• 제목/요약/키워드: LU10

검색결과 1,968건 처리시간 0.028초

의미적 손실 함수를 통한 Cycle GAN 성능 개선 (Improved Cycle GAN Performance By Considering Semantic Loss)

  • 정태영;이현식;엄예림;박경수;신유림;문재현
    • 한국정보처리학회:학술대회논문집
    • /
    • 한국정보처리학회 2023년도 추계학술발표대회
    • /
    • pp.908-909
    • /
    • 2023
  • Recently, several generative models have emerged and are being used in various industries. Among them, Cycle GAN is still used in various fields such as style transfer, medical care and autonomous driving. In this paper, we propose two methods to improve the performance of these Cycle GAN model. The ReLU activation function previously used in the generator was changed to Leaky ReLU. And a new loss function is proposed that considers the semantic level rather than focusing only on the pixel level through the VGG feature extractor. The proposed model showed quality improvement on the test set in the art domain, and it can be expected to be applied to other domains in the future to improve performance.

Automatic Detection of Dead Trees Based on Lightweight YOLOv4 and UAV Imagery

  • Yuanhang Jin;Maolin Xu;Jiayuan Zheng
    • Journal of Information Processing Systems
    • /
    • 제19권5호
    • /
    • pp.614-630
    • /
    • 2023
  • Dead trees significantly impact forest production and the ecological environment and pose constraints to the sustainable development of forests. A lightweight YOLOv4 dead tree detection algorithm based on unmanned aerial vehicle images is proposed to address current limitations in dead tree detection that rely mainly on inefficient, unsafe and easy-to-miss manual inspections. An improved logarithmic transformation method was developed in data pre-processing to display tree features in the shadows. For the model structure, the original CSPDarkNet-53 backbone feature extraction network was replaced by MobileNetV3. Some of the standard convolutional blocks in the original extraction network were replaced by depthwise separable convolution blocks. The new ReLU6 activation function replaced the original LeakyReLU activation function to make the network more robust for low-precision computations. The K-means++ clustering method was also integrated to generate anchor boxes that are more suitable for the dataset. The experimental results show that the improved algorithm achieved an accuracy of 97.33%, higher than other methods. The detection speed of the proposed approach is higher than that of YOLOv4, improving the efficiency and accuracy of the detection process.

Structure of Chloro bis(1,10-phenanthroline)Cobalt(II) Complex, [Co(phen)2(Cl)(H2O)]Cl·2H2O

  • Pu Su Zhao;Lu De Lu;Fang Fang Jian
    • 대한화학회지
    • /
    • 제47권4호
    • /
    • pp.334-338
    • /
    • 2003
  • $[Co(phen)_2(Cl)(H_2O)] Clㆍ2H_2O$(phen=1,10-phenanthroline)의 결정구조는 X-ray에 의하여 결정되었다. 그 결정은 a=9.662(2), b=11.445(1), c=13.037(2)${\AA}$ ${\alpha}$=64.02(1), ${\beta}$=86.364(9), ${\gamma}=78.58(2)^°$ 그리고 Z=2의 격자인자를 갖는 triclinic계와 space group이 P1의 구조로 결정화 되었다. 배위된 양이온은 두개의 Phen 리간드, 하나의 chloride이온과 하나의 $H_2O$ 리간드가 cis 배열로 킬레이크된 6배위 코발트 원자가 포함된다. 코발트에 배위된 chloride에 더해서, 결정구조를 이루는 하나의 chloride이온과 네개의 물분자가 있다. 고체상태에서, 제목의 화합물은 수소결합을 통하여 3차원 그물구조를 갖는다.

근위축성 측삭 경화증 환자 1례를 대상으로 한 사암침법의 효과 (Effects of Sa-am Acupuncture Treatment on a ALS(Amyotrophic Lateral Sclerosis) Patient)

