Predicting Biodiesel Properties and its Optimal Fatty Acid Profile Via Explainable Machine Learning

2021 ◽  
Author(s):  
Manu Suvarna ◽  
Mohammad Islam Jahirul ◽  
Wai Hung Aaron-Yeap ◽  
Cheryl Valencia Augustine ◽  
Anushri Umesh ◽  
...  
Keyword(s):  
Machine Learning ◽  
Fatty Acid ◽  
Fatty Acid Profile ◽  
Biodiesel Properties

scholarly journals Pattern recognition based on machine learning identifies oil adulteration and edible oil mixtures

2020 ◽  
Vol 11 (1) ◽  
Author(s):  
Kevin Lim ◽  
Kun Pan ◽  
Zhe Yu ◽  
Rong Hui Xiao
Keyword(s):  
Machine Learning ◽  
Fatty Acid ◽  
Fatty Acid Profile ◽  
Edible Oils ◽  
Edible Oil ◽  
Learning Method ◽  
Fair Price ◽  
Plant Oil ◽  
Oil Mixtures ◽  
Oil Type

Abstract Previous studies have shown that each edible oil type has its own characteristic fatty acid profile; however, no method has yet been described allowing the identification of oil types simply based on this characteristic. Moreover, the fatty acid profile of a specific oil type can be mimicked by a mixture of 2 or more oil types. This has led to fraudulent oil adulteration and intentional mislabeling of edible oils threatening food safety and endangering public health. Here, we present a machine learning method to uncover fatty acid patterns discriminative for ten different plant oil types and their intra-variability. We also describe a supervised end-to-end learning method that can be generalized to oil composition of any given mixtures. Trained on a large number of simulated oil mixtures, independent test dataset validation demonstrates that the model has a 50th percentile absolute error between 1.4–1.8% and a 90th percentile error of 4–5.4% for any 3-way mixtures of the ten oil types. The deep learning model can also be further refined with on-line training. Because oil-producing plants have diverse geographical origins and hence slightly varying fatty acid profiles, an online-training method provides also a way to capture useful knowledge presently unavailable. Our method allows the ability to control product quality, determining the fair price of purchased oils and in-turn allowing health-conscious consumers the future of accurate labeling.

scholarly journals Fatty Acid Profile as an Indicator of Larval Host for Adult Drosophila suzukii

Insects ◽  
2020 ◽  
Vol 11 (11) ◽  
pp. 752
Author(s):  
Nik G. Wiman ◽  
Heather Andrews ◽  
Erica Rudolph ◽  
Jana Lee ◽  
Man-Yeon Choi
Keyword(s):  
Machine Learning ◽  
Fatty Acids ◽  
Fatty Acid ◽  
Fatty Acid Profile ◽  
Learning Algorithm ◽  
Movement Patterns ◽  
Machine Learning Algorithm ◽  
Fruit Crops ◽  
Drosophila Suzukii ◽  
Larval Host

Drosophila suzukii is a severe economic invasive pest of soft-skinned fruit crops. Management typically requires killing gravid adult female flies with insecticides to prevent damage resulting from oviposition and larval development. Fruits from cultivated and uncultivated host plants are used by the flies for reproduction at different times of the year, and knowledge of D. suzukii seasonal host plant use and movement patterns could be better exploited to protect vulnerable crops. Rearing and various marking methodologies for tracking movement patterns of D. suzukii across different landscapes have been used to better understand host use and movement of the pest. In this study, we report on potential to determine larval host for adult D. suzukii using their fatty acid profile or signature, and to use larval diet as an internal marker for adult flies in release-recapture experiments. Fatty acids can pass efficiently through trophic levels unmodified, and insects are constrained in the ability to synthesize fatty acids and may acquire them through diet. In many holometabolous insects, lipids acquired in the larval stage carry over to the adult stage. We tested the ability of a machine learning algorithm to discriminate adult D. suzukii reared from susceptible small fruit crops (blueberry, strawberry, blackberry and raspberry) and laboratory diet based on the fatty acid profile of adult flies. We found that fatty acid components in adult flies were significantly different when flies were reared on different hosts, and the machine learning algorithm was highly successful in correctly classifying flies according to their larval host based on fatty acid profile.

Determination of biodiesel properties based on a fatty acid profile of eight Amazon cyanobacterial strains grown in two different culture media

RSC Advances ◽  
2016 ◽  
Vol 6 (111) ◽  
pp. 109751-109758 ◽  
Author(s):  
Joseline Barbosa Aboim ◽  
Deborah Oliveira ◽  
John Eric Ferreira ◽  
Andrei Santos Siqueira ◽  
Leonardo Teixeira Dall'Agnol ◽  
...  
Keyword(s):  
Fatty Acid ◽  
Fatty Acid Profile ◽  
Culture Media ◽  
Biotechnological Potential ◽  
Biodiesel Properties

The biotechnological potential of 8 Amazon cyanobacteria was studied and some species shown to be promising biodiesel source.

1679 Fatty acid profile, sensory traits, and aromatic compounds of chops from lambs fed ground woody plants as roughage in feedlot finishing diets

2016 ◽  
Vol 94 (suppl_5) ◽  
pp. 818-818
Author(s):  
K. R. Wall ◽  
C. R. Kerth ◽  
T. R. Whitney ◽  
S. B. Smith ◽  
J. L. Glasscock ◽  
...  
Keyword(s):  
Fatty Acid ◽  
Fatty Acid Profile ◽  
Aromatic Compounds ◽  
Woody Plants ◽  
Finishing Diets

Proximate Chemical Analysis, Fatty Acid Profile and Microstructural Characteristics of Dromedary Camel Fats (Hump, Renal and Mesentery)

2020 ◽  
Keyword(s):  
Fatty Acid ◽  
Fatty Acid Profile ◽  
Meat Product ◽  
Oxidation Stability ◽  
Meat Products ◽  
Raw Material ◽  
Dromedary Camel ◽  
Mean Values ◽  
Animal Fat ◽  
Mesenteric Fat

The quality, safety, and suitability of animal fat for processing of a specific meat product is a critical issue. Increasing the human awareness about the health aspects associated with increased intake of animal fat, makes camel fat a suitable raw material for meat processing due to its excellent nutritional contribution. Therefore, the target of this study is examination of the sensory, physicochemical, fat oxidation, fatty acid profile, and other quality parameters of camel fat to evaluate the feasibility for processing of different meat products. To achieve this goal, 30 fat samples each from the hump, renal, and mesentery of Arabian male camels were investigated. The results showed that both the renal and mesenteric fat had honey color and medium-soft texture, while the hump had greyish-white color and hard texture. The sensory panel scores were significantly different between the hump and other fats. Hump fat had significantly (P<0.05) higher moisture, protein, and collagen content, while higher fat content was recorded in mesenteric fat. The fatty acid analysis showed that hump had high SFA and very low PUFA in comparison with both renal and mesenteric fat. Camel fat had high oxidation stability, and the mean values were very low in comparison with the levels of quality and acceptability. The ultrastructural analysis showed that hump fat had high elastin fibers which increase its hardness. The results indicated that both renal and mesenteric fat were more suitable for the production of various meat products than the hump.

Sign in / Sign up

Export Citation Format

Share Document