• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.441-442
• /
• 2022

교통사고 예측은 차량의 블랙박스 동영상을 통해 사고 발생을 최대한 빨리 예측하는 것을 목표로 한다. 이는 안전한 자율주행 시스템을 보장하는 데 중요한 역할을 한다. 다양한 교통 상황과 카메라의 제한된 시야로 인해 프레임에서 사고 가능성을 조기에 관찰하는 것은 어려운 도전이다. 예측의 핵심 기술은 객체의 시공간 관계를 학습하는 것이다. 본 논문에서는 블랙박스 동영상에서 사고 예측을 위한 계산 모델을 제안한다. 이것을 사용하여 사고 예방을 강화한다. 이 모델은 사고 위험에 대한 운전자의 시각적 인식에서 영감을 받았다. 객체 탐지기는 동영상 프레임에서 다양한 객체를 탐지한다. 탐지한 객체는 노드 생성기와 특징 추출기 동시에 통과한다. 노드 생성기에서 생성한 노드는 GCN 실행기를 사용한다. GCN 실행기는 각 프레임에 대한 객체의 3D 위치 관계를 계산한 후 공간 특징을 취득한다. 동시에 공간 특징과 특징 추출기에서 얻은 객체의 특징은 GRU 실행기로 보내진다. GRU 실행기 안에 시공간 특징을 암기하고 분석하여 교통사고 확률을 예측한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.670-673
• /
• 2022

설명가능한 인공지능은 딥러닝과 같은 복잡한 모델에서 어떠한 원리로 해당 결과를 도출해냈는지에 대한 설명을 함으로써 구축된 모델을 이해할 수 있도록 설명하는 기술이다. 최근 여러 분야에서 그래프 형태의 데이터들이 생성되고 있으며, 이들에 대한 분류를 위해 다양한 그래프 신경망들이 사용되고 있다. 본 논문에서는 대표적인 그래프 신경망인 그래프 합성곱 신경망(graph convolutional network, GCN)에 대한 설명 기법을 제안한다. 제안 기법은 주어진 그래프의 각 노드를 GCN을 사용하여 분류했을 때, 각 노드의 어떤 특징들이 분류에 가장 큰 영향을 미쳤는지를 수치로 알려준다. 제안 기법은 최종 분류 결과에 영향을 미친 요소들을 gradient를 통해 단계적으로 추적함으로써 각 노드의 어떤 특징들이 분류에 중요한 역할을 했는지 파악한다. 가상 데이터를 통한 실험을 통해 제안 방법은 분류에 가장 큰 영향을 주는 노드들의 특징들을 실제로 정확히 찾아냄을 확인하였다.

• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.803-816
• /
• 2023

Explainable artificial intelligence is a method that explains how a complex model (e.g., a deep neural network) yields its output from a given input. Recently, graph-type data have been widely used in various fields, and diverse graph neural networks (GNNs) have been developed for graph-type data. However, methods to explain the behavior of GNNs have not been studied much, and only a limited understanding of GNNs is currently available. Therefore, in this paper, we propose an explanation method for node classification using graph convolutional networks (GCNs), which is a representative type of GNN. The proposed method finds out which features of each node have the greatest influence on the classification of that node using GCN. The proposed method identifies influential features by backtracking the layers of the GCN from the output layer to the input layer using the gradients. The experimental results on both synthetic and real datasets demonstrate that the proposed explanation method accurately identifies the features of each node that have the greatest influence on its classification.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.88-97
• /
• 2023

Traffic flow prediction is of great significance in urban planning and traffic management. As the complexity of urban traffic increases, existing prediction methods still face challenges, especially for the fusion of spatiotemporal information and the capture of long-term dependencies. This study aims to use the fusion model of graph neural network to solve the spatio-temporal information fusion problem in traffic flow prediction. We propose a new deep learning model Spatio-Temporal Information Fusion using Graph Neural Networks (STFGNN). We use GCN module, TCN module and LSTM module alternately to carry out spatiotemporal information fusion. GCN and multi-core TCN capture the temporal and spatial dependencies of traffic flow respectively, and LSTM connects multiple fusion modules to carry out spatiotemporal information fusion. In the experimental evaluation of real traffic flow data, STFGNN showed better performance than other models.

