A Novel Approach to Pine Nut Classification: Combining Near-Infrared Spectroscopy and Image Shape Features with Soft Voting-Based Ensemble Learning
Pine nuts hold significant economic value due to their rich plant protein and healthy fats, yet precise variety classification has long been hindered by limitations of traditional techniques such as chemical analysis and machine vision. This study proposes a novel near-infrared (NIR) spectral featur...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/12/2009 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849432876894912512 |
|---|---|
| author | Yueyun Yu Xin Huang Danjv Lv Benjamin K. Ng Chan-Tong Lam |
| author_facet | Yueyun Yu Xin Huang Danjv Lv Benjamin K. Ng Chan-Tong Lam |
| author_sort | Yueyun Yu |
| collection | DOAJ |
| description | Pine nuts hold significant economic value due to their rich plant protein and healthy fats, yet precise variety classification has long been hindered by limitations of traditional techniques such as chemical analysis and machine vision. This study proposes a novel near-infrared (NIR) spectral feature selection algorithm, termed the improved binary equilibrium optimizer with selection probability (IBiEO-SP), which incorporates a dynamic probability adjustment mechanism to achieve efficient feature dimensionality reduction. Experimental validation on a dataset comprising seven pine nut varieties demonstrated that, compared to particle swarm optimization (PSO) and the genetic algorithm (GA), the IBiEO-SP algorithm improved average classification accuracy by 5.7% (<i>p</i> < 0.01, Student’s <i>t</i>-test) under four spectral preprocessing methods (MSC, SNV, SG1, and SG2). Remarkably, only 2–3 features were required to achieve optimal performance (MSC + random forest: 99.05% accuracy, 100% F1/precision; SNV + KNN: 97.14% accuracy, 100% F1/precision). Furthermore, a multimodal data synergy strategy integrating NIR spectroscopy with morphological features was proposed, and a classification model was constructed using a soft voting ensemble. The final classification accuracy reached 99.95%, representing a 2.9% improvement over single-spectral-mode analysis. The results indicate that the IBiEO-SP algorithm effectively balances feature discriminative power and model generalization needs, overcoming the contradiction between high-dimensional data redundancy and low-dimensional information loss. This work provides a high-precision, low-complexity solution for rapid quality detection of pine nuts, with broad implications for agricultural product inspection and food safety. |
| format | Article |
| id | doaj-art-9cff9c8136ca4151bc523636c43e3a5c |
| institution | Kabale University |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-9cff9c8136ca4151bc523636c43e3a5c2025-08-20T03:27:14ZengMDPI AGMathematics2227-73902025-06-011312200910.3390/math13122009A Novel Approach to Pine Nut Classification: Combining Near-Infrared Spectroscopy and Image Shape Features with Soft Voting-Based Ensemble LearningYueyun Yu0Xin Huang1Danjv Lv2Benjamin K. Ng3Chan-Tong Lam4Faculty of Applied Sciences, Macao Polytechnic University, Macao, ChinaCollege of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650224, ChinaCollege of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650224, ChinaFaculty of Applied Sciences, Macao Polytechnic University, Macao, ChinaFaculty of Applied Sciences, Macao Polytechnic University, Macao, ChinaPine nuts hold significant economic value due to their rich plant protein and healthy fats, yet precise variety classification has long been hindered by limitations of traditional techniques such as chemical analysis and machine vision. This study proposes a novel near-infrared (NIR) spectral feature selection algorithm, termed the improved binary equilibrium optimizer with selection probability (IBiEO-SP), which incorporates a dynamic probability adjustment mechanism to achieve efficient feature dimensionality reduction. Experimental validation on a dataset comprising seven pine nut varieties demonstrated that, compared to particle swarm optimization (PSO) and