• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.12
• /
• pp.579-586
• /
• 2021

Time series forecasting refers to predicting future time information based on past time information. Accurately predicting future information is crucial because it is used for establishing strategies or making policy decisions in various fields. Recently, a transformer model has been mainly studied for a time series prediction model. However, the existing transformer model has a limitation in that it has an auto-regressive structure in which the output result is input again when the prediction sequence is output. This limitation causes a problem in that accuracy is lowered when predicting a distant time point. This paper proposes a sequential decoding model focusing on the style transformation technique to handle these problems and make more precise time series forecasting. The proposed model has a structure in which the contents of past data are extracted from the transformer-encoder and reflected in the style-based decoder to generate the predictive sequence. Unlike the decoder structure of the conventional auto-regressive transformer, this structure has the advantage of being able to more accurately predict information from a distant view because the prediction sequence is output all at once. As a result of conducting a prediction experiment with various time series datasets with different data characteristics, it was shown that the model presented in this paper has better prediction accuracy than other existing time series prediction models.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.539-540
• /
• 2022

본 논문에서는 정확한 장기 시계열 예측을 위해 시계열 데이터의 다양한 스케일 (시간 규모)에서 표현을 학습하는 트랜스포머 모델을 제안한다. 제안하는 모델은 시계열의 다중 스케일 특징을 추출하고, 이를 트랜스포머에 반영하여 예측 시계열을 생성하는 구조로 되어 있다. 스케일 정규화 과정을 통해 시계열의 전역적 및 지역적인 시간 정보를 효율적으로 융합하여 종속성을 학습한다. 3 가지의 다변량 시계열 데이터를 이용한 실험을 통해 제안하는 방법의 우수성을 보인다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.247-249
• /
• 2000

본 논문에서는 대개 잡음이 포함되어 있고 불규칙적인 특성을 갖고 있는 시계열 자료에 대해 신경 트리 모델을 사용하여 시계열 예측 문제를 해결하고자 한다. 주어진 시계열 자료에 적합한 구조와 가중치를 갖는 신경트리를 찾기 위해 베이지안 진화 알고리즘을 적용한 결과, 자료의 개수가 적어 과적합될 우려가 있는 경우 제안된 방법은 모델의 복잡도가 커지는 것을 억제하고 일반화 성능이 급격하게 나빠지지 않는다는 것을 확인하였다.

• Proceedings of the KIEE Conference
• /
• 2009.07a
• /
• pp.1644_1645
• /
• 2009

본 논문은 비정상 시계열 예측을 위한 다중모델 퍼지 시스템과, 제안된 시스템의 최적화를 위한 유전 알고리즘의 응용을 다룬다. 일반적으로, 퍼지 예측시스템의 성능은 비선형 데이터가 가지고 있는 다양한 패턴이나 법칙성, 경향 등을 잘 분석하고 시스템에 반영함으로써 개선될 수 있다. 따라서, 본 논문은 원형 시계열의 특성을 보다 잘 반영할 수 있는 그들의 차분데이터를 시스템에 적용하며, 생성 가능한 차분 데이터들 중 원형 시계열의 특징에 가까운 일부를 추출하여 다중모델 퍼지 예측 시스템을 구현함으로써 다양한 원형시계열의 패턴이나 법칙성 등이 고려될 수 있도록 하였다. 다중 모델 퍼지 시스템의 각각의 예측기에는 구조가 간단한 k-means 클러스터링 기법을 적용하여 구현의 용이성을 꽤하였으며, 성능평가를 통해 선택된 최종 예측기는 RCGKA(real-coded genetic k-means clustering algorithms)를 통해 더욱 최적화된 규칙기반을 가지게 함으로써 예측성능이 개선될 수 있도록 하였다. 본 논문에 사용된 최적화 기법인 RCGKA에는 또한 성능이 우수한 다양한 유전연산자를 도입하여 더욱 예측기 성능이 강화될 수 있도록 하였으며, 시뮬레이션을 통해 제안된 예측시스템의 효용성을 증명하였다.

