• Journal of Radiation Protection and Research
• /
• 제44권4호
• /
• pp.149-155
• /
• 2019

Background: Magnetic resonance (MR) image guided radiation therapy system, enables real time MR guided radiotherapy (RT) without additional radiation exposure to patients during treatment. However, MR image lacks electron density information required for dose calculation. Image fusion algorithm with deformable registration between MR and computed tomography (CT) was developed to solve this issue. However, delivered dose may be different due to volumetric changes during image registration process. In this respect, synthetic CT generated from the MR image would provide more accurate information required for the real time RT. Materials and Methods: We analyzed 1,209 MR images from 16 patients who underwent MR guided RT. Structures were divided into five tissue types, air, lung, fat, soft tissue and bone, according to the Hounsfield unit of deformed CT. Using the deep learning model (U-NET model), synthetic CT images were generated from the MR images acquired during RT. This synthetic CT images were compared to deformed CT generated using the deformable registration. Pixel-to-pixel match was conducted to compare the synthetic and deformed CT images. Results and Discussion: In two test image sets, average pixel match rate per section was more than 70% (67.9 to 80.3% and 60.1 to 79%; synthetic CT pixel/deformed planning CT pixel) and the average pixel match rate in the entire patient image set was 69.8%. Conclusion: The synthetic CT generated from the MR images were comparable to deformed CT, suggesting possible use for real time RT. Deep learning model may further improve match rate of synthetic CT with larger MR imaging data.

• Nuclear Engineering and Technology
• /
• 제53권12호
• /
• pp.4072-4079
• /
• 2021

This article presents a study on the state-of-the-art methods for automated radioactive material detection and identification, using gamma-ray spectra and modern machine learning methods. The recent developments inspired this in deep learning algorithms, and the proposed method provided better performance than the current state-of-the-art models. Machine learning models such as: fully connected, recurrent, convolutional, and gradient boosted decision trees, are applied under a wide variety of testing conditions, and their advantage and disadvantage are discussed. Furthermore, a hybrid model is developed by combining the fully-connected and convolutional neural network, which shows the best performance among the different machine learning models. These improvements are represented by the model's test performance metric (i.e., F1 score) of 93.33% with an improvement of 2%-12% than the state-of-the-art model at various conditions. The experimental results show that fusion of classical neural networks and modern deep learning architecture is a suitable choice for interpreting gamma spectra data where real-time and remote detection is necessary.

• Smart Structures and Systems
• /
• 제24권6호
• /
• pp.693-707
• /
• 2019

This paper proposes an integrated safety assessment method that can take multiple sources data into consideration based on a data fusion approach. Data cleaning using the Kalman filter method (KF) was conducted first for monitoring data from each sensor. The inclination data from the four tilt sensors of the same monitoring section have been associated to synchronize in time. Secondly, the finite element method (FEM) model was established to physically correlate the external forces with various structural responses of the shield tunnel, including the measured inclination. Response surface method (RSM) was adopted to express the relationship between external forces and the structural responses. Then, the external forces were updated based on the in situ monitoring data from tilt sensors using the extended Kalman filter method (EKF). Finally, mechanics parameters of the tunnel lining were estimated based on the updated data to make an integrated safety assessment. An application example of the proposed method was presented for an urban tunnel during a nearby deep excavation with multiple source monitoring plans. The change of tunnel convergence, bolt stress and segment internal forces can also be calculated based on the real time deformation monitoring of the shield tunnel. The proposed method was verified by predicting the data using the other three sensors in the same section. The correlation among different monitoring data has been discussed before the conclusion was drawn.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권10호
• /
• pp.3390-3405
• /
• 2022

Long Short-Term Memory (LSTM) combined with attention mechanism is extensively used to generate semantic sentences of images in image captioning models. However, features of salient regions and spatial information are not utilized sufficiently in most related works. Meanwhile, the LSTM also suffers from the problem of underutilized information in a single time step. In the paper, two innovative approaches are proposed to solve these problems. First, the Synergy-Gated Attention (SGA) method is proposed, which can process the spatial features and the salient region features of given images simultaneously. SGA establishes a gated mechanism through the global features to guide the interaction of information between these two features. Then, the Recurrent Fusion LSTM (RF-LSTM) mechanism is proposed, which can predict the next hidden vectors in one time step and improve linguistic coherence by fusing future information. Experimental results on the benchmark dataset of MSCOCO show that compared with the state-of-the-art methods, the proposed method can improve the performance of image captioning model, and achieve competitive performance on multiple evaluation indicators.

• ETRI Journal
• /
• 제45권5호
• /
• pp.847-861
• /
• 2023

Dynamic object detection is essential for ensuring safe and reliable autonomous driving. Recently, light detection and ranging (LiDAR)-based object detection has been introduced and shown excellent performance on various benchmarks. Although LiDAR sensors have excellent accuracy in estimating distance, they lack texture or color information and have a lower resolution than conventional cameras. In addition, performance degradation occurs when a LiDAR-based object detection model is applied to different driving environments or when sensors from different LiDAR manufacturers are utilized owing to the domain gap phenomenon. To address these issues, a sensor-fusion-based object detection and classification method is proposed. The proposed method operates in real time, making it suitable for integration into autonomous vehicles. It performs well on our custom dataset and on publicly available datasets, demonstrating its effectiveness in real-world road environments. In addition, we will make available a novel three-dimensional moving object detection dataset called ETRI 3D MOD.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.352-368
• /
• 2021

Sign-in point of interest (POI) are extremely sparse in location-based social networks, hindering recommendation systems from capturing users' deep-level preferences. To solve this problem, we propose a content-aware POI recommendation algorithm based on a convolutional neural network. First, using convolutional neural networks to process comment text information, we model location POI and user latent factors. Subsequently, the objective function is constructed by fusing users' geographical information and obtaining the emotional category information. In addition, the objective function comprises matrix decomposition and maximisation of the probability objective function. Finally, we solve the objective function efficiently. The prediction rate and F1 value on the Instagram-NewYork dataset are 78.32% and 76.37%, respectively, and those on the Instagram-Chicago dataset are 85.16% and 83.29%, respectively. Comparative experiments show that the proposed method can obtain a higher precision rate than several other newer recommended methods.

