• 제목/요약/키워드: 자동화 실험

검색결과 948건 처리시간 0.029초

Speech Recognition of the Korean Vowel 'ㅡ' based on Neural Network Learning of Bulk Indicators (벌크 지표의 신경망 학습에 기반한 한국어 모음 'ㅡ'의 음성 인식)

  • Lee, Jae Won
    • KIISE Transactions on Computing Practices
    • /
    • 제23권11호
    • /
    • pp.617-624
    • /
    • 2017
  • Speech recognition is now one of the most widely used technologies in HCI. Many applications where speech recognition may be used (such as home automation, automatic speech translation, and car navigation) are now under active development. In addition, the demand for speech recognition systems in mobile environments is rapidly increasing. This paper is intended to present a method for instant recognition of the Korean vowel 'ㅡ', as a part of a Korean speech recognition system. The proposed method uses bulk indicators (which are calculated in the time domain) instead of the frequency domain and consequently, the computational cost for the recognition can be reduced. The bulk indicators representing predominant sequence patterns of the vowel 'ㅡ' are learned by neural networks and final recognition decisions are made by those trained neural networks. The results of the experiment show that the proposed method can achieve 88.7% recognition accuracy, and recognition speed of 0.74 msec per syllable.

Leather's Environment-friendly Adhesion Surface Treatment of shoe's material by Plasma (플라즈마를 이용한 신발소재의 환경 친화적인 접착 표면 처리(I))

  • Ha, Soon-Hee;Jang, U-Jin;Seul, Soo-Duk
    • Journal of Adhesion and Interface
    • /
    • 제6권2호
    • /
    • pp.6-12
    • /
    • 2005
  • The plasma generally, ionized gas state, is the 4th material state composed the universe. Generating the plasma artificially has been studied by spending energy and it has a lot of applications in human's life. There are several merits to modify the surface of polymer using plasma. Above all, plasma maintains the property of polymer because of it changes the property of surface only. Also, it doesn't use a organic solvent and it is the environment friendship because of there are no waste under processing. Furthemore, in case of high-pressure plasma, it is possible that automated-processing continuously. In this study, we tried the reforming of surface to rise the adhesive strength between the material of polymer, experimented the rising of adhesive strength through a experiment of peel strength by virtue of processing time and using gas, confirmed the change of polymer's surface through measuring the surface contact angle analyzer and scanning electron microscopy (SEM).

  • PDF

Extracting Supporting Evidence with High Precision via Bi-LSTM Network (양방향 장단기 메모리 네트워크를 활용한 높은 정밀도의 지지 근거 추출)

  • Park, ChaeHun;Yang, Wonsuk;Park, Jong C.
    • Annual Conference on Human and Language Technology
    • /
    • 한국정보과학회언어공학연구회 2018년도 제30회 한글 및 한국어 정보처리 학술대회
    • /
    • pp.285-290
    • /
    • 2018
  • 논지가 높은 설득력을 갖기 위해서는 충분한 지지 근거가 필요하다. 논지 내의 주장을 논리적으로 지지할 수 있는 근거 자료 추출의 자동화는 자동 토론 시스템, 정책 투표에 대한 의사 결정 보조 등 여러 어플리케이션의 개발 및 상용화를 위해 필수적으로 해결되어야 한다. 하지만 웹문서로부터 지지 근거를 추출하는 시스템을 위해서는 다음과 같은 두 가지 연구가 선행되어야 하고, 이는 높은 성능의 시스템 구현을 어렵게 한다: 1) 논지의 주제와 직접적인 관련성은 낮지만 지지 근거로 사용될 수 있는 정보를 확보하기 위한 넓은 검색 범위, 2) 수집한 정보 내에서 논지의 주장을 명확하게 지지할 수 있는 근거를 식별할 수 있는 인지 능력. 본 연구는 높은 정밀도와 확장 가능성을 가진 지지 근거 추출을 위해 다음과 같은 단계적 지지 근거 추출 시스템을 제안한다: 1) TF-IDF 유사도 기반 관련 문서 선별, 2) 의미적 유사도를 통한 지지 근거 1차 추출, 3) 신경망 분류기를 통한 지지 근거 2차 추출. 제안하는 시스템의 유효성을 검증하기 위해 사설 4008개 내의 주장에 대해 웹 상에 있는 845675개의 뉴스에서 지지 근거를 추출하는 실험을 수행하였다. 주장과 지지 근거를 주석한 정보에 대하여 성능 평가를 진행한 결과 본 연구에서 제안한 단계적 시스템은 1,2차 추출 과정에서 각각 0.41, 0.70의 정밀도를 보였다. 이후 시스템이 추출한 지지 근거를 분석하여, 논지에 대한 적절한 이해를 바탕으로 한 지지 근거 추출이 가능하다는 것을 확인하였다.