  • 이상미;김성하;정호현;박만용;이정주;박옥주;임진영;김동웅;송봉근;김성철
    • Journal of Acupuncture Research
    • /
    • 제29권5호
    • /
    • pp.187-195
    • /
    • 2012
  • Objectives : Amyotrophic lateral sclerosis(ALS) is a progressive and incurable disease that causes degeneration of the motor neurons of the brain stem and spinal cord. The purpose of this study was to report the effectiveness of Sa-am acupuncture treatment on ALS patient. Methods : Following the stabilization period, a ALS patient respiratory figures(Et $C_{O2}$, Sp $_{O2}$, RR, pulse) were measured by using capnography & pulse oximetry for 30 minutes before acupuncture treatment. Acupuncture treatment such as lung tonification($SP_3(+){\cdot}LU_9(+){\cdot}HT_8(-){\cdot}LU_{10}(-)$), heart tonification($HT_9(+){\cdot}LR_1(+){\cdot}SI_8(-){\cdot}KI_{10}(-)$), liver tonification ($KI_{10}(+){\cdot}LR_8(+){\cdot}LU_8(-){\cdot}LR_4(-)$) were conducted for 5 days. Each Sa-am acupuncture treatment conducted at AM 7 : 00, AM 11 : 00, PM 4 : 30 of the day. During acupuncture treatment, the patient respiratory figures were measured equally for 30 minutes. The patient was treated by using Dong-bang acupuncture needles($0.30{\times}4.0$) and also stimulated using infra red. Results : The value of Et $C_{O2}$ has decreased more after Sa-am acupuncture lung tonification treatment than others. The value of pulse has decreased more after Sa-am acupuncture heart tonification treatment than others. The value of raspiration rate has decreased more after Sa-am acupuncture liver tonification treatment than others. And the value of Sp $O_2$ has increased more after Sa-am acupuncture liver tonification treatment than others. Conclusions : Although this study was subject to a few limitations, but it shows that Sa-am acupuncture treatment for ALS patients has a meaningful effect. This study needs to be developed further using a larger sample size to obtain more valuable and meaningful data.

Optimization of Dual Layer Phoswich Detector for Small Animal PET using Monte Carlo Simulation

  • Y.H. Chung;Park, Y.;G. Cho;Y.S. Choe;Lee, K.H.;Kim, S.E.;Kim, B.T.
    • 한국의학물리학회:학술대회논문집
    • /
    • 한국의학물리학회 2003년도 제27회 추계학술대회
    • /
    • pp.44-44
    • /
    • 2003
  • As a basic measurement tool in the areas of animal models of human disease, gene expression and therapy, and drug discovery and development, small animal PET imaging is being used increasingly. An ideal small animal PET should have high sensitivity and high and uniform resolution across the field of view to achieve high image quality. However, the combination of long narrow pixellated crystal array and small ring diameter of small animal PET leads to the degradation of spatial resolution for the source located at off center. This degradation of resolution can be improved by determining the depth of interaction (DOI) in the crystal and by taking into account the information in sorting the coincident events. Among a number of 001 identification schemes, dual layer phsowich detector has been widely investigated by many research groups due to its practicability and effectiveness on extracting DOI information. However, the effects of each crystal length composing dual layer phoswich detector on DOI measurements and image qualities were not fully characterized. In order to minimize the DOI effect, the length of each layer of phoswich detector should be optimized. The aim of this study was to perform simulations using a simulation tool, GATE to design the optimum lengths of crystals composing a dual layer phoswich detector. The simulated small PET system employed LSO front layer LuYAP back layer phoswich detector modules and the module consisted of 8${\times}$8 arrays of dual layer crystals with 2 mm ${\times}$ 2 mm sensitive area coupled to a Hamamatsu R7600 00 M64 PSPMT. Sensitivities and variation of radial resolutions were simulated by varying the length of LSO front layer from 0 to 10 mm while the total length (LSO + LuYAP) was fixed to 20 mm for 10 cm diameter ring scanner. The radial resolution uniformity was markedly improved by using DOI information. There existed the optimal lengths of crystal layers to minimize the variation of radial resolutions. In 10 cm ring scanner configuration, the radial resolution was kept below 3.4 mm over 8 cm FOV while the sensitivity was higher than 7.4% for LSO 5 mm : LuYAP 15 mm phoswich detector. In this study, the optimal length of dual layer phoswich detector was derived to achieve high and uniform radial resolution.

  • PDF

의약 용기의 다중 카메라 인라인 검사 시스템에서의 품질 검사를 위한 딥러닝 네트워크 개발 (Development of a Deep Learning Network for Quality Inspection in a Multi-Camera Inline Inspection System for Pharmaceutical Containers)

