• Title/Summary/Keyword: Augmentation system

Search Result 473, Processing Time 0.038 seconds

A Substitute Model Learning Method Using Data Augmentation with a Decay Factor and Adversarial Data Generation Using Substitute Model (감쇠 요소가 적용된 데이터 어그멘테이션을 이용한 대체 모델 학습과 적대적 데이터 생성 방법)

  • Min, Jungki;Moon, Jong-sub
    • Journal of the Korea Institute of Information Security & Cryptology
    • /
    • v.29 no.6
    • /
    • pp.1383-1392
    • /
    • 2019
  • Adversarial attack, which geneartes adversarial data to make target model misclassify the input data, is able to confuse real life applications of classification models and cause severe damage to the classification system. An Black-box adversarial attack learns a substitute model, which have similar decision boundary to the target model, and then generates adversarial data with the substitute model. Jacobian-based data augmentation is used to synthesize the training data to learn substitutes, but has a drawback that the data synthesized by the augmentation get distorted more and more as the training loop proceeds. We suggest data augmentation with 'decay factor' to alleviate this problem. The result shows that attack success rate of our method is higher(around 8.5%) than the existing method.

Clinical and Radiological Outcomes of Modified Phemister Operation with Coracoclavicular Ligament Augmentation Using Suture Anchor for Acute Acromioclavicular Joint Dislocation

  • Cho, Nam Su;Bae, Sung Ju;Lee, Joong Won;Seo, Jeung Hwan;Rhee, Yong Girl
    • Clinics in Shoulder and Elbow
    • /
    • v.22 no.2
    • /
    • pp.93-99
    • /
    • 2019
  • Background: Modified Phemister operation has been widely used for the treatment of acute acromioclavicular (AC) joint dislocation. Additionally, the use of suture anchor for coracoclavicular (CC) fixation has been reported to provide CC stability. This study was conducted to evaluate the clinical and radiological results of a modified Phemister operation with CC ligament augmentation using suture anchor for acute AC joint dislocation. Methods: Seventy-four patients underwent the modified Phemister operation with CC ligament augmentation using suture anchor for acute AC joint dislocation and were followed-up for an average of 12.3 months. The visual analogue scale (VAS), range of motion, Constant score, and Korean shoulder scoring system (KSS) were used for clinical assessment. Acromioclavicular interval (ACI), coracoclavicular distance (CCD), and acromioclavicular distance (ACD) were obtained to evaluate the radiological assessments. Results: At the last follow-up, the mean VAS Score was 1.7 points, the mean joint range of the forward flexion was $164.6^{\circ}$, external rotation at the side was $61.2^{\circ}$ and internal rotation to the posterior was a level of T12. The mean Constant score and the mean KSS was 82.7 points and 84.2 points, respectively. At the mean ACI, CCD, and ACD, significant differences were found preoperatively and at the last follow-up. When the ACI, CCD, and ACD were compared with the contralateral unaffected shoulder at the last follow-up, the affected shoulders had significantly higher values. Conclusions: The modified Phemister operation with CC ligament augmentation using suture anchor is clinically and radiologically effective at acute AC joint dislocation.

A Study of Pattern Defect Data Augmentation with Image Generation Model (이미지 생성 모델을 이용한 패턴 결함 데이터 증강에 대한 연구)

  • Byungjoon Kim;Yongduek Seo
    • Journal of the Korea Computer Graphics Society
    • /
    • v.29 no.3
    • /
    • pp.79-84
    • /
    • 2023
  • Image generation models have been applied in various fields to overcome data sparsity, time and cost issues. However, it has limitations in generating images from regular pattern images and detecting defects in such data. In this paper, we verified the feasibility of the image generation model to generate pattern images and applied it to data augmentation for defect detection of OLED panels. The data required to train an OLED defect detection model is difficult to obtain due to the high cost of OLED panels. Therefore, even if the data set is obtained, it is necessary to define and classify various defect types. This paper introduces an OLED panel defect data acquisition system that acquires a hypothetical data set and augments the data with an image generation model. In addition, the difficulty of generating pattern images in the diffusion model is identified and a possibility is proposed, and the limitations of data augmentation and defect detection data augmentation using the image generation model are improved.

