Tan Ailing, Wang Yunxin, Zhao Yong, Wang Bolin, Li Xiaohang, Wang Alan X
School of Information and Science Engineering, Yanshan University, The Key Laboratory for Special Fiber and Fiber Sensor of Hebei Province, Qinhuangdao 066004, China.
School of Information and Science Engineering, Yanshan University, The Key Laboratory for Special Fiber and Fiber Sensor of Hebei Province, Qinhuangdao 066004, China.
Spectrochim Acta A Mol Biomol Spectrosc. 2022 Dec 15;283:121759. doi: 10.1016/j.saa.2022.121759. Epub 2022 Aug 13.
This study proposed a deep transfer learning methodology based on an improved Bi-directional Long Short-Term Memory (Bi-LSTM) network for the first time to address the near infrared spectroscopy (NIR) model transfer issue between samples. We tested its effectiveness on two datasets of manure and polyglutamic acid (γ-PGA) solution, respectively. First, the optimal primary Bi-LSTM networks for cattle manure and the first batch of γ-PGA were developed by ablation experiments and both proved to outperform one-dimensional convolutional neural network (1D-CNN), Partial Least Square (PLS) and Extreme Learning Machine (ELM) models. Then, two types of transfer learning approaches were carried out to determine model transferability to non-homologous samples. For poultry manure and the second batch of γ-PGA, the obtained predicting results verified that the second approach of fine-tuning Bi-LSTM layers and re-training FC layers transcended the first approach of fixing Bi-LSTM layers and only re-training FC layers by reducing the RMSEP of 23.4275% and 50.7343%, respectively. Finally, comparisons with fine-tuning 1D-CNN and other traditional model transfer methods further identified the superiority of the proposed methodology with exceeding accuracy and smaller variation, which decreased RMSEP of poultry manure and the second batch of γ-PGA of 7.2832% and 48.1256%, 67.1117% and 80.6924% when compared to that acquired by fine-tuning 1D-CNN, Tradaboost-ELM and CCA-PLS which were the best of five traditional methods, respectively. The study demonstrates the potential of the Fine-tuning-Bi-LSTM enabled NIR technology to be used as a simple, cost effective and reliable detection tool for a wide range of applications under various new scenarios.
本研究首次提出了一种基于改进的双向长短期记忆（Bi-LSTM）网络的深度迁移学习方法，以解决样本间近红外光谱（NIR）模型迁移问题。我们分别在两个数据集——牛粪和聚谷氨酸（γ-PGA）溶液上测试了其有效性。首先，通过消融实验开发了用于牛粪和第一批γ-PGA的最优初级Bi-LSTM网络，两者均证明优于一维卷积神经网络（1D-CNN）、偏最小二乘法（PLS）和极限学习机（ELM）模型。然后，进行了两种类型的迁移学习方法以确定模型对非同源样本的可迁移性。对于家禽粪便和第二批γ-PGA，获得的预测结果证实，微调Bi-LSTM层并重新训练全连接（FC）层的第二种方法超越了固定Bi-LSTM层并仅重新训练FC层的第一种方法，分别将均方根预测误差（RMSEP）降低了23.4275%和50.7343%。最后，与微调1D-CNN和其他传统模型迁移方法的比较进一步确定了所提出方法的优越性，其具有更高的准确性和更小的变异性，与通过微调1D-CNN、传统增强-极限学习机（Tradaboost-ELM）和典型相关分析-偏最小二乘法（CCA-PLS）（这是五种传统方法中表现最佳的）获得的结果相比，分别将家禽粪便和第二批γ-PGA的RMSEP降低了7.2832%和48.1256%、67.1117%和80.6924%。该研究证明了基于微调Bi-LSTM的近红外技术有潜力作为一种简单、经济高效且可靠的检测工具，用于各种新场景下的广泛应用。