  • 이태윤;윤석문;이승호
    • 전기전자학회논문지
    • /
    • 제28권3호
    • /
    • pp.474-478
    • /
    • 2024
  • 본 논문에서는 의약 용기의 다중카메라 인라인 검사 시스템에서의 품질 검사를 위한 딥러닝 네트워크를 제안한다. 제안하는 딥러닝 네트워크는 현장에서 생산되는 의약 용기의 데이터를 사용하여 의약 용기에 특화된 딥러닝 네트워크로 더욱 정확하게 품질을 검사한다. 또한, 인라인 검사가 가능한 딥러닝 네트워크를 사용하여 품질 검사의 속도를 증대시킬 수 있다. 다중카메라 인라인 검사 시스템에서의 품질 검사를 위한 딥러닝 네트워크의 개발은 3단계로 나뉜다. 첫 번째로 실제 의약 용기 생산 현장에서 1개의 이물검사용 line 카메라, 3개의 치수검사용 area 카메라를 통해 얻은 약 10,000장의 이미지로 데이터셋을 구축한다. 두 번째로 의약 용기 데이터 전처리에서는 이물 검사, 치수검사의 용도에 맞게 불량이 일어날 수 있는 곳에 ROI를 지정하여 데이터를 전처리한다. 세 번째로 전처리된 데이터를 이용하여 딥러닝 네트워크를 학습한다. 딥러닝 네트워크는 적은 채널 수를 적용하여 linear layer를 사용하지 않아 판정 속도를 향상하고, PReLU와 residual learning를 적용하여 정확도를 향상한다. 이를 통해 4개의 카메라에서 구축한 데이터셋에 맞는 4개의 딥러닝 모듈을 제작한다. 제안된 의약 용기의 다중카메라 인라인 검사 시스템에서의 품질 검사를 위한 딥러닝 네트워크의 성능을 평가하기 위하여 공인시험기관에서 실험한 결과는, 딥러닝 모듈의 판별 정확도가 99.4%로 세계 최고 수준인 95% 보다 우수한 성적을 달성하였고, 평균 판별 속도가 0.947초로 측정되어 세계 최고 수준인 1초보다 우수한 성적을 달성하였다. 따라서, 본 논문에서 제안한 의약 용기의 다중카메라 인라인 검사 시스템에서의 품질 검사를 위한 딥러닝 네트워크의 효용성이 입증되었다.

란탄족원소-ALC 착물의 전기화학적 연구 (Electrochemical study on the Lanthanide-Alizarin Complexone Complexes)

  • 손병찬;김재균;박종민
    • 자연과학논문집
    • /
    • 제7권
    • /
    • pp.37-46
    • /
    • 1995
  • 란탄족이온($Gd^{3+},$ $Tb^{3+},$ $Dy^{3+},$ $Ho^{3+},$ $Er^{3+},$ $Yb^{3+}$$Lu^{3+}$)과 alizarin complexone(ALC) 사이에 생성한 착물의 전기화학적 거동을 직류폴라로그래피, 펄스차이폴라로그래피 및 순환전압전류법으로 연구하였다. 0.1M $HOA_C-NaOA_C$ 지지전해질 용액에서, 착화제인 ALC는 2전자 1단계의 1:1의 착물을 형성하였으며 이 착물의 환원파는 펄스차이폴라로그래피 및 순환전압전류법으로 흡착성 착물파임을 확인하였다. 착물파의 환원전위는 ALC의 환원파보다 음전위에서 나타났으며 란탄족이온의 농도의 증가에 따른 ALC의 봉우리전류(PI)의 감소와 착물의 봉우리전류($P_2$)의 증가는 란탄족이온의 농도 $2.5X10^5$~$1.0X10^4M$ 범위에서 직선적으로 변화하였다.

  • PDF

척택.어제 침자가 고해상도 적외선 카메라로 관찰한 촌구맥 부위의 온도 Pulsation 변화에 미치는 영향 연구 (Effect of Acupuncture at the LU5(Reinforcement), LU10(Reduction) on the Pulsation Scale of Chon, Gwan and Chuk region using High Resolution Infrared Camera)

  • 나창수;정효상;김지현
    • 대한의용생체공학회:의공학회지
    • /
    • 제32권2호
    • /
    • pp.127-133
    • /
    • 2011
  • Arteria radialis is a branch of the brachial artery extending down the forearm around the wrist where it closes to skin surface. In the oriental medicine, the skin above arteria radialis has an important role because oriental medicine practitioners put their finger tips on the area, and diagnose patient's health conditions by feeling the pulsation of the arterial contraction. The finger tip diagnostic method relies on subjective decision of the practitioner; and there is a need to develop an objective diagnostic modality. The pulsation of the arterial contraction appears not only a movement on the site but also as temperature fluctuation due to pulsatile feeding of warmer blood. The goal of this study is to demonstrate a feasibility of using an infrared camera quantitatively to detect the temperature fluctuation on the skin. Clinical important three different areas, called chon, gwan, chuk, near a wrist where the arteria radialis reaches close to skin surface are marked with small pieces of surgical tape. A high-speed and high-resolution infrared camera with a 3 cm of field of view measures these areas for 10 second at 200 frames per second with a 320*240 pixel size. The pulsatile temperature fluctuation is calculated after passing a band pass filter to remove any stationary temperature over 10 second. The temperature fluctuation of a healthy male volunteer is measured at a room temperature as a control, and is compared with another measurement performed after 20 minutes staying in a room at a 40 degree Celsius. This comparison is repeated for three times, and indicates that the fluctuation increases after staying 20 minutes in the warm room. This increase becomes smaller when the person stays in the warm room with an acupuncture treatment that decreases body temperature. So that an objective diagnostics on the site may become feasible.