A Robust Identification Model for Herbal Medicine Using Near Infrared Spectroscopy and Artificial Neural Network

應用近紅外光光譜與類神經網路於中草藥鑑別模式之建立

楊翕雯(Ci-Wen Yang) ； 陳世銘(Su-Ming Chen) ； 歐陽孚(Fu Ouyang) ； 楊宜璋(I-Chang Yang) ； 蔡兆胤(Chao-Yin Tsai)

《藥物食品分析》 19卷1期 (2011/03) Pp. 9-17

摘要

藥品的鑑別在中草藥製藥與用藥過程非常關鍵，由於藥用植物來源非常廣泛，就算不是近源種，其外觀也可能相似。本研究應用近紅外及類神經網路技術建立中草藥鑑別模式以區分不同藥材原料，尤其是無法由其外觀以肉眼判斷之藥材。以傳統的化學分析方法作藥材的鑑別成本與效率都有改善的空間。近紅外光檢測技術(near infrared spectroscopy)與現行其他科學檢測方法相比，具有非破壞性、量測快速等優點，本研究所建立之模式，是以類神經網路(artificial neural network)分析中草藥的近紅外光吸收光譜，已成功建立可有效區分30種藥品的中草藥粉末鑑別模式，以最佳模式鑑別具有600個樣本的校正組，其正確率爲99.67%，鑑別含300個樣本的預測組則可達到100%。

關鍵字

近紅外光 ； 類神經網路 ； 中草藥

並列摘要

A robust identification model for herbal medicine was developed by combining near-infrared spectroscopy (NIR) and artificial neural network (ANN) to discriminate raw materials of herbal medicine, which are often similar in appearance and practically impossible to identify by visual inspection alone. The identification by chemical methods is usually higher in cost and lower in efficiency. Compared with other modern inspection methods, NIR is an alternative, which is non-destructive, rapid, and easy to operate. In this study, we employed ANN to analyze the absorption spectra of herbal medicines and successfully built an identification model, which is able to identify 30 different herbal medicines. The best identification model can reach a correct identification rate (CIR) of 99.67% when applied to a training set of 600 samples, and 100% CIR when applied to a test set of 300 samples.

並列關鍵字

near infrared NIR spectroscopy ； artificial neural network ANN ； herbal medicine