Abstract To improve the production efficiency in the pulp and paper industry, the chemical composition of pulp wood species has to be measured in real-time, especially the holocellulose and acid insoluble lignin contents. Near infrared (NIR) spectroscopy, as a promising rapid and on-line technology, is an attractive and promising tool to determine holocellulose and lignin contents in pulp wood. Due to the high complexity and nonlinearity of the spectra of pulp wood, it is significant to select suitable chemometric methods. In this study, in order to eliminate noise and irrelevant information of the original spectra collected by a portable spectrometer, four methods were used to preprocess the original spectra, including the first derivative, moving average filtering, multiplicative scatter correction and standard normal variate transformation. Next a comparison was conducted using four modeling approaches, including partial least squares (PLS) regression, least square support vector machine (LSSVM), back-propagation neural network (BPNN), and kernel extreme learning machine (KELM). The last three approaches were calibrated using spectral features that reduced the dimensions by principal component analysis (PCA). Furthermore, regularization parameter and kernel function parameter of LSSVM and KELM were optimized by a particle swarm optimization (PSO) algorithm. The results indicated that multiplicative scatter correction efficiently eliminated the spectral noise and irrelative information, and that KELM displayed the best prediction performance compared to the other approaches. Therefore, an inexpensive and portable NIR spectrometer has been employed to accurately and efficiently determine the chemical composition of pulp wood when combined with multiplicative scatter correction and the KELM method.

中文翻译：

---

近红外光谱和内核极限学习机快速测定木材中的全纤维素和木质素

摘要 为了提高制浆造纸行业的生产效率，必须实时测量制浆木材的化学成分，尤其是全纤维素和酸不溶性木质素含量。近红外 (NIR) 光谱作为一种有前途的快速在线技术，是一种有吸引力且有前途的工具，可用于确定纸浆木材中的全纤维素和木质素含量。由于纸浆木材光谱的高度复杂性和非线性，选择合适的化学计量方法具有重要意义。本研究为了消除便携式光谱仪采集到的原始光谱的噪声和无关信息，采用一阶导数、移动平均滤波、乘法散射校正和标准正态变量变换四种方法对原始光谱进行预处理。接下来使用四种建模方法进行比较，包括偏最小二乘 (PLS) 回归、最小二乘支持向量机 (LSSVM)、反向传播神经网络 (BPNN) 和核极限学习机 (KELM)。最后三种方法使用光谱特征进行校准，通过主成分分析 (PCA) 减少维度。此外，LSSVM和KELM的正则化参数和核函数参数通过粒子群优化（PSO）算法进行了优化。结果表明，乘法散射校正有效地消除了光谱噪声和无关信息，并且与其他方法相比，KELM 显示出最佳的预测性能。所以，