A Study on the development and Implementation of Multi-purpose All Airspace Satellite Based Augmentation System (SBAS) (다목적 전 공역 위성항법보정시스템 개발 및 적용에 대한 연구)

  • Lee, Gun Young
    • Journal of the Korean Society for Aviation and Aeronautics
    • /
    • v.22 no.1
    • /
    • pp.15-21
    • /
    • 2014
  • Modern aircraft air navigation has been changed from the conventional air navigation aid to utilizing Global Navigation Satellite System. For the air navigation of fast moving aircraft, GNSS required extremely high accuracy and reliability. This study reviews the basic concept of Satellite Based Augmentation System which is discussed in the International Working Group of International Civil Aviation Organization and status of some SBAS leading State's case. In addition to that, a progress of SBAS development and implementation in the Republic of Korea was reviewed with pointing out of general hurdles and counter measures.

A Transfer Alignment Considering Measurement Time-Delay and Ship Body Flexure (측정치 시간지연과 선체의 유연성을 고려한 전달정렬 기법)

  • Lim, You-Chol;Lyou, Joon
    • Journal of the Korea Institute of Military Science and Technology
    • /
    • v.4 no.1
    • /
    • pp.225-233
    • /
    • 2001
  • This paper deals with the transfer alignment problem of SDINS(StrapDown Inertial Navigation System) subjected to roll and pitch motions of the ship. Specifically, to reduce alignment errors induced by measurement time-delay and ship body flexure, an error compensation method is suggested based on delay state augmentation and DCM(Direction Cosine Matrix) partial matching. A linearized error model for the velocity and attitude matching transfer alignment system is first derived by linearizing the nonlinear measurement equation with respect to its time delay and augmenting the delay state into the conventional linear state equations. And then DCM partial matching is properly combined to reduce effects of a ship's Y axis flexure. The simulation results show that the suggested method is effective enough resulting in considerably less azimuth alignment errors.

  • PDF

A Study on the Heat Transfer Augmentation by Using Wire-mesh Impinging Water Jet (충돌수분류계(衝突水噴流系)에서 와이어 메쉬를 사용(使用)한 열전달(熱傳達) 증진(增進)에 관(關)한 연구(硏究))

  • Na, G.D.
    • Korean Journal of Air-Conditioning and Refrigeration Engineering
    • /
    • v.6 no.3
    • /
    • pp.291-301
    • /
    • 1994
  • This paper presents the promotion of heat transfer through the use of wire-mesh screens. To improve heat transfer in an impingement water system, the wire-mesh screens are installed between the nozzle-to-heater surfaces. When the wire-mesh screens are not employed, this report exhibits the maximum heat transfer and the secondary maximum value at the stagnation point. But in case of using the wire-mesh screens, the transfer coefficient value of maximum heat exists at the stagnation point, and the second maximum value doesn't occur. Therefore, the heat transfer is more improved than 4~6 times that of the mean Nusselt numbers of simple water jet system, Also, within the region presented in this study, the heat transfer was promoted by using the wire-mesh screens at the stagnation point ; thus, the heat transfer was more increased than 6-7. 5 times that of simple water jet system.

  • PDF

Wide Area Augmentation System Estimating C1P1 DCB (C1P1 DCB를 추정하는 광역보강항법 시스템)

  • Bu, Sung-Chun;So, Hyoung-Min;Kim, Kap-Jin;Lee, Chul-Soo;Kim, Do-Kyoung;Ko, Yo-Han
    • Journal of Advanced Navigation Technology
    • /
    • v.22 no.5
    • /
    • pp.400-408
    • /
    • 2018
  • Wide area augmentation system is a system that generates and transmits correction and Integrity information for use in wide area. Typical system is SBAS. In the United States, it operates under the name WAAS, EGNOS in Europe, MSAS in Japan, SDCM in Russia, GAGAN in India. it is developing Korean SBAS which named KASS by 2022 in Korea. SBAS is a standard System that is operated as civil aviation service base and set as international standards by ICAO. So the correction data can only is used for civil SPS receiver. In this paper, we discuss C1P1 DCB estimation which need to use SPS correction service for PPS receiver. Then we analyze C1P1 DCB correction effect under standalone Satellite Navigation and method to use PPS receiver under SPS DGPS. Finally we organize wide area augmentation system for PPS receiver and analysis performance.

