• Journal of Digital Convergence
• /
• v.19 no.8
• /
• pp.319-325
• /
• 2021

With the advancement of wireless technology and the rapid growth of the infrastructure of mobile communication technology, systems applying AI-based platforms are drawing attention from users. In particular, the system that understands users' tastes and interests and recommends preferred items is applied to advanced e-commerce customized services and smart homes. However, there is a problem that these recommendation systems are difficult to reflect in real time the preferences of various users for tastes and interests. In this research, we propose a Fuzzy-AHP-based movies recommendation system using the Gated Recurrent Unit (GRU) language model to address a problem. In this system, we apply Fuzzy-AHP to reflect users' tastes or interests in real time. We also apply GRU language model-based models to analyze the public interest and the content of the film to recommend movies similar to the user's preferred factors. To validate the performance of this recommendation system, we measured the suitability of the learning model using scraping data used in the learning module, and measured the rate of learning performance by comparing the Long Short-Term Memory (LSTM) language model with the learning time per epoch. The results show that the average cross-validation index of the learning model in this work is suitable at 94.8% and that the learning performance rate outperforms the LSTM language model.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.173-180
• /
• 2023

Smart factory companies are installing various sensors in production facilities and collecting field data. However, there are relatively few companies that actively utilize collected data, academic research using field data is actively underway. This study seeks to develop a model that detects anomalies in the process by analyzing spindle power data from a company that processes shafts used in automobile throttle valves. Since the data collected during machining processing is time series data, the model was developed through unsupervised learning by applying the Holt Winters technique and various deep learning algorithms such as RNN, LSTM, GRU, BiRNN, BiLSTM, and BiGRU. To evaluate each model, the difference between predicted and actual values was compared using MSE and RMSE. The BiLSTM model showed the optimal results based on RMSE. In order to diagnose abnormalities in the developed model, the critical point was set using statistical techniques in consultation with experts in the field and verified. By collecting and preprocessing real-world data and developing a model, this study serves as a case study of utilizing time-series data in small and medium-sized enterprises.

• Journal of Korea Water Resources Association
• /
• v.55 no.8
• /
• pp.565-575
• /
• 2022

Recently, in the field of water resource engineering, interest in predicting time series water levels and flow rates using deep learning technology that has rapidly developed along with the Fourth Industrial Revolution is increasing. In addition, although water-level and flow-rate prediction have been performed using the Long Short-Term Memory (LSTM) model and Gated Recurrent Unit (GRU) model that can predict time-series data, the accuracy of flow-rate prediction in rivers with rapid temporal fluctuations was predicted to be very low compared to that of water-level prediction. In this study, the Paldang Bridge Station of the Han River, which has a large flow-rate fluctuation and little influence from tidal waves in the estuary, was selected. In addition, time-series data with large flow fluctuations were selected to collect water-level and flow-rate data for 2 years and 7 months, which are relatively short in data length, to be used as training and prediction data for the LSTM and GRU models. When learning time-series water levels with very high time fluctuation in two models, the predicted water-level results in both models secured appropriate accuracy compared to observation water levels, but when training rapidly temporal fluctuation flow rates directly in two models, the predicted flow rates deteriorated significantly. Therefore, in this study, in order to accurately predict the rapidly changing flow rate, the water-level data predicted by the two models could be used as input data for the rating curve to significantly improve the prediction accuracy of the flow rates. Finally, the results of this study are expected to be sufficiently used as the data of flood warning system in urban rivers where the observation length of hydrological data is not relatively long and the flow-rate changes rapidly.

• Smart Media Journal
• /
• v.7 no.4
• /
• pp.17-23
• /
• 2018

We proposed a LSTM-based RNN model that can effectively perform the automatic spacing characteristics. For those long or noisy sentences which are known to be difficult to handle within Neural Network Learning, we defined a proper input data format and decoding data format, and added dropout, bidirectional multi-layer LSTM, layer normalization, and attention mechanism to improve the performance. Despite of the fact that Sejong corpus contains some spacing errors, a noise-robust learning model developed in this study with no overfitting through a dropout method helped training and returned meaningful results of Korean word spacing and its patterns. The experimental results showed that the performance of LSTM sequence-to-sequence model is 0.94 in F1-measure, which is better than the rule-based deep-learning method of GRU-CRF.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.3
• /
• pp.71-80
• /
• 2021

