• Communications for Statistical Applications and Methods
• /
• v.28 no.1
• /
• pp.39-57
• /
• 2021

Time series prediction is an area of great interest to many people. Algorithms for time series prediction are widely used in many fields such as stock price, temperature, energy and weather forecast; in addtion, classical models as well as recurrent neural networks (RNNs) have been actively developed. After introducing the attention mechanism to neural network models, many new models with improved performance have been developed; in addition, models using attention twice have also recently been proposed, resulting in further performance improvements. In this paper, we consider time series prediction by introducing attention twice to an RNN model. The proposed model is a method that introduces H-attention and T-attention for output value and time step information to select useful information. We conduct experiments on stock price, temperature and energy data and confirm that the proposed model outperforms existing models.

• Journal of the Korean Geotechnical Society
• /
• v.36 no.3
• /
• pp.5-14
• /
• 2020

The railway concrete track has been increasingly adopted for high-speed train such as KTX due to its high running stability, improved ride quality for the passengers, and low maintenance cost. However, excessive settlement of the railway concrete track has been monitored at embankment sections of the ◯◯ High-speed Line, resulting in the concerns on the safety of railway operation. In order to establish an effective maintenance plan for the concrete track railway exceeding the allowable residual settlement, it is essential to reasonably predict their long-term settlement behavior during the public period. In this study, we developed a model for predicting the long-term settlement behavior of concrete track using recurrent neural network (RNN) and examined the applicability of the developed model.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.177-183
• /
• 2022

Recently, interesting of home training is getting bigger due to COVID-19. Accordingly, research on applying HAR(human activity recognition) technology to home training has been conducted. However, existing paper of HAR proposed static activity instead of dynamic activity. In this paper, the deep learning model where dynamic exercise posture can be analyzed and the accuracy of the user's exercise posture can be shown is proposed. Fitness images of AI-hub are analyzed by blaze pose. The experiment is compared with three types of deep learning model: RNN(recurrent neural network), LSTM(long short-term memory), CNN(convolution neural network). In simulation results, it was shown that the f1-score of RNN, LSTM and CNN is 0.49, 0.87 and 0.98, respectively. It was confirmed that CNN is more suitable for human activity recognition than other models from simulation results. More exercise postures can be analyzed using a variety learning data.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.18 no.1
• /
• pp.50-58
• /
• 2009

For precise tracking control of a servo system with nonlinear friction, a robust friction compensation scheme is presented in this paper. The nonlinear friction is difficult to identify the friction parameters exactly through experiments. Friction parameters can be also varied according to contact conditions such as the variation of temperature and lubrication. Thus, in order to overcome these problems and obtain the desired position tracking performance, a robust adaptive back-stepping control scheme with a dual friction observer is developed. In addition, to estimate lumped friction uncertainty due to modeling errors, a DEKF recurrent neural network and adaptive reconstructed error estimator are also developed. The feasibility of the proposed control scheme is verified through the experiment fur a ball-screw system.

• Journal of Advanced Information Technology and Convergence
• /
• v.10 no.1
• /
• pp.15-23
• /
• 2020

In this paper, we propose a new method to detect traffic accidents in video from vehicle-mounted cameras (vehicle black box). We use the distance between vehicles to determine whether an accident has occurred. To calculate the position of each vehicle, we use object detection and tracking method. By the way, in a crowded road environment, it is so difficult to decide an accident has occurred because of parked vehicles at the edge of the road. It is not easy to discriminate against accidents from non-accidents because a moving vehicle and a stopped vehicle are mixed on a regular downtown road. In this paper, we try to increase the accuracy of the vehicle accident detection by using not only the motion of the surrounding vehicle but also ego-motion as the input of the Recurrent Neural Network (RNN). We improved the accuracy of accident detection compared to the previous method.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.47-48
• /
• 2024