Suggestion on the SBAS Augmentation Message Providing System for the the Low-cost GPS Receiver of Drone Operation (드론의 저가형 GPS 수신기용 SBAS 보강 정보 전송 시스템 제안)

  • Seok, Hyo-jeong;Yoon, Dong-hwan;Lim, Cheol-soon;Park, Byung-woon
    • Journal of Advanced Navigation Technology
    • /
    • v.21 no.3
    • /
    • pp.272-278
    • /
    • 2017
  • In order to meet performance requirements specified by the ICAO in drone operation, a system that provides augmentation information such as SBAS is needed. However, the operating range of the drone is limited in situation where the drone can not received the SBAS message continuously. In this paper, we propose a system to transmit SBAS augmentation message using a separate communication channel assuming the SBAS satellite signal to the drone has been shielded. We implemented the proposed system and verified its performance in the static environment. The DGPS positioning results showed that the accuracy difference is about 10cm, which means the accuracy performance was very similar. In addition, the protection level calculated by the system also shows the difference within 2m from the value calculated by the airborne receiver.

Application of Software Quality Model and Metric for Software Product Assurance for KASS Control Station (KASS 통합운영국 소프트웨어 품질 보증을 위한 소프트웨어 품질 모델 및 메트릭 적용방안)

  • Kim, Youn-sil;Lee, Eun-sung
    • Journal of Advanced Navigation Technology
    • /
    • v.24 no.1
    • /
    • pp.28-36
    • /
    • 2020
  • Korea augmentation satellite system (KASS) is the Korean satellite based augmentation system (SBAS) developed by ministry of land, infrastructure, and transport (MOLIT) since 2014. Since KASS is the safety critical system that can affect to the safety of airplane, the software of KASS is developed according to the DO178B software level induced from safety analysis. In case of KASS control station (KCS), most of the software of KCS get assigned software level E in DO178B. In that case, ECSS-Q-ST-80C category D is assigned as a software product assurance standard. In this paper, the software related standard ECSS-E-ST-40C, ECSS-Q-HB-80-04A are analyzed to satisfy ECSS-Q-ST-80C and as a result the software product assurance activities regarding software life cycle and the software quality model, metric is proposed for the product assurance of the KCS software.

Deep Learning Based On-Device Augmented Reality System using Multiple Images (다중영상을 이용한 딥러닝 기반 온디바이스 증강현실 시스템)

  • Jeong, Taehyeon;Park, In Kyu
    • Journal of Broadcast Engineering
    • /
    • v.27 no.3
    • /
    • pp.341-350
    • /
    • 2022
  • In this paper, we propose a deep learning based on-device augmented reality (AR) system in which multiple input images are used to implement the correct occlusion in a real environment. The proposed system is composed of three technical steps; camera pose estimation, depth estimation, and object augmentation. Each step employs various mobile frameworks to optimize the processing on the on-device environment. Firstly, in the camera pose estimation stage, the massive computation involved in feature extraction is parallelized using OpenCL which is the GPU parallelization framework. Next, in depth estimation, monocular and multiple image-based depth image inference is accelerated using the mobile deep learning framework, i.e. TensorFlow Lite. Finally, object augmentation and occlusion handling are performed on the OpenGL ES mobile graphics framework. The proposed augmented reality system is implemented as an application in the Android environment. We evaluate the performance of the proposed system in terms of augmentation accuracy and the processing time in the mobile as well as PC environments.