• 말소리와 음성과학
• /
• 제4권3호
• /
• pp.95-101
• /
• 2012

In this paper, we introduce the automatic speaker identification system 'SPO(Supreme Prosecutors Office) Verifier'. SPO Verifier is a GMM(Gaussian mixture model)-UBM(universal background model) based automatic speaker recognition system and has been developed using Korean speakers' utterances. This system uses a channel compensation algorithm to compensate recording device characteristics. The system can give the users the ability to manage reference models with utterances from various environments to get more accurate recognition results. To evaluate the performance of SPO Verifier on Korean speakers, we compared this system with one of the most widely used commercial systems in the forensic field. The results showed that SPO Verifier shows lower EER(equal error rate) than that of the commercial system.

• 동력기계공학회지
• /
• 제15권2호
• /
• pp.69-77
• /
• 2011

In this paper, an optimal PID sliding mode controller is proposed for the position control of electro-hydrostatic actuator(ERA) systems with system uncertainties and saturation in the motor. An ERA prototype is developed and system modeling and parameter identification are executed. Then, optimal PID and optimal anti-windup PID controller are designed based on identified system model by using optimization toolbox in MA TLAB/Simulink and the performance of the two control systems are compared by experiment. It was found that the optimal anti-windup PID control system has better performance than the optimal anti-windup PID control system.

• 대한수의학회지
• /
• 제34권2호
• /
• pp.315-320
• /
• 1994

The API STAPH-IDENT system was evaluated as a means for identifying Staphylococcus hyicus subsp hyicus straints isolated from swine and poultry. Of 80 strains from swine, 68 (85%) were correctly identified by the API STAPH-IDENT system alone after 5 h of incubation. When results were determined after 24 h of incubation, the accuracy of this system alone was 93.8%. By additional tests in conjunction with the API STAPH-IDENT system, however, all 80 strains could be correctly identified. Of 120 strains from poultry, 87 (72.5%) required additional testing to achieve a correct identification, and 33 (27.5%) were incorrectly identified by this system after 5 h of incubation. After 24 h of incubation, 99 of 120 (82.5%) avian strains were incorrectly identified as Staph epidermidis owing to false-negative mannose and trehalose utilizations. Seventy-seven (96.3%) of swine strains were positive for ${\beta}-glucuronidase$, whereas all 120 strains recovered tram poultry were negative for it.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1998년도 제13차 학술회의논문집
• /
• pp.335-339
• /
• 1998

This paper presents a closed loop identification algorithm in time domain. This algorithm can be used for identification of unstable system and for model validation of system which is difficult to derive analytical model. In time domain, projection filter, which projects a finite number of input output data of a system into its current space, is used to relate the state space model with a finite difference model. Then recursive relations between the Markov parameters and the ARX model coefficients are derived to identify the system, controller and Kalman filter Markov parameters recursively, which are finally used to identify the system, controller and Kalman filter gains. The NASA LAMSTF is used to validate the algorithms developed.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 추계종합학술대회 논문집
• /
• pp.1297-1300
• /
• 1998

In this paper, we discuss the identification of a chaotic system using chaotic neural networks. Because of selfconnections in neuron itself and interconnections between neurons, chaotic neural networks identifiers show good performance in highly nonlinear dynamics such as chaotic system. Simulation results are presented to demonstrate robustness of chaotic neural networks identifier.

• Journal of Biosystems Engineering
• /
• 제16권2호
• /
• pp.111-117
• /
• 1991

An empirical model for diesel engine control was obtained using a system identification method. A pseudo-random binary sequence was used as an input signal. Spectral anaylsis was used to find the frequency response of system. Model parameters of transfer functions were obtained using nonlinear regression.

• 한국철도학회지
• /
• 제6권2호
• /
• pp.9-18
• /
• 2003

This paper discuss advanced safety in the railway signaling system. The specified methods and HAZOP about Hazard identification and analysis of railway signalling system were studied, and loss analysis and ALARP model in order to calculate safety as a standard capacity were proposed. It was also resulted from Hazard identification, analysis and evaluation by applying advanced safety to the railway signalling system.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2004년도 추계학술대회논문집
• /
• pp.428-428
• /
• 2004

• Preventive Nutrition and Food Science
• /
• 제7권3호
• /
• pp.305-309
• /
• 2002

Raw soybean sprouts were tested for contamination with the following bacteria which have potential for pathogenesis or food spoilage : Salmonella spp., Escherichia coli O157:H7, Yersinia enterocolitica, Vibrio parahae-molyticus, Aeromonas hydrophila, Plesidomonas shigeloides, Pseudomonas aeruginosa, Staphylococcus aureus, Lis-teria monocytogenes, Bacillus cereus, Clostridium perfringens, Campylobacter jejuni, Erwinia spp., and Fusarium spp. Three of the above strains were isolated from the sprouts, and identified by morphological and biochemical methods including an API kit and ATB automated identification system. The isolate cultured in Cereus selective agar, a selective medium, was a Gram-positive, rod shaped, anaerobic spore former. The biochemical and culture tests revealed the following characteristics: catalase-positive, no growth on Simmon's citrate, NO₂ production and requirement of arginine for growth; the ATB automated identification system gave 99.8 % agreement for the identification of Bacillus cereus to the species level. The isolate cultured in Macconkey agar selective medium was Gram-negative, rod shaped and a gas former; the ATB-system gave 99.9% agreement for the identification of Aeromonas hydrophila to the species level. The isolate found in Pseudomonas isolation agar was Gram-negative, rod shaped, cytochrome oxidase-positive, a reducer of nitrates to nitrogen, and pyocyanin producer; the ATB-system gave 99.9 % agreement for the identification of Pseudomonas aeruginosa to the species level. These results indicate that the three bacteria species present in the soybean sprouts were Bacillus cereus, Aero-monas hydrophila, and Pseudomonas aeruginosa. Salmonella spp., Escherichia coli O157:H7, and Yersinia enter-ocolitica, which are associated with serious disease in humans, were not isolated from soybean sprouts examined in this study.

• 한국정보통신학회논문지
• /
• 제6권2호
• /
• pp.207-213
• /
• 2002

지문은 개인마다 서로 다르고 평생 변하지 않는 특성이 있다. 그리고 식별 성능에 대한 신뢰도와 보안성이 높아 여러 생체인식분야에 보편적으로 적용되고 있으며 본인임을 인증할 수 있는 가장 우수 한 방법으로 주목받고 있다 본 논문에서는 현재 빠른 속도로 발전하고 대중화되어 가고 있는 인터넷에 기반한 전자상거래, 인터넷뱅킹, 주식거래, 쇼핑몰 등의 서비스 이용시 본인인증의 신뢰도를 높이기 위해 웹 사이트 로그인에 개인 지문인증을 적용한다. 본 논문에서 구현한 지문인증을 이용한 웹 사이트 로그인 시스템은 지문인증을 위한 임베디드 모듈, 웹 서버, 그리고 웹 사이트로 구성된다. 본 논문에서는 지문인증을 웹 서버에서 수행하는 기존 시스템과는 달리 클라이언트 측에서 지문인증을 수행함으로써 서버의 부하를 줄일 수 있게 하였다. 그리고 지문인증의 성공 없이는 웹 사이트 로그인을 차단함으로써 본인인증이 필요한 인터넷 서비스의 신뢰도를 높이 수 있을 것이다.