机器学习和深度学习算法的比较分析,用于使用NIRS评估农产品质量
Jiwen Ren1, Yuming Xiong1, Xinyu Chen2
1School of Mechatronics and Vehicle Engineering, East China Jiaotong University, Nanchang 330013, China.
Sensors (Basel, Switzerland)
|August 29, 2024
概括
与浅层学习 (SL) 相比,深度学习 (DL) 模型显著提高了近红外光谱 (NIRS) 分析准确性. 一个新的格拉米安角差场和卷积神经网络 (G-CACNN) 模型证明了NIRS应用的卓越稳定性和耐噪性能.
科学领域:
- 分析化学 分析化学
- 化学测量 化学测量 化学测量
- 频谱学是一种光谱学.
背景情况:
- 近红外光谱 (NIRS) 分析的成功取决于精确的校准模型.
- 浅层学习 (SL) 算法与光谱数据复杂性和噪声作斗争,限制了NIRS应用程序.
- 深度学习 (DL) 提供了从有限的光谱样本中改进特征提取的潜力.
研究的目的:
- 评估NIRS校准模型的稳定性和有效性.
- 为了比较SL,共识学习 (CL) 和DL方法的性能.
- 提出和验证一个新的G-CACNN模型用于NIRS歧视性分析.
主要方法:
- 利用小麦核和Yali梨数据集的歧视性分析.
- 与DL和CL模型进行了部分最小平方差分分析 (PLS-DA) 的比较.
- 开发了格拉米安角差场和协调注意力卷积神经网络 (G-CACNN) 模型.
主要成果:
- DL和CL模型对光谱预处理的敏感性低于SL.
- 提出的G-CACNN模型在分辨任务中实现了高精度 (98.48%和99.39%).
- 与其他车型相比,G-CACNN表现出优越的坚固性和抗噪能力.
结论:
- 深度学习显著提高了NIRS分析的准确性和稳定性.
- G-CACNN模型为NIRS应用提供了一种强大且耐噪的方法.
- 这项研究推动了NIRS校准模型的开发,使其具有更广泛的适用性.
相关概念视频
02:35Key Elements for Plant Nutrition
18.7K
Like all living organisms, plants require organic and inorganic nutrients to survive, reproduce, grow and maintain homeostasis. To identify nutrients that are essential for plant functioning, researchers have leveraged a technique called hydroponics. In hydroponic culture systems, plants are grown—without soil—in water-based solutions containing nutrients. At least 17 nutrients have been identified as essential elements required by plants. Plants acquire these elements from the...
18.7K
02:16Light Acquisition
8.4K
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.
8.4K