scholarly journals Prediksi Kadar Air Beras Menggunakan NIRS dengan Metode PLS dan Pretreatment Standard Normal Variate, Derivative-I, Savitzky Golay Smoothing

2019 ◽  
Vol 4 (1) ◽  
pp. 628-637
Author(s):  
Nurhasanah Nurhasanah ◽  
Kiman Siregar ◽  
Zulfahrizal Zulfahrizal
Keyword(s):  
Moisture Content ◽  
Least Squares ◽  
Water Content ◽  
Partial Least Squares ◽  
Correction Method ◽  
Standard Normal Variate ◽  
Standard Normal ◽  
Ft Ir ◽  
Rice Water ◽  
Pls Method

Abstrak. Kadar air merupakan suatu komponen penting dalam beras. Pengukuran kadar air dapat dilakukan menggunakan oven, alat elektronik seperti moisture tester, serta dengan penggunaan gelombang elektromagnetik seperti NIRS. Penelitian ini bertujuan menguji dan mengevaluasi teknologi NIRS sebagai metode cepat dan tepat dalam memprediksi kadar air beras dengan metode Partial Least Squares (PLS) serta menentukan metode koreksi spektrum yang terbaik dan akurat untuk memprediksi kadar air beras dengan menggunakan pretreatment Standard Normal Variate (SNV), Derivative- I (D-1)danSavitzky Golay Smoothing (SGS). Penelitian ini menggunakan Beras merk MB yang berasal dari pasar Rukoh Banda Aceh, yang berjumlah 20 sampel atau 300 gram. Perlakuan yang diberikan pada beras yaitu tanpa perendaman dan perendaman selama 5, 10, dan 15 menit. Prediksi kadar air beras dengan NIRS menggunakan alat self developed FT-IR IPTEK T-1516 dan metode referensi yang digunakan adalah metode gravimetri yang berdasarkan pada Association of Official Analytical Chemists (AOAC). Pengolahan data menggunakan Unscramble software® X version 10.5. Hasil penelitian menunjukkan prediksi kadar air beras dengan metode Partial Least Squares (PLS) menghasilkan good model performance dengan nilai RPD yang didapat yaitu 2,24 dan metode koreksi terbaik pada penelitian ini adalah Derivative-I dengan nilai RPD 2,57, r sebesar 0,9169, R2 sebesar 0,8407 dan RMSEC sebesar 1,6620.Prediction of Rice Moisture Content Using NIRS with PLS and Pretreatment Standard Normal Variate, Derivative-I, Savitsky Golay SmoothingAbstract. Moisture content is an important component of rice. Measurement of moisture content can be analyzed using an oven, electronic devices such as moisture tester, and by using the use of electromagnetic waves such as NIRS. This study aims to examine and evaluate NIRS technology as a faster and proper method in predicting rice moisture content by Partial Least Squares (PLS) method and determining the best and accurate spectrum correction method to predict rice water content using Standard Normal Variate (SNV) pretreatment, Derivative-I (D-1) and Savitzky Golay Smoothing (SGS). This study uses MB brand rice from the Rukoh market in Banda Aceh, with a total of 20 samples or 300 grams. The treatment given to rice is without soaking and soaking for 5, 10, and 15 minutes. Prediction of rice water content with NIRS using a self-developed FT-IR IPTEK T-1516 and the reference method used is a gravimetric method based on the Association of Official Analytical Chemists (AOAC). Data processing using Unscramble software® X version 10.5. The results showed the prediction of rice water content by the Partial Least Squares (PLS) method showed a good performance model with the RPD value obtained was 2.24 and the best correction method in this study was Derivative-I with an RPD value of 2.57, r of 0, 9169, R2 of 0.8407 and RMSEC of 1.6620.

scholarly journals Pendugaan Kadar Air Beras Ketan Putih Dengan Teknologi NIRS Menggunakan Metode Principal Component Regression (pretreatment De-Trending, Derivative-2, dan Standart Normal Variate)

2020 ◽  
Vol 4 (4) ◽  
pp. 502-511
Author(s):  
Mardiantono Mardiantono ◽  
Fachruddin Fachruddin ◽  
Zulfahrizal Zulfahrizal
Keyword(s):  
Water Content ◽  
Model Performance ◽  
Principal Component Regression ◽  
Principal Component ◽  
Standard Normal Variate ◽  
Glutinous Rice ◽  
Standard Normal ◽  
Ft Ir ◽  
Pcr Method ◽  
Rice Water

