• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.333-336
• /
• 2023

Recently, the transformer model used in natural language processing is also applied to the image super resolution field, showing good performance. However, these transformer based models have a disadvantage that they are difficult to use in small mobile devices because they are complex and have many learning parameters and require high hardware resources. Therefore, in this paper, we propose a knowledge distillation technique that can effectively reduce the size of a transformer based super resolution model. As a result of the experiment, it was confirmed that by applying the proposed technique to the student model with reduced number of transformer blocks, performance similar to or higher than that of the teacher model could be obtained.

• Journal of Convergence for Information Technology
• /
• v.12 no.3
• /
• pp.1-10
• /
• 2022

Vegetables such as cabbage are greatly affected by natural disasters, so price fluctuations increase due to disasters such as heavy rain and disease, which affects the farm economy. Various efforts have been made to predict the price of agricultural products to solve this problem, but it is difficult to predict extreme price prediction fluctuations. In this study, cabbage prices were analyzed using the ensemble Voting technique, a method of determining the final prediction results through various classifiers by combining a single classifier. In addition, the results were compared with LSTM, a time series analysis method, and XGBoost and RandomForest, a boosting technique. Daily data was used for price data, and weather information and price index that affect cabbage prices were used. As a result of the study, the RMSE value showing the difference between the actual value and the predicted value is about 236. It is expected that this study can be used to select other time series analysis research models such as predicting agricultural product prices

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1872-1879
• /
• 2022

Recently, with the development of artificial intelligence technology, research to use artificial intelligence to detect hacking attacks is being actively conducted. However, the fact that security data is a representative imbalanced data is recognized as a major obstacle in composing the learning data, which is the key to the development of artificial intelligence models. Therefore, in this paper, we propose a W-VAE oversampling technique that applies VAE, a deep learning generation model, to data extraction for oversampling, and sets the number of oversampling for each class through weight calculation using K-NN for sampling. In this paper, a total of five oversampling techniques such as ROS, SMOTE, and ADASYN were applied through NSL-KDD, an open network security dataset. The oversampling method proposed in this paper proved to be the most effective sampling method compared to the existing oversampling method through the F1-Score evaluation index.

• 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 Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.67-77
• /
• 2023

This study represents an innovative research conducted in the smart farm environment, developing a deep learning-based disease and pest detection model and applying it to the Intelligent Internet of Things (IoT) platform to explore new possibilities in the implementation of digital agricultural environments. The core of the research was the integration of the latest ImageNet models such as Pseudo-Labeling, RegNet, EfficientNet, and preprocessing methods to detect various diseases and pests in complex agricultural environments with high accuracy. To this end, ensemble learning techniques were applied to maximize the accuracy and stability of the model, and the model was evaluated using various performance indicators such as mean Average Precision (mAP), precision, recall, accuracy, and box loss. Additionally, the SHAP framework was utilized to gain a deeper understanding of the model's prediction criteria, making the decision-making process more transparent. This analysis provided significant insights into how the model considers various variables to detect diseases and pests.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.263-283
• /
• 2024

Users' comments after online shopping are critical to product reputation and business improvement. These comments, sometimes known as e-commerce reviews, influence other customers' purchasing decisions. To confront large amounts of e-commerce reviews, automatic analysis based on machine learning and deep learning draws more and more attention. A core task therein is sentiment analysis. However, the e-commerce reviews exhibit the following characteristics: (1) inconsistency between comment content and the star rating; (2) a large number of unlabeled data, i.e., comments without a star rating, and (3) the data imbalance caused by the sparse negative comments. This paper employs Bidirectional Encoder Representation from Transformers (BERT), one of the best natural language processing models, as the base model. According to the above data characteristics, we propose the F_MixBERT framework, to more effectively use inconsistently low-quality and unlabeled data and resolve the problem of data imbalance. In the framework, the proposed MixBERT incorporates the MixMatch approach into BERT's high-dimensional vectors to train the unlabeled and low-quality data with generated pseudo labels. Meanwhile, data imbalance is resolved by Focal loss, which penalizes the contribution of large-scale data and easily-identifiable data to total loss. Comparative experiments demonstrate that the proposed framework outperforms BERT and MixBERT for sentiment analysis of e-commerce comments.