• Journal of Information Processing Systems
• /
• 제17권4호
• /
• pp.754-771
• /
• 2021

In the task of continuous dimension emotion recognition, the parts that highlight the emotional expression are not the same in each mode, and the influences of different modes on the emotional state is also different. Therefore, this paper studies the fusion of the two most important modes in emotional recognition (voice and visual expression), and proposes a two-mode dual-modal emotion recognition method combined with the attention mechanism of the improved AlexNet network. After a simple preprocessing of the audio signal and the video signal, respectively, the first step is to use the prior knowledge to realize the extraction of audio characteristics. Then, facial expression features are extracted by the improved AlexNet network. Finally, the multimodal attention mechanism is used to fuse facial expression features and audio features, and the improved loss function is used to optimize the modal missing problem, so as to improve the robustness of the model and the performance of emotion recognition. The experimental results show that the concordance coefficient of the proposed model in the two dimensions of arousal and valence (concordance correlation coefficient) were 0.729 and 0.718, respectively, which are superior to several comparative algorithms.

• 한국측량학회지
• /
• 제39권6호
• /
• pp.381-392
• /
• 2021

본 연구에서는 UAV (Unmanned Aerial Vehicle)로 촬영한 이미지를 활용하여 수치지도 지형지물 표준 코드에서 정의하고 있는 건물 8종에 대하여 딥러닝 기반의 객체 탐지 분석을 수행하였다. UAV로 촬영한 이미지 509매에 대하여 이미지 라벨링을 하였고 YOLO (You Only Look Once) v5 모델을 적용하여 학습 및 추론을 진행하였다. 실험 및 분석은 오픈소스 기반의 분석 플랫폼과 알고리즘을 적용하여 데이터를 분석하였으며 분석결과 88%~98%의 예측 확률로 건물 객체를 탐지하였다. 또한 학습데이터의 구축 및 반복 학습의 과정에서 건물 객체 탐지의 높은 정확도를 위해 필요한 학습 방식 및 모델 구축방식을 분석하였고, 학습한 모델을 다른 영상자료에 적용하는 방안을 모색하였다. 본 연구를 통해 고효율 심층 신경망과 공간정보데이터가 융합하는 모델을 제안하며 공간정보데이터와 딥러닝 기술의 융합은 향후 공간정보데이터 구축의 효율성, 분석 및 예측의 정확도 향상에 많은 도움을 제공할 것이다.

• 디지털콘텐츠학회 논문지
• /
• 제19권2호
• /
• pp.415-423
• /
• 2018

최근, 컴퓨터 분야의 기계 학습(Machine Learning)과 딥러닝(Deep Learning) 등 컴퓨터 관련 학습이 각광을 받고 있다. 이들은 인공 신경망(Artificial Neural Network)을 이용하여 가장 하위 레벨로부터 학습을 시작하여, 최상위 레벨까지 그 결과를 전달하여 최종 결과를 산출하는 방식이다. 하위레벨로부터의 체계적인 학습을 통한 효과적인 성장 및 교육 방안에 대한 연구는 다양한 분야에서 이루어지고 있으나, 체계적인 규칙과 방법에 기반한 모델은 찾아보기가 힘들다. 이에, 본 논문에서는 성장 및 융합 모델인, TNT 모델(Transitive Nested Triangle Model)을 처음으로 제안한다. 제안하는 모델은 기하학적인 형태를 통해 형성된 각 기능들이 유기적 계층 관계를 형성하여, 상위로 성장 및 융합하면서, 그 결과가 반복 사용되는 순환적 재귀 모델이다. 즉, '수평적 형제 병합에 이은 상위로의 융합(Horizontal Sibling Merges and Upward Convergence)'의 분석적 방법이다. 이러한 모델은 공학, 디지털공학, 인문학, 예술학 등에 모두 적용될 수 있는 기본기적 이론으로, 본 연구에서는 제안하는 TNT 모델을 설명하는 것에 그 초점을 둔다.

• 한국측량학회지
• /
• 제38권5호
• /
• pp.407-414
• /
• 2020

SVM (Support vector machine) analysis was performed after applying a deep learning technique based on an Inception-based model (GoogLeNet). The accuracy of automatic image classification was analyzed using an SVM with multiple virtual grid sizes. Six classes were selected from a standard land cover map. Cars were added as a separate item to increase the classification accuracy of roads. The virtual grid size was 2-5 m for natural areas, 5-10 m for traffic areas, and 10-15 m for building areas, based on the size of items and the resolution of input images. The results demonstrate that automatic classification accuracy can be increased by adopting an integrated approach that utilizes weighted virtual grid sizes for different classes.