• 한국자동차공학회논문집
• /
• 제20권5호
• /
• pp.44-52
• /
• 2012

Fuel cell electric vehicles have some noise problems due to its air processing unit which is required to feed the ambient air into the fuel cell stack. Discrete-frequency noises are radiated from a centrifugal blower due to rotor-stator interaction. Their fundamental frequency is the blade passing frequency, which is determined by the number of rotor blades and their rotating speed. To reduce such noises, multi-chamber perforated muffler has been designed. In this paper, in order to improve the transmission loss of a perforated muffler, the relationship between the impedance model of a perforated hole and its noise reduction performance is studied, and the applicability of a short-length perforated muffler to air processing unit of fuel cell system is described using acoustic simulation results and experimental data. The acoustic velocity vector across the neck of a perforated hole is very important design factor to optimize the transmission of an intake muffler. The suggested short-length perforated muffler is effective on discrete-frequency noises while keeping the volume of intake muffler minimized.

• 융합신호처리학회논문지
• /
• 제5권4호
• /
• pp.263-270
• /
• 2004

최근 웨이블릿 변환은 많은 분야에서 다양하게 적용된다. 본 논문에서 tasks뇌파의 중요한 몇가지 특성파 검출을 위한 다비치 웨이블릿은 뇌파분석에 필요하다. 우리가 제안한 시스템은 다른 방법보다는 특성파 검출에 높은 성능을 가졌다. 본 연구의 뉴럴시스템의 구조는 하나의 은닉층과 3계층 피드포워드층은 오류 BP 학습알고리즘을 적용하였다. 4명의 피험자에게 알고리즘을 적용하여 92% 분류율을 보였다. 제안된 시스템은 웨이블릿과 신경망으로 tasks 뇌파의 보다 정확하게 분석함을 보였다. 모의실험결과 tasks 뇌파는 의사의 노동력을 줄일수 있고 정량적 해석이 가능함을 보였다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2016년도 춘계학술발표대회
• /
• pp.633-635
• /
• 2016

Convolutional Networks (ConvNets) are powerful models that learn hierarchies of visual features, which could also be used to obtain image representations for transfer learning. The basic pipeline for transfer learning is to first train a ConvNet on a large dataset (source task) and then use feed-forward units activation of the trained ConvNet as image representation for smaller datasets (target task). Our key contribution is to demonstrate superior performance of multiple ConvNet layer features over single ConvNet layer features. Combining multiple ConvNet layer features will result in more complex feature space with some features being repetitive. This requires some form of feature selection. We use AdaBoost with single stumps to implicitly select only distinct features that are useful towards classification from concatenated ConvNet features. Experimental results show that using multiple ConvNet layer activation features instead of single ConvNet layer features consistently will produce superior performance. Improvements becomes significant as we increase the distance between source task and the target task.

• Journal of International Society for Simulation Surgery
• /
• 제3권1호
• /
• pp.1-8
• /
• 2016

In the field of Radiology, the Computer Aided Diagnosis is the technology which gives valuable information for surgical purpose. For its importance, several computer vison methods are processed to obtain useful information of images acquired from the imaging devices such as X-ray, Magnetic Resonance Imaging (MRI) and Computed Tomography (CT). These methods, called pattern recognition, extract features from images and feed them to some machine learning algorithm to find out meaningful patterns. Then the learned machine is then used for exploring patterns from unseen images. The radiologist can therefore easily find the information used for surgical planning or diagnosis of a patient through the Computer Aided Diagnosis. In this paper, we present a review on three widely-used methods applied to Computer Aided Diagnosis. The first one is the image processing methods which enhance meaningful information such as edge and remove the noise. Based on the improved image quality, we explain the second method called segmentation which separates the image into a set of regions. The separated regions such as bone, tissue, organs are then delivered to machine learning algorithms to extract representative information. We expect that this paper gives readers basic knowledges of the Computer Aided Diagnosis and intuition about computer vision methods applied in this area.

• 한국표면공학회지
• /
• 제50권6호
• /
• pp.460-464
• /
• 2017

As increasing thermal efficiency of the gas turbine, the performance improvement of thermal barrier coatings is also becoming important. Ytrria stabilized zirconia(YSZ) is the most popular materials for ceramic top coating because of its low thermal conductivity. In order to enhance the performance of thermal barrier coatings for hot sections in the gas turbine, suspension plasma spraying was developed in order to feed nano-sized powders. YSZ coatings formed by suspension plasma spraying showed better performance than YSZ coatings due to its exclusive microstructure. In this research, two YSZ coatings were deposited by suspension vacuum plasma spraying at 400 mbar and 250 mbar. Microstructures of YSZ coatings were analyzed by scanning electron image(SEM) on each spraying conditions, respectively. Crystalline structure transformation was not detected by X-ray diffraction. Thermal conductivity of suspension vacuum plasma sprayed YSZ coatings were measured by laser flash analysis. Thermal conductivity of suspension vacuum plasma sprayed YSZ coatings containing horizontally oriented nano-sized pores and vertical cracks showed $0.6-1.0W/m{\cdot}K$, similar to thermal conductivity of YSZ coatings formed by atmospheric plasma spraying.