• Smart Media Journal
• /
• v.13 no.6
• /
• pp.24-34
• /
• 2024

If the future can be predicted from network traffic data, which is a time series, it can achieve effects such as efficient resource allocation, prevention of malicious attacks, and energy saving. Many models based on statistical and deep learning techniques have been proposed, and most of these studies have focused on improving model structures and learning algorithms. Another approach to improving the prediction performance of the model is to obtain a good-quality data. With the aim of obtaining a good-quality data, this paper applies a dense sampling technique that augments time series data to the application of network traffic prediction and analyzes the performance improvement. As a dataset, UNSW-NB15, which is widely used for network traffic analysis, is used. Performance is analyzed using RMSE, MAE, and MAPE. To increase the objectivity of performance measurement, experiment is performed independently 10 times and the performance of existing sparse sampling and dense sampling is compared as a box plot. As a result of comparing the performance by changing the window size and the horizon factor, dense sampling consistently showed a better performance.

• Smart Media Journal
• /
• v.13 no.10
• /
• pp.79-91
• /
• 2024

The rapid expansion of unmanned retail stores has raised critical security concerns, thereby necessitating the development and implementation of robust protective measures. The absence of real-time monitoring systems in these environments has heightened the vulnerability to risks such as theft and property damage. Although closed-circuit television (CCTV) systems have been deployed to retrospectively investigate criminal activities, these systems are often insufficient in preventing incidents. This study introduces a Transformer-based intelligent CCTV system designed for the real-time detection of anomalous behaviors within unmanned retail environments. Unlike conventional systems that rely on basic machine learning models, our proposed system leverages human joint position data extracted from CCTV footage to classify a range of anomalous behaviors, including theft, falls, and property damage. Additionally, extensive hyperparameter optimization was performed to maximize the model's effectiveness in these specific environments. Our System enhances the system's usability by enabling real-time identification of anomalous behavior, complete with location data, timestamps, and corresponding video frame sequences.

• Smart Media Journal
• /
• v.13 no.7
• /
• pp.9-17
• /
• 2024

Due to the increase in energy consumption, and eco-friendly policies, there is a need for efficient energy consumption in buildings. Anomaly power detection based on deep learning are being used. Because of the difficulty in collecting anomaly data, anomaly detection is performed using reconstruction error with a Recurrent Neural Network(RNN) based autoencoder. However, there are some limitations such as the long time required to fully learn temporal features and its sensitivity to noise in the train data. To overcome these limitations, this paper proposes the TCN-USAD, combined with Temporal Convolution Network(TCN) and UnSupervised Anomaly Detection for multivariate data(USAD). The proposed model using TCN-based autoencoder and the USAD structure, which uses two decoders and adversarial training, to quickly learn temporal features and enable robust anomaly detection. To validate the performance of TCN-USAD, comparative experiments were performed using two building energy datasets. The results showed that the TCN-based autoencoder can perform faster and better reconstruction than RNN-based autoencoder. Furthermore, TCN-USAD achieved 20% improved F1-Score over other anomaly detection models, demonstrating excellent anomaly detection performance.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.48 no.4
• /
• pp.19-28
• /
• 2020

The Urban Heat Island (UHI) Effect has intensified due to urbanization and heat management at the urban level is treated as an important issue. Green space improvement projects and environmental policies are being implemented as a way to alleviate Urban Heat Islands. Several studies have been conducted to analyze the correlation between urban green areas and heat with linear regression models. However, linear regression models have limitations explaining the correlation between heat and the multitude of variables as heat is a result of a combination of non-linear factors. This study evaluated the Heat Island alleviating effects in Seoul during the summer by using a deep neural network model methodology, which has strengths in areas where it is difficult to analyze data with existing statistical analysis methods due to variable factors and a large amount of data. Wide-area data was acquired using Landsat 8. Seoul was divided into a grid (30m × 30m) and the heat island reduction variables were enter in each grid space to create a data structure that is needed for the construction of a deep neural network using ArcGIS 10.7 and Python3.7 with Keras. This deep neural network was used to analyze the correlation between land surface temperature and the variables. We confirmed that the deep neural network model has high explanatory accuracy. It was found that the cooling effect by NDVI was the greatest, and cooling effects due to the park size and green space proximity were also shown. Previous studies showed that the cooling effects related to park size was 2℃-3℃, and the proximity effect was found to lower the temperature 0.3℃-2.3℃. There is a possibility of overestimation of the results of previous studies. The results of this study can provide objective information for the justification and more effective formation of new urban green areas to alleviate the Urban Heat Island phenomenon in the future.