• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.2
• /
• pp.103-111
• /
• 2023

This paper proposes a new data correction technique that transforms anomalies in time series data into normal values. With the recent development of IT technology, a vast amount of time-series data is being collected through sensors. However, due to sensor failures and abnormal environments, most of time-series data contain a lot of anomalies. If we build a predictive model using original data containing anomalies as it is, we cannot expect highly reliable predictive performance. Therefore, we utilizes the LSTM-GAN model to detect anomalies in the original time series data, and combines DTW (Dynamic Time Warping) and GAN techniques to replace the anomaly data with normal data in partitioned window units. The basic idea is to construct a GAN model serially by applying the statistical information of the window with normal distribution data adjacent to the window containing the detected anomalies to the DTW so as to generate normal time-series data. Through experiments using open NAB data, we empirically prove that our proposed method outperforms the conventional two correction methods.

• Smart Media Journal
• /
• v.11 no.1
• /
• pp.38-45
• /
• 2022

A lot of research is being going until this day in order to obtain stable profit in the stock market. Trading algorithms are widely used, accounting for over 80% of the trading volume of the US stock market. Despite a lot of research, there is no trading algorithm that always shows good performance. In other words, there is no guarantee that an algorithm that performed well in the past will perform well in the future. The reason is that there are many factors that affect the stock price and there are uncertainties about the future. Therefore, in this paper, we propose a model using TimeGAN that predicts future returns well and selects algorithms that are expected to have high returns based on past records of the returns of algorithms. We use TimeGAN becasue it is probabilistic, whereas LSTM method predicts future time series data is deterministic. The advantage of TimeGAN probabilistic prediction is that it can reflect uncertainty about the future. As an experimental result, the method proposed in this paper achieves a high return with little volatility and shows superior results compared to many comparison algorithms.

• Journal of Korean Society for Quality Management
• /
• v.50 no.3
• /
• pp.459-471
• /
• 2022

Purpose: The purpose of this study was to increase prediction accuracy for an anomaly interval identified using an artificial intelligence-based time series anomaly detection technique by establishing a pre-processing process. Methods: Significant variables were extracted by applying feature selection techniques, and anomalies were derived using the TadGAN time series anomaly detection algorithm. After applying machine learning and deep learning methodologies using normal section data (excluding anomaly sections), the explanatory power of the anomaly sections was demonstrated through performance comparison. Results: The results of the machine learning methodology, the performance was the best when SHAP and TadGAN were applied, and the results in the deep learning, the performance was excellent when Chi-square Test and TadGAN were applied. Comparing each performance with the papers applied with a Conventional methodology using the same data, it can be seen that the performance of the MLR was significantly improved to 15%, Random Forest to 24%, XGBoost to 30%, Lasso Regression to 73%, LSTM to 17% and GRU to 19%. Conclusion: Based on the proposed process, when detecting unsupervised learning anomalies of data that are not actually labeled in various fields such as cyber security, financial sector, behavior pattern field, SNS. It is expected to prove the accuracy and explanation of the anomaly detection section and improve the performance of the model.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.9-17
• /
• 2021

With the advancement of big data analysis, artificial intelligence, machine learning, etc., data analytics technology has developed to help with optimal decision-making. However, in certain areas, the lack of data restricts the use of these techniques. For example, real estate related data often have a long release cycle because of its recent release or being a non-liquid asset. In order to overcome these limitations, we studied the scalability of the existing time series through the TimeGAN model. A total of 45 time series related to weekly real estate data were collected within the period of 2012 to 2021, and a total of 15 final time series were selected by considering the correlation between the time series. As a result of data expansion through the TimeGAN model for the 15 time series, it was found that the statistical distribution between the real data and the extended data was similar through the PCA and t-SNE visualization algorithms.

