• The Korean Journal of Pain
• /
• v.27 no.2
• /
• pp.152-161
• /
• 2014

Background: According to the reports of the World Health Organization 20% of world population suffer from pain and 33% of them suffer to some extent that they cannot live independently. Methods: This is a cross-sectional study which was conducted in the emergency department (ED) of Valiasr Hospital of Arak, Iran, in order to determine the causes of delay in prescription of analgesics and to construct a model for prediction of circumstances that aggravate oligoanalgesia. Data were collected during a period of 7 days. Results: Totally, 952 patients participated in this study. In order to reduce their pain intensity, 392 patients (42%) were treated. Physicians and nurses recorded the intensity of pain for 66.3% and 41.37% of patients, respectively. The mean (SD) of pain intensity according to visual analogue scale (VAS) was 8.7 (1.5) which reached to 4.4 (2.3) thirty minutes after analgesics prescription. Median and mean (SD) of delay time in injection of analgesics after the physician's order were 60.0 and 45.6 (63.35) minutes, respectively. The linear regression model suggested that when the attending physician was male or intern and patient was from rural areas the delay was longer. Conclusions: We propose further studies about analgesics administration based on medical guidelines in the shortest possible time and also to train physicians and nurses about pain assessment methods and analgesic prescription.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.5
• /
• pp.93-99
• /
• 2019

In this paper, we propose a smart meter that uses GRU model, which is one of artificial neural networks, for the efficient energy management. We collected power consumption data that train GRU model through the proposed smart meter. The implemented smart meter has automatic power measurement and real-time observation function and load control function through power consumption prediction. We determined a reference value to control the load by using Root Mean Squared Error (RMS), which is one of performance evaluation indexes, with 20% margin. We confirmed that the smart meter with automatic load control increases the efficiency of energy management.

• Journal of Digital Convergence
• /
• v.16 no.12
• /
• pp.293-299
• /
• 2018

The weather has a lot of influence on the cultivation of crops. Weather information on agricultural crop cultivation areas is indispensable for efficient cultivation and management of agricultural crops. Despite the high demand for agricultural weather, research on this is in short supply. In this research, we deal with the production method of agricultural weather in Jeollanam-do, which is the main production area of onions through GloSea5 and deep learning. A deep neural network model using the sliding window method was used and utilized to train daily weather prediction for predicting the agricultural weather. RMSE and MAE are used for evaluating the accuracy of the model. The accuracy improves as the learning period increases, so we compare the prediction performance according to the learning period and the prediction period. As a result of the analysis, although the learning period and the prediction period are similar, there was a limit to reflect the trend according to the seasonal change. a modified deep layer neural network model was presented, that applying the difference between the predicted value and the observed value to the next day predicted value.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.5
• /
• pp.49-63
• /
• 2019

Crowdedness management at subway platforms is essential to improve services, including the prevention of train delays and ensuring passenger safety. Establishing effective crowdedness mitigation measures for platforms requires accurate estimation of the congestion level. There are temporal and spatial constraints since crowdedness on subway platforms is assessed at certain locations every 1-2 years by hand counting. However, smart cards generate real-time big data 24 hours a day and could be used in estimating congestion. This study proposes a model based on data from transit cards to estimate crowdedness dynamically. Crowdedness was defined as demand, which can be translated into passengers dynamically moving along a subway network. The trajectory of an individual passenger can be identified through this model. Passenger flow that concentrates or disperses at a platform is also calculated every minute. Lastly, the platform congestion level is estimated based on effective waiting areas for each platform structure.

• Ecology and Resilient Infrastructure
• /
• v.7 no.4
• /
• pp.345-352
• /
• 2020

Securing the lead time for evacuation is crucial to minimize flood damage. In this study, downstream water levels for heavy rainfall were predicted using measured water level observation data. Multiple regression analysis and artificial neural networks were applied to the Seom River experimental watershed to predict the water level. Water level observation data for the Seom River experimental watershed from 2002 to 2010 were used to perform the multiple regression analysis and to train the artificial neural networks. The water level was predicted using the trained model. The simulation results for the coefficients of determination of the artificial neural network level prediction ranged from 0.991 to 0.999, while those of the multiple regression analysis ranged from 0.945 to 0.990. The water level prediction model developed using an artificial neural network was better than the multiple-regression analysis model. This technique for forecasting downstream water levels is expected to contribute toward flooding warning systems that secure the lead time for streams.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.24 no.4
• /
• pp.382-391
• /
• 2021

Unsupervised domain adaptation often gives impressive solutions to handle domain shift of data. Most of current approaches assume that unlabeled target data to train is abundant. This assumption is not always true in practices. To tackle this issue, we propose a general solution to solve the domain gap minimization problem without any target data. Our method consists of two regularization steps. The first step is a pixel regularization by arbitrary style transfer. Recently, some methods bring style transfer algorithms to domain adaptation and domain generalization process. They use style transfer algorithms to remove texture bias in source domain data. We also use style transfer algorithms for removing texture bias, but our method depends on neither domain adaptation nor domain generalization paradigm. The second regularization step is a feature regularization by feature alignment. Adding a feature alignment loss term to the model loss, the model learns domain invariant representation more efficiently. We evaluate our regularization methods from several experiments both on small dataset and large dataset. From the experiments, we show that our model can learn domain invariant representation as much as unsupervised domain adaptation methods.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.63-69
• /
• 2021

