문화기술의 융합 (The Journal of the Convergence on Culture Technology)

  • 제9권4호
  • /
  • Pages.487-494
  • /
  • 2023
  • /
  • 2384-0358(pISSN)
  • /
  • 2384-0366(eISSN)
국제문화기술진흥원 (The International Promotion Agency of Culture Technology)
권호 표지
DOI QR코드

DOI QR Code

R과 텐서플로우 딥러닝 성능 비교

A Deep Learning Performance Comparison of R and Tensorflow

  • 장성봉 (금오공과대학교 산학협력단)
  • Sung-Bong Jang (Dept. of Industry-Academy, Kumoh Institute of Technnology)
  • 투고 : 2023.05.08
  • 심사 : 2023.07.01
  • 발행 : 2023.07.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 연구에서는 무료 딥러닝 도구인 R과 텐서플로우에 대한 성능 비교를 수행하였다. 실험에서는 각 도구를 사용하여 6종류의 심층 신경망을 구축하고 10년간의 한국 온도 데이터셋을 사용하여 신경망을 학습시켰다. 구축된 신경망의 입력층 노드 갯수는 10개, 출력층은 5개로 설정 하였으며, 은닉층은 5, 10, 20개로 설정하여 실험을 진행 하였다. 학습 데이터는 2013년 3월 1일부터 2023년 3월 29일까지 서울시 강남구에서 수집된 온도 데이터 3681건을 사용하였다. 성능 비교를 위해, 학습된 신경망을 사용하여, 5일간의 온도를 예측하고 예측된 값과 실제값을 사용하여 평균 제곱근 오차(root mean square error, RMSE)값을 측정하였다. 실험결과, 은닉층이 1개인 경우, R의 학습 오차는 0.04731176이었으며, 텐서플로우는 0.06677193으로 측정되었으며, 은닉층이 2개인 경우에는 R이 0.04782134, 텐서플로 우는 0.05799060로 측정되었다. 전체적으로 R이 더 우수한 성능을 보였다. 우리는 기계학습을 처음 접하는 사용자들에게 두 도구에 대한 정량적 성능 정보를 제공함으로써, 도구 선택에서 발생하는 어려움을 해소하고자 하였다.

In this study, performance comparison was performed on R and TensorFlow, which are free deep learning tools. In the experiment, six types of deep neural networks were built using each tool, and the neural networks were trained using the 10-year Korean temperature dataset. The number of nodes in the input layer of the constructed neural network was set to 10, the number of output layers was set to 5, and the hidden layer was set to 5, 10, and 20 to conduct experiments. The dataset includes 3600 temperature data collected from Gangnam-gu, Seoul from March 1, 2013 to March 29, 2023. For performance comparison, the future temperature was predicted for 5 days using the trained neural network, and the root mean square error (RMSE) value was measured using the predicted value and the actual value. Experiment results shows that when there was one hidden layer, the learning error of R was 0.04731176, and TensorFlow was measured at 0.06677193, and when there were two hidden layers, R was measured at 0.04782134 and TensorFlow was measured at 0.05799060. Overall, R was measured to have better performance. We tried to solve the difficulties in tool selection by providing quantitative performance information on the two tools to users who are new to machine learning.

키워드

과제정보

본 연구는 금오공과대학교 교수연구년제에 의하여 연구된 실적물임.

참고문헌

  1. R.V.D. Schoot, J.D. Bruin, R. Schram, P. Zahedi, J.D. Boer, F. Weijdema, B. Kramer, M. Huijts, M. Hoogerwerf, G. Ferdinands, A. Harkema, J. Willemsen, Y. Ma, Q. Fang, S. Hindriks, L. Tummers, D. L. Oberski, "An open source machine learning framework for efficient and transparent systematic reviews," Nature Machine Intelligence, Vol. 3, pp. 125-133, 2021(https://doi.org/10.1038/s42256-020-00287-7) 
  2. Y.G. Yoon and T.G Oh, "A Study on the Improvement of Construction Site Worker Detection Performance Using YOLOv5 and Open Pose," The Journal of the Convergence on Culture Technology (JCCT), Vol. 8, No. 5, pp.735-740, 2022(DOI: http://dx.doi.org/10.17703/JCCT.2022.8.5.735) 
  3. P. Sherkhane and D. Vora, "Survey of deep learning software tools," 2017 International Conference on Data Management, Analytics and Innovation (ICDMAI), pp. 24-26, 2017 February, Pune, India. 
  4. Z. Pala, "Examining EMF Time Series Using Prediction Algorithms With R," IEEE Canadian Journal of Electrical and Computer Engineering, Vol.44, No.2, 2021, pp. 223-227 (https://10.1109/ICJECE.2020.3037805) 
  5. Y.-S. Lee and P.J. Moon, "A Comparison and Analysis of Deep Learning Framework," The Journal of the Korea Institute of Electronic Communication Sciences, Vol.12, No.1, pp. 115-122, 2017((https://doi.org/10.13067/JKIECS.2017.12.1.115.) 
  6. J.H. Jang , J.H. Park, H.J. Kim, S. R. Yoon, "A Comparative Performance Analysis of SparkBased Distributed Deep-Learning Frameworks," KIISE transactions on computing practices, Vol.23 No.5, pp. 299-303, 2017(DOI:https://doi.org/10.5626/KTCP.2017.23.5.299) 
  7. L. Ferreira, A. Pilastri, C. M. Martins, P. M. Pires, P. Cortez, "A Comparison of AutoML Tools for Machine Learning, Deep Learning and XGBoost," 2021 International Joint Conference on Neural Networks (IJCNN), July 2021(https://10.1109/IJCNN52387.2021.9534091) 
  8. Y.-S. Lee, "Comparison of Machine Learning Tools for Mobile Application," International Journal of Advanced Culture Technology(IJACT), Vol. 10 No.3, pp.360-370, 2022(https://doi.org/10.17703/IJACT.2022.10.3.360) 
  9. S.A. Ali, "LOsMonitor: A Machine Learning Tool for Analyzing and Monitoring Cognitive Levels of Assessment Questions," IEEE Transactions on Learning Technologies, Vol. 14, No.5, pp.640-652, 2021(https://doi.org/10.1109/TLT.2021.3116952) 
  10. C. Francisco, "A Comprehensive and Didactic Review on Multilabel Learning Software Tools," IEEE Access, Vol. 8, pp. 50330-50354, 2020(DOI:https://doi.org/10.1109/ACCESS.2020.2979787)