Abtrak. Kadar Air merupakan salah satu komponen penting dalam beras ketan putih yang dapat mempengaruhi kualitas dari beras ketan putih. Penelitian ini bertujuan menguji dan mengevaluasi teknologi NIRS sebagai metode cepat dan tepat dalam memprediksi kadar air beras ketan dengan metode Principal Component Regression (PCR) serta menentukan metode koreksi spektrum yang terbaik dan akurat untuk memprediksi kadar air beras ketan dengan menggunakan pretreatment De- Trending, Derivative-2, dan Standart Normal Variate (SNV). Penelitian ini menggunakan beras ketan putih yang didapat dari pasar Rukoh Banda Aceh, yang berjumlah 35 sampel. Perlakuan yang diberikan adalah tanpa perendaman, dibasahi, dan perendaman selama 5, 10, 15, 20, dan 25 menit. Prediksi kadar air beras ketan dengan NIRS menggunakan alat self developed FT-IR IPTEK T-1516 dan metode referensi yang digunakan adalah metode gravimetri yang berdasarkan pada Association of Official Analytical Chemists (AOAC). Pengolahan data menggunakan Unsclambers sofware® X version 10.5. Hasil penelitian menunjukkan bahwa NIRS dengan metode PCR mampu menghasilkan model yang baik untuk pendugaan beras ketan. Penelitian ini menghasilkan empat model pendugaan kadar air beras ketan dimana satu model tergolong very good performance (RPD3) dan tiga model tergolong good model performance (RPD2) sehingga dapat dikatakan bahwa semua model yang dihasilkan layak dan baik untuk pendugaan kadar air beras ketan. Pretreatment terbaik pada penelitian ini adalah Standart Normal Variate (SNV) dengan nilai RPD 3,12, r sebesar 0,95, R2 sebesar 0,89, dan RMSEC sebesar 2,34.Estimation of White Gluttony Rice Rate With NIRS Technology Using Principal Component Regression Method (Pretreatment De-Trending, Derivative-2, dan Standart Normal Variate)Abstract. Water content is one important component in white glutinous rice which can affect the quality of white glutinous rice. This study aims to test and evaluate NIRS technology as a fast and precise method for predicting glutinous rice water content with the Principal Component Regression (PCR) method and determine the best and accurate spectrum correction method for predicting glutinous rice water content using the De-Trending, Derivative pretreatment -2, and Standard Normal Variate (SNV). This study uses white sticky rice obtained from the Rukoh market in Banda Aceh, which amounted to 35 samples. The treatment given is without soaking, soaking, and soaking for 5, 10, 15, 20, and 25 minutes. The prediction of glutinous rice moisture content with NIRS uses a self-developed FT-IR IPTEK T-1516 tool and the reference method used is the gravimetric method based on the Association of Official Analytical Chemists (AOAC). Data processing using Unsclambers software X version 10.5. The results showed that NIRS with the PCR method was able to produce a good model for estimating glutinous rice. This study produced four models of estimation of glutinous rice water content where one model was classified as very good performance (RPD 3) and three models were classified as good model performance (RPD 2) so that it could be said that all the models produced were suitable and good for estimating rice water content sticky rice. The best pretreatment in this study is the Standard Normal Variate (SNV) with an RPD value of 3.12, r of 0.95, R2 of 0.89, and RMSEC of 2.34. 

scholarly journals Komparasi Metode Koreksi Spektrum NIRS (De-Trending dan Derivatif ke-2) untuk Penentuan Kadar Air Bubuk Biji kakao

2016 ◽  
Vol 1 (1) ◽  
pp. 1059-1068
Author(s):  
Masdar Masdar ◽  
Agus Arip Munawar ◽  
Zulfahrizal Zulfahrizal
Keyword(s):  
Least Squares ◽  
Water Content ◽  
Partial Least Squares ◽  
Near Infrared ◽  
Reflectance Spectroscopy ◽  
Second Derivative ◽  
Infrared Reflectance ◽  
Near Infrared Reflectance Spectroscopy ◽  
Near Infrared Reflectance ◽  
Ft Ir

