• 제목/요약/키워드: reference based

검색결과 7,467건 처리시간 0.033초

Deep Reference-based Dynamic Scene Deblurring

  • Cunzhe Liu;Zhen Hua;Jinjiang Li
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제18권3호
    • /
    • pp.653-669
    • /
    • 2024
  • Dynamic scene deblurring is a complex computer vision problem owing to its difficulty to model mathematically. In this paper, we present a novel approach for image deblurring with the help of the sharp reference image, which utilizes the reference image for high-quality and high-frequency detail results. To better utilize the clear reference image, we develop an encoder-decoder network and two novel modules are designed to guide the network for better image restoration. The proposed Reference Extraction and Aggregation Module can effectively establish the correspondence between blurry image and reference image and explore the most relevant features for better blur removal and the proposed Spatial Feature Fusion Module enables the encoder to perceive blur information at different spatial scales. In the final, the multi-scale feature maps from the encoder and cascaded Reference Extraction and Aggregation Modules are integrated into the decoder for a global fusion and representation. Extensive quantitative and qualitative experimental results from the different benchmarks show the effectiveness of our proposed method.

IEEE 802.l1e 무선랜에서 MSI를 이용한 개선된 스케줄링 및 수락제어 알고리즘 (Improved MSI Based Scheduling and Admission Control Algorithm for IEEE 802.l1e Wireless LAN)

  • 양근혁;옥치영;이채우
    • 대한전자공학회논문지TC
    • /
    • 제44권10호
    • /
    • pp.99-109
    • /
    • 2007
  • 무선랜에서 QoS를 지원하기 위해 제안된 IEEE 802.l1e의 HCCA (HCF Controlled Channel Access)는 폴링에 의한 채널 제어 방식이다. 즉 HCCA는 중앙 제어 방식이기 때문에 자원을 분배하기 위한 스케줄링 알고리즘이 필요하며 IEEE 802.11e 표준에는 Reference 스케줄러가 제시되어 있다. Reference 스케줄러븐 폴링 리스트에 있는 모든 스테이션들을 동일한 주기로 폴링하기 때문에 잦은 폴링으로 인해 오버헤드 면에서 비효율적이며, TXOP (Transmission Opportunity)의 활용률 면에서도 낮다. 본 논문에서는 이러한 단점을 극복하고자 스테이션들의 MSI (Maximum Service Interval)에 따라 폴링 주기를 단계별로 나누어서 스케줄링하기 위한 트래픽 스케줄링 및 수락 제어 (admission control) 알고리즘을 제안한다. 제안하는 알고리즘에서는 스테이션들이 자시의 MSI와 가능한 비슷한 주기로 폴링되기 때문에 Reference 스케줄러에 비해 폴링 오버헤드가 감소하게 되며, TXOP 활용률도 증가하게 된다. 시뮬레이션을 통한 Reference 스케줄러와의 성능 비교는 제안된 알고리즘이 전체적인 전송률 면에서 더 높은 성능을 보이고 더 많은 수의 스테이션이 서비스가 가능함을 보여준다.

A Security Reference Model for the Construction of Mobile Banking Services based on Smart Phones

  • Shin, Yong-Nyuo;Shin, Woo-Chang
    • International Journal of Fuzzy Logic and Intelligent Systems
    • /
    • 제11권4호
    • /
    • pp.229-237
    • /
    • 2011
  • As smart phones have become widely adopted, they have brought about changes in individual lifestyles, as well as significant changes in the industry. As the mobile technology of smart phones has become associated with all areas of industry, it is not only accelerating innovation in other industries such as shopping, healthcare service, education, and finance, but is also creating new markets and business opportunities. The preparation of thorough security measures for smart phones is increasing in demand. While offering excellent mobility and convenience, smart phones can be exposed to a range of violation threats. In particular, it is necessary to make efforts to develop a security system that can preemptively cope with potential security threats in the banking service area, which requires a high level of reliability. This paper suggests a security reference model that is considered for the smart phone-based joint mobile banking development project being undertaken by the Bank of Korea in 2010. The purpose of this study is to make a security reference model for a reliable smart phone-based mobile financial service, by recognizing the specific security threats directed toward smart phones, and providing countermeasures to these security threats. The proposed mobile banking security reference model is useful in improving system security by systematically analyzing information security threats to the mobile financial service, and by presenting the guideline for the preparation of countermeasures.

