• Title/Summary/Keyword: PNG

Search Result 80, Processing Time 0.024 seconds

The Effect of Type of Input Image on Accuracy in Classification Using Convolutional Neural Network Model (컨볼루션 신경망 모델을 이용한 분류에서 입력 영상의 종류가 정확도에 미치는 영향)

  • Kim, Min Jeong;Kim, Jung Hun;Park, Ji Eun;Jeong, Woo Yeon;Lee, Jong Min
    • Journal of Biomedical Engineering Research
    • /
    • v.42 no.4
    • /
    • pp.167-174
    • /
    • 2021
  • The purpose of this study is to classify TIFF images, PNG images, and JPEG images using deep learning, and to compare the accuracy by verifying the classification performance. The TIFF, PNG, and JPEG images converted from chest X-ray DICOM images were applied to five deep neural network models performed in image recognition and classification to compare classification performance. The data consisted of a total of 4,000 X-ray images, which were converted from DICOM images into 16-bit TIFF images and 8-bit PNG and JPEG images. The learning models are CNN models - VGG16, ResNet50, InceptionV3, DenseNet121, and EfficientNetB0. The accuracy of the five convolutional neural network models of TIFF images is 99.86%, 99.86%, 99.99%, 100%, and 99.89%. The accuracy of PNG images is 99.88%, 100%, 99.97%, 99.87%, and 100%. The accuracy of JPEG images is 100%, 100%, 99.96%, 99.89%, and 100%. Validation of classification performance using test data showed 100% in accuracy, precision, recall and F1 score. Our classification results show that when DICOM images are converted to TIFF, PNG, and JPEG images and learned through preprocessing, the learning works well in all formats. In medical imaging research using deep learning, the classification performance is not affected by converting DICOM images into any format.

A Dynamic Analysis of Import Price of Roundwood (원목수입가격(原木輸入價格)의 동태적(動態的) 분석(分析))

  • Han, Sang-Yoel;Kim, Tae-Kyun;Cho, Jae-Hwan;Choi, Kwan
    • Journal of Korean Society of Forest Science
    • /
    • v.88 no.1
    • /
    • pp.1-10
    • /
    • 1999
  • The dynamic relationships among import prices of roundwood are analyzed using the time series approach. A vector autoregression(VAR) model is estimated for six import prices(New Zealand, Chile, Russia, U.S.A., PNG, and Malaysia). Then Granger's causality test, variance decomposition analysis, and impulse response function analysis are also conducted. The major results are summarized as follows : (1) The prices of New Zealand and Russia are caused by only own lagged prices. (2) The prices of Chile and PNG are effected by New Zealand, the price of PNG is effected by New Zealand and Russia, and the price of U.S.A. is effected by those of Chile and PNG, respectively. (3) An exogenous shock in New Zealand will affect the prices of New Zealand, PNG, U.S.A., Chile, Russia. (4) An exogenous shock in Chile may also affect the prices of Chile, U.S.A., Russia.

  • PDF

The Recent Trend on Oil and Gas Industry in Canada (캐나다 오일, 가스 산업 최신 동향 분석)

  • Seo, Hyeogjun;Moon, Bryan;Kwon, Sunil
    • Journal of the Korean Institute of Gas
    • /
    • v.21 no.2
    • /
    • pp.10-19
    • /
    • 2017
  • This paper presents the status and characteristics of oil and gas industry and the guideline for investment of producing asset or petroleum and natural gas rights(PNG rights) in Canada. The Western Canadian Sedimentary Basin(WSCB) consists of around 11 main formations, and petroleum has actively been produced at the Montney, Cardium, Viking and Bakken formation. However, the drilling activity declined to 1,917 in Q1, 2016 from 5,724 in Q1, 2014 and 3,365 in Q1, 2015 which dropped 67% and 43% respectively because of the low oil price since 2014. Also, the price of oil and gas asset decreased 34~47% on reserves and production base, and the PNG rights for development decreased 81~97% based on total bidding price, bidding area and unit bidding price. Therefore, it is very favorable environment for Korean companies entering into the Canadian petroleum business especially in PNG rights acquisition which needs smaller investment compare to asset acquisition and shows sharpest value depreciation.

Analysis on Optimality of Proportional Navigation Based on Nonlinear Formulation (비선형 운동방정식에 근거한 비례항법유도의 최적성에 관한 해석)

  • Jeon, In-Soo;Lee, Jin-Ik
    • Journal of the Korean Society for Aeronautical & Space Sciences
    • /
    • v.37 no.4
    • /
    • pp.367-371
    • /
    • 2009
  • Analysis on optimality of the proportional navigation guidance(PNG) law is presented in this paper. While most of previous studies on optimality of PNG were relied on the linear formulation, this paper is based on the nonlinear formulation. The analysis shows that PNG is an optimal solution minimizing a range-weighted control energy, where the weighting function is an inverse of $\alpha$ power of the distance-to-target. We show that the navigation constant N is related to $\alpha$ directly. And also the conditions required to ensure the analysis result are investigated.

