• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.814-822
• /
• 2022

The deployment of sensors for Structural Health Monitoring requires a complicated network arrangement, ground truthing, and calibration for validating sensor performance periodically. Any conventional sensor on a structural element is also subjected to static and dynamic vertical loadings in conjunction with other environmental factors, such as brightness, noise, temperature, and humidity. A structural model with strain gauges was built and tested to get realistic sensory information. This paper investigates different deep learning architectures and algorithms, including unsupervised, autoencoder, and supervised methods, to benchmark blind drift calibration methods using deep learning. It involves a fully connected neural network (FCNN), a long short-term memory (LSTM), and a gated recurrent unit (GRU) to address the blind drift calibration problem (i.e., performing calibrations of installed sensors when ground truth is not available). The results show that the supervised methods perform much better than unsupervised methods, such as an autoencoder, when ground truths are available. Furthermore, taking advantage of time-series information, the GRU model generates the most precise predictions to remove the drift overall.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.439-449
• /
• 2023

In an era marked by the increasing use of drones and the growing demand for indoor surveillance, the development of a robust application for detecting and tracking both drones and humans within indoor spaces becomes imperative. This study presents an innovative application that uses FMCW radar to detect human and drone motions from the cloud point. At the outset, the DBSCAN (Density-based Spatial Clustering of Applications with Noise) algorithm is utilized to categorize cloud points into distinct groups, each representing the objects present in the tracking area. Notably, this algorithm demonstrates remarkable efficiency, particularly in clustering drone point clouds, achieving an impressive accuracy of up to 92.8%. Subsequently, the clusters are discerned and classified into either humans or drones by employing a deep learning model. A trio of models, including Deep Neural Network (DNN), Residual Network (ResNet), and Long Short-Term Memory (LSTM), are applied, and the outcomes reveal that the ResNet model achieves the highest accuracy. It attains an impressive 98.62% accuracy for identifying drone clusters and a noteworthy 96.75% accuracy for human clusters.

• Journal of Service Research and Studies
• /
• v.13 no.2
• /
• pp.99-113
• /
• 2023

In a customer-based industry, customer retention is the competitiveness of a company, and improving customer retention improves the competitiveness of the company. Therefore, accurate prediction and management of potential dormant customers is paramount to increasing the competitiveness of the enterprise. In particular, there are numerous competitors in the domestic card industry, and the government is introducing an automatic closing system for dormant card management. As a result of these social changes, the card industry must focus on better predicting and managing potential dormant cards, and better predicting dormant customers is emerging as an important challenge. In this study, the Recurrent Neural Network (RNN) methodology was used to predict potential dormant customers in the card industry, and in particular, Long-Short Term Memory (LSTM) was used to efficiently learn data for a long time. In addition, to redefine the variables needed to predict dormant customers in the card industry, Unified Theory of Technology (UTAUT), an integrated technology acceptance theory, was applied to redefine and group the variables used in the model. As a result, stable model accuracy and F-1 score were obtained, and Hit-Ratio proved that models using LSTM can produce stable results compared to other algorithms. It was also found that there was no moderating effect of demographic information that could occur in UTAUT, which was pointed out in previous studies. Therefore, among variable selection models using UTAUT, dormant customer prediction models using LSTM are proven to have non-biased stable results. This study revealed that there may be academic contributions to the prediction of dormant customers using LSTM algorithms that can learn well from previously untried time series data. In addition, it is a good example to show that it is possible to respond to customers who are preemptively dormant in terms of customer management because it is predicted at a time difference with the actual dormant capture, and it is expected to contribute greatly to the industry.

• Information Systems Review
• /
• v.23 no.1
• /
• pp.23-43
• /
• 2021

Recently, many studies have been conducted to increase the accuracy of stock price prediction by analyzing candlestick charts using artificial intelligence techniques. However, these studies failed to consider the time-series characteristics of candlestick charts and to take into account the emotional state of market participants in data learning for stock price prediction. In order to overcome these limitations, this study produced input data by combining volatility index and candlestick charts to consider the emotional state of market participants, and used the data as input for a new method proposed on the basis of combining variantion autoencoder (VAE) and attention mechanisms for considering the time-series characteristics of candlestick chart. Fifty firms were randomly selected from the S&P 500 index and their stock prices were predicted to evaluate the performance of the method compared with existing ones such as convolutional neural network (CNN) or long-short term memory (LSTM). The results indicated the method proposed in this study showed superior performance compared to the existing ones. This study implied that the accuracy of stock price prediction could be improved by considering the emotional state of market participants and the time-series characteristics of the candlestick chart.

