• Journal of Korea Water Resources Association
• /
• v.57 no.2
• /
• pp.73-85
• /
• 2024

Predicting water quality of rivers and reservoirs is necessary for the management of water resources. Artificial Neural Networks (ANNs) have been used in many studies to predict water quality with high accuracy. Previous studies have used Gradient Descent (GD)-based optimizers as an optimizer, an operator of ANN that searches parameters. However, GD-based optimizers have the disadvantages of the possibility of local optimal convergence and absence of a solution storage and comparison structure. This study developed improved optimizers to overcome the disadvantages of GD-based optimizers. Proposed optimizers are optimizers that combine adaptive moments (Adam) and Nesterov-accelerated adaptive moments (Nadam), which have low learning errors among GD-based optimizers, with Harmony Search (HS) or Novel Self-adaptive Harmony Search (NSHS). To evaluate the performance of Long Short-Term Memory (LSTM) using improved optimizers, the water quality data from the Dasan water quality monitoring station were used for training and prediction. Comparing the learning results, Mean Squared Error (MSE) of LSTM using Nadam combined with NSHS (NadamNSHS) was the lowest at 0.002921. In addition, the prediction rankings according to MSE and R² for the four water quality indices for each optimizer were compared. Comparing the average of ranking for each optimizer, it was confirmed that LSTM using NadamNSHS was the highest at 2.25.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.3
• /
• pp.491-501
• /
• 2019

In side-channel analysis, which exploit physical leakage from a cryptographic device, deep learning based attack has been significantly interested in recent years. However, most of the state-of-the-art methods have been focused on classifying side-channel information in a profiled scenario where attackers can obtain label of training data. In this paper, we propose a new method based on deep learning to improve non-profiling side-channel attack such as Differential Power Analysis and Correlation Power Analysis. The proposed method is a signal preprocessing technique that reduces the noise in a trace by modifying Auto-Encoder framework to the context of side-channel analysis. Previous work on Denoising Auto-Encoder was trained through randomly added noise by an attacker. In this paper, the proposed model trains Auto-Encoder through the noise from real data using the noise-reduced-label. Also, the proposed method permits to perform non-profiled attack by training only a single neural network. We validate the performance of the noise reduction of the proposed method on real traces collected from ChipWhisperer board. We demonstrate that the proposed method outperforms classic preprocessing methods such as Principal Component Analysis and Linear Discriminant Analysis.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.6
• /
• pp.859-865
• /
• 2018

A construction of infrastructures and base station on the moon could be undertaken by linking with the regions where construction materials and energy could be supplied on site. It is necessary to detect craters on the lunar surface and gather their topological information in advance, which forms permanent shaded regions (PSR) in which rich ice deposits might be available. In this study, an effective method for automatic detection of lunar craters on the moon surface is taken into consideration by employing a latest version of deep-learning algorithm. A training of a deep-learning algorithm is performed by involving the still images of 90000 taken from the LRO orbiter on operation by NASA and the label data involving position and size of partly craters shown in each image. the Faster RCNN algorithm, which is a latest version of deep-learning algorithms, is applied for a deep-learning training. The trained deep-learning code was used for automatic detection of craters which had not been trained. As results, it is shown that a lot of erroneous information for crater's positions and sizes labelled by NASA has been automatically revised and many other craters not labelled has been detected. Therefore, it could be possible to automatically produce regional maps of crater density and topological information on the moon which could be changed through time and should be highly valuable in engineering consideration for lunar construction.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.10
• /
• pp.1423-1431
• /
• 2022

Volatility is one of the variables that the Black-Scholes model requires for option pricing. It is an unknown variable at the present time, however, since the option price can be observed in the market, implied volatility can be derived from the price of an option at any given point in time and can represent the market's expectation of future volatility. Although volatility in the Black-Scholes model is constant, when calculating implied volatility, it is common to observe a volatility smile which shows that the implied volatility is different depending on the strike prices. We implement supervised learning to target implied volatility by adding V-KOSPI to ease volatility smile. We examine the estimation performance of KOSPI200 index options' implied volatility using various Machine Learning algorithms such as Linear Regression, Tree, Support Vector Machine, KNN and Deep Neural Network. The training accuracy was the highest(99.9%) in Decision Tree model and test accuracy was the highest(96.9%) in Random Forest model.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.15-30
• /
• 2023

