東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Development and Comparison of Machine Learning Models for Predicting Fatty Acid Classes in Snacks and Authenticating Oils and Margarine.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Development and Comparison of Machine Learning Models for Predicting Fatty Acid Classes in Snacks and Authenticating Oils and Margarine./
作者:	Tachie, Christabel Yeboah Edna.
面頁冊數:	1 online resource (100 pages)
附註:	Source: Masters Abstracts International, Volume: 84-11.
Contained By:	Masters Abstracts International84-11.
標題:	Food science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30420261click for full text (PQDT)
ISBN:	9798379589653

Development and Comparison of Machine Learning Models for Predicting Fatty Acid Classes in Snacks and Authenticating Oils and Margarine.
Tachie, Christabel Yeboah Edna.

Development and Comparison of Machine Learning Models for Predicting Fatty Acid Classes in Snacks and Authenticating Oils and Margarine. - 1 online resource (100 pages)

Source: Masters Abstracts International, Volume: 84-11.

Thesis (M.S.)--Delaware State University, 2023.

Includes bibliographical references

Advancement in food science research, the sophistication of current instruments, complexity, and dimension of data has driven the need for the incorporation of machine learning (ML) techniques, a subset of data science in data analysis. The study described herein aimed at exploring the application of ML techniques in food science research to minimize the need for tedious experiments, authenticate food and for rapid data analysis. In the first case study, NHANES data (2017 to 2018) and support vector machine (SVM), artificial neural network (ANN) K-nearest number, (KNN), random forest (RF) decision tree (DT) LightGBM was used to predict fatty acid classes in popular US snacks. DT (7.35 to 8.39) and SVM (9 to 21.02) recorded the highest mean squared error in models one and two, respectively while KNN (0.23 to 0.50) and RF (0.06 to 0.089) had the least scores in predicting all fatty acid classes. The second case study involved the use of Fourier transform infrared (FTIR) and ML algorithms to classify three pure oil (palm kernel, njangsa seed and coconut oils) types and two formulated margarines (njangsa seed-palm kernel oil and njangsa seed coconut oil margarines) to quantify and predict adulterant concentrations in all the samples. The spectra data (4000 - 600 cm-1) were combined with SVR, KNN, RF, DT, LightGBM regressors for oil and margarine authentication whiles SVM, KNN, RF, DT, Light GBM and LR classifiers were used for pure samples. All models for pure oil classification had 100% accuracy while KNN scored the highest for margarine classification. KNN and XGBoost regressors recorded the highest coefficient of determination (R2) in both oil and margarine samples while the LightGBM, DT and logistic regression (LR) had the least for quantitative analysis. This study identified an efficient method for the quick determination of fatty acid classes in popular snacks that facilitates data collation and analysis. The FTIR-ML method proved to be a rapid technique for oil and margarine authentication.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798379589653Subjects--Topical Terms:

3173303
Food science.
Subjects--Index Terms:

AuthenticationIndex Terms--Genre/Form:

542853
Electronic books.

Development and Comparison of Machine Learning Models for Predicting Fatty Acid Classes in Snacks and Authenticating Oils and Margarine.
LDR:03492nmm a2200421K 4500 001 2363185
005 20231116093818.5
006 m o d
007 cr mn ---uuuuu
008 241011s2023 xx obm 000 0 eng d
020 $a 9798379589653
035 $a (MiAaPQ)AAI30420261
035 $a AAI30420261
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Tachie, Christabel Yeboah Edna. $3 3703935
245 1 0 $a Development and Comparison of Machine Learning Models for Predicting Fatty Acid Classes in Snacks and Authenticating Oils and Margarine.
264 0 $c 2023
300 $a 1 online resource (100 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 84-11.
500 $a Advisor: Aryee, Alberta N.A.
502 $a Thesis (M.S.)--Delaware State University, 2023.
504 $a Includes bibliographical references
520 $a Advancement in food science research, the sophistication of current instruments, complexity, and dimension of data has driven the need for the incorporation of machine learning (ML) techniques, a subset of data science in data analysis. The study described herein aimed at exploring the application of ML techniques in food science research to minimize the need for tedious experiments, authenticate food and for rapid data analysis. In the first case study, NHANES data (2017 to 2018) and support vector machine (SVM), artificial neural network (ANN) K-nearest number, (KNN), random forest (RF) decision tree (DT) LightGBM was used to predict fatty acid classes in popular US snacks. DT (7.35 to 8.39) and SVM (9 to 21.02) recorded the highest mean squared error in models one and two, respectively while KNN (0.23 to 0.50) and RF (0.06 to 0.089) had the least scores in predicting all fatty acid classes. The second case study involved the use of Fourier transform infrared (FTIR) and ML algorithms to classify three pure oil (palm kernel, njangsa seed and coconut oils) types and two formulated margarines (njangsa seed-palm kernel oil and njangsa seed coconut oil margarines) to quantify and predict adulterant concentrations in all the samples. The spectra data (4000 - 600 cm-1) were combined with SVR, KNN, RF, DT, LightGBM regressors for oil and margarine authentication whiles SVM, KNN, RF, DT, Light GBM and LR classifiers were used for pure samples. All models for pure oil classification had 100% accuracy while KNN scored the highest for margarine classification. KNN and XGBoost regressors recorded the highest coefficient of determination (R2) in both oil and margarine samples while the LightGBM, DT and logistic regression (LR) had the least for quantitative analysis. This study identified an efficient method for the quick determination of fatty acid classes in popular snacks that facilitates data collation and analysis. The FTIR-ML method proved to be a rapid technique for oil and margarine authentication.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Food science. $3 3173303
650 4 $a Computer science. $3 523869
653 $a Authentication
653 $a Chemometrics
653 $a Fatty acid classes
653 $a FTIR
653 $a Machine learning
653 $a NHANES data
653 $a XGBoost regressors
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0359
690 $a 0984
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a Delaware State University. $b Food Science and Biotechnology. $3 3346653
773 0 $t Masters Abstracts International $g 84-11.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30420261 $z click for full text (PQDT)