International Journal of Internet, Broadcasting and Communication

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Abnormal Data Processing Process of LSTM AE - With applying Data based Intelligent Factory

  • Youn-A Min (Applied Software Engineering, Hanyang Cyber University)
  • Received : 2023.04.16
  • Accepted : 2023.04.22
  • Published : 2023.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, effective data management in industrial sites such as intelligent factories using time series data was studied. For effective management of time series data, variables considering the significance of the data were used, and hyper parameters calculated through LSTM AE were applied. We propose an optimized modeling considering the importance of each data section, and through this, outlier data of time series data can be efficiently processed. In the case of applying data significance and applying hyper parameters to which the research in this paper was applied, it was confirmed that the error rate was measured at 5.4%/4.8%/3.3%, and the significance of each data section and the significance of applying hyper parameters to optimize modeling were confirmed.

Keywords

References

  1. Smart contract processing, 2020, Available: https://www.lgcns.com/blog/cns-tech/30841/
  2. Bini, S.A et al., "Artificial intelligence, machine learning and cognitive computing", The Journal of Arthroplasty, Vol.33, No.8, pp.2358-2361, 2018. DOI: 10.1016/j.arth.2018.02.067
  3. KDI International Information Center, " Overseas Trend of Smart Factory for 2021-04", Available: https://eiec.kdi.re.kr/reviewCallDownliad
  4. Lindsay et al., "A Novel Stochastic LSTM Model Inspired by Quantum Machine Learning", 2023 24th International Symposium on Quality Electronic Design, pp. 05-07, 2023 DOI:10.1109/ISQED57927.2023.10129344
  5. Haruna et al., "CNN-LSTM Learning Approach for Classification of Foliar Disease of Apple", 2023 1st International Conference on Advanced Innovations in Smart Cities, pp. 23-25, 2023. DOI:10.1109/ICAISC56366.2023.10085039
  6. Chung.S, Jeon. JY et al., "Standardization strategy of smart factory for improving sme's global competitiveness", Journal of Korea Technology Innovation Society, Vol.19, No.3, pp.545-571, 2018. Available:https://koreascience.kr/article/JAKO201610364778724.pdf
  7. Van Quan Nguyen et al., "LSTM-based Anomaly Detection on Big Data for Smart Factory Monitoring", Journal of Digital Contents Society Vol. 19, No. 4, pp. 789-799, 2018. DOI:10.9728/dcs.2018.19.4.789039
  8. Wonjin Jang et al., "RNN-LSTM Based Soil Moisture Estimation Using Terra MODIS NDVI and LST", Journal of the Korean Society of Agricultural Engineers, Vol.61, No.6, pp. 123 - 132, 2019. DOI:10.5389/KSAE.2019.61.6.123
  9. Tae-Won Jung et al., "Traffic-based reinforcement learning with neural network algorithm in fog computing environment", The International Journal of Internet, Broadcasting and Communication, Vol.12, No.1, pp. 144-150, 2020. DOI: 10.7236/IJIBC.2020.12.1.144
  10. Shen, Peng et al., "Pronunciation-Aware Unique Character Encoding for RNN Transducer-Based Mandarin Speech Recognition", J022 IEEE Spoken Language Technology Workshop, pp. 09-12, 2023. DOI:10.1109/SLT54892.2023.10022528
  11. Donkol, A.A.E. et al., "Optimization of Intrusion Detection Using Likely Point PSO and Enhanced LSTM-RNN Hybrid Technique in Communication Networks", IEEE Access, Vol. 11, pp. 9469 - 9482, 2023. DOI: 10.1109/ACCESS.2023.3240109
  12. N. Par et al., "Time-step interleaved weight reuse for LSTM neural network computing", IEEE Int. Symp. on Low Power Electron, pp. 13-18, 2020. DOI: 10.1145/3370748.3406561
  13. Y. Guan, Z. Yuan, G. Sun, J. Cong, "FPGA-based accelerator for long short-term memory recurrent neural networks", ASP-DAC, pp. 629-634, 2017. DOI: 10.1109/ASPDAC.2017.7858394
  14. LSTM Process Diagram, Available: https://towardsdatascience.com/lstm-networks-a-detailed-explanation-8fae6aefc7f9