頁籤選單縮合
題 名 | 果汁糖度檢測模式之研究=The Study on Prediction Models for Determination of Sugar Content in Fruit Juice |
---|---|
作 者 | 陳世銘; 張文宏; 謝廣文; | 書刊名 | 農業機械學刊 |
卷 期 | 7:3 1998.09[民87.09] |
頁 次 | 頁41-60 |
分類號 | 463.843 |
關鍵詞 | 糖度; 檢測模式; 近紅外線光譜; 水蜜桃果汁; Sugar content; Prediction models; NIR spectroscopy; Peach juice; |
語 文 | 中文(Chinese) |
中文摘要 | 本研究應用多重線性迴歸(MultipleLine Linear Regression,MLR、部份最小平方 迴歸 (Partial Least Square Regression, PLSR) 及類神經網路 (Artificial Neural Network, ANN) 三種不同檢測模式來探討不同光譜處理(原始光譜、一次微分光譜,二次微 分光譜)之近紅外線光譜對果汁糖度檢測的影響。 以 196 個水蜜桃果汁樣本作為各模式之 分析與驗証的範例,近紅外線光譜量測範圍為 1000 ∼ 2500nm。在 MLR 模式中,三種光譜 處理對糖度檢測的影響, 以二次微分光譜所得的結果最好, 原始光譜所得到的結果最差。 MLR 模式之最大優點在於應用少數相關波長之線性組合即可作為糖度之檢測,在二次微分光 譜中 2273、 1689 及 2080nm 所組成約三波長校正方程式, 有最佳的預測結果 (r �d�� =0.974,SEP=0.271,bias=-0.0343)。 PLSR 模式乃是將整段波長範圍內每個光譜均納入計算 ,因此在原始光譜及一次微分光譜之校正與預測的結果均較 MLR 之結果有明顯改善。 但是 由於運算較為複雜,所以應用時最好擷取有效波長範圍作為輸入; 其中原始光譜在部份波長 範圍 (2050 ∼ 2350nm) 的預測結果最好 (r �d�� =0.987, SEP=0.192, bias=-0.004)。 ANN 模式之應用,乃是以非線性的關係來描述光譜形狀與糖度的關係,對三種光譜處理的差 異性並不明顯, 一次微分光譜在 2050 ∼ 2350nm 有極佳的預測結果 (r �d�� =0.986,SEP=0.201,bias= -0.003),但是在實際應用時因為原始光譜可以有效地簡化光譜處 理的步驟,而且仍檢測準確,具有較高的應用價值。 |
英文摘要 | Three kinds of models including Multiple Linear Regression (MLR), Partial Least Square Regression (PLSR), and Artificial Neural Network (ANN ) were evaluated for the determination of sugar content in peach juice. Three different kinds of mathematical treatments ( original, first derivative and second derivative) of spectra in the range of 1000∼2500 nm were discussed. There were 196 peach juice samples used for analysis in this study. In MLR analysis, the second derivative spectra showed the best results in both calibration and prediction while the original spectra were the worst. The linear combination of effective wavelengths in second derivative mode could prove very good in predictions, the triple-wavelength calibration equation consisted of 2273, 1689 and 2080 nm had a high coefficient of determination (0.974) and low SEP (0.271). All the wavelengths in the specified range were included in PLSR analysis, which made the model complex. Therefore, it was necessary to investigate the most effective wavelength@ range as an input to PLSR. The performance of the original spectra and the first derivative of spectral data was improved compared to those in MLR analysis. The original spectra achieved the best result (r�d��=0.987, SEP=0.192, bias=-0.004) if the range of 2050∼2350 nm was used as an input to PLSR. The ANN model established the nonlinear relationship between the spectrum and the sugar content. The difference in the performance of mathematical treatments of tlie spectra was little when using ANN analysis. The first derivative of the spectral data in the range of 2050∼2350 nm gave the best prediction result (r�d�� =0.986, SEP=0.201, bias=-0.003), however, the original spectra, which required no derivative transformation, yielded a comparable result. The ANN model with the original spectra was suggested for applications due to its simplicity and accuracy. |
本系統中英文摘要資訊取自各篇刊載內容。