Heating, Ventilating, and Air Conditioning(HVAC) 시스템은 난방(Heating), 환기(Ventilating), 공기조화(Air Conditioning)를 제공하는 공조시스템으로, 실내 환경의 온도, 습도 조절 및 지속적인 순환 및 여과를 통해 실내 공기 질을 개선한다. 이러한 HVAC 시스템에 이상이 생기는 경우 공기 여과율이 낮아지며, COVID-19와 같은 법정 감염병 예방에 취약해진다. 또한 장비의 과부하를 유발하여, 시스템의 효율성 저하 및 에너지 낭비를 불러올 수 있다. 따라서 본 논문에서는 HVAC 시스템의 이상 탐지 및 조기 조치를 위한 Transformer 기반 이상 탐지 기법의 적용을 제안한다. Transformer는 기존 시계열 데이터 처리를 위한 기법인 Recurrent Neural Network(RNN)기반 모델의 구조적 한계점을 극복함에 따라 Long Term Dependency 문제를 해결하고, 병렬처리를 통해 효율적인 Feature 추출이 가능하다. Transformer 모델이 HVAC 시스템의 이상 탐지에서 RNN 기반의 비교군 모델보다 약 1.31%의 향상을 보이며, Transformer 모델을 통한 HVAC의 이상 탐지에 효율적임을 확인하였다.

• Communications for Statistical Applications and Methods
• /
• v.31 no.2
• /
• pp.213-234
• /
• 2024

In recent decades, increasing research attention has been directed toward predicting the price of stocks in financial markets using deep learning methods. For instance, recurrent neural network (RNN) is known to be competitive for datasets with time-series data. Long short term memory (LSTM) further improves RNN by providing an alternative approach to the gradient loss problem. LSTM has its own advantage in predictive accuracy by retaining memory for a longer time. In this paper, we combine both supervised and unsupervised dimension reduction methods with LSTM to enhance the forecasting performance and refer to this as a dimension reduction based LSTM (DR-LSTM) approach. For a supervised dimension reduction method, we use methods such as sliced inverse regression (SIR), sparse SIR, and kernel SIR. Furthermore, principal component analysis (PCA), sparse PCA, and kernel PCA are used as unsupervised dimension reduction methods. Using datasets of real stock market index (S&P 500, STOXX Europe 600, and KOSPI), we present a comparative study on predictive accuracy between six DR-LSTM methods and time series modeling.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.

• Journal of Digital Convergence
• /
• v.19 no.2
• /
• pp.215-220
• /
• 2021

In order to reduce the harmful effects on the human body caused by the recent increase in the generation of fine dust in Korea, there is a need for technology to help predict the level of fine dust and take precautions. In this paper, we propose a 1D Convolutional-Recurrent Neural Network (1-D CRNN) model to predict the level of fine dust in Korea. The proposed model is a structure that combines the CNN and the RNN, and uses domestic and foreign fine dust, wind direction, and wind speed data for data prediction. The proposed model achieved an accuracy of about 76%(Partial up to 84%). The proposed model aims to data prediction model for time series data sets that need to consider various data in the future.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.5
• /
• pp.1197-1207
• /
• 2018

PowerShell is command line shell and scripting language, built on the .NET framework, and it has several advantages as an attack tool, including built-in support for Windows, easy code concealment and persistence, and various pen-test frameworks. Accordingly, malwares using PowerShell are increasing rapidly, however, there is a limit to cope with the conventional malware detection technique. In this paper, we propose an improved monitoring method to observe commands executed in the PowerShell and a deep learning based malware classification model that extract features from commands using Convolutional Neural Network(CNN) and send them to Recurrent Neural Network(RNN) according to the order of execution. As a result of testing the proposed model with 5-fold cross validation using 1,916 PowerShell-based malwares collected at malware sharing site and 38,148 benign scripts disclosed by an obfuscation detection study, it shows that the model effectively detects malwares with about 97% True Positive Rate(TPR) and 1% False Positive Rate(FPR).