When a person sees a sentence and understands the sentence, the person understands the sentence by reminiscent of the main word in the sentence as an image. Text-to-image is what allows computers to do this associative process. The previous deep learning-based text-to-image model extracts text features using Convolutional Neural Network (CNN)-Long Short Term Memory (LSTM) and bi-directional LSTM, and generates an image by inputting it to the GAN. The previous text-to-image model uses basic embedding in text feature extraction, and it takes a long time to train because images are generated using several modules. Therefore, in this research, we propose a method of extracting features by using the attention mechanism, which has improved performance in the natural language processing field, for sentence embedding, and generating an image by inputting the extracted features into the GAN. As a result of the experiment, the inception score was higher than that of the model used in the previous study, and when judged with the naked eye, an image that expresses the features well in the input sentence was created. In addition, even when a long sentence is input, an image that expresses the sentence well was created.

• Design & Manufacturing
• /
• v.15 no.1
• /
• pp.48-56
• /
• 2021

The quality of products produced by injection molding process is greatly influenced by the process variables set on the injection molding machine during manufacturing. It is very difficult to predict the quality of injection molded product considering the stochastic nature of manufacturing process, because the process variables complexly affect the quality of the injection molded product. In the present study we predicted the quality of injection molded product using Artificial Neural Network (ANN) method specifically from Multiple Input Single Output (MISO) and Multiple Input Multiple Output (MIMO) perspectives. In order to train the ANN model a systematic plan was prepared based on a combination of orthogonal sampling and random sampling methods to represent various and robust patterns with small number of experiments. According to the plan the injection molding experiments were conducted to generate data that was separated into training, validation and test data groups to optimize the parameters of the ANN model and evaluate predicting performance of 4 structures (MISO1-2, MIMO1-2). Based on the predicting performance test, it was confirmed that as the number of output variables were decreased, the predicting performance was improved. The results indicated that it is effective to use single output model when we need to predict the quality of injection molded product with high accuracy.

• The Journal of Information Systems
• /
• v.30 no.4
• /
• pp.21-42
• /
• 2021

Purpose In order for companies to continue to grow, they should properly manage human resources, which are the core of corporate competitiveness. Employee turnover means the loss of talent in the workforce. When an employee voluntarily leaves his or her company, it will lose hiring and training cost and lead to the withdrawal of key personnel and new costs to train a new employee. From an employee's viewpoint, moving to another company is also risky because it can be time consuming and costly. Therefore, in order to reduce the social and economic costs caused by employee turnover, it is necessary to accurately predict employee turnover intention, identify the factors affecting employee turnover, and manage them appropriately in the company. Design/methodology/approach Prior studies have mainly used logistic regression and decision trees, which have explanatory power but poor predictive accuracy. In order to develop a more accurate prediction model, XGBoost is proposed as the classification technique. Then, to compensate for the lack of explainability, SHAP, one of the XAI techniques, is applied. As a result, the prediction accuracy of the proposed model is improved compared to the conventional methods such as LOGIT and Decision Trees. By applying SHAP to the proposed model, the factors affecting the overall employee turnover intention as well as a specific sample's turnover intention are identified. Findings Experimental results show that the prediction accuracy of XGBoost is superior to that of logistic regression and decision trees. Using SHAP, we find that jobseeking, annuity, eng_test, comm_temp, seti_dev, seti_money, equl_ablt, and sati_safe significantly affect overall employee turnover intention. In addition, it is confirmed that the factors affecting an individual's turnover intention are more diverse. Our research findings imply that companies should adopt a personalized approach for each employee in order to effectively prevent his or her turnover.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.5
• /
• pp.45-54
• /
• 2021

Recently, deep learning-based denoising approaches have been actively studied. In particular, with the advances of blind denoising techniques, it become possible to train a deep learning-based denoising model only with noisy images in an image domain where it is impossible to obtain a clean image. We no longer require pairs of a clean image and a noisy image to obtain a restored clean image from the observation. However, it is difficult to recover the target using a deep learning-based denoising model trained by only noisy images if the distribution of the noisy image is far from the distribution of the clean image. To address this limitation, unpaired image denoising approaches have recently been studied that can learn the denoising model from unpaired data of the noisy image and the clean image. ISCL showed comparable performance close to that of supervised learning-based models based on pairs of clean and noisy images. In this study, we propose suitable normalization techniques for each purpose of architectures (e.g., generator, discriminator, and extractor) of ISCL. We demonstrate that the proposed method outperforms state-of-the-art unpaired image denoising approaches including ISCL.