摘要
机器人与机器学习的新闻编辑每日新闻-机器学习的新研究是一篇报道的主题。根据NewsRx编辑在印度果阿的新闻报道，研究表明，“牛奶掺假是一个全球性的重大问题，因为它是消费最广泛和必不可少的食品。因此，监测牛奶质量对于维持人类健康是必要的。”我们的新闻记者引用了果阿大学的研究，建立了基于机器学习(ML)的近红外(NIR)光谱无损检测系统,将牛奶中不同比例(0～40%)的水混合,建立数据库,利用紧凑型TI DLP近红外扫描纳米光谱技术在900～1700nm范围内捕获光谱,采集光谱用Savitzky-Golay(SG)滤波器进行预处理。乘性散射校正(MSC)和标准正态变量(SNV)方法。利用Wa velength/Feature Selection技术选择信息最丰富的波长点，并利用主成分分析(PCA)对这些波长的维数进行降维。利用多种ML模型预测牛奶中的水分浓度。采用分类和回归方法检验系统的性能。在回归分析中，在分类时，K近邻(KNN)获得了最佳的R 2，均方根误差(RMSE)，预测标准误差(SEP)，平均绝对误差(MAE)，对偏差(RPD)的性能Ra，剔除交叉验证(LOOCV)-R 2，LOOCV-RMSE分别为0.999，0.399 mL(%v/v)，0.096 mL(%v/v)，0.227 mL(%v/v)，33.005，0.999随机森林(RF)AC的准确率为100%，马太相关系数为(MCC)。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news reporting out of Goa, India, by NewsRx editors, research stated, “Milk adulteration is a significant problem globally, as it is the most widely consumed and essential food product. Due to this, monit oring milk quality is necessary for sustaining human health.” Our news journalists obtained a quote from the research from Goa University, “A Machine Learning (ML) based non-destructive system was developed to identify wat er adulteration in milk using Near Infrared (NIR) Spectroscopy. A database was c reated by mixing water in milk in varying proportions (0 - 40 %) an d capturing spectra using compact TI DLP NIR scan Nano spectroscopy in the 900 - 1700 nm range. The captured spectra were preprocessed with the Savitzky-Golay ( SG) filter, Multiplicative Scatter Correction (MSC), and Standard Normal Variate (SNV) method. The most informative wavelength points were selected using the wa velength/feature selection technique, and the dimensions of these wavelengths we re reduced using Principal Component Analysis (PCA). Various ML models were empl oyed to predict the water concentration in milk. Both classification and regress ion methods were applied to check the system ‘ s performance. In the regression analysis, the k-Nearest Neighbour (KNN) achieved the best R 2 , Root Mean Square Error (RMSE), Standard Error of Prediction (SEP), Mean Absolute Error (MAE), Ra tio of Performance to Deviation (RPD), Leave One Out Cross-Validation (LOOCV)-R 2 , and LOOCV-RMSE of 0.999, 0.399 mL ( % v/v), 0.096 mL ( % v/v), 0.227 mL ( % v/v), 33.005, 0.999, and 0.353 mL ( % v/v), respectively, while for classification analysis, the Random Forest (RF) ac hieved 100 % accuracy and Matthew ‘ s Correlation Coefficient (MCC ).”
NETL
NSTL