• 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.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.110-110
• /
• 2022

본 연구는 자율운항 선박의 원격 고장 진단 기법 개발의 일부로 수행되었다. 특히, 엔진 연료 계통 장비로부터 계측된 시계열 데이터로부터 상태 진단을 위한 알고리즘 구현 결과를 제시하였다. 엔진 연료 펌프와 청정기를 가진 육상 실험 장비로부터 진동 시계열 데이터 계측하였으며, 이상 감지, 고장 분류 및 고장 예측이 가능한 심층 학습(Deep Learning) 및 기계 학습(Machine Learning) 알고리즘을 구현하였다. 육상 실험 장비에 고장 유형 별로 인위적인 고장을 발생시켜 특징적인 진동 신호를 계측하여, 인공 지능 학습에 이용하였다. 계측된 신호 데이터는 선행 발생한 사건의 신호가 후행 사건에 영향을 미치는 특성을 가지고 있으므로, 시계열에 내포된 고장 상태는 시간 간의 선후 종속성을 반영할 수 있는 학습 알고리즘을 제시하였다. 고장 사건의 시간 종속성을 반영할 수 있도록 순환(Recurrent) 계열의 RNN(Recurrent Neural Networks), LSTM(Long Short-Term Memory models)의 모델과 합성곱 연산 (Convolution Neural Network)을 기반으로 하는 Conv1D 모델을 적용하여 예측 정확성을 비교하였다. 특히, 합성곱 계열의 RNN LSTM 모델이 고차원의 순차적 자연어 언어 처리에 장점을 보이는 모델임을 착안하여, 신호의 시간 종속성을 학습에 반영할 수 있는 합성곱 계열의 Conv1 알고리즘을 고장 예측에 사용하였다. 또한 기계 학습 모델의 효율성을 감안하여 XGBoost를 추가로 적용하여 고장 예측을 시도하였다. 최종적으로 연료 펌프와 청정기의 진동 신호로부터 Conv1D 모델과 XGBoost 모델의 고장 예측 성능 결과를 비교하였다

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.4 s.310
• /
• pp.37-45
• /
• 2006

In this paper, we propose the development of MHLA(Modulatory Hippocampus Learning Algorithm) which remodel a principle of brain of hippocampus. Hippocampus takes charge auto-associative memory and controlling functions of long-term or short-term memory strengthening. We organize auto-associative memory based 3 steps system(DG, CA3, CAl) and improve speed of learning by addition of modulator to long-term memory learning. In hippocampal system, according to the 3 steps order, information applies statistical deviation on Dentate Gyrus region and is labelled to responsive pattern by adjustment of a good impression. In CA3 region, pattern is reorganized by auto-associative memory. In CAI region, convergence of connection weight which is used long-term memory is learned fast by neural networks which is applied modulator. To measure performance of MHLA, PCA(Principal Component Analysis) is applied to face images which are classified by pose, expression and picture quality. Next, we calculate feature vectors and learn by MHLA. Finally, we confirm cognitive rate. The results of experiments, we can compare a proposed method of other methods, and we can confirm that the proposed method is superior to the existing method.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.1
• /
• pp.1-16
• /
• 2020

With the advent of the fourth industrial revolution era, there has been a growing interest in deep learning using big data, and studies using deep learning have been actively conducted in various fields. In the transportation sector, there are many advantages to using deep learning in research as much as using deep traffic big data. In this study, a short -term travel speed prediction model using LSTM, a deep learning technique, was constructed to predict the travel speed. The LSTM model suitable for time series prediction was selected considering that the travel speed data, which is used for prediction, is time series data. In order to predict the travel speed more precisely, we constructed a model that reflects both temporal and spatial effects. The model is a short-term prediction model that predicts after one hour. For the analysis data, the 5minute travel speed collected from the Seoul Transportation Information Center was used, and the analysis section was selected as a part of Gangnam where traffic was congested.

• Journal of Advanced Navigation Technology
• /
• v.22 no.3
• /
• pp.233-239
• /
• 2018

Since solar power generation is intermittent depending on weather conditions, it is necessary to predict the accurate generation amount of solar power to improve the efficiency and economical efficiency of solar power generation. This study proposes a short - term deep learning prediction model of solar power generation using meteorological data from Mokpo meteorological agency and generation data of Yeongam solar power plant. The meteorological agency forecasts weather factors such as temperature, precipitation, wind direction, wind speed, humidity, and cloudiness for three days. However, sunshine and solar radiation, the most important meteorological factors for forecasting solar power generation, are not predicted. The proposed model predicts solar radiation and solar radiation using forecast meteorological factors. The power generation was also forecasted by adding the forecasted solar and solar factors to the meteorological factors. The forecasted power generation of the proposed model is that the average RMSE and MAE of DNN are 0.177 and 0.095, and RNN is 0.116 and 0.067. Also, LSTM is the best result of 0.100 and 0.054. It is expected that this study will lead to better prediction results by combining various input.

• The Journal of the Korea Contents Association
• /
• v.11 no.3
• /
• pp.271-280
• /
• 2011

Heart Rate Variability (HRV) analysis is a convenient tool to assess Myocardial Ischemia (MI). The analysis methods of HRV can be divided into time domain and frequency domain analysis. This paper uses wavelet transform as frequency domain analysis in contrast to time domain analysis in short term HRV analysis. ST-T and normal episodes are collected from the European ST-T database and the MIT-BIH Normal Sinus Rhythm database, respectively. An episode can be divided into several segments, each of which is formed by 32 successive RR intervals. Eighteen HRV features are extracted from each segment by the time and frequency domain analysis. To diagnose MI, the Neural Network with Weighted Fuzzy Membership functions (NEWFM) is used with the extracted 18 features. The results show that the average accuracy from time and frequency domain features is 75.29% and 80.93%, respectively.