• 제목/요약/키워드: Fusion Model

검색결과 971건 처리시간 0.022초

New Medical Image Fusion Approach with Coding Based on SCD in Wireless Sensor Network

  • Zhang, De-gan;Wang, Xiang;Song, Xiao-dong
    • Journal of Electrical Engineering and Technology
    • /
    • 제10권6호
    • /
    • pp.2384-2392
    • /
    • 2015
  • The technical development and practical applications of big-data for health is one hot topic under the banner of big-data. Big-data medical image fusion is one of key problems. A new fusion approach with coding based on Spherical Coordinate Domain (SCD) in Wireless Sensor Network (WSN) for big-data medical image is proposed in this paper. In this approach, the three high-frequency coefficients in wavelet domain of medical image are pre-processed. This pre-processing strategy can reduce the redundant ratio of big-data medical image. Firstly, the high-frequency coefficients are transformed to the spherical coordinate domain to reduce the correlation in the same scale. Then, a multi-scale model product (MSMP) is used to control the shrinkage function so as to make the small wavelet coefficients and some noise removed. The high-frequency parts in spherical coordinate domain are coded by improved SPIHT algorithm. Finally, based on the multi-scale edge of medical image, it can be fused and reconstructed. Experimental results indicate the novel approach is effective and very useful for transmission of big-data medical image(especially, in the wireless environment).

다중센서자료 시뮬레이터 설계 및 자료융합 알고리듬 개발 (Design of a Multi-Sensor Data Simulator and Development of Data Fusion Algorithm)

  • 이용재;이자성;고선준;송종화
    • 한국항공우주학회지
    • /
    • 제34권5호
    • /
    • pp.93-100
    • /
    • 2006
  • 본 논문에서는 레이더와 원격측정시스템으로부터 수신되는 다중센서자료를 모사하는 시뮬레이터 설계와 이들 자료를 융합하기 위한 알고리듬 개발에 대하여 소개한다. 설계된 데이터 시뮬레이터는 실제 센서 시스템으로부터 얻게 되는 시간의 비동기, 통신지연, 다중 갱신주기들을 갖는 모의센서 자료를 생성하며 실제적인 센서 모델을 이용하여 측정 잡음을 생성한다. 융합알고리듬은 센서 바이어스 상태를 고려한 PVA모델을 기초로 21차 분산형 칼만 필터로 설계되었고, 센서의 이상이나 정상적이 아닌 측정치를 검출하기 위한 로직도 포함되었다. 설계된 알고리듬을 시뮬레이터에서 생성한 모의 자료 및 실제 자료를 적용하여 검증하였다.

이질적 템플릿 매칭의 융합을 이용한 얼굴 영역 검출 (Face Detection Using Fusion of Heterogeneous Template Matching)

  • 이경미
    • 한국콘텐츠학회논문지
    • /
    • 제7권12호
    • /
    • pp.311-321
    • /
    • 2007
  • 본 논문은 영상에 포함된 얼굴을 보다 빠르고 강건하게 검출하기 위해서 이질적 템플릿 매칭의 결과들을 융합하여 얼굴을 검출하는 방법을 제안한다. 먼저 광범위한 조명 환경과 인종을 포괄하는 피부색 모델을 이용해 피부 영역을 검출한다. 그리고 영역 라벨링과 필터링으로 매칭에 필요한 검색 범위를 줄인 후, 피부색과 에지를 이용한 템플릿 매칭을 검출된 영역에 적용한다. 이들 매칭 결과가 융합되어 두 매칭 결과를 동시에 최적으로 만족하는 얼굴이 검출된다. 실험 결과는 제안된 방법이 단일 템플릿을 적용할 때보다 얼굴색과 유사한 배경에서 얼굴을 강건하게 검출하며, 얼굴 후보 영역으로 검색 범위를 줄여 검출 시간을 줄였음을 보여준다. 또한 전역 누산기를 사용하여 템플릿 매칭의 과도한 공간 요구의 문제점을 해결할 수 있었다.

