• 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.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2011년도 춘계학술발표대회
• /
• pp.78-80
• /
• 2011

In the area of data fusion, dealing with heterogeneous data sources, numerous models have been proposed in last three decades to facilitate different application domains i.e. Department of Defense (DoD), monitoring of complex machinery, medical diagnosis and smart buildings. All of these models shared the theme of multiple levels processing to get more reliable and accurate information. In this paper, we consider five most widely acceptable fusion models (Intelligence Cycle, Joint Directors of Laboratories, Boyd control, Waterfall, Omnibus) applied to different areas for data fusion. When they are exposed to a real scenario, where large dataset from heterogeneous sources is utilize for object monitoring, then it may leads us to non-efficient and unreliable information for decision making. The proposed variation works better in terms of time and accuracy due to prior data diminution.

• Smart Structures and Systems
• /
• 제22권5호
• /
• pp.631-641
• /
• 2018

This paper outlines a computational procedure for the effective merging of diverse sensor measurements, displacement and acceleration signals in particular, in order to successfully monitor and simulate the current health condition of civil structures under dynamic loadings. In particular, it investigates a Kalman Filter implementation for the Heterogeneous Data Fusion of displacement and acceleration response signals of a structural system toward dynamic identification purposes. The procedure is perspectively aimed at enhancing extensive remote displacement measurements (commonly affected by high noise), by possibly integrating them with a few standard acceleration measurements (considered instead as noise-free or corrupted by slight noise only). Within the data fusion analysis, a Kalman Filter algorithm is implemented and its effectiveness in improving noise-corrupted displacement measurements is investigated. The performance of the filter is assessed based on the RMS error between the original (noise-free, numerically-determined) displacement signal and the Kalman Filter displacement estimate, and on the structural modal parameters (natural frequencies) that can be extracted from displacement signals, refined through the combined use of displacement and acceleration recordings, through inverse analysis algorithms for output-only modal dynamics identification, based on displacements.

• 한국항공우주학회지
• /
• 제48권7호
• /
• pp.513-522
• /
• 2020

본 논문은 PSD와 이종 센서 융합을 이용한 상대 항법 알고리즘에 대해 기술한다. 추종 시스템(Chaser)과 목표 시스템(Target) 간의 상대 항법을 수행하기 위해 하드웨어 시스템을 구축하고 알고리즘을 설계하여 시뮬레이션을 수행하였다. 이를 통해 상대 거리에 따른 오차 발생 경향을 확인하여 이종 센서 융합에 대한 분석을 수행하였다. 이후 구축한 하드웨어 시스템으로 지상 시험 환경을 구성하여 측정값을 획득하고 이를 후처리하여 상대 항법 알고리즘의 성능을 최종적으로 확인하였다.

• 한국해양공학회지
• /
• 제37권1호
• /
• pp.38-48
• /
• 2023

To maintain the existing systems of ships and introduce autonomous operation technology, it is necessary to improve situational awareness through the sensor fusion of the automatic identification system (AIS) and automatic radar plotting aid (ARPA), which are installed sensors. This study proposes an algorithm for determining whether AIS and ARPA signals are sent to the same ship in real time. To minimize the number of errors caused by the time series and abnormal phenomena of heterogeneous signals, a tracking method based on the combination of the unscented Kalman filter and probabilistic data association filter is performed on ARPA radar signals, and a position prediction method is applied to AIS signals. Especially, the proposed algorithm determines whether the signal is for the same vessel by comparing motion-related components among data of heterogeneous signals to which the corresponding method is applied. Finally, a measurement test is conducted on a training ship. In this process, the proposed algorithm is validated using the AIS and ARPA signal data received by the voyage data recorder for the same ship. In addition, the proposed algorithm is verified by comparing the test results with those obtained from raw data. Therefore, it is recommended to use a sensor fusion algorithm that considers the characteristics of sensors to improve the situational awareness accuracy of existing ship systems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권6호
• /
• pp.2801-2816
• /
• 2016

Owing to their low scalability, weak support on big data, insufficient data collaborative analysis and inadequate situational awareness, the traditional methods fail to meet the needs of the security data analysis. This paper proposes visualization methods to fuse the multi-source security data and grasp the network situation. Firstly, data sources are classified at their collection positions, with the objects of security data taken from three different layers. Secondly, the Heatmap is adopted to show host status; the Treemap is used to visualize Netflow logs; and the radial Node-link diagram is employed to express IPS logs. Finally, the Labeled Treemap is invented to make a fusion at data-level and the Time-series features are extracted to fuse data at feature-level. The comparative analyses with the prize-winning works prove this method enjoying substantial advantages for network analysts to facilitate data feature fusion, better understand network security situation with a unified, convenient and accurate mode.

