Journal of Korea Society of Industrial Information Systems (한국산업정보학회논문지)

Korea Society of Industrial Information Systems (한국산업정보학회)
권호 표지
DOI QR코드

DOI QR Code

Design of a Mirror for Fragrance Recommendation based on Personal Emotion Analysis

개인의 감성 분석 기반 향 추천 미러 설계

  • 김현지 (대구대학교 일반대학원 정보통신공학과) ;
  • 오유수 (대구대학교 AI학부)
  • Received : 2023.04.25
  • Accepted : 2023.08.08
  • Published : 2023.08.30
Download PDF
⟨ Previous Next ⟩

Abstract

The paper proposes a smart mirror system that recommends fragrances based on user emotion analysis. This paper combines natural language processing techniques such as embedding techniques (CounterVectorizer and TF-IDF) and machine learning classification models (DecisionTree, SVM, RandomForest, SGD Classifier) to build a model and compares the results. After the comparison, the paper constructs a personal emotion-based fragrance recommendation mirror model based on the SVM and word embedding pipeline-based emotion classifier model with the highest performance. The proposed system implements a personalized fragrance recommendation mirror based on emotion analysis, providing web services using the Flask web framework. This paper uses the Google Speech Cloud API to recognize users' voices and use speech-to-text (STT) to convert voice-transcribed text data. The proposed system provides users with information about weather, humidity, location, quotes, time, and schedule management.

본 논문에서는 사용자의 감정 분석에 따른 향을 추천하는 스마트 미러 시스템을 제안한다. 본 논문은 자연어 처리 중 임베딩 기법(CounterVectorizer와 TF-IDF 기법), 머신러닝 분류 기법 중 최적의 모델(DecisionTree, SVM, RandomForest, SGD Classifier)을 융합하여 시스템을 구축하고 그 결과를 비교한다. 실험 결과, 가장 높은 성능을 보이는 SVM과 워드 임베딩을 파이프라인 기법으로 감정 분류기 모델에 적용한다. 제안된 시스템은 Flask 웹 프레임워크를 이용하여 웹 서비스를 제공하는 개인감정 분석 기반 향 추천 미러를 구현한다. 본 논문은 Google Speech Cloud API를 이용하여 사용자의 음성을 인식하고 STT(Speech To Text)로 음성 변환된 텍스트 데이터를 사용한다. 제안된 시스템은 날씨, 습도, 위치, 명언, 시간, 일정 관리에 대한 정보를 사용자에게 제공한다.

Keywords

Acknowledgement

이 연구는 2020학년도 대구대학교 학술연구비지원으로 수행되었음

References

  1. Choi, U. J., Seo, J. H., Park, J. H., Park, J. W., Park, H. W., Choi, M. S., Ko, B. C.(2018). Emotional Companion Smart Mirror Based on Facial Expression Recognition. Proceedings of the Korean Information Science Society Conference,1823-1824.
  2. Ham, H. J.(2015). "The Study on Aroma Essential Use and Scent Preference." Domestic master's thesis Hansung University Graduate School of Arts, Seoul.
  3. Jeong, M. U., Kim, H. J., Gwak, C. W and Oh, Y. S.(2022)"A Study On User Skin Color-Based Foundation Color Recommendation Method Using Deep Learning", J OURNAL OF KOREA MULTIMEDIA SOCIETY 25.9: 1367-1374.
  4. Jeong, S. H. and Jin, C. H. (2020). A Study on the Office Rent Estimation by the Machine Learning Methods -Focusing on the Use of Random Forests, Artificial Neural Networks, Support Vector Machines-. Journal of KREAA, 26(2), 23-53. https://doi.org/10.19172/KREAA.26.2.2
  5. Kang, S. B., Kwon, S. H., Kim, Y. H., Lee, S. I., & Han, Y. O. (2021). Smart Mirror for Styling. Journal of the Korean Institute of Communications and Information Sciences, 16(6), 1271-1277.
  6. Kim, H. W., Zhang, X. , Kim, Y. S., Jung, I. H. (2022). Comparison of the Performance of CNN Models for Retinal Diseases Diagnosis. Journal of Korean institute of intelligent systems, 32(1), 51-60. https://doi.org/10.5391/JKIIS.2022.32.1.51
  7. Ko, H. M., Kim, S. R., Kang, N. H. (2017). Design and Implementation of Smart-Mirror Supporting Recommendation Service based on Personal Usage Data. KIISE Transactions on Computing Practices, 23(1), 65-73. https://doi.org/10.5626/KTCP.2017.23.1.65
  8. Lee, C. S., Lim, D. W., Noh, S. H., Kim, T. H., Park, S. B., Yoon, K. H., and Jeong, C. W.(2021) "Urinary Stones Segmentation Model and AI Web Application Development in Abdominal CT Images Through Machine Learning." KIP S Transactions on Computer and Communication Systems 10.11: 305-310.
  9. Lee, J. H., Lee, M. B. and Kim, J. W.(2019) "A study on Korean language processing using TF-IDF." Journal of information systems 28.3 : 105-121.
  10. Lee, J. J. and Park, B. J. (2022). A Study on Artificial Intelligence of Things Trends. Jounal of The Korea Society of Information Technology Policy & Management (ITPM), 14(2), 2901-2906.
  11. Lee, J. M., Kim, H. S., Ha, T. B., Park, H. J., Ahn, Y. M. (2022). Open-Domain Dialogue Generation using Pre-trained Language Models in Korean. Proceedings of the Korean Information Science Society Conference, 624-626.
  12. Oh, T. K.(2021) "TPR-TNR plot for confusion matrix and correlation plot for a contingency table." Domestic master's thesis Sungkyunkwan University Graduate School, Seoul
  13. Park, J. H. and Kim, C. B.(2020) "Implementation of Face Recognition Pipeline Model using Caffe" The journal of Korea Navigation Institute 24.5: 430-437.
  14. Ren, M. Y. ,and Kang, S. J.(2017) "Sentiment Analysis by Using Semantics-Enhanced Word Embedding." Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology 7.2: 321-329. https://doi.org/10.14257/AJMAHS.2017.02.53
  15. Yeo, U. C., Park, S. H. ,Moon, J. W., An, S. W.and Han, Y. O.(2019) "Smart Mirror of Personal Environment using Voice Recognition." The J ournal of The Korea Institute of Electronic Communication Sciences 14.1: 199-204.