This paper adopts STEAM (Science, Technology, Engineering, Artificial Intelligence, Math) approach. The objectives of this paper are to use Multivariate Clustering Statistics to study the Chocolate Science and Products. Chocolate contains flavonoids and antioxidants which can prevent aging and beneficial to heart disease and diabetes patients. Antioxidants can prevent heart disease is because it reduces free radical formation. Data has been collected on 20+ chocolate ingredient nutrition contents from 60+ different types of chocolate. Both Clustering Variables and Principle Component Analysis methods are utilized to cluster (1) chocolate nutrition, (2) chocolate product types. Chocolate nutrition are clustered into four clusters which is consistent with Chocolate science research and can explain the common chocolate food science very well. Chocolate products can also be clustered into 4 clusters which can distinguish the major chocolate types (dark, milk, white). Five clustering distance algorithms are studied and compared based on the impact of clustering sequence and patterns. Number of clusters are also studied in order to determine which clustering distance algorithm can provide the best clustering pattern to explore the chocolate science research. This paper has demonstrated the effectiveness and power of adopting STEAM approach on the general Scientific Research.
0 Comments
This paper will apply “STEAMS” methodology on Chocolate Science. The science will mainly address how the antioxidants in chocolate help reduce free radical formation. Free radicals, atoms with an odd number of electrons, damage blood vessels when oxidized by LDL which consequently increases the risk of heart disease (Technology and Engineering). Data was collected on 20+ chocolate ingredient nutrition factors from 60+ different types of chocolate but were missing the Cocoa%. AI Neural Network algorithm was utilized to impute the missing Cocoa%. The hyperbolic tangent activation function was used to create the hidden layer. In order to overcome the Neural over-fit issue, definitive screening design (DSD) DOE technique was used to optimize the AI Neural algorithm. The optimal Neural setting can improve validation fitness R-Square by more than 20%. Based on the optimized neural model, Chocolate Type and Vitamin C are the highest predictors of estimating Cocoa%. Because fruit is high in Vitamin C, there could be further health benefits from dark fruit chocolate. This may indicate the potential to evaluate a 4th Chocolate Type: Fruit Chocolate – which may be healthier than Dark Chocolate. However, commercial fruit chocolate adds a lot of sugar, and Vitamin C is destroyed after processing.
This paper will apply “STEAMS” methodology on Chocolate Science. The science will mainly address how the antioxidants in chocolate help reduce free radical formation. Free radicals, atoms with an odd number of electrons, damage blood vessels when oxidized by LDL which consequently reducing the risk of heart disease (Technology and Engineering). Data was collected on 20+ chocolate ingredient nutrition contents from 60+ different types of chocolate but were missing the Cocoa%. AI Neural Network algorithm was utilized to impute the missing Cocoa%. The hyperbolic tangent activation function was used to create the hidden layer. In order to overcome the Neural over-fit issue, definitive screening design (DSD) DOE technique was designed to optimize the AI Neural algorithm. The optimal Neural setting can improve validation fitness R-Square by more than 20%. Based on the optimized neural model, Chocolate Type and Vitamin C are the highest predictors of estimating Cocoa%. Because fruit is high in Vitamin C, there could be further health benefits from dark fruit chocolate. This may indicate the potential to produce 4th Chocolate Type- Fruit Chocolate which may be even healthier than Dark Chocolate. However, commercial fruit chocolate adds a lot of sugar and Vitamin C is destroyed after processing.
|