Recently, generative models based on the Transformer architecture, such as ChatGPT, have been gaining significant attention. The Transformer architecture has been applied to various neural network models, including Google's BERT(Bidirectional Encoder Representations from Transformers) sentence generation model. In this paper, a method is proposed to create a text binary classification model for determining whether a comment on Korean movie review is positive or negative. To accomplish this, a pre-trained multilingual BERT sentence generation model is fine-tuned and transfer learned using a new Korean training dataset. To achieve this, a pre-trained BERT-Base model for multilingual sentence generation with 104 languages, 12 layers, 768 hidden, 12 attention heads, and 110M parameters is used. To change the pre-trained BERT-Base model into a text classification model, the input and output layers were fine-tuned, resulting in the creation of a new model with 178 million parameters. Using the fine-tuned model, with a maximum word count of 128, a batch size of 16, and 5 epochs, transfer learning is conducted with 10,000 training data and 5,000 testing data. A text sentiment binary classification model for Korean movie review with an accuracy of 0.9582, a loss of 0.1177, and an F1 score of 0.81 has been created. As a result of performing transfer learning with a dataset five times larger, a model with an accuracy of 0.9562, a loss of 0.1202, and an F1 score of 0.86 has been generated.

• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.1-12
• /
• 2019

As Artificial Intelligence (AI) technology develops, it is applied to various fields such as image, voice, and text. AI has shown fine results in certain areas. Researchers have tried to predict the stock market by utilizing artificial intelligence as well. Predicting the stock market is known as one of the difficult problems since the stock market is affected by various factors such as economy and politics. In the field of AI, there are attempts to predict the ups and downs of stock price by studying stock price patterns using various machine learning techniques. This study suggest a way of predicting stock price patterns based on the Convolutional Neural Network(CNN) among machine learning techniques. CNN uses neural networks to classify images by extracting features from images through convolutional layers. Therefore, this study tries to classify candlestick images made by stock data in order to predict patterns. This study has two objectives. The first one referred as Case 1 is to predict the patterns with the images made by the same-day stock price data. The second one referred as Case 2 is to predict the next day stock price patterns with the images produced by the daily stock price data. In Case 1, data augmentation methods - random modification and Gaussian noise - are applied to generate more training data, and the generated images are put into the model to fit. Given that deep learning requires a large amount of data, this study suggests a method of data augmentation for candlestick images. Also, this study compares the accuracies of the images with Gaussian noise and different classification problems. All data in this study is collected through OpenAPI provided by DaiShin Securities. Case 1 has five different labels depending on patterns. The patterns are up with up closing, up with down closing, down with up closing, down with down closing, and staying. The images in Case 1 are created by removing the last candle(-1candle), the last two candles(-2candles), and the last three candles(-3candles) from 60 minutes, 30 minutes, 10 minutes, and 5 minutes candle charts. 60 minutes candle chart means one candle in the image has 60 minutes of information containing an open price, high price, low price, close price. Case 2 has two labels that are up and down. This study for Case 2 has generated for 60 minutes, 30 minutes, 10 minutes, and 5minutes candle charts without removing any candle. Considering the stock data, moving the candles in the images is suggested, instead of existing data augmentation techniques. How much the candles are moved is defined as the modified value. The average difference of closing prices between candles was 0.0029. Therefore, in this study, 0.003, 0.002, 0.001, 0.00025 are used for the modified value. The number of images was doubled after data augmentation. When it comes to Gaussian Noise, the mean value was 0, and the value of variance was 0.01. For both Case 1 and Case 2, the model is based on VGG-Net16 that has 16 layers. As a result, 10 minutes -1candle showed the best accuracy among 60 minutes, 30 minutes, 10 minutes, 5minutes candle charts. Thus, 10 minutes images were utilized for the rest of the experiment in Case 1. The three candles removed from the images were selected for data augmentation and application of Gaussian noise. 10 minutes -3candle resulted in 79.72% accuracy. The accuracy of the images with 0.00025 modified value and 100% changed candles was 79.92%. Applying Gaussian noise helped the accuracy to be 80.98%. According to the outcomes of Case 2, 60minutes candle charts could predict patterns of tomorrow by 82.60%. To sum up, this study is expected to contribute to further studies on the prediction of stock price patterns using images. This research provides a possible method for data augmentation of stock data.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.1
• /
• pp.95-107
• /
• 2017

In this study, a preliminary study was undertaken for development of a tunnel incident automatic detection system based on a machine learning algorithm which is to detect a number of incidents taking place in tunnel in real time and also to be able to identify the type of incident. Two road sites where CCTVs are operating have been selected and a part of CCTV images are treated to produce sets of training data. The data sets are composed of position and time information of moving objects on CCTV screen which are extracted by initially detecting and tracking of incoming objects into CCTV screen by using a conventional image processing technique available in this study. And the data sets are matched with 6 categories of events such as lane change, stoping, etc which are also involved in the training data sets. The training data are learnt by a resilience neural network where two hidden layers are applied and 9 architectural models are set up for parametric studies, from which the architectural model, 300(first hidden layer)-150(second hidden layer) is found to be optimum in highest accuracy with respect to training data as well as testing data not used for training. From this study, it was shown that the highly variable and complex traffic and incident features could be well identified without any definition of feature regulation by using a concept of machine learning. In addition, detection capability and accuracy of the machine learning based system will be automatically enhanced as much as big data of CCTV images in tunnel becomes rich.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.10
• /
• pp.397-402
• /
• 2019