다중주기 칼만 필터를 이용한 비동기 센서 융합 (Asynchronous Sensor Fusion using Multi-rate Kalman Filter)

  • 손영섭;김원희;이승희;정정주
    • 전기학회논문지
    • /
    • 제63권11호
    • /
    • pp.1551-1558
    • /
    • 2014
  • We propose a multi-rate sensor fusion of vision and radar using Kalman filter to solve problems of asynchronized and multi-rate sampling periods in object vehicle tracking. A model based prediction of object vehicles is performed with a decentralized multi-rate Kalman filter for each sensor (vision and radar sensors.) To obtain the improvement in the performance of position prediction, different weighting is applied to each sensor's predicted object position from the multi-rate Kalman filter. The proposed method can provide estimated position of the object vehicles at every sampling time of ECU. The Mahalanobis distance is used to make correspondence among the measured and predicted objects. Through the experimental results, we validate that the post-processed fusion data give us improved tracking performance. The proposed method obtained two times improvement in the object tracking performance compared to single sensor method (camera or radar sensor) in the view point of roots mean square error.

내부확산법으로 제조된 $Nb_3Sn$ 초전도 선재의 임계전류 및 n-값의 자장, 변이 의존성 (Field and Strain Dependence of the Critical Current and the n-value for an Internal-tin Processed $Nb_3Sn$ Strand)

  • 오상준;최희경;이철희;김기만
    • Progress in Superconductivity
    • /
    • 제9권2호
    • /
    • pp.152-156
    • /
    • 2008
  • Detailed field and strain dependence of the critical current and the n-value for an internal-tin processed $Nb_3Sn$ strand have been measured. Both the compressive and tensile strain is applied reversibly using Walter spiral probe made of BeCu up to 0.73 %. There is a correlation between the critical current and the n-value for the $Nb_3Sn$ strand studied in this work and the field dependence of the n-value is in agreement with a recent empirical formula. It was further shown that the critical current can be reasonably well fitted by the scaling law based on strong-coupling theory of superconductivity using the relation between the critical current and the n-value.

  • PDF

Precision Analysis of NARX-based Vehicle Positioning Algorithm in GNSS Disconnected Area

  • Lee, Yong;Kwon, Jay Hyoun
    • 한국측량학회지
    • /
    • 제39권5호
    • /
    • pp.289-295
    • /
    • 2021
  • Recently, owing to the development of autonomous vehicles, research on precisely determining the position of a moving object has been actively conducted. Previous research mainly used the fusion of GNSS/IMU (Global Positioning System / Inertial Navigation System) and sensors attached to the vehicle through a Kalman filter. However, in recent years, new technologies have been used to determine the location of a moving object owing to the improvement in computing power and the advent of deep learning. Various techniques using RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory), and NARX (Nonlinear Auto-Regressive eXogenous model) exist for such learning-based positioning methods. The purpose of this study is to compare the precision of existing filter-based sensor fusion technology and the NARX-based method in case of GNSS signal blockages using simulation data. When the filter-based sensor integration technology was used, an average horizontal position error of 112.8 m occurred during 60 seconds of GNSS signal outages. The same experiment was performed 100 times using the NARX. Among them, an improvement in precision was confirmed in approximately 20% of the experimental results. The horizontal position accuracy was 22.65 m, which was confirmed to be better than that of the filter-based fusion technique.

Effective Pre-rating Method Based on Users' Dichotomous Preferences and Average Ratings Fusion for Recommender Systems

  • Cheng, Shulin;Wang, Wanyan;Yang, Shan;Cheng, Xiufang
    • Journal of Information Processing Systems
    • /
    • 제17권3호
    • /
    • pp.462-472
    • /
    • 2021
  • With an increase in the scale of recommender systems, users' rating data tend to be extremely sparse. Some methods have been utilized to alleviate this problem; nevertheless, it has not been satisfactorily solved yet. Therefore, we propose an effective pre-rating method based on users' dichotomous preferences and average ratings fusion. First, based on a user-item ratings matrix, a new user-item preference matrix was constructed to analyze and model user preferences. The items were then divided into two categories based on a parameterized dynamic threshold. The missing ratings for items that the user was not interested in were directly filled with the lowest user rating; otherwise, fusion ratings were utilized to fill the missing ratings. Further, an optimized parameter λ was introduced to adjust their weights. Finally, we verified our method on a standard dataset. The experimental results show that our method can effectively reduce the prediction error and improve the recommendation quality. As for its application, our method is effective, but not complicated.