• 융합신호처리학회논문지
• /
• 제3권4호
• /
• pp.49-56
• /
• 2002

본 논문에서는 기존의 PDFF 제어기에 비선형 보상기를 적용한 위치제어에 대하여 기술한다. 이 방법은 기존의 방법보다 주어진 사양을 쉽게 만족시킬 수 있다 제어기 설계에 있어서 위상 여유와 대역폭을 동시에 조절할 수 있는 개선된 PDFF 제어기를 제시한다. PDFF 제어기의 전향 보상항을 비선형 보상기(CDIDF 제어기)로 치환함으로서 폐루프시스템의 대역폭을 감소시키지 않으면서 원하는 위상여유를 얻는 것이다. 제시된 방법은 시뮬레이션과 실험을 통하여 확인된다 시뮬레이션 및 실험결과에 따라 CDIDF 제어기를 사용한 개선된 PDFF 시스템에서는 제어기의 파라미터를 적절히 설정함으로서 전반적인 설계사양을 만족시키는 것이 확인된다.

• Journal of Information Processing Systems
• /
• 제13권4호
• /
• pp.703-715
• /
• 2017

Mammogram images are sensitive in nature and even a minor change in the environment affects the quality of the images. Due to the lack of expert radiologists, it is difficult to interpret the mammogram images. In this paper an algorithm is proposed for a computer-aided diagnosis system, which is based on the wavelet based adaptive sigmoid function. The cascade feed-forward back propagation technique has been used for training and testing purposes. Due to the poor contrast in digital mammogram images it is difficult to process the images directly. Thus, the images were first processed using the wavelet based adaptive sigmoid function and then the suspicious regions were selected to extract the features. A combination of texture features and gray-level co-occurrence matrix features were extracted and used for training and testing purposes. The system was trained with 150 images, while a total 100 mammogram images were used for testing. A classification accuracy of more than 95% was obtained with our proposed method.

• 융합신호처리학회논문지
• /
• 제18권1호
• /
• pp.25-30
• /
• 2017

현재 곡물선별기는 대부분 CCD 광학카메라를 이용하여 불량품을 찾아내고 있다. 본 논문에서는 CCD 카메라를 이용함과 동시에 근거리적외선 센서의 수분측정 방법을 추가하여 곡물선별기의 선별력향상을 목표로 한다. 그리고 구현한 알고리즘을 곡물선별기에 실제로 적용할 수 있도록 근거리적외선 영상보드 시스템을 개발하여, 원료의 내부 수분 함량을 고속으로 체크하여 일정함량 미달인 경우 불량으로 간주하여, 불량품을 실시간으로 제거하는 곡물선별기 시스템을 개발하고자 한다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 추계학술발표대회
• /
• pp.315-318
• /
• 2020

반려동물을 키우는 사람들 중 1인 가구 증가로 인하여 주인의 부재 시 반려동물에게 배식하는데 어려움이 있어 자동급식기가 고안되었다. 본 논문에서는 아두이노 플랫폼을 이용한 사료 배급뿐만 아니라 약 배급 기능을 갖춘 IoT 약, 사료 혼합 자동급식기를 제안한다. 제안한 지동급식기에서는 사용자가 웹사이트를 통해 급식 서비스에 접근할 수 있고, 두 재료의 혼합 자동 배식 시스템을 통하여 편리하며 확장된 배식 기능을 경험 할 것 이라고 기대된다.

• 한국섬유공학회:학술대회논문집
• /
• 한국섬유공학회 2003년도 봄 학술발표회 논문집
• /
• pp.402-403
• /
• 2003

Garment manufacture represents the final stage of processing a finished fabric. The main task of the garment manufacturer is to produce shell structures out of flat fabrics to match the shape of the human body, and the most acceptable means of joining textile materials for apparel use is by sewing. On the sewing process, the bottom layer is pushed forward by the feed-dog, but the presser foot tends to retard the passage of the top layer. Since the friction between the layers is low, is possible that the components will move out of phase and pucker. (omitted)