  • PDF

Highway Incident Detection and Classification Algorithms using Multi-Channel CCTV (다채널 CCTV를 이용한 고속도로 돌발상황 검지 및 분류 알고리즘)

  • Jang, Hyeok;Hwang, Tae-Hyun;Yang, Hun-Jun;Jeong, Dong-Seok
    • Journal of the Institute of Electronics and Information Engineers
    • /
    • 제51권2호
    • /
    • pp.23-29
    • /
    • 2014
  • The advanced traffic management system of intelligent transport systems automates the related traffic tasks such as vehicle speed, traffic volume and traffic incidents through the improved infrastructures like high definition cameras, high-performance radar sensors. For the safety of road users, especially, the automated incident detection and secondary accident prevention system is required. Normally, CCTV based image object detection and radar based object detection is used in this system. In this paper, we proposed the algorithm for real time highway incident detection system using multi surveillance cameras to mosaic video and track accurately the moving object that taken from different angles by background modeling. We confirmed through experiments that the video detection can supplement the short-range shaded area and the long-range detection limit of radar. In addition, the video detection has better classification features in daytime detection excluding the bad weather condition.

A Similar Price Zone Determination of Public Land Price Using a Hybrid Clustering Technique (평균연결법과 K-means 혼합클러스터링 기법을 이용한 공시지가 유사가격권역의 설정)

  • Yi Seong-Kyu;Park Soo-Hong;Hong Sung-Eon
    • Journal of the Korean Geographical Society
    • /
    • 제41권1호
    • /
    • pp.121-135
    • /
    • 2006
  • Even though the similar land price zone is very important element in the public land appraisal procedure, the concept is implicitly described and applied into the actual land appraisal system. This situation makes it worse when applying for the automatic selection of a comparative standard land parcel. In addition, the division of similar land price zones requires the objective and reasonable process for improving ALPAS(Automatic land Price Appraisal System), which becomes an issue today. To solve the similar land price zone determination problem that is caused by the lack of objective numerical standard, this study proposed a similar land price zone determination method using a hybrid clustering technique. Results showed that this hybrid clustering method that applied into the test area could easily detect similar land price zones with considerable accuracy levels, which are verified with some test statistics and real comparative standard land parcels done by manually.

Sliding-Mode Control of Container Cranes (컨테이너크레인 시스템의 슬라이딩모드제어)

  • Lee Suk-Jae;Park Hahn;Hong Keum-Shik
    • Journal of Navigation and Port Research
    • /
    • 제29권8호
    • /
    • pp.747-753
    • /
    • 2005
  • In this paper, as an anti-sway control strategy of container cranes, we investigate a variable structure control in which the moving load follows a given trajectory, whereas both the trolley and hoist controllers achieve their positioning problems. It is crucial, in an automated container terminal, that collisions should be avoided during the transference of containers from one place to another. It is also necessary, in the case of a quay crane, to select suitable loading and unloading trajectories of containers, so that possible collisions with surrounding obstacles are avoided. After a brief introduction of the mathematical model, a robust control scheme (i.e., a second-order sliding mode control that guarantees a fast and precise transference and a suppression of the resulted swing) is presented. Despite model uncertainties and unmodeled actuators dynamics, the swing suppression from the given trajectory is obtained by constraining the system motion on suitable sliding surfaces, which include both the desired path and the swing angle. The proposed controller has been tested with a laboratory-size pilot crane. Experimental results are provided.

An Iris Detection Algorithm for Disease Prediction based Iridology (홍채학기반이 질병예측을 위한 홍채인식 알고리즘)

  • Cho, Young-bok;Woo, Sung-Hee;Lee, Sang-Ho
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • 제21권1호
    • /
    • pp.107-114
    • /
    • 2017
  • Iris diagnosis is an alternative medicine to diagnose the disease of the patient by using different of the iris pattern, color and other characteristics. This paper proposed a disease prediction algorithm that using the iris regions that analyze iris change to using differential image of iris image. this method utilize as patient's health examination according to iris change. Because most of previous studies only find a sign pattern in a iris image, it's not enough to be used for a iris diagnosis system. We're developed an iris diagnosis system based on a iris images processing approach, It's presents the extraction algorithms of 8 major iris signs and correction manually for improving the accuracy of analysis. As a result, PNSR of applied edge detection image is about 132, and pattern matching area recognition presented practical use possibility by automatic diagnostic that presume situation of human body by iris about 91%.