인공신경망모형을 이용한 기온기반 기준증발산량 산정 (Estimating Reference Crop Evapotranspiration Using Artificial Neural Network and Temperature-based Climatic Data)

  • 이성학;김마가;최진용;방재홍
    • 한국농공학회논문집
    • /
    • 제61권1호
    • /
    • pp.95-105
    • /
    • 2019
  • Evapotranpiration (ET) is one of the important factor in Hydrological cycle and irrigation planning. In this study, temperature-based artificial neural network (ANN) model for daily reference crop ET estimation was developed and compared with reference crop evapotranpiration ($ET_0$) from FAO-56 Penman-Monteith method (FAO-56 PM) and parameter regionalized Hargreaves method. The ANN model was trained and tested for 10 weather stations (5 inland stations and 5 costal stations) and two input climate factors, maximum temperature ($T_{max}$), minimum temperature ($T_{min}$), and extraterrestrial radiation (RA) were used for training and validation of temperature-based ANN model. Monthly reference ET by the ANN model also compared with parameter regionalized Hargreaves method for ANN model applicability evaluation. The ANN model evapotranspiration demonstrated more accordance to FAO-56 PM evapotranspiration than the $ET_0$ from parameter regionalized Hargreaves method(R-Hargreaves). The results of this study proposed that daily reference crop ET estimated by the ANN model could be used in the condition of no sufficient climate data.

Reference Particles-based LTE Base Station Positioning

  • Cho, Seong Yun;Kwon, Jae Uk
    • Journal of Positioning, Navigation, and Timing
    • /
    • 제10권3호
    • /
    • pp.207-214
    • /
    • 2021
  • A new positioning technique for positioning of LTE base stations is proposed. The positioning information of the base station is absolutely necessary for model-based wireless positioning, and is required in some of the various merhodologies for estimating signals in an uncorrected area when construnting a database for fingerprinting-based positioning. Using the acquired location-based Reference Signal Received Power (RSRP) information to estimate the location of the base station, it is impossible with the existing trilateration methods. Therefore, in this paper, a method using reference particles is proposed. Particles are randomly generated in the application area, and signal propagation modeling is performed assuming that a base station is located in each particle. Based on this, the errors of measurements are calculated. The particle group with the minimum measurement errors is selected, the position of the base station is estimated through weighted summation, and the signal propagation model of the corresponding base station is built at the same time. The performance of the proposed technology is verified using data acquired in Seocho-dong, Seoul.

Design of Model-based VCU Software for Driving Performance Optimization of Electric Vehicle

  • Changkyu Lee;Youngho Koo;Kwangnam Park;Gwanhyung Kim
    • Journal of information and communication convergence engineering
    • /
    • 제21권4호
    • /
    • pp.351-358
    • /
    • 2023
  • This study designed a model-based Vehicle Control Unit (VCU) software for electric vehicles. Electric vehicles have transitioned from conventional powertrains (e.g., engines and transmissions) to electric powertrains. The primary role of the VCU is to determine the optimal torque for driving control. This decision is based on the driver's power request and current road conditions. The determined torque is then transmitted to the electric drive system, which includes motors and controllers. The VCU employs an Artificial Neural Network (ANN) and calibrated reference torque to enhance the electric vehicle's performance. The designed VCU software further refines the final reference torque by comparing the control logic with the torque calculation functions and ANN-generated reference torque. Vehicle tests confirmed the effective optimization of vehicle performance using the model-based VCU software, which includes an ANN.

BRM 운영을 위한 단위과제 정비방안 (Business Transaction Preparation Plan for Business Reference Model Management)

  • 김화경;김은주
    • 한국기록관리학회지
    • /
    • 제14권4호
    • /
    • pp.199-219
    • /
    • 2014
  • BRM(Business Reference Model, 이하 BRM)은 기관 간 업무관련 정보공유, 업무처리의 신속성, 조직운영의 효율성, 행정서비스를 제고하기 위한 목적으로 도입되었으며 이와 함께 업무기반의 기록관리체계인 기록관리기준표도 운용하게 되었다. 하지만 BRM이 도입된 지 10여년이 지난 현 시점에서 과연 그 취지 및 목적에 맞게 사용되고 있는지 현재 당면한 문제점이나 개선사항을 통해 재정립할 필요가 있다. 이에 본 연구에서는 BRM의 최하위 단위인 '단위과제' 운영상 문제점을 통해 단위과제 관리의 필요성을 살펴보고 업무분석을 통한 단위과제 도출 방안을 제시하였다. 그리하여 효율적인 BRM관리를 위한 개선방안을 크게 세 가지로 제안하였다.

