基于改进的条件相互信息最大化和SHAP分析预测玉米的原油含量
Haichao Zhou1, Xiaodan Ma1, Haiou Guan1
1College of Information and Electrical Engineering, Heilongjiang Bayi Agricultural University, Da Qing 163319, China.
Food chemistry
|August 28, 2025
概括
这项研究引入了一种新方法,它结合了有条件的相互信息最大化 (CMIM) 和SHAP,用于使用近红外光谱 (NIR) 准确地预测玉米中的原油脂肪. 这种方法增强了非线性依赖性分析,以改善农业质量检测.
科学领域:
- 农业科学
- 光谱学
- 化学测量
背景情况:
- 传统的条件相互信息最大化 (CMIM) 算法在连续近红外 (NIR) 光谱数据中的分析非线性依赖性方面存在局限性.
- 准确和快速预测作物质量参数,如玉米的原油含量,对于农业管理至关重要.
研究的目的:
- 开发一个新的框架,将改进的CMIM与SHAP (SHapley添加剂解释) 结合起来,以有效地预测玉米的原油含量.
- 克服传统CMIM在NIR光谱分析中处理非线性关系的局限性.
主要方法:
- 实施一个修改后的CMIM算法 (CMIM_KDE),使用连续变量估计而不是离散.
- 采用两阶段过器包装器特征选择策略.
- 与SHAP集成,以便对选定的光谱特征进行解释.
- 使用部分最小平方回归 (PLSR) 和支向量回归 (SVR) 模型进行验证.
主要成果:
- CMIM_KDE方法实现了高预测精度,其R2p值为0.7618 (PLSR) 和0.7531 (SVR).
- 与其他增强策略相比,其平均绩效提高了6.18%和4.42%.
- SHAP 分析确定了与玉米中 CH 组相关的关键波数 (约为 5684 cm-1 和 4312 cm-1),为预测机制提供了洞察力.
- 在外部数据集上验证了该方法的有效性和通用性.
结论:
- 拟议的CMIM_KDE-SHAP框架有效地解决了用于预测玉米原油脂肪含量的NIR光谱分析中的传统CMIM的局限性.
- 这种方法为农产品质量检测提供了可靠的解决方案,在遥感和实时监测方面具有潜在的应用.
相关概念视频
Prediction Intervals
2.3K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
2.3K
Fats as Energy Storage Molecules
25.6K
Triglycerides are a form of long-term energy storage molecules. They are made of glycerol and three fatty acids. To obtain energy from fat, triglycerides must first be broken down by hydrolysis into their two principal components, fatty acids and glycerol. This process, called lipolysis, takes place in the cytoplasm. The resulting fatty acids are oxidized by β-oxidation into acetyl-CoA, which is used by the Krebs cycle. The glycerol that is released from triglycerides after lipolysis...
25.6K
Light Acquisition
8.6K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
8.6K


