• The Journal of Bigdata
• /
• v.4 no.1
• /
• pp.29-38
• /
• 2019

In this paper, we propose a sales forecasting model that forecasts the sales volume of short sleeves and outerwear according to the temperature change by utilizing accumulated big data from the online shopping mall 'A' over the past five years to increase sales volume and efficient inventory management. The proposed model predicts sales of short sleeves and outerwear according to temperature changes in 2018 by analyzing sales volume of short sleeves and outerwear from 2014 to 2017. Using the proposed sales forecasting model, we compared the sales forecasts of 2018 with the actual sales volume and found that the error rates are ±1.5% and ±8% for short sleeve and outerwear respectively.

• Journal of Digital Convergence
• /
• v.19 no.2
• /
• pp.215-220
• /
• 2021

In order to reduce the harmful effects on the human body caused by the recent increase in the generation of fine dust in Korea, there is a need for technology to help predict the level of fine dust and take precautions. In this paper, we propose a 1D Convolutional-Recurrent Neural Network (1-D CRNN) model to predict the level of fine dust in Korea. The proposed model is a structure that combines the CNN and the RNN, and uses domestic and foreign fine dust, wind direction, and wind speed data for data prediction. The proposed model achieved an accuracy of about 76%(Partial up to 84%). The proposed model aims to data prediction model for time series data sets that need to consider various data in the future.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.20-29
• /
• 2021

In the Industry 4.0 era, artificial intelligence has attracted considerable interest for learning mass data to improve the accuracy of forecasting and classification. On the other hand, the current method of detecting anomalies relies on traditional statistical methods for a limited amount of data, making it difficult to detect accurate anomalies. Therefore, this paper proposes an artificial intelligence-based anomaly detection methodology to improve the prediction accuracy and identify new data patterns. In particular, data were collected and analyzed from the point of view that sensor data collected at vehicle idle could be used to detect abnormalities. To this end, a sensor was designed to determine the appropriate time length of the data entered into the forecast model, compare the results of idling data with the overall driving data utilization, and make optimal predictions through a combination of various sensor data. In addition, the predictive accuracy of artificial intelligence techniques was presented by comparing Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) as the predictive methodologies. According to the analysis, using idle data, using 1.5 times of the data for the idling periods, and using CNN over LSTM showed better prediction results.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.1
• /
• pp.1-16
• /
• 2020

With the advent of the fourth industrial revolution era, there has been a growing interest in deep learning using big data, and studies using deep learning have been actively conducted in various fields. In the transportation sector, there are many advantages to using deep learning in research as much as using deep traffic big data. In this study, a short -term travel speed prediction model using LSTM, a deep learning technique, was constructed to predict the travel speed. The LSTM model suitable for time series prediction was selected considering that the travel speed data, which is used for prediction, is time series data. In order to predict the travel speed more precisely, we constructed a model that reflects both temporal and spatial effects. The model is a short-term prediction model that predicts after one hour. For the analysis data, the 5minute travel speed collected from the Seoul Transportation Information Center was used, and the analysis section was selected as a part of Gangnam where traffic was congested.

• Smart Media Journal
• /
• v.10 no.2
• /
• pp.16-21
• /
• 2021

Financial time series analysis plays a very important role economically and socially in modern society and is an important task affecting global development, but due to difficulties such as a lot of noise and uncertainty, financial time series analysis prediction is a difficult research topic. In this paper, we propose a market prediction method (MPIL) by converting unstructured data and structured data into images. For market prediction, it analyzes SNS and news data, which is unstructured data for n days, and converts the market data, which is structured data, to an image with the GADF algorithm, and predicts an ultra-short market that predicts the price of n+1 days through image learning. MPIL has an average accuracy of 56%, which is higher than the 50% average accuracy of the model that predicts the market with LSTM by using sentiment analysis used for existing market forecasting.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.1
• /
• pp.25-33
• /
• 2009

Recently, the TS fuzzy models that include the linear equations in the consequent part are widely used for time series forecasting, and the prediction performance of them is somewhat dependent on the characteristics of time series such as stationariness. Thus, a new prediction method is suggested in this paper which is especially effective to nonstationary time series prediction. First, data preprocessing is introduced to extract the patterns and regularities of time series well, and then multiple model TS fuzzy predictors are constructed. Next, an appropriate model is chosen for each input data by an adaptive model selection mechanism based on rough sets, and the prediction is going. Finally, the error compensation procedure is added to improve the performance by decreasing the prediction error. Computer simulations are performed on typical cases to verify the effectiveness of the proposed method. It may be very useful for the prediction of time series with uncertainty and/or nonstationariness because it handles and reflects better the characteristics of data.