Rendahnya pengawasan mutu kakao menyebabkan harga jual di pasar dunia menurun akibat kurangnya pengawasan kadar air. Salah satu metode yang tepat dan cepat dalam penentuan kadar air adalah menggunakan atau Near Infrared Reflectance Spectroscopy (NIRS). Tujuan penelitian adalah melihat kemampuan NIRS dalam memprediksi kadar air bubuk biji kakao dengan menggunakan metode Partial Least Squares (PLS) serta membandingkan dua metode pretreatment De-trending dan Derivatif ke-2.Alat yang digunakan FT-IR IPTEK T-1516, dan pengolahan data dengan unscrambler software® X version 10. Hasil penelitian menunjukkan NIRS mampu menduga kadar air dalam jumlah 10 gram dengan selang kadar air 7.42 – 11.09 % menggunakan PLS secara non pretreatment maupun pretreatment. Panjang gelombang relevan dalam menduga kadar air bubuk biji kakao adalah  1400-1450 nm dan 1800-1950 nm. Peningkatkan kinerja PLS yang paling bagus menggunakan pretreatment derivative ke-2.Abstract The lowest quality of cocoa supervision cause the selling price descrease due to the lack of supervision on the water content. One of the exact method in determining the water content is Near Infrared Reflectance Spectroscopy (NIRS). The purpose of this study is to know the capability of NIRS in order to predict the water content of cocoa by using Partial Least Squares (PLS) method then compared the two pretreatment methods namely De-trending and second Derivative. The instrument used was FT-IR IPTEK T-1516, and the spectra data were analyzed by using unscrambler software® X version 10. The results showed that NIRS can be used to predict the water content in amount 10 grams in a range of water content 7:42 to 11:09% by using PLS non pretreatment and vice versa. The relevantwavelengthsused to predict water content of cocoa powder ware1400-1450 nm and 1800-1950 nm. The optimum best pretreatment method was found to be second Derivative.

scholarly journals Determination of Total Flavonoids for Paris Polyphylla Var. Yunnanensis in Different Geographical Origins Using UV and FT-IR Spectroscopy

2019 ◽  
Vol 102 (2) ◽  
pp. 457-464
Author(s):  
Yuangui Yang ◽  
Yanli Zhao ◽  
Zhitian Zuo ◽  
Yuanzhong Wang
Keyword(s):  
Uv Spectrophotometry ◽  
Total Flavonoids ◽  
Least Squares Regression ◽  
Standard Normal Variate ◽  
Paris Polyphylla ◽  
Orthogonal Signal Correction ◽  
Relevant Variables ◽  
Standard Normal ◽  
Ft Ir

Abstract Background: Paris polyphylla var. Yunnanensis (PPY) is used in the clinical treatment of tumors, hemorrhages, and anthelmintic. Objective: The aim of this study is to determine total flavonoids of PPY in the Yunnan and Guizhou Provinces, China. Methods: In this study, total flavonoids were determined by UV spectrophotometry at first. Then, Fourier transform mid-infrared (FT-IR) based on various pretreatments include standard normal variate (SNV), first derivative (FD), second derivative (SD), Savitzky-Golay (SG), and orthogonal signal correction (OSC) were investigated. In addition, several relevant variables were screened by competitive adaptive reweighted sampling (CARS). The contentof total flavonoids and selected variables of FT-IRwere used to establish a partial least squares regression for PPY in different regions. Results: The results indicated that CARS was an effective method for decreasing the variable of thedatabase and improving the prediction of the model.FT-IR with pretreatment SNV + OSC + FD + SG had thebest performance, with R2 > 0.9 and residual predictive deviation = 3.3515, which could be used forthe predictive model of total flavonoids. Conclusions: Those results would provide a fast and robust strategy for the determination of total flavonoids of PPY in different geographical origin. Highlights: Various pretreatments, including SNV, FD, SD, SG, and OSC, were compared; several relevant variables were selected by CARS; and the content of total flavonoids and selected variable were used to establish a partial leastsquares regression for PPY in different regions.