the genetic algorithm (GA), the IBiEO-SP algorithm improved average classification accuracy by 5.7% (<i>p</i> < 0.01, Student’s <i>t</i>-test) under four spectral preprocessing methods (MSC, SNV, SG1, and SG2). Remarkably, only 2–3 features were required to achieve optimal performance (MSC + random forest: 99.05% accuracy, 100% F1/precision; SNV + KNN: 97.14% accuracy, 100% F1/precision). Furthermore, a multimodal data synergy strategy integrating NIR spectroscopy with morphological features was proposed, and a classification model was constructed using a soft voting ensemble. The final classification accuracy reached 99.95%, representing a 2.9% improvement over single-spectral-mode analysis. The results indicate that the IBiEO-SP algorithm effectively balances feature discriminative power and model generalization needs, overcoming the contradiction between high-dimensional data redundancy and low-dimensional information loss. This work provides a high-precision, low-complexity solution for rapid quality detection of pine nuts, with broad implications for agricultural product inspection and food safety.https://www.mdpi.com/2227-7390/13/12/2009IBiEO-SPpine nutnear-infrared spectroscopyfeature selectionensemble learning |
| spellingShingle | Yueyun Yu Xin Huang Danjv Lv Benjamin K. Ng Chan-Tong Lam A Novel Approach to Pine Nut Classification: Combining Near-Infrared Spectroscopy and Image Shape Features with Soft Voting-Based Ensemble Learning Mathematics IBiEO-SP pine nut near-infrared spectroscopy feature selection ensemble learning |
| title | A Novel Approach to Pine Nut Classification: Combining Near-Infrared Spectroscopy and Image Shape Features with Soft Voting-Based Ensemble Learning |
| title_full | A Novel Approach to Pine Nut Classification: Combining Near-Infrared Spectroscopy and Image Shape Features with Soft Voting-Based Ensemble Learning |
| title_fullStr | A Novel Approach to Pine Nut Classification: Combining Near-Infrared Spectroscopy and Image Shape Features with Soft Voting-Based Ensemble Learning |
| title_full_unstemmed | A Novel Approach to Pine Nut Classification: Combining Near-Infrared Spectroscopy and Image Shape Features with Soft Voting-Based Ensemble Learning |
| title_short | A Novel Approach to Pine Nut Classification: Combining Near-Infrared Spectroscopy and Image Shape Features with Soft Voting-Based Ensemble Learning |
| title_sort | novel approach to pine nut classification combining near infrared spectroscopy and image shape features with soft voting based ensemble learning |
| topic | IBiEO-SP pine nut near-infrared spectroscopy feature selection ensemble learning |
| url | https://www.mdpi.com/2227-7390/13/12/2009 |
| work_keys_str_mv | AT yueyunyu anovelapproachtopinenutclassificationcombiningnearinfraredspectroscopyandimageshapefeatureswithsoftvotingbasedensemblelearning AT xinhuang anovelapproachtopinenutclassificationcombiningnearinfraredspectroscopyandimageshapefeatureswithsoftvotingbasedensemblelearning AT danjvlv anovelapproachtopinenutclassificationcombiningnearinfraredspectroscopyandimageshapefeatureswithsoftvotingbasedensemblelearning AT benjaminkng anovelapproachtopinenutclassificationcombiningnearinfraredspectroscopyandimageshapefeatureswithsoftvotingbasedensemblelearning AT chantonglam anovelapproachtopinenutclassificationcombiningnearinfraredspectroscopyandimageshapefeatureswithsoftvotingbasedensemblelearning AT yueyunyu novelapproachtopinenutclassificationcombiningnearinfraredspectroscopyandimageshapefeatureswithsoftvotingbasedensemblelearning AT xinhuang novelapproachtopinenutclassificationcombiningnearinfraredspectroscopyandimageshapefeatureswithsoftvotingbasedensemblelearning AT danjvlv novelapproachtopinenutclassificationcombiningnearinfraredspectroscopyandimageshapefeatureswithsoftvotingbasedensemblelearning AT benjaminkng novelapproachtopinenutclassificationcombiningnearinfraredspectroscopyandimageshapefeatureswithsoftvotingbasedensemblelearning AT chantonglam novelapproachtopinenutclassificationcombiningnearinfraredspectroscopyandimageshapefeatureswithsoftvotingbasedensemblelearning |