• Proceedings of the KIEE Conference
• /
• 2001.11b
• /
• pp.51-53
• /
• 2001

전력 수요 예측은 전력 수급 안정과 양질의 전력을 공급하기 위한 필수 기법이며 경쟁적인 전력시장에서 전력요금과 밀접한 관련이 있다. 그러므로, 경쟁적인 전력시장 구조하의 시장 참여자에게 있어서 전력 수요 예측은 매우 관심 있는 사항이다. 최근의 전력 수요 예측 기법으로 예측한 오차율을 살펴보면 평일과는 다르게 특수일의 전력 수요예측은 평균 5%를 상회하는 수준으로 예측의 정확도가 평일 예측에 비해 크게 낮은데 이유는 특수일이 평일에 비하여 부하의 크기가 다소 낮게 나타나고 특수일 마다 계절적인 차이가 있으며 각각의 특수일 마다 고유한 부하의 특성이 있으므로 과거 데이터를 이용할 때 동일 특수일을 이용하게 되며 따라서 평일과는 다르게 일년 단위로 과거 데이터 값들이 취득되므로 오차율이 커진다. 따라서 데이터들을 퍼지화하여 선형계획법을 수행하여 평균 $2{\sim}3%$ 정도의 우수한 결과를 도출한 바 있다. 본 논문에서는 퍼지 선형회귀분석법을 이용한 예측 기법에 최소자승법을 도입하여 특수일 전력 수요예측의 정확도를 개선하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.07a
• /
• pp.329-330
• /
• 2012

인터넷과 웹의 발전으로 수많은 정보가 발생하고 있으며, 공공기간도 많은 정보를 축적하고 있다. 이에 각 국에서는 공공기간이 보유하는 데이터를 공개하고 있으며 우리나라도 통계청을 중심으로 다양한 데이터를 공개하고 있다. 그러나 공개된 자료의 활용도가 낮은 편이다. 본 논문에서는 공개된 공공데이터 중 에너지 소비 데이터를 활용하고자 한다. 에너지 소비 데이터를 미래 예측 연구에 많이 이용되고 있는 마코프 프로세스를 적용하여, 에너지 소비를 예측할 수 있는 모델링을 제안하고, 그 기대 효과에 대해 논의 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.453-455
• /
• 2023

본 연구는 은행에서 리스크 관리 자동화를 위해 고객의 대출 상환 여부 예측 모델을 제안하고자 한다. 예측 모델로 금융 데이터 같은 정형데이터에서 전통적으로 높은 성능을 보인 의사결정나무기반 모델 LightGBM, CatBoost, XGB 와 최근 제안된 정형데이터에서 사용할 수 있는 설명 가능한 딥러닝 기반 모델 TabNet 간의 성능 비교를 진행한다. 다만, 대출 상환 여부 데이터는 불균형 클래스 데이터로 구성되어있어 샘플링을 진행한다. SMOTE, Random Under Sampling, 혼합 방식을 비교해 가장 높은 성능의 샘플링 기법을 제안한다. 대출 상환 여부 예측 결과 TabNet 모델이 의사결정나무모델들보다 좋은 성능을 보여 정형데이터에서 의사결정나무 기반 모델을 딥러닝 모델이 대체 할 수 있는 가능성을 확인했다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.96-98
• /
• 2000

본 논문에서는 상거래 환경에서 구매자와 비구매자들에 대한 데이터를 학습한 후, 잠재고객들 중에서 구매 확률이 높은 사람을 예측하는 문제에 효율적으로 접근하기 위해 능동적인 데이터 선택 기법을 이용한다. 실험 데이터는 ColL Challenge 2000에서 얻은 데이터로서, 구매자들의 정보보다 비구매자들의 정보가 더 많기 때문에 상당히 균형이 맞지 않는다. 따라서 모든 데이터를 한꺼번에 학습하는 경우에 성능이 좋지 않다. 본 논문에서는 이러한 불균형 분포를 갖는 실제적인 문제에 있어서 성능이 좋지 않다. 본 논문에서는 이러한 불균형 분포를 갖는 실제적인 문제에 있어서 RBF 기반의 신경망을 가지고 능동 학습을 함으로써 기존의 뱃치학습 보다 예측의 정확도를 향상시킬 수 있음을 보인다.