The selection of an appropriate neural network algorithm is an important step for accurate data prediction in machine learning. Many algorithms based on basic artificial neural networks have been devised to efficiently predict future data. These networks include deep neural networks (DNNs), recurrent neural networks (RNNs), long short-term memory (LSTM) networks, and gated recurrent unit (GRU) neural networks. Developers face difficulties when choosing among these networks because sufficient information on their performance is unavailable. To alleviate this difficulty, we evaluated the performance of each algorithm by comparing their errors and processing times. Each neural network model was trained using a tax dataset, and the trained model was used for data prediction to compare accuracies among the various algorithms. Furthermore, the effects of activation functions and various optimizers on the performance of the models were analyzed The experimental results show that the GRU and LSTM algorithms yields the lowest prediction error with an average RMSE of 0.12 and an average R2 score of 0.78 and 0.75 respectively, and the basic DNN model achieves the lowest processing time but highest average RMSE of 0.163. Furthermore, the Adam optimizer yields the best performance (with DNN, GRU, and LSTM) in terms of error and the worst performance in terms of processing time. The findings of this study are thus expected to be useful for scientists and developers.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.26 no.1
• /
• pp.53-62
• /
• 2024

In this study, we built a model to estimate frost occurrence in South Korea using single-input deep learning and multi-input deep learning. Meteorological factors used as learning data included minimum temperature, wind speed, relative humidity, cloud cover, and precipitation. As a result of statistical analysis for each factor on days when frost occurred and days when frost did not occur, significant differences were found. When evaluating the frost occurrence models based on single-input deep learning and multi-input deep learning model, the model using both GRU and MLP was highest accuracy at 0.8774 on average. As a result, it was found that frost occurrence model adopting multi-input deep learning improved performance more than using MLP, LSTM, GRU respectively.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.563-568
• /
• 2023

ECG(electrocardiogram) is used to measure the rate and regularity of heartbeats, as well as the size and position of the chambers, the presence of any damage to the heart, and the cause of all heart diseases can be found. Because the ECG signal obtained using the ECG-KIT includes noise in the ECG signal, noise must be removed from the ECG signal to apply to the deep learning. In this paper, Noise included in the ECG signal was removed by using a lowpass filter of the Digital FIR Hamming window function. When the performance evaluation of the three activation functions, sigmoid(), ReLU(), and tanh() functions, which was confirmed that the activation function with the smallest error was the tanh() function, the elapsed time was longer when the batch size was small than large. Also, it was confirmed that result of the performance evaluation for the GRU model was superior to that of the LSTM model.

• Journal of Information Technology Services
• /
• v.17 no.1
• /
• pp.79-89
• /
• 2018

Sentiment analysis is a technique of text mining that extracts feelings of the person who wrote the sentence like movie review. The preliminary researches of sentiment analysis identify sentiments by using the dictionary which contains negative and positive words collected in advance. As researches on deep learning are actively carried out, sentiment analysis using deep learning model with morpheme or word unit has been done. However, this model has disadvantages in that the word dictionary varies according to the domain and the number of morphemes or words gets relatively larger than that of phonemes. Therefore, the size of the dictionary becomes large and the complexity of the model increases accordingly. We construct a sentiment analysis model using recurrent neural network by dividing input data into phoneme-level which is smaller than morpheme-level. To verify the performance, we use 30,000 movie reviews from the Korean biggest portal, Naver. Morpheme-level sentiment analysis model is also implemented and compared. As a result, the phoneme-level sentiment analysis model is superior to that of the morpheme-level, and in particular, the phoneme-level model using LSTM performs better than that of using GRU model. It is expected that Korean text processing based on a phoneme-level model can be applied to various text mining and language models.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.17-26
• /
• 2023

In this paper, we propose a several smoothing techniques are compared and applied to increase the application of the LSTM-based learning model and its effectiveness. The applied smoothing technique is Savitky-Golay, exponential smoothing, and weighted moving average. Through this study, the LSTM algorithm with the Savitky-Golay filter applied in the preprocessing process showed significant best results in prediction performance than the result value shown when applying the LSTM model to Bitcoin data. To confirm the predictive performance results, the learning loss rate and verification loss rate according to the Savitzky-Golay LSTM model were compared with the case of LSTM used to remove complex factors from Bitcoin price prediction, and experimented with an average value of 20 times to increase its reliability. As a result, values of (3.0556, 0.00005) and (1.4659, 0.00002) could be obtained. As a result, since crypto-currencies such as Bitcoin have more volatility than stocks, noise was removed by applying the Savitzky-Golay in the data preprocessing process, and the data after preprocessing were obtained the most-significant to increase the Bitcoin prediction rate through LSTM neural network learning.

• Communications for Statistical Applications and Methods
• /
• v.26 no.5
• /
• pp.497-506
• /
• 2019

Forecasting the U.S. employment level is made using machine learning methods of the artificial neural network: deep neural network, long short term memory (LSTM), gated recurrent unit (GRU). We consider the big data of the federal reserve economic data among which 105 important macroeconomic variables chosen by McCracken and Ng (Journal of Business and Economic Statistics, 34, 574-589, 2016) are considered as predictors. We investigate the influence of the two statistical issues of the dimension reduction and time series differencing on the machine learning forecast. An out-of-sample forecast comparison shows that (LSTM, GRU) with differencing performs better than the autoregressive model and the dimension reduction improves long-term forecasts and some short-term forecasts.