2023, Vol.28, No.7

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

pISSN : 1598-849X / eISSN : 2383-9945
https://journal.kci.go.kr/jksci

Currently, as the demand for stops in the urban increases resulting from an increase in the supply of express trains, the development of trains capable of operating both high-floor platforms in the urban and low-floor platforms in the suburbs is required. In this paper, we studied the design and fabrication of a controller for train doors that consists of low and high steps as a plug-in type door mechanism and thus can be used on low and high platforms. This DCU H/W was designed and implemented using 32 bit MCU to control 4 motors, 33 digital inputs and 16 digital outputs. In addition, based on the software life cycle of EN50128, 2 items of operation requirements and 12 items of control requirements were derived, and then they were designed and implemented as operation SW. The implemented SW was tested for each requirement. As a result, we performed tests on 13 items that could be tested in the mock-up out of 14 total requirement items and showed that the requirements were satisfied.

In this paper, we evaluate deep learning time series forecasting models. Recent studies show that those models perform better than the traditional prediction model such as ARIMA. Among them, recurrent neural networks to store previous information in the hidden layer are one of the prediction models. In order to solve the gradient vanishing problem in the network, LSTM is used with small memory inside the recurrent neural network along with BI-LSTM in which the hidden layer is added in the reverse direction of the data flow. In this paper, we compared the performance of Informer by comparing with other models (LSTM, BI-LSTM, and Transformer) for real Nitrogen dioxide (NO2) data. In order to evaluate the accuracy of each method, mean square root error and mean absolute error between the real value and the predicted value were obtained . Consequently, Informer has improved prediction accuracy compared with other methods.

In the process of collecting social reviews, a number of noise reviews irrelevant to a given search keyword can be included in the search results. To filter out such reviews, machine learning can be used. However, if the number of reviews is insufficient for a target place to be analyzed, filtering accuracy can be degraded due to the lack of training data. To resolve this issue, we propose a supervised learning method to improve accuracy of the noise review filtering for the places with insufficient reviews. In the proposed method, training is not performed by an individual place, but by a group including several places with similar characteristics. The classifier obtained through the training can be used for the noise review filtering of an arbitrary place belonging to the group, so the problem of insufficient training data can be resolved. To verify the proposed method, a noise review filtering model was implemented using LSTM and BERT, and filtering accuracy was checked through experiments using real data collected online. The experimental results show that the accuracy of the proposed method was 92.4% on the average, and it provided 87.5% accuracy when targeting places with less than 100 reviews.