scholarly journals PREDIKSI MODEL PENETAPAN KADAR FLAVONOID TOTAL PADA EKSTRAK Abelmoschus manihot L. MENGGUNAKAN SPEKTROSKOPI IR YANG DIKOMBINASIKAN DENGAN KEMOMETRIK

PHARMACON ◽  
2019 ◽  
Vol 8 (2) ◽  
pp. 480
Author(s):  
Juliandro Fangohoy ◽  
Sri Sudewi ◽  
Adithya Yudistira
Keyword(s):  
Ir Spectroscopy ◽  
Standard Error ◽  
Partial Least Square ◽  
Least Square ◽  
Total Flavonoid ◽  
Partial Least Square Regression ◽  
Total Flavonoid Content ◽  
Flavonoid Content ◽  
Least Square Regression ◽  
Error Calibration

ABSTRACT This study aims to determine the validation of IR spectroscopy method in determining the total flavonoid level in Abelmoschus manihot L., can meet the requirements and can be applied. The method for determining the total flavonoid content model using a combination of IR Spectroscopy and Chemometrics Partial Least Square Regression (PLSR). The calorimetrics method was used to determine the total flavonoid content in the green gedi leaves axtracts onn eight samples of growth where Bitung Was 2.64 mg QE/g extract  ± 0.035, Minahasa Selatan is  1.91 mg QE/g extract ± 0.027, Kotamobagu is 4.84 mg QE/g extract  ± 0.03, Minahasa Utara is  4.40 mg QE/g extract ± 0.091, Manado is 3.45 mg QE/g extract  ± 0.012, Minahasa Tenggara is  1.72 mg QE/g extract ± 0.006, Minahasa is 3.67 mg QE/g extract ± 0.033, Tomohon is 3.40 mg QE/g extract ± 0.003. This combination is involves involving x-variables (FTIR measurement results) and y-variables (data from the results of the calorimetric method analysis). Error value [standard error calibration (SEC=0.003), standard error of prediction (SEP = 0.052)] and cslibration r value 0.999, and r validation 0.975. Keywords: Flavonoids, Green Gedi Leaves, FTIR Spectrofotometry, UV-VIS Spectrofotometry, Chemometrics ABSTRAK Penelitian ini bertujuan untuk mengetahui Validasi Metode Spektroskopi IR Pada Penetapan kadar Flavonoid Total   pada   Abelmoschus manihot L Dapat Memenuhi Persyaratan dan Dapat di Aplikasikan. Metode penentuan model  kandungan flavonoid total  menggunakan kombinasi Spektroskopi IR dan Kemometrik Partial Least Square Regression (PLSR). Metode Kalorimetrik digunakan untuk mengetahui kandungan Flavonoid Total pada pada Ekstra Daun Gedi Hijau pada 8 sampel tempat tumbuh yaitu Bitung sebesar 2.64 mg QE/g ekstrak  ± 0.035, Minahasa Selatan sebesar  1.91 mg QE/g ekstrak ± 0.027, Kotamobagu sebesar 4.84 mg QE/g ekstrak ± 0.03, Minahasa Utara sebesar  4.40 mg QE/g ekstrak ± 0.091, Manado sebesar 3.45 mg QE/g ekstrak  ± 0.012, Minahasa Tenggara sebesar  1.72 mg QE/g ekstrak ± 0.006, Minahasa sebesar 3.67 mg QE/g ekstrak ± 0.033, Tomohon sebesar 3.40 mg QE/g ekstrak ± 0.003. Kombinasi ini melibatkan melibatkan variabel x (hasil pengukuran FTIR) dan variabel y (data hasil analisis metode Kalorimetrik). Nilai kesalahan (standar error calibration (SEC = 0.003), standard error of prediction (SEP = 0.052)) dan nilai r kalibrasi 0.999, serta r validasi 0.975. Kata Kunci: Total Flavonoid, Daun Gedi Hijau, Spektrofotometri FTIR, Spektrofotometri UV-VIS,  Kemometrik.

scholarly journals Prediction Is The Determination Of The Levels Of Total Flavonoid Extract Of 70% Ethanol On The Leaves Of Rose Guava (Syzigium Jambos (L.) Alston) By Using A Combination Of FTIR And Chemometrics Plsr (Partial Least Square Regression)

2019 ◽  
Author(s):  
Nur Tsalits Fahman Mughni
Keyword(s):  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Partial Least Square ◽  
Least Square ◽  
Total Flavonoid ◽  
Partial Least Square Regression ◽  
Mean Square ◽  
Syzygium Jambos ◽  
Least Square Regression

Rose Guava (Syzygium jambos (L.) Alston) is known to have flavonoid compounds. Where flavonoids are natural product compounds that have uses as a treatment. An alternative method used to determine the prediction of total flavonoid levels is a combination of FTIR and Chemometrics (Partial least square regression) through the parameter RMSEC value (Root mean square error of calibration), RMSECV (Root mean square error of validation), PRESS (Predicted residual error sum of squares) and R2. The results of the combination of FTIR and CEMOMETRICS (Partial least square regression) on the prediction of total flavonoid levels can provide a good model with calibration obtained R2 value0.9999, RMSEC 0.0000637 and the results of vaid obtained PRESS value0.19225, R2 0.978 and RMSECV 0.041 . Based on the literature, the model can be said to be good if the RMSEC and RMSECV values are smaller than R2.

