• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.21-28
• /
• 2022

All health problems that occur in the circulatory system are refer to cardiovascular illness, such as heart and vascular diseases. Deaths from cardiovascular disorders are recorded one third of in total deaths in 2019 worldwide, and the number of deaths continues to rise. Therefore, if it is possible to predict diseases that has high mortality rate with patient's data and AI system, they would enable them to be detected and be treated in advance. In this study, models are produced to predict heart disease, which is one of the cardiovascular diseases, and compare the performance of models with Accuracy, Precision, and Recall, with description of the way of improving the performance of the Decision Tree(Decision Tree, KNN (K-Nearest Neighbor), SVM (Support Vector Machine), and DNN (Deep Neural Network) are used in this study.). Experiments were conducted using scikit-learn, Keras, and TensorFlow libraries using Python as Jupyter Notebook in macOS Big Sur. As a result of comparing the performance of the models, the Decision Tree demonstrates the highest performance, thus, it is recommended to use the Decision Tree in this study.

• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.840-847
• /
• 2022

In a deep neural network (DNN)-based speech enhancement, using global and local input speech information is closely related to model performance. Recently, a nested U-Net structure that utilizes global and local input data information using multi-scale has bee n proposed. This nested U-Net was also applied to speech enhancement and showed outstanding performance. However, a single skip connection used in nested U-Nets must be modified for the nested structure. In this paper, we propose a multi-level skip connection (MLS) to optimize the performance of the nested U-Net-based speech enhancement algorithm. As a result, the proposed MLS showed excellent performance improvement in various objective evaluation metrics compared to the standard skip connection, which means th at the MLS can optimize the performance of the nested U-Net-based speech enhancement algorithm. In addition, the final proposed m odel showed superior performance compared to other DNN-based speech enhancement models.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.3
• /
• pp.326-332
• /
• 2019

Recently, the deep learning technology has gained lots of attention which leads to its application to various fields. Especially, there are recent attempts to overcome the limit of wireless communications systems through the use of the deep learning. In this paper, we have verified the performance of deep learning based transmit power control scheme. Unlike previous transmit power control schemes where the optimal transmit power is derived by solving the optimization problem explicitly, in the deep learning based transmit power control, the general solver for the optimization problem is derived through the deep neural network (DNN). Especially, by using the spectral efficiency as the loss function of DNN, the training can be performed without needing labels. Through simulation based on Tensorflow, we confirm that the transmit power control based on deep learning can achieve the optimal performance while reducing the computational complexity by 1/200.

• Annual Conference on Human and Language Technology
• /
• 2015.10a
• /
• pp.157-162
• /
• 2015

자동통역(Speech-to-speech translation)의 최우선 단계인 음성인식과정에서 발생한 오류문장은 대부분 비문법적 구조를 갖거나 의미를 이해할 수 없는 문장들이다. 이러한 문장으로 자동번역을 할 경우 심각한 통역오류가 발생하게 되어 이에 대한 개선이 반드시 필요한 상황이다. 이에 본 논문에서는 음성인식 오류문장이 정상적인 인식문장에 비해 비문법적이거나 무의미하다는 특징을 이용하여 DNN(Deep Neural Network) 기반 음성인식오류 판별기를 구현하였으며 84.20%의 오류문장 분류성능결과를 얻었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.1122-1140
• /
• 2024

The importance of indoor positioning has grown in numerous application areas such as emergency response, logistics, and industrial automation. In ships, indoor positioning is also needed to provide services to passengers on board. Due to the complex structure and dynamic nature of ship environments, conventional positioning techniques have limitations in providing accurate positions. Compared to other indoor positioning technologies, Bluetooth 5.1-based indoor positioning technology is highly suitable for ship environments. Bluetooth 5.1 attains centimeter-level positioning accuracy by collecting In-phase and Quadrature (IQ) samples from wireless signals. However, distorted IQ samples can lead to significant errors in the final estimated position. Therefore, we propose an indoor positioning method for ships that utilizes a Deep Neural Network (DNN) combined with IQ fingerprint maps to overcome the challenges associated with accurate location detection within the ship. The results indicate that the accuracy of our proposed method can reach up to 97.76%.

• Journal of Broadcast Engineering
• /
• v.25 no.4
• /
• pp.569-575
• /
• 2020

The serial arc is one of factors causing electrical fires. Over past decades, various researches have been carried out to detect arc occurrences. Even though frequency analysis, wavelet, and statistical features have been used, additional steps such as transformation and feature extraction are required. On the contrary, deep learning models directly use the raw data without any feature extraction processes. Therefore, the usage of time-domain data is preferred, but the performance is not satisfactory. To solve this problem, subsequent 1-D signals are transformed into 2-D data that can feed into a convolutional neural network (CNN). Experiments validated that CNN model outperforms deep neural network (DNN) by the classification accuracy of 8.6%. In addition, data augmentation is utilized, resulting in the accuracy improvement by 14%.

