• Journal of Information Processing Systems
• /
• v.16 no.6
• /
• pp.1407-1423
• /
• 2020

A graph is a data structure consisting of nodes and edges between these nodes. Graph embedding is to generate a low dimensional vector for a given graph that best represents the characteristics of the graph. Recently, there have been studies on graph embedding, especially using deep learning techniques. However, until now, most deep learning-based graph embedding techniques have focused on unweighted graphs. Therefore, in this paper, we propose a graph embedding technique for weighted graphs based on long short-term memory (LSTM) autoencoders. Given weighted graphs, we traverse each graph to extract node-weight sequences from the graph. Each node-weight sequence represents a path in the graph consisting of nodes and the weights between these nodes. We then train an LSTM autoencoder on the extracted node-weight sequences and encode each nodeweight sequence into a fixed-length vector using the trained LSTM autoencoder. Finally, for each graph, we collect the encoding vectors obtained from the graph and combine them to generate the final embedding vector for the graph. These embedding vectors can be used to classify weighted graphs or to search for similar weighted graphs. The experiments on synthetic and real datasets show that the proposed method is effective in measuring the similarity between weighted graphs.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.6
• /
• pp.684-692
• /
• 2024

Effective border security is crucial in managing and mitigating firearm-related threats. While prior research has focused on firearm detection, it lacks contextual analysis. This paper advances firearm-related incident assessment by integrating pose estimation to improve gun violence detection. Our novel approach extracts body and firearm pose graphs and employs Graph Attention Networks(GAT) for graph analysis to accurately identify gun violence incidents. By recognizing associated actions, our system provides greater situational awareness beyond mere firearm detection. Utilizing Graph-LSTM, we capture spatial and temporal information. As a result, our proposed algorithm is lighter and more accurate than the CNN-LSTM model used as a baseline, achieving test F1-scores of 82.04 % on our collected data.

• 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.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.10
• /
• pp.399-406
• /
• 2021

With the steady growth of the content industry, the need for research that automatically recommending content suitable for individual tastes is increasing. In order to improve the accuracy of automatic content recommendation, it is needed to fuse existing recommendation techniques using users' preference history for contents along with recommendation techniques using content metadata or features extracted from the content itself. In this work, we propose a new graph-based music recommendation method which learns an LSTM-based classification model to automatically extract appropriate tagging words from sound data and apply the extracted tagging words together with the users' preferred music lists and music metadata to graph-based music recommendation. Experimental results show that the proposed method outperforms existing recommendation methods in terms of the recommendation accuracy.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.321-326
• /
• 2020

본 연구에서는 한국어 감성분석 성능 향상을 위한 DECO(Dictionnaire Electronique du COreen) 한국어 전자사전과 LGG(Local-Grammar Graph) 패턴문법 기술 프레임에 의존파서 및 LSTM을 적용하는 하이브리드 방법론을 제안하였다. 본 연구에 사용된 DECO-LGG 언어자원을 소개하고, 이에 기반하여 의미 정보를 의존파서(D-PARS)와 페어링하는 한편 OOV(Out Of Vocabulary)의 문제를 LSTM을 통해 해결하여 자질기반 감성분석 결과를 제시하였다. 부트스트랩 방식으로 반복 확장될 수 있는 LGG 언어자원 및 알고리즘을 통해 수행되는 자질기반 감성분석 프로세스는 전용 플랫폼 DecoFESA를 통해 그 범용성을 확장하였다. 실험을 위해서 네이버 쇼핑몰의 '화장품 구매 후기글'을 크롤링하였으며, DecoFESA 플랫폼을 통해 현재 구축된 DECO-LGG 언어자원 기반의 감성분석 성능을 평가하였다. 이를 통해 대용량 언어자원의 구축과 이를 활용하기 위한 어휘 시퀀스 처리 알고리즘의 구현이 보다 정확한 자질기반 감성분석 결과를 제공할 수 있음을 확인하였다.

• Journal of Convergence for Information Technology
• /
• v.11 no.7
• /
• pp.31-38
• /
• 2021

In this paper, in order to obtain the optimization of the RNN model used for sentiment analysis, the correlation of each model was studied by observing the trend of loss and accuracy according to hyperparameter tuning. As a research method, after configuring the hidden layer with LSTM and the embedding layer that are most optimized to process sequential data, the loss and accuracy of each model were measured by tuning the unit, batch-size, and embedding size of the LSTM. As a result of the measurement, the loss was 41.9% and the accuracy was 11.4%, and the trend of the optimization model showed a consistently stable graph, confirming that the tuning of the hyperparameter had a profound effect on the model. In addition, it was confirmed that the decision of the embedding size among the three hyperparameters had the greatest influence on the model. In the future, this research will be continued, and research on an algorithm that allows the model to directly find the optimal hyperparameter will continue.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.342-344
• /
• 2018

This paper shows the possibility to substitute statistical methods such as mean imputation, correlation coefficient analysis, graph correlation analysis for the proposed algorithm, and replace statistician for processing various abnormal data measured in the water treatment process with it. In addition, this study aims to model a data-filtering system based on a recent fractile pattern and a deep learning-based LSTM algorithm in order to improve the reliability and validation of the algorithm, using the open-sourced libraries such as KERAS, THEANO, TENSORFLOW, etc.