• Korean Journal of Construction Engineering and Management
• /
• v.12 no.2
• /
• pp.111-120
• /
• 2011

High-rise buildings have recently increased over the residential, commercial and office facilities, thus an understanding of construction cost for high-rise building projects has been a fundamental issue due to enormous construction cost as well as unpredictable market conditions and fluctuations in the rate of inflation by long-term construction periods of high-rise projects. Especially, recent violent fluctuations of construction material prices add to problems in construction cost forecasting. This research, therefore, develops a time-series model with the Box-Jenkins methodologies and material prices time-series data in Korea in order to forecast future trends of unit prices of required materials. BIM (Building Information Modeling) approaches are also used to analyze injection time of construction resources and to conduct quantity takeoff so that total material price can be forecasted. Comparative analysis of Predictability of tentative ARIMA (Autoregressive Integrated Moving Average) models was conducted to determine optimal time-series model for forecasting future price trends. Proposed BIM based time series forecasting model can help to deal with sudden changes in economic conditions by estimating future material prices.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.2
• /
• pp.81-86
• /
• 2022

Given that time series are used in various fields, such as finance, IoT, and manufacturing, data analytical methods for accurate time-series forecasting can serve to increase operational efficiency. Among time-series analysis methods, multi-horizon forecasting provides a better understanding of data because it can extract meaningful statistics and other characteristics of the entire time-series. Furthermore, time-series data with exogenous information can be accurately predicted by using multi-horizon forecasting methods. However, traditional deep learning-based models for time-series do not account for the heterogeneity of inputs. We proposed an improved time-series predicting method, called the temporal fusion transformer method, which combines multi-horizon forecasting with interpretable insights into temporal dynamics. Various real-world data such as stock prices, fine dust concentrates and electricity consumption were considered in experiments. Experimental results showed that our temporal fusion transformer method has better time-series forecasting performance than existing models.

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.1547-1548
• /
• 2008

본 논문에서는 유동적 비정상 시계열의 패턴과 규칙성을 잘 반영할 수 있는 최적의 차분 간격 후보군을 이용한 TS 퍼지 모델로 다중 퍼지 모델을 구현하였고, 각각의 모델들의 예측 특성을 반영하기 위하여 러프집합을 이용한 모델선택법을 제안하였다. 또한 TS퍼지 모델의 파라미터 식별에는 적절한 오차보정 메커니즘을 추가하여 더욱 예측 성능을 향상 시켰다.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.2
• /
• pp.225-233
• /
• 2011

Stock market prices, economic indices, trends and changes of social phenomena, etc. are categorized as time series data. Research on time series data has been prevalent for a while as it could not only lead to valuable representation of data but also provide future trends as well as changes in direction. We take a conventional model based approach, known as Markov chain modeling for the prediction on stock market prices. To improve prediction accuracy, we apply Markov modeling over carefully selected intervals of training data to fit the trend under consideration to the model. Another method we take is to apply clustering to data and build models of the resultant clusters. We confirmed that clustered models are better off in predicting, however, with the loss of prediction rate.

• The KIPS Transactions:PartB
• /
• v.14B no.7
• /
• pp.531-540
• /
• 2007

In this research, we proposed a two-phase hybrid stock price forecasting model with cointegration tests and artificial neural networks. Using not only the related stocks to the target stock but also the past information as input features in neural networks, the new model showed an improved performance in forecasting than that of the usual neural networks. Firstly in order to extract stocks which have long run relationships with the target stock, we made use of Johansen's cointegration test. In stock market, some stocks are apt to vary similarly and these phenomenon can be very informative to forecast the target stock. Johansen's cointegration test provides whether variables are related and whether the relationship is statistically significant. Secondly, we learned the model which includes lagged variables of the target and related stocks in addition to other characteristics of them. Although former research usually did not incorporate those variables, it is well known that most economic time series data are depend on its past value. Also, it is common in econometric literatures to consider lagged values as dependent variables. We implemented a price direction forecasting system for KOSPI index to examine the performance of the proposed model. As the result, our model had 11.29% higher forecasting accuracy on average than the model learned without cointegration test and also showed 10.59% higher on average than the model which randomly selected stocks to make the size of the feature set same as that of the proposed model.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.5
• /
• pp.689-694
• /
• 2009

In this paper an approach to building fuzzy models for predicting daily and weekly stock prices is presented. Predicting stock prices with traditional time series analysis has proven to be difficult. Fuzzy logic based models have advantage of expressing the input-output relation linguistically, which facilitates the understanding of the system behavior. In building a stock prediction model we bear a burden of selecting most effective indicators for the stock prediction. In this paper information used in traditional candle stick-chart analysis is considered as input variables of our fuzzy models. The fuzzy rules have the premises and the consequents composed of trapezoidal membership functions and nonlinear equations, respectively. DE(Differential Evolution) identifies optimal fuzzy rules through an evolutionary process. The fuzzy models to predict daily and weekly open, high, low, and close prices of KOSPI(KOrea composite Stock Price Index) are built, and their performances are demonstrated.