• The Journal of the Acoustical Society of Korea
• /
• v.39 no.2
• /
• pp.137-142
• /
• 2020

Many studies based on I-vector have been conducted in a variety of environments, from text-dependent short-utterance to text-independent long-utterance. In this paper, we propose a speaker verification system employing a combination of I-vector with Probabilistic Linear Discriminant Analysis (PLDA) and speaker embedding of Long Short Term Memory (LSTM) with attention mechanism in far-field and noisy environments. The LSTM model's Equal Error Rate (EER) is 15.52 % and the Attention-LSTM model is 8.46 %, improving by 7.06 %. We show that the proposed method solves the problem of the existing extraction process which defines embedding as a heuristic. The EER of the I-vector/PLDA without combining is 6.18 % that shows the best performance. And combined with attention-LSTM based embedding is 2.57 % that is 3.61 % less than the baseline system, and which improves performance by 58.41 %.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.5
• /
• pp.592-601
• /
• 2016

The recurrent neural network (RNN) is a deep learning model which is suitable to sequential or length-variable data. The Long Short-Term Memory (LSTM) mitigates the vanishing gradient problem of RNNs so that LSTM can maintain the long-term dependency among the constituents of the given input sequence. In this paper, we propose a LSTM based language model which can predict following words of a given incomplete sentence to generate a complete sentence. To evaluate our method, we trained our model using multiple Korean corpora then generated the incomplete part of Korean sentences. The result shows that our language model was able to generate the fluent Korean sentences. We also show that the word based model generated better sentences compared to the other settings.

• Journal of Aerospace System Engineering
• /
• v.16 no.4
• /
• pp.45-52
• /
• 2022

In the field of UAM, which is attracting attention as a next-generation transportation system, technology developments for using UAVs have been actively conducted in recent years. Since UAVs adopted with these technologies are mainly operated in urban areas, it is imperative that accidents are prevented. However, it is not easy to predict the abnormal flight state of an UAV causing a crash, because of its strong non-linearity. In this paper, we propose a method for predicting a flight state of an UAV, based on a CNN-LSTM hybrid model. To predict flight state variables at a specific point in the future, the proposed model combines the CNN model extracting temporal and spatial features between flight data, with the LSTM model extracting a short and long-term temporal dependence of the extracted features. Simulation results show that the proposed method has better performance than the prediction methods, which are based on the existing artificial neural network model.

• The Korean Journal of Applied Statistics
• /
• v.37 no.2
• /
• pp.191-207
• /
• 2024

Many studies have been conducted to quickly detect out-of-control situations in autocorrelated processes. The most traditionally used method is a residual control chart, which uses residuals calculated from a fitted time series model. However, many procedures for monitoring autocorrelated processes using statistical learning methods have recently been proposed. In this paper, we propose a monitoring procedure using the latent vector of LSTM Autoencoder, a deep learning-based unsupervised learning method. We compare the performance of this procedure with the LSTM Autoencoder procedure based on the reconstruction error, the RNN classification procedure, and the residual charting procedure through simulation studies. Simulation results show that the performance of the proposed procedure and the RNN classification procedure are similar, but the proposed procedure has the advantage of being useful in processes where sufficient out-of-control data cannot be obtained, because it does not require out-of-control data for training.

• Journal of Korea Multimedia Society
• /
• v.25 no.11
• /
• pp.1547-1556
• /
• 2022

As mechanical facilities are interacting with each other, the failure of some equipment can affect the entire system, so it is necessary to quickly detect and diagnose the abnormality of mechanical equipment. This study proposes a deep learning model that can effectively diagnose abnormalities in rotating machinery and equipment. CNN is widely used for feature extraction and LSTMs are known to be effective in learning sequential information. In LSTM, the number of parameters and learning time increase as the length of input data increases. In this study, we propose a method of segmenting an input segment signal into shorter-length sub-segment signals, sequentially inputting them to CNN through a time-distributed method for extracting features, and inputting them into LSTM. A failure diagnosis test was performed using the vibration data collected from the motor for ventilation equipment installed at the urban railway station. The experiment showed an accuracy of 99.784% in fault diagnosis. It shows that the proposed method is effective in the fault diagnosis of rotating machinery and equipment.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.5
• /
• pp.79-85
• /
• 2019