• Molecules and Cells
• /
• v.38 no.12
• /
• pp.1037-1043
• /
• 2015

The TAZ activator 2-butyl-5-methyl-6-(pyridine-3-yl)-3-[2'-(1H-tetrazole-5-yl)-biphenyl-4-ylmethyl]-3H-imidazo[4,5-b]pyridine] (TM-25659) inhibits adipocyte differentiation by interacting with peroxisome proliferator-activated receptor gamma. 1 TM-25659 was previously shown to decrease weight gain in a high fat (HF) diet-induced obesity (DIO) mouse model. However, the fundamental mechanisms underlying the effects of TM-25659 remain unknown. Therefore, we investigated the effects of TM-25659 on skeletal muscle functions in C2 myotubes and C57BL/6J mice. We studied the molecular mechanisms underlying the contribution of TM-25659 to palmitate (PA)-induced insulin resistance in C2 myotubes. TM-25659 improved PA-induced insulin resistance and inflammation in C2 myotubes. In addition, TM-25659 increased FGF21 mRNA expression, protein levels, and FGF21 secretion in C2 myotubes via activation of GCN2 pathways (GCN2-$phosphoelF2{\alpha}$-ATF4 and FGF21). This beneficial effect of TM-25659 was diminished by FGF21 siRNA. C57BL/6J mice were fed a HF diet for 30 weeks. The HF-diet group was randomly divided into two groups for the next 14 days: the HF-diet and HF-diet + TM-25659 groups. The HF diet + TM-25659-treated mice showed improvements in their fasting blood glucose levels, insulin sensitivity, insulin-stimulated Akt phosphorylation, and inflammation, but neither body weight nor food intake was affected. The HF diet + TM-25659-treated mice also exhibited increased expression of both FGF21 mRNA and protein. These data indicate that TM-25659 may be beneficial for treating insulin resistance by inducing FGF21 in models of PA-induced insulin resistance and HF diet-induced insulin resistance.

• Proceedings of the Microbiological Society of Korea Conference
• /
• 2005.05a
• /
• pp.220.4-220
• /
• 2005

• BMB Reports
• /
• v.52 no.3
• /
• pp.163-164
• /
• 2019

The ribosomal synthesis of proteins in the eukaryotic cytosol has always been thought to start from the unformylated N-terminal (Nt) methionine (Met). In contrast, in virtually all nascent proteins in bacteria and eukaryotic organelles, such as mitochondria and chloroplasts, Nt-formyl-methionine (fMet) is the first building block of ribosomal synthesis. Through extensive approaches, including mass spectrometric analyses of the N-termini of proteins and molecular genetic techniques with an affinity-purified antibody for Nt-formylation, we investigated whether Nt-formylated proteins could also be produced and have their own metabolic fate in the cytosol of a eukaryote, such as yeast Saccharomyces cerevisiae. We discovered that Nt-formylated proteins could be generated in the cytosol by yeast mitochondrial formyltransferase (Fmt1). These Nt-formylated proteins were massively upregulated in the stationary phase or upon starvation for specific amino acids and were crucial for the adaptation to specific stresses. The stress-activated kinase Gcn2 was strictly required for the upregulation of Nt-formylated proteins by regulating the activity of Fmt1 and its retention in the cytosol. We also found that the Nt-fMet residues of Nt-formylated proteins could be distinct N-terminal degradation signals, termed fMet/N-degrons, and that Psh1 E3 ubiquitin ligase mediated the selective destruction of Nt-formylated proteins as the recognition component of a novel eukaryotic fMet/N-end rule pathway, termed fMet/N-recognin.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.752-759
• /
• 2022

The instantiation of spaces as a discrete entity allows users to utilize BIM models in a wide range of analyses. However, in practice, their utility has been limited as spaces are erroneously entered due to human error and often omitted entirely. Recent studies attempted to automate space allocation using artificial intelligence approaches. However, there has been limited success as most studies focused solely on the use of geometric features to distinguish spaces. In this study, in addition to geometric features, semantic relations between spaces and elements were modeled and used to improve space classification in BIM models. Graph Convolutional Networks (GCN), a deep learning algorithm specifically tailored for learning in graphs, was deployed to classify spaces via a similarity graph that represents the relationships between spaces and their surrounding elements. Results confirmed that accuracy (ACC) was +0.08 higher than the baseline model in which only geometric information was used. Most notably, GCN was able to correctly distinguish spaces with no apparent difference in geometry by discriminating the specific elements that were provided by the similarity graph.

• Korean Journal of Construction Engineering and Management
• /
• v.23 no.3
• /
• pp.45-55
• /
• 2022

BIM models allow building spaces to be instantiated and recognized as unique objects independently of model elements. These instantiated spaces provide the required semantics that can be leveraged for building code checking, energy analysis, and evacuation route analysis. However, theses spaces or rooms need to be designated manually, which in practice, lead to errors and omissions. Thus, most BIM models today does not guarantee the semantic integrity of space designations, limiting their potential applicability. Recent studies have explored ways to automate space allocation in BIM models using artificial intelligence algorithms, but they are limited in their scope and relatively low classification accuracy. This study explored the use of Graph Convolutional Networks, an algorithm exclusively tailored for graph data structures. The goal was to utilize not only geometry information but also the semantic relational data between spaces and elements in the BIM model. Results of the study confirmed that the accuracy was improved by about 8% compared to algorithms that only used geometric distinctions of the individual spaces.

• Proceedings of the Zoological Society Korea Conference
• /
• 1998.10b
• /
• pp.93-93
• /
• 1998

No Abstract, See Full Text