• Annual Conference of KIPS
• /
• 2021.05a
• /
• pp.463-465
• /
• 2021

센서 데이터는 여러가지 원인으로 인해 데이터 결측치가 발생할 수 있으며, 결측치로 인한 데이터의 처리 방식에 따라 데이터 분석 결과가 다르게 해석될 수 있다. 이는 펫 헬스 케어 서비스에서 치명적인 문제로 연결될 수 있다. 따라서 본 논문에서는 펫 웨어러블 디바이스로부터 수집되는 다양한 센서 데이터의 결측치를 처리하기 위해 GATs(Graph Attention neTworks)와 LSTM(Long Short Term Memory)을 결합하여 활용한 데이터 결측치 처리 기법을 제안한다. 펫 웨어러블 디바이스의 센서 데이터가 서로 연관성을 가지고 있다는 점을 바탕으로 인접 노드의 Attention 수치와 Feature map을 도출한다. 이후 Prediction Layer 를 통해 결측치의 Feature 를 예측한다. 예측된 Feature 를 기반으로 Decoding 과정과 함께 결측치 보간이 이루어진다. 제안된 기법은 모델의 변형을 통해 이상치 탐지에도 활용할 수 있을 것으로 기대한다.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.161-177
• /
• 2019

In this paper, we study the performance improvement of the answer extraction in Question-Answering system by using sentence dependency parsing result. The Question-Answering (QA) system consists of query analysis, which is a method of analyzing the user's query, and answer extraction, which is a method to extract appropriate answers in the document. And various studies have been conducted on two methods. In order to improve the performance of answer extraction, it is necessary to accurately reflect the grammatical information of sentences. In Korean, because word order structure is free and omission of sentence components is frequent, dependency parsing is a good way to analyze Korean syntax. Therefore, in this study, we improved the performance of the answer extraction by adding the features generated by dependency parsing analysis to the inputs of the answer extraction model (Bidirectional LSTM-CRF). The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. In this study, we compared the performance of the answer extraction model when inputting basic word features generated without the dependency parsing and the performance of the model when inputting the addition of the Eojeol tag feature and dependency graph embedding feature. Since dependency parsing is performed on a basic unit of an Eojeol, which is a component of sentences separated by a space, the tag information of the Eojeol can be obtained as a result of the dependency parsing. The Eojeol tag feature means the tag information of the Eojeol. The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. From the dependency parsing result, a graph is generated from the Eojeol to the node, the dependency between the Eojeol to the edge, and the Eojeol tag to the node label. In this process, an undirected graph is generated or a directed graph is generated according to whether or not the dependency relation direction is considered. To obtain the embedding of the graph, we used Graph2Vec, which is a method of finding the embedding of the graph by the subgraphs constituting a graph. We can specify the maximum path length between nodes in the process of finding subgraphs of a graph. If the maximum path length between nodes is 1, graph embedding is generated only by direct dependency between Eojeol, and graph embedding is generated including indirect dependencies as the maximum path length between nodes becomes larger. In the experiment, the maximum path length between nodes is adjusted differently from 1 to 3 depending on whether direction of dependency is considered or not, and the performance of answer extraction is measured. Experimental results show that both Eojeol tag feature and dependency graph embedding feature improve the performance of answer extraction. In particular, considering the direction of the dependency relation and extracting the dependency graph generated with the maximum path length of 1 in the subgraph extraction process in Graph2Vec as the input of the model, the highest answer extraction performance was shown. As a result of these experiments, we concluded that it is better to take into account the direction of dependence and to consider only the direct connection rather than the indirect dependence between the words. The significance of this study is as follows. First, we improved the performance of answer extraction by adding features using dependency parsing results, taking into account the characteristics of Korean, which is free of word order structure and omission of sentence components. Second, we generated feature of dependency parsing result by learning - based graph embedding method without defining the pattern of dependency between Eojeol. Future research directions are as follows. In this study, the features generated as a result of the dependency parsing are applied only to the answer extraction model in order to grasp the meaning. However, in the future, if the performance is confirmed by applying the features to various natural language processing models such as sentiment analysis or name entity recognition, the validity of the features can be verified more accurately.

• ETRI Journal
• /
• v.45 no.4
• /
• pp.650-665
• /
• 2023

A novel smart metering technique capable of anomaly detection was proposed for real-time home power management system. Smart meter data generated in real-time were obtained from 900 households of single apartments. To detect outliers and missing values in smart meter data, a deep learning model, the autoencoder, consisting of a graph convolutional network and bidirectional long short-term memory network, was applied to the smart metering technique. Power management based on the smart metering technique was executed by multi-objective optimization in the presence of a battery storage system and an electric vehicle. The results of the power management employing the proposed smart metering technique indicate a reduction in electricity cost and amount of power supplied by the grid compared to the results of power management without anomaly detection.