 여성의 체형에 맞음새가 우수한 재킷원형을 개발하기 위해 Plus-size 여성복의 재킷 원형 중 4종의 기존원형을 선정하고, 착의 피험자 3인을 대상으로 3차에 걸친 착의실험을 통해 연구 원형을 개발하고 평가단을 구성해 객관적인 평가 33문항에 대한 외관 관능검사를 실시하였다. 1) 가슴둘레 여유분을 8~9cm, 허리둘레 여유분을 6~7cm, 엉덩이둘레 여유분을 6~8cm로 적용하여 맞음새를 향상시켜 날씬해 보이는 효과를 높였다. 2) 진동깊이 계산식은 (B/10+10.5)+2cm 적용하고, 진동두께 계산식은 (B/8-1.5)+2cm를 적용함으로써 진동깊이와 진동두께의 편차가 작아짐으로 인해 소매부위와 진동부위의 맞음새를 향상시켰다. 3) 가슴둘레의 증가에 따라 등길이에 앞길이 치수를 증가시키는 계산식을 설정하여 앞가슴둘레의 맞음새를 향상시켰다. 4) Plus-size여성의 경우 허리부분의 신체적합성을 높이기 위하여 사이드 판넬(side panel)의 재킷원형으로 하였다. 앞 허리와 배 부분의 지방 침착이 크므로 앞 허리둘레 다아트 폭과 앞판 사이드 판넬(side panel) 솔기 다아트 폭을 작게 설정하고, 뒤판 사이드 판넬 솔기 폭을 크게 설정하였다. 5) 어깨끝점 사이길이는 다른 부위의 체지방 침착과 같이 비례적으로 증가하지 않으므로 표준체형에 비해 좁게 설정하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.3 no.1
• /
• pp.185-196
• /
• 1999

In this dissertation, a new off-line recognition system is proposed using a subgraph pattern, neural network. After thinning is applied to input characters, balance having a noise elimination function on location is performed. Then as the first step for recognition procedure, circular elements are extracted and recognized. From the subblock HT, space feature points such as endpoint, flex point, bridge point are extracted and a subgraph pattern is formed observing the relations among them. A region where vowel can exist is allocated and a candidate point of the vowel is extracted. Then, using the subgraph pattern dictionary, a vowel is recognized. A same method is applied to extract horizontal vowels and the vowel is recognized through a simple structural analysis. For verification of recognition subgraph in this paper, experiments are done with the most frequently used Myngjo font, Gothic font for printed characters and handwritten characters. In case of Gothic font, character recognition rate was 98.9%. For Myngjo font characters, the recognition rate was 98.2%. For handwritten characters, the recognition rate was 92.5%. The total recognition rate was 94.8% with mixed handwriting and printing characters for multi-font recognition.

• Journal of the Korean Geophysical Society
• /
• v.2 no.1
• /
• pp.45-56
• /
• 1999

Seismic refracrion and reflection surveys were conducted along an E-W trending track of 482 m long in Ilwall-dong, Pohang. End-on spread was employed as source-receiver configuration with 2 m for both geophone interval and offset. Seismic data were acquired using 24 channels at every shot fired every 2 m along the track. Refraction data were interpreted using equations for multi-horizontal layers. Reflection data were processed in the sequence of trace edit, gain control, CMP sorting, NMO correction, mute, common offset gathering, and filtering to produce a single fold seismic section. There are two layers in shallow subsurface of the study area. Upper layer has the P-wave velocities ranging from 267 to 566 m/s and is interpreted as a layer of unconsolidated sediments. Lower layer has P-wave velocities of 1096-3108 m/s and is interpreted as weathered rock to hard rock. Most of the lower layer classified as soft rock. Upper layer has lateral variations in both P-wave velocity and thickness. The upper layer in the eastern part of the seismic line is 3-5 m thick and has P-wave velocity of 400 m/s in average. The upper layer in the western part is 8-10 m thick and has P-wave velocity of 340 m/s in average. The eastern part is interpreted as unconsolidated beach sand, while the western part is interpreted as infilled soil to develop a construction site. Three fault systems of high angle are imaged in seismic reflection section. It is interpreted that the area between these fault systems are relatively safe. Large buildings should be located in the safe ground condition of no fault and footings should be designed to be in the basement rock of 3-10 m deep below the surface.