• Journal of Korea Multimedia Society
• /
• v.22 no.9
• /
• pp.1069-1079
• /
• 2019

In this study, we developed a $PM_{10}$ forecasting model using DNN and Membership Function, and improved the forecasting performance. The model predicts the $PM_{10}$ concentrations of the next 3 days in the Seoul area by using the weather and air quality observation data and forecast data. The best model(RM14)'s accuracy (82%, 76%, 69%) and false alarm rate(FAR:14%,33%,44%) are good. Probability of detection (POD: 79%, 50%, 53%), however, are not good performance. These are due to the lack of training data for high concentration $PM_{10}$ compared to low concentration. In addition, the model dose not reflect seasonal factors closely related to the generation of high concentration $PM_{10}$. To improve this, we propose Julian date membership function as inputs of the $PM_{10}$ forecasting model. The function express a given date in 12 factors to reflect seasonal characteristics closely related to high concentration $PM_{10}$. As a result, the accuracy (79%, 70%, 66%) and FAR (24%, 48%, 46%) are slightly reduced in performance, but the POD (79%, 75%, 71%) are up to 25% improved compared with those of the RM14 model. Hence, this shows that the proposed Julian forecast model is effective for high concentration $PM_{10}$ forecasts.

• The Journal of the Korea Contents Association
• /
• v.21 no.10
• /
• pp.1-10
• /
• 2021

Log data accumulated in the Learning Management System (LMS) provide high-quality information for the learning process of students. Until now, various studies have been conducted to predict students' academic achievement using LMS log data. However, previous studies were based on relatively small sample sizes of students and courses, limiting the possibility of generalization. This study developed and validated a deep neural network model for the early prediction of academic achievement of college students using massive LMS log data. To this end, we used 78,466,385 cases of LMS log data and 165,846 cases of grade data. The proposed model predicted the excellent-grade students with a high level of accuracy from the beginning of the semester. Meanwhile, the prediction accuracy for the moderate and underachieving groups was relatively low, but the accuracy improved as the time points of the prediction were delayed. This study is meaningful in that we developed an early prediction model based on a deep neural network with sufficient accuracy for practical utilization by only using LMS log data.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.20 no.3
• /
• pp.262-276
• /
• 2018

Models to predict Leaf Wetness Duration (LWD) were evaluated using the observed meteorological and dew data at the 11 citrus orchards in Jeju, South Korea from 2016 to 2017. The sensitivity and the prediction accuracy were evaluated with four models (i.e., Number of Hours of Relative Humidity (NHRH), Classification And Regression Tree/Stepwise Linear Discriminant (CART/SLD), Penman-Monteith (PM), Deep-learning Neural Network (DNN)). The sensitivity of models was evaluated with rainfall and seasonal changes. When the data in rainy days were excluded from the whole data set, the LWD models had smaller average error (Root Mean Square Error (RMSE) about 1.5hours). The seasonal error of the DNN model had the similar magnitude (RMSE about 3 hours) among all seasons excluding winter. The other models had the greatest error in summer (RMSE about 9.6 hours) and the lowest error in winter (RMSE about 3.3 hours). These models were also evaluated by the statistical error analysis method and the regression analysis method of mean squared deviation. The DNN model had the best performance by statistical error whereas the CART/SLD model had the worst prediction accuracy. The Mean Square Deviation (MSD) is a method of analyzing the linearity of a model with three components: squared bias (SB), nonunity slope (NU), and lack of correlation (LC). Better model performance was determined by lower SB and LC and higher NU. The results of MSD analysis indicated that the DNN model would provide the best performance and followed by the PM, the NHRH and the CART/SLD in order. This result suggested that the machine learning model would be useful to improve the accuracy of agricultural information using meteorological data.

• Journal of Korea Water Resources Association
• /
• v.56 no.5
• /
• pp.347-356
• /
• 2023

In Water Distribution Systems (WDSs), can abnormal hydraulic and water quality conditions such as red-water phenomenon and leakage occur. To restore them, data is generated through various meters data to predict and detect. However, in the case of leakage if difficult to detect unless direct exploration is performed. Among them, unreported leakage, are not seen visually and account for the most considerable volumes of leakage, which leads to economic loss. Bur direct exploration is limited through on site conditions such as securing professional manpower. In this paper, leakage volumes and location were randomly generated for the WDS, which was assumed to be calibrated, and it was detected through a deep learning model. For abnormal data generation, the leakage was simulated using the emitter coefficient, and leakage detection was successfully performed through the generated abnormal data and normal data.