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 the Influence of Changing Data Classification Criteria Depending on the Correlation of Variables

  • Received : 2024.10.24
  • Accepted : 2024.11.05
  • Published : 2024.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

Currently, many industrial fields are pursuing research and development toward a hyper-connected society. However, as we become a hyper-connected society that perceives virtual reality as if it were reality, accurate classification of data to recognize objects, emotions and facial expressions must be accompanied. In other words, only when data meaning objects, emotions, and facial expressions are accurately classified will reliability of cognition and recognition be obtained not only in the physical world but also in a hyper-connected society. In addition, errors in perception and recognition of objects, emotions, and facial expressions can be reduced through big data analysis, and it will be protected from secondary incidents and damages. Therefore, in this study, we try to find out whether the classification of data is well done in the stage where AI with automatic cognition ability recognizes and recognizes objects, emotions, and facial expressions, and whether the data classified according to characteristics is a reliable classification result. In the experiment, when classifying data using a decision tree, we plan to conduct a study to find out whether the classification criteria of the data affect the classification criteria according to the degree of correlation between variables.

Keywords

References

  1. Suchul Lee and Mihyun Ko, "Exploring the Key Technologies on Next Production Innovation," Journal of the Korea Convergence Society, Vol. 9, No. 9, pp. 199-207, 2018. DOI: https://doi.org/10.15207/JKCS.2018.9.9.199
  2. Youngsoon Kim, "Fourth Industrial Revolution(4IR) Hyper-Connected Society and Internet of Things Age," The Korea contents Association Review, Vol. 17, No. 3, pp. 14-19, Sep 2019.
  3. Se Hoon Jung, Jong Chan Kim, Kim Cheeyong, Kang Soo You and Chun Bo Sim, "A Study on Classification Evaluation Prediction Model by Cluster for Accuracy Measurement of Unsupervised Learning Data," Journal of Korea Multimedia Society, Vol. 21, No. 7, pp. 779-786, July 2018. DOI: https://doi.org/10.9717/kmms.2018.21.7.779
  4. Hayoung Eom, Jeonghwan Kim, Seungyun Ji and Heeyoul Choi, "Autonomous Parking Simulator for Reinforcement Learning," Journal of Digital Contents Society, Vol. 21, No. 2, pp. 381-386, Feb 2020. DOI: http://dx.doi.org/10.9728/dcs.2020.21.2.381
  5. Hyung-Woo Lee, "Development of Supervised Machine Learning based Catalog Entry Classification and Recommendation System," Journal of Internet Computing and Services(JICS), Vol. 20, No. 1, pp. 57-65, Feb 2019. DOI: http://dx.doi.org/10.7472/jksii.2019.20.1.57
  6. Young Jin Kim, Joung Woo Ryu, Won Moon Song and Myung Won Kim, "Fire Probability Prediction Based on Weather Information Using Decision Tree," Journal of KIISE : Software and Applications, Vol. 40, No. 11, pp. 705-715, Feb 2013. DOI: http://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/11916
  7. Jihyun Lee, Jiyoung Woo, Ah Reum Kang, Young-Seob Jeong, Woohyun Jung, Misoon Lee and Sang HyunKim, "Comparative Analysis on Machine Learning and Deep Learning to Predict Post-Induction Hypotension," Sensors 2020, 20(16), 4575, Aug 2020. DOI: https://doi.org/10.3390/s20164575
  8. Yi-na Jeong, Yong-bo Sim and Su-rak Son, "DFLM(Deeplearning facial landmark model) for facial emotion classification," Journal of Internet Computing and Services (JICS), Vol. 24, No. 3, pp. 43-50, June 2023. DOI: http://dx.doi.org/10.7472/jksii.2023.24.3.43
  9. Jiyoung Lee, Jiho Kim, Euna Lee and Hongchul Lee, "Deep Learning Model Structure for Korean Facial Expression Detection," Journal of KIIT, Vol. 21, No. 2, pp. 9-17, 2023. DOI: http://dx.doi.org/10.14801/jkiit.2023.21.2.9
  10. Kyung-Seob Yoon and SangWon Lee, "Music player using emotion classification of facial expressions," The Korean Society Of Computer And Information, Vol. 27, No. 1, pp. 243-246, Jan 2019.
  11. In-Kyung Byun and Jae-Ho Lee, "The Effect of Cognitive Movement Therapy on Emotional Rehabilitation for Children with Affective and Behavioral Disorder Using Emotional Expression and Facial Image Analysis," The Journal of the Korea Contents Association(KCA), Vol. 16, No. 12, pp. 327-345, 2016. DOI: http://dx.doi.org/10.5392/JKCA.2016.16.12.327
  12. Taebok Yoon and Jee-Hyong Lee, "Design of Heuristic Decision Tree (HDT) Using Human Knowledge," Korean Institute of Intelligent Systems, Vol. 19, No. 4, pp. 525-531, Aug 2009.
  13. Jae-Ho Kim and Jang-Young Kim, "The Analysis of Correlation Between COVID-19 and Seoul Small Business Commercial Districts," Journal of the Korea Institute of Information and Communication Engineering, Vol. 25, No. 3, pp. 384-388, 2021. DOI: http://doi.org/10.6109/jkiice.2021.25.3.384
  14. Jae-Wan Yang, Young-Doo Lee and In-Soo Koo, "Sensor Fault Detection Scheme based on Deep Learning and Support Vector Machine," The Journal of The Institute of Internet, Broadcasting and Communication (IIBC), Vol. 18, No. 2, pp. 185-195, Apr. 30, 2018. DOI: https://doi.org/10.7236/JIIBC.2018.18.2.185
  15. Kyoungho Choi1 and Jin Ah Yoo, "A reviews on the social network analysis using R," Journal of the Korean Chemical Society(JKCS), Vol. 6, No. 1, pp. 77-83, 2015. DOI: http://dx.doi.org/10.15207/JKCS.2015.6.1.077
  16. Youngseok Lee, "Python-based Software Education Model for Non-Computer Majors," Journal of the Korea Convergence Society, Vol. 9, No. 3, pp. 73-78, 2018. DOI: https://doi.org/10.15207/JKCS.2018.9.3.073