Accurately predicting cancer prognosis to provide appropriate treatment strategies for patients is one of the critical challenges in bioinformatics. Many researches have suggested machine learning models to predict patients' outcomes based on their gene expression data. Gene expression data is high-dimensional numerical data containing about 17,000 genes, so traditional researches used feature selection or dimensionality reduction approaches to elevate the performance of prognostic prediction models. These approaches, however, have an issue of making it difficult for the predictive models to grasp any biological interaction between the selected genes because feature selection and model training stages are performed independently. In this paper, we propose a novel two-dimensional image formatting approach for gene expression data to achieve feature selection and prognostic prediction effectively. Node2Vec is exploited to integrate biological interaction network and gene expression data and a convolutional neural network learns the integrated two-dimensional gene expression image data and predicts cancer prognosis. We evaluated our proposed model through double cross-validation and confirmed superior prognostic prediction accuracy to traditional machine learning models based on raw gene expression data. As our proposed approach is able to improve prediction models without loss of information caused by feature selection steps, we expect this will contribute to development of personalized medicine.

• Imaging Science in Dentistry
• /
• v.54 no.1
• /
• pp.81-91
• /
• 2024

Purpose: The objective of this study was to propose a deep-learning model for the detection of the mandibular canal on dental panoramic radiographs. Materials and Methods: A total of 2,100 panoramic radiographs (PANs) were collected from 3 different machines: RAYSCAN Alpha (n=700, PAN A), OP-100 (n=700, PAN B), and CS8100 (n=700, PAN C). Initially, an oral and maxillofacial radiologist coarsely annotated the mandibular canals. For deep learning analysis, convolutional neural networks (CNNs) utilizing U-Net architecture were employed for automated canal segmentation. Seven independent networks were trained using training sets representing all possible combinations of the 3 groups. These networks were then assessed using a hold-out test dataset. Results: Among the 7 networks evaluated, the network trained with all 3 available groups achieved an average precision of 90.6%, a recall of 87.4%, and a Dice similarity coefficient (DSC) of 88.9%. The 3 networks trained using each of the 3 possible 2-group combinations also demonstrated reliable performance for mandibular canal segmentation, as follows: 1) PAN A and B exhibited a mean DSC of 87.9%, 2) PAN A and C displayed a mean DSC of 87.8%, and 3) PAN B and C demonstrated a mean DSC of 88.4%. Conclusion: This multi-device study indicated that the examined CNN-based deep learning approach can achieve excellent canal segmentation performance, with a DSC exceeding 88%. Furthermore, the study highlighted the importance of considering the characteristics of panoramic radiographs when developing a robust deep-learning network, rather than depending solely on the size of the dataset.

• Journal of Korea Water Resources Association
• /
• v.54 no.10
• /
• pp.795-805
• /
• 2021

In this study, after developing an LSTM-based deep learning model for estimating daily runoff in the Soyang River Dam basin, the accuracy of the model for various combinations of model structure and input data was investigated. A model was built based on the database consisting of average daily precipitation, average daily temperature, average daily wind speed (input up to here), and daily average flow rate (output) during the first 12 years (1997.1.1-2008.12.31). The Nash-Sutcliffe Model Efficiency Coefficient (NSE) and RMSE were examined for validation using the flow discharge data of the later 12 years (2009.1.1-2020.12.31). The combination that showed the highest accuracy was the case in which all possible input data (12 years of daily precipitation, weather temperature, wind speed) were used on the LSTM model structure with 64 hidden units. The NSE and RMSE of the verification period were 0.862 and 76.8 m³/s, respectively. When the number of hidden units of LSTM exceeds 500, the performance degradation of the model due to overfitting begins to appear, and when the number of hidden units exceeds 1000, the overfitting problem becomes prominent. A model with very high performance (NSE=0.8~0.84) could be obtained when only 12 years of daily precipitation was used for model training. A model with reasonably high performance (NSE=0.63-0.85) when only one year of input data was used for model training. In particular, an accurate model (NSE=0.85) could be obtained if the one year of training data contains a wide magnitude of flow events such as extreme flow and droughts as well as normal events. If the training data includes both the normal and extreme flow rates, input data that is longer than 5 years did not significantly improve the model performance.