基于拉曼光谱的预测,使用一种新的损失函数和改进的GA-CNN模型来预测溶液中的奥洛辛度
Chenyu Ma1, Yuanbo Shi2, Yueyang Huang1
1School of Information and Control Engineering, Liaoning Petrochemical University, Fushun, 113001, China.
这项研究引入了一种新的内核-胡贝尔损失函数与遗传算法-卷积神经网络 (GA-CNN) 来准确预测从拉曼光谱数据的洛辛度. 这种新方法显著改进了化学分析的传统方法.
科学领域:
- 分析化学 分析化学
- 频谱学是一种光谱学.
- 机器学习 机器学习
背景情况:
- 拉曼光谱仪提供了快速而准确的洛辛度测量.
- 传统的手动分析拉曼光谱数据往往无法捕获非线性特征,限制了预测准确度.
- 由于数据的复杂性,现有的方法难以准确地预测度.
研究的目的:
- 开发一种先进的深度学习模型,使用拉曼光谱数据精确预测ofloxacin度.
- 克服拉曼光谱中手动数据分析的局限性.
- 为改进光谱数据建模引入一种新的内核-胡伯损失函数.
主要方法:
- 开发了一个新的内核-胡贝尔损失函数,将胡贝尔损失和高斯内核结合起来.
- 改进的遗传算法-卷积神经网络 (GA-CNN) 用于建模和预测.
- 进行比较的实验包括循环神经网络 (RNN),长期短期记忆 (LSTM),双向长期短期记忆 (BiLSTM) 和封闭循环单元 (GRU).
- 使用根平均平方误差 (RMSE) 和剩余预测偏差 (RPD) 评估性能.
主要成果:
- 拟议的GA-CNN方法在测试数据上实现了0.9989的确定系数 ([公式:参见文本]).
- 这种新方法比传统的卷积神经网络 (CNN) 有了3%的改进.
- 在预测洛克萨辛度方面,GA-CNN方法始终优于RNN,LSTM,BiLSTM和GRU模型.
结论:
- 开发的内核-胡贝尔损失函数与GA-CNN相结合,有效地预测了从拉曼光谱数据中的洛辛度.
- 这项研究为拉曼光谱度预测中的深度学习应用提供了强大的解决方案.
- 这些发现突显了先进机器学习技术在分析化学中的潜力.
更多相关视频
07:54Surface-enhanced Resonance Raman Scattering Nanoprobe Ratiometry for Detecting Microscopic Ovarian Cancer via Folate Receptor Targeting
Published on: March 25, 2019
10:25Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements
Published on: June 28, 2016
相关概念视频
Drug Concentration Versus Time Correlation
Two pivotal parameters are the minimum effective concentration (MEC) and the minimum toxic concentration (MTC). The MEC is the...
Analysis Methods of Pharmacokinetic Data: Model and Model-Independent Approaches
The model approach uses mathematical models to describe changes in drug concentration over time. Pharmacokinetic models help characterize drug behavior in patients, predict drug concentration in the body fluids, calculate optimum dosage regimens, and evaluate the risk of toxicity. However, ensuring that the model fits the experimental data accurately...
Predicting Molecular Geometry
Pharmacokinetic Models: Comparison and Selection Criterion
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