Reference 기반 AI 모델의 효과적인 해석에 관한 연구 (A Study on Effective Interpretation of AI Model based on Reference)

  • 이현우;한태현;박영지;이태진
    • 정보보호학회논문지
    • /
    • 제33권3호
    • /
    • pp.411-425
    • /
    • 2023
  • 오늘날 AI(Artificial Intelligence) 기술은 다양한 분야에서 활용 목적에 맞게 분류, 회기 작업을 수행하며 광범위하게 활용되고 있으며, 연구 또한 활발하게 진행 중인 분야이다. 특히 보안 분야에서는 예기치 않는 위협을 탐지해야 하며, 모델 훈련과정에 알려진 위협 정보를 추가하지 않아도 위협을 탐지할 수 있는 비 지도학습 기반의 이상 탐지 기법이 유망한 방법이다. 하지만 AI 판단에 대한 해석 가능성을 제공하는 선행 연구 대부분은 지도학습을 대상으로 설계되었기에 학습 방법이 근본적으로 다른 비 지도학습 모델에 적용하기는 어려우며, Vision 중심의 AI 매커니즘 해석연구들은 이미지로 표현되지 않는 보안 분야에 적용하기에 적합하지 않다. 따라서 본 논문에서는 침해공격의 원본인 최적화 Reference를 탐색하고 이와 비교함으로써 탐지된 이상에 대한 해석 가능성을 제공하는 기법을 활용한다. 본 논문에서는 산출된 Reference를 기반으로 실존 데이터에서 가장 가까운 데이터를 탐색하는 로직을 추가 제안함으로써 실존 데이터를 기반으로 이상 징후에 대한 더욱 직관적인 해석을 제공하고 보안 분야에서의 효과적인 이상 탐지모델 활용을 도모하고자 한다.

네트워크 기반 AIS 기준국 시스템 설계 (Design of Network-based AIS Reference Station System)

  • 서기열;박상현;정호철;조득재
    • 한국정보통신학회논문지
    • /
    • 제14권4호
    • /
    • pp.824-830
    • /
    • 2010
  • 본 논문에서는 국제해사기구(IMO), 국제항로표지협회(IALA) 등 국제기구의 DGNSS 서비스 요구성능 증가에 기술적으로 대처하고, 해상교통안전 증대를 위하여 선박자동식별시스템(AIS)의 기지국 시스템에서 DGPS 기준국 기능을 수행할 수 있는 효과적인 방안을 제안한다. 본 논문에서 제안하는 방식은 DGPS 기준국에서 제공하는 보정 정보를 네트워크를 통하여 AIS 기지국에서 수신하고, 수신된 보정정보를 단순히 해상 선박의 AIS 단말기에 중계하는 방법이 아니라 AIS 기지국에서 커버리지 내의 선박에 최적화된 보정정보를 생성하여 전송하는 방법이다. 이를 구현하기 위하여, 본 논문에서는 먼저 DGPS 기준국과 네트워크를 통해 연결되는 AIS 기준국을 설계하고, AIS 기준국에서 보정정보를 생성하기 위한 알고리즘을 제안한다. 그리고 DGPS 기준국 보정정보의 실측 데이터를 기반으로 제안한 알고리즘의 성능평가를 수행하고 그 결과를 제시한다. 마지막으로 제안한 시스템의 효율적 적용 방안에 대해 논의한다.

A Study for Improving the Positioning Accuracy of DGPS Based on Multi-Reference Stations by Applying Exponential Modeling on Pseudorange Corrections

  • Kim, Koon-Tack;Park, Kwan-Dong;Lee, Eunsung;Heo, Moon Beom
    • Journal of Positioning, Navigation, and Timing
    • /
    • 제2권1호
    • /
    • pp.9-17
    • /
    • 2013
  • In this paper, a pseudorange correction regeneration algorithm was developed to improve the positioning accuracy of DGPS using multi-reference stations, and the optimal minimum number of reference sites was determined by trying out different numbers of reference. This research was conducted using from two to five sites, and positioning errors of less than 1 m were obtained when pseudorange corrections are collected from at least four reference stations and interpolated as the pseudorange correction at the rover. After determining the optimal minimum number of reference stations, the pseudorange correction regeneration algorithm developed was tested by comparison with the performance of other algorithms. Our approach was developed based on an exponential model. If pseudorange corrections are regenerated using an exponential model, the effect of a small difference in the baseline distance can be enlarged. Therefore, weights can be applied sensitively even when the baseline distance differs by a small amount. Also weights on the baseline distance were applied differently by assigning weights depending on the difference of the longest and shortest baselines. Through this method, the positioning accuracy improved by 19% compared to the result of previous studies.