用高光谱成像与机器学习区分蜂蜜植物来源，准确率达95.13%
Honey Classification using Hyperspectral Imaging and Machine Learning
- 通过类别变换增强不同蜂蜜类别的可分性
- 结合LDA降维与SVM/KNN分类，最高准确率达95.13%
- 适合食品溯源、智能质检等实际应用场景
本文提出一种基于机器学习的自动蜂蜜植物来源分类方法。该方法包含数据集准备、特征提取和分类三个阶段。在数据集准备阶段采用类别变换方法以最大化类间可分性；特征提取阶段使用线性判别分析（LDA）提取相关特征并降低维度；分类阶段采用支持向量机（SVM）与K近邻（KNN）模型对蜂蜜样本特征进行分类。在标准蜂蜜高光谱成像（HSI）数据集上评估系统性能，实验结果表明，该系统在基于高光谱图像的分类任务中达到95.13%的最高准确率，在基于高光谱实例的分类任务中达到92.80%的准确率，优于现有方法。
原文摘要 · Abstract (English)
In this paper, we propose a machine learning-based method for automatically classifying honey botanical origins. Dataset preparation, feature extraction, and classification are the three main steps of the proposed method. We use a class transformation method in the dataset preparation phase to maximize the separability across classes. The feature extraction phase employs the Linear Discriminant Analysis (LDA) technique for extracting relevant features and reducing the number of dimensions. In the classification phase, we use Support Vector Machines (SVM) and K-Nearest Neighbors (KNN) models to classify the extracted features of honey samples into their botanical origins. We evaluate our system using a standard honey hyperspectral imaging (HSI) dataset. Experimental findings demonstrate that the proposed system produces state-of-the-art results on this dataset, achieving the highest classification accuracy of 95.13% for hyperspectral image-based classification and 92.80% for hyperspectral instance-based classification.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。