Efficient Technology Mapping of FPGA Circuits Using Fuzzy Logic Technique (퍼지이론을 이용한 FPGA회로의 효율적인 테크놀로지 매핑)

  • Lee, Jun-Yong;Park, Do-Soon
    • The Transactions of the Korea Information Processing Society
    • /
    • 제7권8호
    • /
    • pp.2528-2535
    • /
    • 2000
  • Technology mapping is a part of VLSI CAD system, where circuits in logical level are mapped into circuits in physical level. The performance of technology mapping system is evaluatecJ by the delay and area of the resulting circuits. In the sequential circuits, the delay of the circuit is decided by the maximal delay between registers. In this work, we introduce an FPGA mapping algorithm improved by retiming technique used in constructive level and iterative level, and by fuzzy logic technique. Initial circuit is mapped into an FPGA circuit by constructive manner and improved by iterative retiming. Criteria given to the initial circuit are structured hierarchically by decision-making functions of fuzzy logic. The proposed system shows better results than previous systems by the experiments with MCNC benchmarkers.

  • PDF

Development of nuclear measurement system for gamma column scanning (증류탑 진단을 위한 방사선 응용계측기 개발)

  • Kim, Jong-Bum;Jung, Sung-Hee;Jin, Jun-Ha;Jun, Jong-Kuj
    • Proceedings of the KIEE Conference
    • /
    • 대한전기학회 2004년도 하계학술대회 논문집 D
    • /
    • pp.2619-2621
    • /
    • 2004
  • 감마선 또는 x-선 등 방사선을 이용한 구조물 진단은 산업전반에 걸쳐 널리 이용되고 있다. 기존의 x-선이나 Ir-192의 감마선 등을 이용한 비파괴검사는 용접부의 확인이나 구조물의 내부 결점 확인과 같이 국부적인 진단에는 유용하나 석유화학산업에서 반응물의 분리 또는 정제 등에 많이 사용되고 있는 증류탑의 내부진단 실험에는 적합하지 않다. 증류탑은 목적에 따라 직경이 $3{\sim}10m$, 높이 $10{\sim}100m$에 달하는 대형 장치로서 내부의 이상현상에 대한 정확한 진단은 공정 전체의 가동효율 최적화에 결정적인 영향을 끼친다. 밀봉 감마선원으로부터 방출된 방사선의 투과율 변화를 증류탑의 반대편에 설치한 방사선 검출기로 측정하여 수직밀도분포(vertical density profile)를 구하여 증류탑의 내부현상에 대한 정확한 정보를 얻을 수 있는데 이러한 작업을 자동으로 수행할 수 있도록 한 것이 자동 증류탑 검사장치이다. 증류탑 진단장치는 크게 방사선 계측 및 데이터 전송회로, 방사선원부와 방사선검출부의 구동장치 및 구동회로, 데이터 수집 및 제어장치 둥으로 구성되어 있으며, 증류탑 검사를 자동화하여 진단결과의 신뢰도와 재현성을 향상시켰다. 본 논문은 방사선원과 방사선 검출장치의 위치를 자동으로 제어하면서 방사선 계측결과를 전송시키는 장치의 개발에 관한 내용으로서 개발된 장치의 소개와 산업현장 적용의 예를 소개함으로써 기존의 비파괴검사기술로는 진단할 수 없는 대형 증류탑의 진단에 효과적인 방사선 응용 계측장치임을 보이고자 한다.

  • PDF

Development of Dental Light Robotic System using Image Processing Technology (영상처리 기술을 이용한 치과용 로봇 조명장치의 개발)

  • Moon, Hyun-Il;Kim, Myoung-Nam;Lee, Kyu-Bok
    • Journal of Dental Rehabilitation and Applied Science
    • /
    • 제26권3호
    • /
    • pp.285-296
    • /
    • 2010
  • Robot-assisted illuminating equipment based on image-processing technology was developed and then its accuracy was measured. The current system was designed to detect facial appearance using a camera and to illuminate it using a robot-assisted system. It was composed of a motion control component, a light control component and an image-processing component. Images were captured with a camera and following their acquisition the images that showed motion change were extracted in accordance with the Adaboost algorithm. Following the detection experiment for the oral cavity of patients based on image-processing technology, a higher degree of the facial recognition was obtained from the frontal view and the light robot arm was stably controlled.