• 한국정보과학회논문지:데이타베이스
• /
• 제28권3호
• /
• pp.406-417
• /
• 2001

웹에서의 멀티미디어 데이터베이스가 발달함에 따라 분산 멀티미디어 데이터에 대한 검색 기능의 필요성이 높아지고 있다. 그러나 지금까지는 주로 웹상에 분산된 텍스트 데이터베이스를 선택하고 선택된 텍스트 데이터베이스에 대해소 질의 결과를 결합하는 연구가 이루어졌을 뿐 멀티미디어 데이터베이스에 대해서는 연구가 미진하였다. 웹상의 멀티미디어 데이터베이스는 자율적이고 이질적인 특성을 가지고 있고 주로 내용 기반으로 검색된다. 멀티미디어 데이터베이스에서의 수집 융합 문제는 웹상의 이질적인 멀티미디어 데이터베이스에서 내용 기반 검색으로 검색된 경과를 병합하는 것을 다룬다. 이 문제는 분산 멀티미디어 데이터베이스의 검색에 매우 중요하지만 아직까지 연구된 바가 없다. 본 논문은 웹상에서 이질적인 멀티미디어 데이터베이스의 수집 융합을 처리하는 새로운 알고리즘을 제안한다. 본 논문은 데이터베이스에서 검색할 객체의 개수를 추정하는 휴리스틱 방법과 선형 회귀분석을 이용한 알고리즘을 사용한다. 그리고 실험에 의해서 이 알고리즘들의 효율성을 보였다. 이 알고리즘들은 향후 웹상의 멀티미디어 데이터베이스들에 대한 분산 내용 기반 검색 알고리즘들의 기본이 될 수 있다.

• 한국정밀공학회지
• /
• 제28권9호
• /
• pp.1040-1047
• /
• 2011

This paper proposes a novel method based on error back propagation neural networks to fuse laser sensor data and ultrasonic sensor data for enhancing the accuracy of mapping. For navigation of single robot, the robot has to know its initial position and accurate environment information around it. However, due to the inherent properties of sensors, each sensor has its own advantages and drawbacks. In our system, the robot equipped with seven ultrasonic sensors and a laser sensor navigates to map two different corridor environments. The experimental results show the effectiveness of the heterogeneous sensor fusion using an error backpropagation algorithm for mapping.

• 대한토목학회논문집
• /
• 제42권1호
• /
• pp.67-74
• /
• 2022

최근 높은 스마트폰 보급율과 ITS (intelligent transportation systems) 인프라 확충 등 정보통신기술(information and communications technology, ICT) 이용 활성화로 실시간 교통정보의 수집원이 증가하였다. 이렇게 다양하게 수집되는 실시간 교통정보의 정확도는 VDS(vehicle detection system), DSRC (dedicated short-range communications), GPS (global positioning system) probe와 같은 다양한 교통정보 수집원별 시공간 혹은 교통상황 등 다양한 환경에 따라 다르게 나타날 수 있다. 본 연구의 목적은 이질적 교통정보가 동시에 수집될 경우, 실시간 교통정보의 정확도를 향상시키기 위한 융합 전략의 제시에 있다. 이를 위해 고속국도(892.2 km, 227개 링크), 일반국도(937.0 km, 2,074개 링크)를 대상으로 주행 조사를 실시하였으며, 해당 링크 및 시간대에 probe 차량 5대의 평균 통행속도는 실시간 교통정보 수집원별(VDS or DSRC, GPS-based A, B) 정확도 평가의 기준 혹은 참값으로 활용되었다. 결과적으로 제시된 융합 전략에 대한 정확도 개선 효과는 일반국도에서 1개 수집원을 제외하고 모두 통계적으로 유의한 것으로 나타났으며, 향후 다양한 기관으로부터 서비스되는 실시간 교통정보가 동시에 연계되는 환경에서 보다 정확한 교통정보 서비스의 가능성을 확인하였다.

• 대한산업공학회지
• /
• 제43권1호
• /
• pp.39-48
• /
• 2017

In a digital economy, users actively express their needs in many ways. Thus, many researchers analyze what users need and whether they are satisfied or not through opinion mining. In addition, they begin to find technology opportunities in heterogeneous technology fields. But they did not connect users' opinion to technology development process, only focused on natural language processing or marketing or manufacturing area. Also, heterogeneous technology fields are focused on fusion technology. Thus, this study suggests a novel approach that is based on sentimental value and can be applied to exploring technology opportunities in heterogeneous fields. Sentimental value is calculated from users' opinion through sLDA. The heterogeneous technology opportunity is explored by patent analysis. This research contributes to suggesting a hybrid methodology through patent and users' opinion. In addition, it can provide managerial efficiency by suggesting base data onto decision making.