정보처리학회논문지:컴퓨터 및 통신 시스템 (KIPS Transactions on Computer and Communication Systems)

  • 제8권4호
  • /
  • Pages.79-86
  • /
  • 2019
  • /
  • 2287-5891(pISSN)
  • /
  • 2734-049X(eISSN)
한국정보처리학회 (Korea Information Processing Society)
권호 표지
DOI QR코드

DOI QR Code

텐서 플로우 신경망 라이브러리를 이용한 시계열 데이터 예측

A Time-Series Data Prediction Using TensorFlow Neural Network Libraries

  • 투고 : 2019.01.23
  • 심사 : 2019.02.19
  • 발행 : 2019.04.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서 인공 신경망을 이용한 시계열 데이터 예측 사례에 대해 서술한다. 본 연구에서는 텐서 플로우 라이브러리를 사용하여 배치 기반의 인공 신경망과 스타케스틱 기반의 인공신경망을 구현하였다. 실험을 통해, 구현된 각 신경망에 대해 훈련 에러와 시험에러를 측정하였다. 신경망 훈련과 시험을 위해서 미국의 인디아나주의 공식 웹사이트로부터 8개월간 수집된 세금 데이터를 사용하였다. 실험 결과, 배치 기반의 신경망 기법이 스타케스틱 기법보다 좋은 성능을 보였다. 또한, 좋은 성능을 보인 배치 기반의 신경망을 이용하여 약 7개월 간 종합 세수 예측을 수행하고 예측된 결과와 실제 데이터를 수집하여 비교 실험을 진행 하였다. 실험 결과, 예측된 종합 세수 금액 결과가 실제값과 거의 유사하게 측정되었다.

This paper describes a time-series data prediction based on artificial neural networks (ANN). In this study, a batch based ANN model and a stochastic ANN model have been implemented using TensorFlow libraries. Each model are evaluated by comparing training and testing errors that are measured through experiment. To train and test each model, tax dataset was used that are collected from the government website of indiana state budget agency in USA from 2001 to 2018. The dataset includes tax incomes of individual, product sales, company, and total tax incomes. The experimental results show that batch model reveals better performance than stochastic model. Using the batch scheme, we have conducted a prediction experiment. In the experiment, total taxes are predicted during next seven months, and compared with actual collected total taxes. The results shows that predicted data are almost same with the actual data.

키워드

JBCRIN_2019_v8n4_79_f0001.png 이미지

Fig. 1. Topology of Artificial Neural Network Model in the Experiment

JBCRIN_2019_v8n4_79_f0002.png 이미지

Fig. 2. A Flow of the Whole Implementation

JBCRIN_2019_v8n4_79_f0003.png 이미지

Fig. 3. Sample Code of the Implementation

JBCRIN_2019_v8n4_79_f0004.png 이미지

Fig. 4. Experimental Results in a Batch with the Size of 10

JBCRIN_2019_v8n4_79_f0005.png 이미지

Fig. 5. Experimental Results in a Batch with the Size of 20

JBCRIN_2019_v8n4_79_f0006.png 이미지

Fig. 6. Experimental Results in a Stochastic Model

JBCRIN_2019_v8n4_79_f0007.png 이미지

Fig. 7. Experimental Results with Gradient Descent Optimizer

JBCRIN_2019_v8n4_79_f0008.png 이미지

Fig. 8. Experimental Results According to the Learning Rate Changes

JBCRIN_2019_v8n4_79_f0009.png 이미지

Fig. 9. A Comparison of Actual Tax and Predicted Taxes

Table 1. Original Dataset Sample

JBCRIN_2019_v8n4_79_t0001.png 이미지

Table 2. A Sample of Extended Dataset

JBCRIN_2019_v8n4_79_t0002.png 이미지

Table 3. A Comparison of Predicted and Actual Taxes

JBCRIN_2019_v8n4_79_t0003.png 이미지

참고문헌

  1. L. Sheng, C. Zhong-jian, and Z. Xiao-bin, "Application of GA-SVM time series prediction in tax forecasting," 2009 2nd IEEE International Conference on Computer Science and Information Technology, Beijing, 2009, pp.34-36.
  2. Y. Zhang, "Research on the Model of Tax Revenue Forecast of Jilin Province Based on Gray Correlation Analysis," 2014 Sixth International Conference on Intelligent Human-Machine Systems and Cybernetics, Hangzhou, 2014, pp.30-33.
  3. D. Liu, R. Zhang, and J. Li, "Tax Revenue Combination Forecast of Hebei Province Based on the IOWA Operator," 2011 Fourth International Joint Conference on Computational Sciences and Optimization, Yunnan, 2011, pp.516-519.
  4. D. Sena and N. K. Nagwani, "Application of time series based prediction model to forecast per capita disposable income," 2015 IEEE International Advance Computing Conference (IACC), Banglore, 2015, pp.454-457.
  5. T. W. Ayele and R. Mehta, "Real Time Temperature Prediction Using IoT," 2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT), Coimbatore, 2018, pp.1114-1117.
  6. T. W. Ayele and R. Mehta, "Air pollution monitoring and prediction using IoT," 2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT), Coimbatore, 2018, pp.1123-1132.
  7. Y. Wang, J. Zhou, K. Chen, Y. Wang, and L. Liu, "Water quality prediction method based on LSTM neural network," 2017 12th International Conference on Intelligent Systems and Knowledge Engineering (ISKE), Nanjing, 2017, pp.1-5.
  8. A. M. Ertugrul and P. Karagoz, "Movie Genre Classification from Plot Summaries Using Bidirectional LSTM," 2018 IEEE 12th International Conference on Semantic Computing (ICSC), Laguna Hills, CA, 2018, pp.248-251.
  9. K. Greff, R. K. Srivastava, J. Koutník, B. R. Steunebrink, and J. Schmidhuber, "LSTM: A Search Space Odyssey," in IEEE Transactions on Neural Networks and Learning Systems, Vol.28, No.10, pp.2222-2232, Oct. 2017. https://doi.org/10.1109/TNNLS.2016.2582924
  10. G. Botla, V.K. Vadlagattu, and Y. R. Kalipatnapu, "Modeling of Batch Processes Using Explicitly Time-Dependent Artificial Neural Networks," in IEEE Transactions on Neural Networks and Learning Systems, Vol.25, No.5, pp.970-979, 2014. https://doi.org/10.1109/TNNLS.2013.2285242
  11. Y. A. Alma, "Electricity Prices Forecasting using Artificial Neural Networks," in IEEE Latin America Transactions, Vol.16, No.1, pp.105-111, 2018. https://doi.org/10.1109/TLA.2018.8291461
  12. R. Saman, and A. T. Bryan, "A New Formulation for Feedforward Neural Networks," in IEEE Transactions on Neural Networks, Vol.22, No.10, pp.1588-1598, Oct. 2011. https://doi.org/10.1109/TNN.2011.2163169
  13. W.-C. Yeh, "New Parameter-Free Simplified Swarm Optimization for Artificial Neural Network Training and its Application in the Prediction of Time Series," in IEEE Transactions on Neural Networks and Learning Systems, Vol.24, No.4, pp.661-665, 2013. https://doi.org/10.1109/TNNLS.2012.2232678
  14. Y. Weizhong, "Toward Automatic Time-Series Forecasting Using Neural Networks," in IEEE Transactions on Neural Networks and Learning Systems, Vol.23, No.7, pp.1028-1039, 2012. https://doi.org/10.1109/TNNLS.2012.2198074