Strengthened Madden-Julian Oscillation Variability improved the 2020 Summer Rainfall Prediction in East Asia

  • Jieun Wie;Semin Yun;Jinhee Kang;Sang-Min Lee;Johan Lee;Baek-Jo Kim;Byung-Kwon Moon
    • 한국지구과학회지
    • /
    • 제44권3호
    • /
    • pp.185-195
    • /
    • 2023
  • The prolonged and heavy East Asian summer precipitation in 2020 may have been caused by an enhanced Madden-Julian Oscillation (MJO), which requires evaluation using forecast models. We examined the performance of GloSea6, an operational forecast model, in predicting the East Asian summer precipitation during July 2020, and investigated the role of MJO in the extreme rainfall event. Two experiments, CON and EXP, were conducted using different convection schemes, 6A and 5A, respectively to simulate various aspects of MJO. The EXP runs yielded stronger forecasts of East Asian precipitation for July 2020 than the CON runs, probably due to the prominent MJO realization in the former experiment. The stronger MJO created stronger moist southerly winds associated with the western North Pacific subtropical high, which led to increased precipitation. The strengthening of the MJO was found to improve the prediction accuracy of East Asian summer precipitation. However, it is important to note that this study does not discuss the impact of changes in the convection scheme on the modulation of MJO. Further research is needed to understand other factors that could strengthen the MJO and improve the forecast.

Transfer Learning-Based Feature Fusion Model for Classification of Maneuver Weapon Systems

  • Jinyong Hwang;You-Rak Choi;Tae-Jin Park;Ji-Hoon Bae
    • Journal of Information Processing Systems
    • /
    • 제19권5호
    • /
    • pp.673-687
    • /
    • 2023
  • Convolutional neural network-based deep learning technology is the most commonly used in image identification, but it requires large-scale data for training. Therefore, application in specific fields in which data acquisition is limited, such as in the military, may be challenging. In particular, the identification of ground weapon systems is a very important mission, and high identification accuracy is required. Accordingly, various studies have been conducted to achieve high performance using small-scale data. Among them, the ensemble method, which achieves excellent performance through the prediction average of the pre-trained models, is the most representative method; however, it requires considerable time and effort to find the optimal combination of ensemble models. In addition, there is a performance limitation in the prediction results obtained by using an ensemble method. Furthermore, it is difficult to obtain the ensemble effect using models with imbalanced classification accuracies. In this paper, we propose a transfer learning-based feature fusion technique for heterogeneous models that extracts and fuses features of pre-trained heterogeneous models and finally, fine-tunes hyperparameters of the fully connected layer to improve the classification accuracy. The experimental results of this study indicate that it is possible to overcome the limitations of the existing ensemble methods by improving the classification accuracy through feature fusion between heterogeneous models based on transfer learning.

타겟 분해 기반 특징과 확률비 모델을 이용한 다중 주파수 편광 SAR 자료의 결정 수준 융합 (Decision Level Fusion of Multifrequency Polarimetric SAR Data Using Target Decomposition based Features and a Probabilistic Ratio Model)

  • 지광훈;박노욱
    • 대한원격탐사학회지
    • /
    • 제23권2호
    • /
    • pp.89-101
    • /
    • 2007
  • 이 논문에서는 토지 피복분류를 목적으로 C 밴드와 L 밴드 다중 편광 자료의 결정 수준 융합을 수행하여 융합 효과를 살펴보았다. 앞으로 이용이 가능해질 C 밴드 Radarsat-2 자료와 L 밴드 ALOS PALSAR 자료를 모사하기 위해 C 밴드와 L 밴드 NASA JPL AIRSAR 자료를 감독분류에 이용하였다. Target decomposition으로부터 얻어지는 산란 특성과 관련된 특징들을 입력으로 SVM을 분류 기법으로 적용한 후에, 사후확률을 확률비 모델의 틀안에서 융합하는 결정수준 융합을 수행하였다. 적용 결과, L 밴드가 C 밴드에 비해 피복 구분에 적절한 투과 심도를 나타내어 22% 정도 높은 분류 정확도를 나타내었지만, 결정수준 융합을 통해 개별 토지피복 항목의 구분력의 향상으로 인해 L 밴드 자료의 분류결과에 비해 10% 정도의 보다 향상된 분류 정확도를 얻을 수 있었다.