Tiled Image Compression Method to Reduce the Amount of Memory Needed for Image Processing in Mobile Devices (모바일 단말기에서 이미지 처리에 필요한 메모리 사용량을 줄이기 위한 타일화 이미지 압축 기법)

  • Oh, Hwang-Seok
    • Journal of Korea Game Society
    • /
    • v.13 no.6
    • /
    • pp.35-42
    • /
    • 2013
  • A new compressed image format is proposed to use a large size of image in mobile games without the constraints of hardware specifications such as memory amount, processing power, which encodes each block of a large size image in scan line order. Using the experiments, we show the effectiveness of proposed method compared with a general PNG in terms of compression ratios and required memory in decoding processes. Also, the loading delay can be reduced by decoding only the displaying area of a large image in run-time.

Target Adaptive Guidance Using Near-Zone Information from IR Seeker (근접영역에서의 IR 탐색기 정보를 이용한 표적적응유도)

  • 엄태윤;김필성
    • Journal of the Korea Institute of Military Science and Technology
    • /
    • v.5 no.3
    • /
    • pp.113-119
    • /
    • 2002
  • A target adaptive guidance(TAG) algorithm is proposed employing the near-zone signal that can be measured from an infrared seeker. The guidance order is composed of a conventional PNG command and an additional command to be calculable from an additional LOS rate between a hot point of target and a required intercept point. The characteristic of the near-zone signal is similar to that of LOS rate that is inversely proportional to the square of time-to-go. Hence the proposed scheme can be applied to real systems with no estimator for time-to-go. From analysis results on the miss distance with perfect missile and perfect seeker, it follows that the proposed TAG algorithm guarantees missile to be ideally guided to the required intercept point. And it is less affected by the TAG start time and a proportional navigation ratio than other TAG schemes using a LOS rate such as a step bias or a ramp bias.

Time-varying biased proportional navigation for terminal guidance with impact attitude angle constraint (충돌 자세각 제한조건을 갖는 종단 유도를 위한 시변 편향 비례항법)

  • 김병수;이보형;이장규;김삼수;조현진
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 1996.10b
    • /
    • pp.355-358
    • /
    • 1996
  • The primary objective of guidance system is to generate suitable commands so that the pursuer comes closer to its target. It is necessary, however, in the guidance of a certain pursuer that the attitude angle at impact should be within a prescribed range in addition to specification on the miss distance. These guidance requirements can not be satisfied by the general guidance laws developed for miss distance minimization. Compared with the demand in many applications, the guidance laws dealing with impact attitude angle constraint are not easily found. In this paper, biased PNG laws are proposed to obtain the guidance purposes. By Lyapunov method, it is shown that the pursuer can intercept the target with a prescribed attitude angle under the assumption that the pursuer is sufficiently fast and the target maneuver is negligible. The simulation results are presented to demonstrate the performance of the suggested guidance laws.

  • PDF

Constraining primordial non-Gaussianity with the 3-point correlation function of the SDSS-IV eBOSS DR14 quasar sample

  • Choi, Peter D.;Rossi, Graziano;Slepian, Zachary;Eisenstein, Daniel;Ho, Shirley;Schlegel, David
    • The Bulletin of The Korean Astronomical Society
    • /
    • v.42 no.1
    • /
    • pp.53.3-53.3
    • /
    • 2017
  • While quasars are sparse in number density, they reside at relatively high-redshift as compared to galaxies. Hence, they are likely to be less non-linearly evolved than the galaxy population, and thus have a distribution that more closely mirrors the primordial density field. Therefore, they offer an intriguing opportunity to search for primordial non-Gaussianity (PNG). To this end, the 3-point correlation function (3PCF) is an excellent statistical tool to detect departures from Gaussianity, vanishing for a Gaussian field. In this work, we will make the first-ever measurement of the large-scale quasar 3PCF from the SDSS-IV DR14 quasar sample (spanning the largest volume to-date) to place constraints on PNG through the usual f_NL-type parametrization. This work will use the order N^2-time 3PCF algorithm of Slepian & Eisenstein (2015), with N the number of objects.

  • PDF

Characteristics, Mass Transfer Coefficient and Effectiveness Factor of $\beta$-glucosidase Immobilized on the Diazotized Chitin in Bioreactors (Diazotized Chitin에 고정된 $\beta$-glucosidase의 생물반응기에서의 특성, 물질전달계수 및 효율인자에 관한 연구)

  • 김종덕;이경희;서석수
    • Journal of the Korean Society of Food Science and Nutrition
    • /
    • v.20 no.5
    • /
    • pp.494-502
    • /
    • 1991
  • Diazotized chitin(CHITN) as supports of immobilized enzyme, which was obtained by alkaline hydrolysed chitin with NaN3 and HCI was employed to produce CHITN-Gase with glutaraldehyde as bifunctional reagent. Activities of CHITN-Gase were determined with reaction of p-nitro-pheol-$\beta$-D-glucopyranoside(PNG) in plug flow reactor as a reference of CHITA-Gase. Their optimum temperature, pH, Km and Vmax, mass transfer coefficient (h), effctiveness factor(η)were plotted with variation of flow rate and H/D. Mass transfer coefficient(h) of those enzymes increased because of their flux, as flow rates were increased and controlled by reaction rate. Effectiveness factor(η) of both enzymes were nearly 1.0.

  • PDF