In this paper, we propose a short-term power forecasting method by applying Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) neural network to Internet of Things (IoT) power meter. We analyze performance based on real power consumption data of households. Mean absolute error (MAE), mean absolute percentage error (MAPE), mean percentage error (MPE), mean squared error (MSE), and root mean squared error (RMSE) are used as performance evaluation indexes. The experimental results show that the GRU-based model improves the performance by 4.52% in the MAPE and 5.59% in the MPE compared to the LSTM-based model.

• KNOM Review
• /
• v.24 no.2
• /
• pp.13-23
• /
• 2021

Recently, as networks become more complex due to the activation of IoT devices, research on long-term traffic prediction beyond short-term traffic prediction is being activated to predict and prepare for network congestion in advance. The recursive strategy, which reuses short-term traffic prediction results as an input, has been extended to multi-step traffic prediction, but as the steps progress, errors accumulate and cause deterioration in prediction performance. In this paper, an LSTM-based multi-step traffic prediction method using a multi-output strategy is introduced and its performance is evaluated. As a result of experiments based on actual DNS request traffic, it was confirmed that the proposed LSTM-based multiple output strategy technique can reduce MAPE of traffic prediction performance for non-stationary traffic by 6% than the recursive strategy technique.

• International Journal of Advanced Culture Technology
• /
• v.10 no.1
• /
• pp.274-283
• /
• 2022

Korea is facing a number difficulties arising from rising housing prices. As 'housing' takes the lion's share in personal assets, many difficulties are expected to arise from fluctuating housing prices. The purpose of this study is creating housing price prediction model to prevent such risks and induce reasonable real estate purchases. This study made many attempts for understanding real estate instability and creating appropriate housing price prediction model. This study predicted and validated housing prices by using the LSTM technique - a type of Artificial Intelligence deep learning technology. LSTM is a network in which cell state and hidden state are recursively calculated in a structure which added cell state, which is conveyor belt role, to the existing RNN's hidden state. The real sale prices of apartments in autonomous districts ranging from January 2006 to December 2019 were collected through the Ministry of Land, Infrastructure, and Transport's real sale price open system and basic apartment and commercial district information were collected through the Public Data Portal and the Seoul Metropolitan City Data. The collected real sale price data were scaled based on monthly average sale price and a total of 168 data were organized by preprocessing respective data based on address. In order to predict prices, the LSTM implementation process was conducted by setting training period as 29 months (April 2015 to August 2017), validation period as 13 months (September 2017 to September 2018), and test period as 13 months (December 2018 to December 2019) according to time series data set. As a result of this study for predicting 'prices', there have been the following results. Firstly, this study obtained 76 percent of prediction similarity. We tried to design a prediction model of real estate transaction price with the LSTM Model based on AI and Bigdata. The final prediction model was created by collecting time series data, which identified the fact that 76 percent model can be made. This validated that predicting rate of return through the LSTM method can gain reliability.

• Smart Structures and Systems
• /
• v.32 no.5
• /
• pp.297-308
• /
• 2023

Dynamic deflection is important for evaluating the performance of a long-span cable-stayed bridge, and its continuous measurement is still cumbersome. This study proposes a dynamic deflection monitoring method for cable-stayed bridge based on Bi-directional Long Short-term Memory (BiLSTM) neural network taking advantages of the characteristics of spatial variation of cable acceleration response (CAR) and main girder deflection response (MGDR). Firstly, the relationship between the spatial and temporal variation of the CAR and the MGDR is described based on the geometric deformation of the bridge. Then a data-driven relational model based on BiLSTM neural network is established using CAR and MGDR data, and it is further used to monitor the MGDR via measuring the CAR. Finally, numerical simulations and field test are conducted to verify the proposed method. The root mean squared error (RMSE) of the numerical simulations are less than 4 while the RMSE of the field test is 1.5782, which indicate that it provides a cost-effective and convenient method for real-time deflection monitoring of cable-stayed bridges.

• 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.