Random forest regressor for predicting sensory texture of emotional designed packaging films
A random forest (RF) regression model was developed to predict sensory texture preferences of packaging films, enhancing their emotional appeal to consumers. Five films, including matte and varnish-textured prints, were analyzed using a surface profilometer to measure roughness parameters (Ra, Ry, R...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S259012302500235X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206910331125760 |
|---|---|
| author | Yong Ju Lee Min Jung Joo Ha Kyoung Yu Tai-Ju Lee Hyoung Jin Kim |
| author_facet | Yong Ju Lee Min Jung Joo Ha Kyoung Yu Tai-Ju Lee Hyoung Jin Kim |
| author_sort | Yong Ju Lee |
| collection | DOAJ |
| description | A random forest (RF) regression model was developed to predict sensory texture preferences of packaging films, enhancing their emotional appeal to consumers. Five films, including matte and varnish-textured prints, were analyzed using a surface profilometer to measure roughness parameters (Ra, Ry, Rz, Rq, and R-MAD) in compliance with ISO 4287 and ISO 24118–1. Sensory preferences were evaluated through tests involving 75 panelists, and correlations between roughness parameters and preferences were established. Power spectral density (PSD) analysis with Welch window preprocessing provided detailed surface texture insights. The RF model achieved a coefficient of determination of 0.977, outperforming partial least squares regression, and highlighted the importance of significant wavelength regions in predictive modeling. This study demonstrates a robust framework for integrating machine learning in packaging design to optimize sensory appeal. |
| format | Article |
| id | doaj-art-e7c5caa6d1084233ad11005324f1b1a5 |
| institution | Kabale University |
| issn | 2590-1230 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-e7c5caa6d1084233ad11005324f1b1a52025-02-07T04:48:11ZengElsevierResults in Engineering2590-12302025-03-0125104147Random forest regressor for predicting sensory texture of emotional designed packaging filmsYong Ju Lee0Min Jung Joo1Ha Kyoung Yu2Tai-Ju Lee3Hyoung Jin Kim4Department of Forest Products and Biotechnology, Kookmin University, 77 Jeongneung-ro, Seongbuk-gu, Seoul 02707 , Republic of KoreaComponent and Material Division, Korea Conformity Laboratories, 199 Gasan digital 1-ro, Geumcheon-gu, Seoul 08503, Republic of KoreaSoftpack, 420-18, Opo-ro, Gwangju-si, Gyeonggi-do 12774, Republic of KoreaDepartment of Forest Products and Biotechnology, Kookmin University, 77 Jeongneung-ro, Seongbuk-gu, Seoul 02707 , Republic of Korea; Corresponding authors.Department of Forest Products and Biotechnology, Kookmin University, 77 Jeongneung-ro, Seongbuk-gu, Seoul 02707 , Republic of Korea; Corresponding authors.A random forest (RF) regression model was developed to predict sensory texture preferences of packaging films, enhancing their emotional appeal to consumers. Five films, including matte and varnish-textured prints, were analyzed using a surface profilometer to measure roughness parameters (Ra, Ry, Rz, Rq, and R-MAD) in compliance with ISO 4287 and ISO 24118–1. Sensory preferences were evaluated through tests involving 75 panelists, and correlations between roughness parameters and preferences were established. Power spectral density (PSD) analysis with Welch window preprocessing provided detailed surface texture insights. The RF model achieved a coefficient of determination of 0.977, outperforming partial least squares regression, and highlighted the importance of significant wavelength regions in predictive modeling. This study demonstrates a robust framework for integrating machine learning in packaging design to optimize sensory appeal.http://www.sciencedirect.com/science/article/pii/S259012302500235XSurface textureSurface roughnessPower spectral density (PSD)Machine learningSensory panel testPartial least square regression (PLSR) |
| spellingShingle | Yong Ju Lee Min Jung Joo Ha Kyoung Yu Tai-Ju Lee Hyoung Jin Kim Random forest regressor for predicting sensory texture of emotional designed packaging films Results in Engineering Surface texture Surface roughness Power spectral density (PSD) Machine learning Sensory panel test Partial least square regression (PLSR) |
| title | Random forest regressor for predicting sensory texture of emotional designed packaging films |
| title_full | Random forest regressor for predicting sensory texture of emotional designed packaging films |
| title_fullStr | Random forest regressor for predicting sensory texture of emotional designed packaging films |
| title_full_unstemmed | Random forest regressor for predicting sensory texture of emotional designed packaging films |
| title_short | Random forest regressor for predicting sensory texture of emotional designed packaging films |
| title_sort | random forest regressor for predicting sensory texture of emotional designed packaging films |
| topic | Surface texture Surface roughness Power spectral density (PSD) Machine learning Sensory panel test Partial least square regression (PLSR) |
| url | http://www.sciencedirect.com/science/article/pii/S259012302500235X |
| work_keys_str_mv | AT yongjulee randomforestregressorforpredictingsensorytextureofemotionaldesignedpackagingfilms AT minjungjoo randomforestregressorforpredictingsensorytextureofemotionaldesignedpackagingfilms AT hakyoungyu randomforestregressorforpredictingsensorytextureofemotionaldesignedpackagingfilms AT taijulee randomforestregressorforpredictingsensorytextureofemotionaldesignedpackagingfilms AT hyoungjinkim randomforestregressorforpredictingsensorytextureofemotionaldesignedpackagingfilms |