Modeling CO2 exchange and meteorological factors of an apple orchard using partial least square regression

2020 ◽  
Vol 27 (35) ◽  
pp. 43439-43451 ◽  
Author(s):  
Jianfeng Yang ◽  
Yumin Duan ◽  
Xiaoni Yang ◽  
Mukesh Kumar Awasthi ◽  
Huike Li ◽  
...  
Keyword(s):  
Meteorological Factors ◽  
Co2 Exchange ◽  
Apple Orchard ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Least Square Regression

QSPR MODELLING OF STABILITY CONSTANTS OF METAL-THIOSEMICARBAZONE COMPLEXES USING MULTIVARIATE REGRESSION METHODS AND ARTIFICIAL NEURAL NETWORK

2021 ◽  
Vol 36 (06) ◽  
Author(s):  
NGUYEN MINH QUANG ◽  
TRAN NGUYEN MINH AN ◽  
NGUYEN HOANG MINH ◽  
TRAN XUAN MAU ◽  
PHAM VAN TAT
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Stability Constants ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Structure Property ◽  
Least Square Regression ◽  
Thiosemicarbazone Complexes ◽  
Artificial Neural

In this study, the stability constants of metal-thiosemicarbazone complexes, logb11 were determined by using the quantitative structure property relationship (QSPR) models. The molecular descriptors, physicochemical and quantum descriptors of complexes were generated from molecular geometric structure and semi-empirical quantum calculation PM7 and PM7/sparkle. The QSPR models were built by using the ordinary least square regression (QSPROLS), partial least square regression (QSPRPLS), primary component regression (QSPRPCR) and artificial neural network (QSPRANN). The best linear model QSPROLS (with k of 9) involves descriptors C5, xp9, electric energy, cosmo volume, N4, SsssN, cosmo area, xp10 and core-core repulsion. The QSPRPLS, QSPR PCR and QSPRANN models were developed basing on 9 varibles of the QSPROLS model. The quality of the QSPR models were validated by the statistical values; The QSPROLS: R2train = 0.944, Q2LOO = 0.903 and MSE = 1.035; The QSPRPLS: R2train = 0.929, R2CV = 0.938 and MSE = 1.115; The QSPRPCR: R2train = 0.934, R2CV = 0.9485 and MSE = 1.147. The neural network model QSPRANN with architecture I(9)-HL(12)-O(1) was presented also with the statistical values: R2train = 0.9723, and R2CV = 0.9731. The QSPR models also were evaluated externally and got good performance results with those from the experimental literature.

scholarly journals Estimation of carcass weight of Hanwoo (Korean native cattle) as a function of body measurements using statistical models and a neural network

2020 ◽  
Vol 33 (10) ◽  
pp. 1633-1641
Author(s):  
Dae-Hyun Lee ◽  
Seung-Hyun Lee ◽  
Byoung-Kwan Cho ◽  
Collins Wakholi ◽  
Young-Wook Seo ◽  
...  
Keyword(s):  
Neural Network ◽  
Multiple Regression ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Carcass Weight ◽  
Body Measurements ◽  
Least Square Regression ◽  
Data Points ◽  
Hanwoo Cattle

Objective: The objective of this study was to develop a model for estimating the carcass weight of Hanwoo cattle as a function of body measurements using three different modeling approaches: i) multiple regression analysis, ii) partial least square regression analysis, and iii) a neural network.Methods: Data from a total of 134 Hanwoo cattle were obtained from the National Institute of Animal Science in South Korea. Among the 372 variables in the raw data, 20 variables related to carcass weight and body measurements were extracted to use in multiple regression, partial least square regression, and an artificial neural network to estimate the cold carcass weight of Hanwoo cattle by any of seven body measurements significantly related to carcass weight or by all 19 body measurement variables. For developing and training the model, 100 data points were used, whereas the 34 remaining data points were used to test the model estimation.Results: The R2 values from testing the developed models by multiple regression, partial least square regression, and an artificial neural network with seven significant variables were 0.91, 0.91, and 0.92, respectively, whereas all the methods exhibited similar R2 values of approximately 0.93 with all 19 body measurement variables. In addition, relative errors were within 4%, suggesting that the developed model was reliable in estimating Hanwoo cattle carcass weight. The neural network exhibited the highest accuracy.Conclusion: The developed model was applicable for estimating Hanwoo cattle carcass weight using body measurements. Because the procedure and required variables could differ according to the type of model, it was necessary to select the best model suitable for the system with which to calculate the model.

Ironmaking Process Parameter Analysis and Optimization for the Blast Furnace

2009 ◽  
Vol 620-622 ◽  
pp. 21-24
Author(s):  
Shuang Ping Yang ◽  
Yong Hui Song ◽  
Liu Hua Xin
Keyword(s):  
Optimal Operation ◽  
Partial Least Square ◽  
Least Square ◽  
Parameter Analysis ◽  
Partial Least Square Regression ◽  
Evaluation Indicator ◽  
Least Square Regression ◽  
Calculation Results ◽  
Set Up ◽  
Reasonable Description

With practical data of the BF ironmaking from Jiuquan Iron&Steel Cooperation Ltd. (JISC), taking the quality of pig iron as evaluation indicator, mathematical models based on the least square regression and partial least square regression were set up respectively by co-relation analysis of feeding-to-product interval of the BF processing. The calculation results showed that the reasonable description can be obtained by the partial least square regression model; and 10 of 29 parameters with obvious impact on the BF operation were listed accordingly. Meanwhile, an optimal group of parameters was found by genetic algorism calculation method. The optimal index of the group was 99.13％. This study is beneficial to the improvement of feeding adjustment and optimal operation of BF ironmaking.

Sign in / Sign up

Export Citation Format

Share Document