International Journal of Advanced Culture Technology

The International Promotion Agency of Culture Technology (국제문화기술진흥원)
권호 표지
DOI QR코드

DOI QR Code

Development of CNN-Transformer Hybrid Model for Odor Analysis

  • Kyu-Ha Kim (Department of Computer Engineering, Honam University) ;
  • Sang-Hyun Lee (Department of Computer Engineering, Honam University)
  • Received : 2023.07.17
  • Accepted : 2023.08.10
  • Published : 2023.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

The study identified the various causes of odor problems, the discomfort they cause, and the importance of the public health and environmental issues associated with them. To solve the odor problem, you must identify the cause and perform an accurate analysis. Therefore, we proposed a CNN-Transformer hybrid model (CTHM) that combines CNN and Transformer and evaluated its performance. It was evaluated using a dataset consisting of 120,000 odor samples, and experimental results showed that CTHM achieved an accuracy of 93.000%, a precision of 92.553%, a recall of 94.167%, an F1 score of 92.880%, and an RMSE of 0.276. Our results showed that CTHM was suitable for odor analysis and had excellent prediction performance. Utilization of this model is expected to help address odor problems and alleviate public health and environmental concerns.

Keywords

Acknowledgement

This research was supported by "Regional Innovation Stratery (RIS)" through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (MOE) (2021RIS-002).

References

  1. Y. Shi, M. Li and G. Li, "Analysis of Odor Emissions from Industrial Processes," International Journal of Environmental Science and Technology, vol. 15, no. 11, pp. 2523-2534, Nov. 2018.
  2. J. H. Park, S. W. Kim and D. Kim, "Odor Concentration Analysis of Landfill Sites in Korea," Journal of Korean Society for Environmental Analysis, vol. 22, no. 1, pp. 37-44, 2019.
  3. J. H. Lee and K. W. Kim, "Odor Emissions from Livestock Production and Agriculture," International Journal of Agricultural and Environmental Sciences, vol. 10, no. 2, pp. 100-107, 2017.
  4. S. -H. Lee, "A study on classification and detection of small moths using CNN model," Computer. Mater. Contin, vol.71, no.1, 1987-1998, 2022. DOI: https://doi.org/10.32604/cmc.2022.022554
  5. H. Lee, H. S. Kim, and O. S. Kwon, "Analysis of Vehicle Emission Odor and its Impact on Urban Air Quality," Journal of Korean Society of Transportation, vol. 34, no. 6, pp. 506-513, 2016.
  6. G. -S. Lee and S. -H. Lee, "A Study on Real-time Detection Using Odor Data Based on Mixed Neural Network of CNN and LSTM," The International Journal of Advanced Culture Technology, vol.11, no.1, pp.325-331, 2023. DOI: https://doi.org/10.17703/IJACT.202 2.11.1.325
  7. G. -S. Lee and Sang-Hyun Lee, "Prediction of changes in fine dust concentration using LSTM model," The International Journal of Advanced Smart Convergence, vol.11, no.2, pp.30-37, 2022.  DOI: http://dx.doi.org/10.7236/IJASC.2022.11.2.30
  8. S. -H. Lee, "A study on road damage detection for safe driving of autonomous vehicles based on OpenCV and CNN," International Journal of Internet, Broadcasting and Communication, vol.14, no.2 pp.47-54, 2022. DOI: http://dx.doi.org/10.7236/IJIBC.2022.14.2.47
  9. N. Patwardhan, S. Marrone and C. Sansone, "Transformers in the Real World: A Survey on NLP Applications," Information, vol .14, no.4, 242, 2023. DOI: https://doi.org/10.3390/info14040242