A weighted ensemble method based on wavelength selection for near-infrared spectroscopic calibration

2019 ◽  
Vol 11 (36) ◽  
pp. 4593-4599
Author(s):  
Shaohui Yu ◽  
Jing Liu
Keyword(s):  
Least Squares ◽  
Partial Least Squares ◽  
Near Infrared ◽  
Ensemble Method ◽  
Wavelength Selection ◽  
Weighted Clustering ◽  
Infrared Spectroscopic ◽  
Selection For ◽  
Pls Method

A weighted clustering and pruning of wavelength variables-partial least squares (WCPV-PLS) method was proposed.

scholarly journals Automated Fitting Process Using Robust Reliable Weighted Average on Near Infrared Spectral Data Analysis

Symmetry ◽  
2020 ◽  
Vol 12 (12) ◽  
pp. 2099
Author(s):  
Divo Dharma Silalahi ◽  
Habshah Midi ◽  
Jayanthi Arasan ◽  
Mohd Shafie Mustafa ◽  
Jean-Pierre Caliman
Keyword(s):  
Least Squares ◽  
Spectral Data ◽  
Partial Least Squares ◽  
Near Infrared ◽  
Weighted Average ◽  
Optimal Number ◽  
Optimum Number ◽  
Plsr Model ◽  
Pls Method ◽  
Selection Of

With the complexity of Near Infrared (NIR) spectral data, the selection of the optimal number of Partial Least Squares (PLS) components in the fitted Partial Least Squares Regression (PLSR) model is very important. Selecting a small number of PLS components leads to under fitting, whereas selecting a large number of PLS components results in over fitting. Several methods exist in the selection procedure, and each yields a different result. However, so far no one has been able to determine the more superior method. In addition, the current methods are susceptible to the presence of outliers and High Leverage Points (HLP) in a dataset. In this study, a new automated fitting process method on PLSR model is introduced. The method is called the Robust Reliable Weighted Average—PLS (RRWA-PLS), and it is less sensitive to the optimum number of PLS components. The RRWA-PLS uses the weighted average strategy from multiple PLSR models generated by the different complexities of the PLS components. The method assigns robust procedures in the weighing schemes as an improvement to the existing Weighted Average—PLS (WA-PLS) method. The weighing schemes in the proposed method are resistant to outliers and HLP and thus, preserve the contribution of the most relevant variables in the fitted model. The evaluation was done by utilizing artificial data with the Monte Carlo simulation and NIR spectral data of oil palm (Elaeis guineensis Jacq.) fruit mesocarp. Based on the results, the method claims to have shown its superiority in the improvement of the weight and variable selection procedures in the WA-PLS. It is also resistant to the influence of outliers and HLP in the dataset. The RRWA-PLS method provides a promising robust solution for the automated fitting process in the PLSR model as unlike the classical PLS, it does not require the selection of an optimal number of PLS components.

Multivariate Analysis of Attenuated Total Reflection—Fourier Transform Infrared Spectroscopic Data to Confirm the Origin of Honeys

2008 ◽  
Vol 62 (10) ◽  
pp. 1115-1123 ◽  
Author(s):  
Siobhán Hennessy ◽  
Gerard Downey ◽  
Colm O'Donnell
Keyword(s):  
Fourier Transform ◽  
Discriminant Analysis ◽  
Fourier Transform Infrared ◽  
Total Reflection ◽  
Attenuated Total Reflection ◽  
Correct Classification ◽  
Standard Normal Variate ◽  
Standard Normal ◽  
Ft Ir ◽  
Solids Content

Fourier transform infrared (FT-IR) spectroscopy and chemometrics were used to verify the origin of honey samples ( n = 150) from Europe and South America. Authentic honey samples were collected from five sources, namely unfiltered samples from Mexico in 2004, commercially filtered samples from Ireland and Argentina in 2004, commercially filtered samples from the Czech Republic in 2005 and 2006, and commercially filtered samples from Hungary in 2006. Samples were diluted with distilled water to a standard solids content (70° Brix) and their spectra (2500–12 500 nm) recorded at room temperature using an FT-IR spectrometer equipped with a germanium attenuated total reflection (ATR) accessory. First- and second-derivative and standard normal variate (SNV) data pretreatments were applied to the recorded spectra, which were analyzed using partial least squares (PLS) regression analysis, factorial discriminant analysis (FDA), and soft independent modeling of class analogy (SIMCA). In general, when an attenuated wavelength range (6800–11 500 nm) rather than the whole spectrum (2500–12 500 nm) was studied, higher correct classification rates were achieved. An overall correct classification of 93.3% was obtained for honeys by PLS discriminant analysis, while FDA techniques correctly classified 94.7% of honey samples. Correct classifications of up to 100% were achieved using SIMCA, but models describing some classes had very high false positive rates.

Sign in / Sign up

Export Citation Format

Share Document