• Korean Journal of Remote Sensing
• /
• v.38 no.1
• /
• pp.33-43
• /
• 2022

This study presents a method to restore an optical satellite image with distortion and occlusion due to fog, haze, and clouds to one that minimizes degradation factors by referring to the same type of peripheral image. Specifically, the time and cost of re-photographing were reduced by partially occluding a region. To maintain the original image's pixel value as much as possible and to maintain restored and unrestored area continuity, a simulation restoration technique modified with the Cycle Generative Adversarial Network (CycleGAN) method was developed. The accuracy of the simulated image was analyzed by comparing CycleGAN and histogram matching, as well as the pixel value distribution, with the original image. The results show that for Site 1 (out of three sites), the root mean square error and R² of CycleGAN were 169.36 and 0.9917, respectively, showing lower errors than those for histogram matching (170.43 and 0.9896, respectively). Further, comparison of the mean and standard deviation values of images simulated by CycleGAN and histogram matching with the ground truth pixel values confirmed the CycleGAN methodology as being closer to the ground truth value. Even for the histogram distribution of the simulated images, CycleGAN was closer to the ground truth than histogram matching.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.2
• /
• pp.349-354
• /
• 2023

As the population interested in interior design has been increasing, the global interior market has grown significantly. Global interior companies are developing and providing simulation services for various interior elements. Although wallpaper design is the most important interior element, existing wallpaper design simulation services are difficult to use due to drawbacks such as differences between expected and actual results, long simulation time, and the need for professional skills. We proposed a wallpaper image transformation method for interior design using cycle generative adversarial networks (GAN). The proposed method demonstrates that users can simulate wallpaper design within a short period of time based on interior image data using various types of wallpaper.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.4
• /
• pp.591-597
• /
• 2022

Recently, many studies have been done on the data augmentation technique as a way to efficiently build datasets. Among them, a representative data augmentation technique is a method of utilizing Generative Adversarial Network (GAN), which generates data similar to real data by competitively learning generators and discriminators. However, when learning GAN, there are cases where a broken pixel image occurs among similar data generated according to the environment and progress, which cannot be used as a dataset and causes an increase in learning time. In this paper, an algorithm was developed to select these damaged images by analyzing the histogram of image data generated during the GAN learning process, and as a result of comparing them with the images generated in the existing GAN, the ratio of the damaged images was reduced by 33.3 times(3,330%).

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.351-358
• /
• 2022

Recently, Generative Adversarial Networks (GAN) and Variational AutoEncoders (VAE) have been applied to voice conversion that can make use of non-parallel training data. Especially, Conditional Cycle-Consistent Generative Adversarial Networks (CC-GAN) and Cycle-Consistent Variational AutoEncoders (CycleVAE) show promising results in many-to-many voice conversion among multiple speakers. However, the number of speakers has been relatively small in the conventional voice conversion studies using the CC-GANs and the CycleVAEs. In this paper, we extend the number of speakers to 100, and analyze the performances of the many-to-many voice conversion methods experimentally. It has been found through the experiments that the CC-GAN shows 4.5 % less Mel-Cepstral Distortion (MCD) for a small number of speakers, whereas the CycleVAE shows 12.7 % less MCD in a limited training time for a large number of speakers.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.4
• /
• pp.7-16
• /
• 2023

For decades, creating a desired locomotive motion in a goal-oriented manner has been a challenge in character animation. Data-driven methods using generative models have demonstrated efficient ways of predicting long sequences of motions without the need for explicit conditioning. While these methods produce high-quality long-term motions, they can be limited when it comes to synthesizing motion for challenging novel scenarios, such as punching a random target. A state-of-the-art solution to overcome this limitation is by using a GAN Discriminator to imitate motion data clips and incorporating reinforcement learning to compose goal-oriented motions. In this paper, our research aims to create characters performing combat sports such as boxing, using a novel reward design in conjunction with existing GAN-based approaches. We experimentally demonstrate that both the Adversarial Motion Prior [3] and Adversarial Skill Embeddings [4] methods are capable of generating viable motions for a character punching a random target, even in the absence of mocap data that specifically captures the transition between punching and locomotion. Also, with a single learned policy, multiple task controllers can be constructed through the TimeChamber framework.

• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1476-1485
• /
• 2020

Segmenting OCT retinal images into layers is important to diagnose and understand the progression of retinal diseases or identify potential symptoms. The task of manually identifying these layers is a difficult task that requires a lot of time and effort even for medical professionals, and therefore, various studies are being conducted to automate this using deep learning technologies. In this paper, we use cGAN-based neural network to automatically segmenting OCT retinal images into seven terrain-type regions defined by six layer boundaries. The network is composed of a Segnet-based generator model and a discriminator model. We also proposed a dynamic programming algorithm for refining the outputs of the network. We performed experiments using public OCT image data set and compared its performance with the Segnet-only version of the network. The experimental results show that the cGAN-based network outperforms Segnet-only version.