STEAMS THE ANTI- HEART DISEASE WARRIORS Mason Chen Black Belt, Stanford OHS 1 st Place Best Contributed Paper, 2018 JMP Discovery Summit, CARY NC 1
Project Scope and Presentation Flow • Many people like chocolate, but have some concerns that chocolate is unhealthy. • Some people who have heart t di diseases es might need to eat chocolate, but do not know which one to eat. S T 1. Anti-Oxidant Science 4. Missing Value Neural E Literature Research Imputation of Cocoa% A M 3. Clustering Chocolate S Types 2. Clustering Nutritions 5. DSD Optimization of & Science Neural Setting 2
STEAMS DIAGRAM 3 Clusteri tering Prod oducts ucts Cent ntroid oid Sing ngle ( A rti Chocolate late tifi ficial al Intell llige gence) e) Ingred redien ents s and Linkage ge 3 Prod oducts ucts Clusteri tering Algori rithm thm Nutri rition tions Choices es ( M at ath) Complete Clusteri tering Nutri rition tions 2 S Chocolate late Proc oces ess s 1 ( A rti tifi ficial al Intell llige gence) e) ( T echnology ology and E nginee eeri ring) g) T E 4 Neural ral Imputatio ation A ( A rti tifi ficial al Intell llige gence) e) Anti-Oxi Oxidan ant M S cience 1 S DSD Optimi mizat zation on 5 ( S tatis tistics) s) 3 Mason C., “STEAMS” Methodology ology of of Conduct ucting Chocolat late Science Research”, submi mitte ted to to NSTA STEM Expo
15- 2018 “ STEA MS” Jou 20 2015 Journe ney S T E M T E A M S S T E A M S M S De Develop op Mat ath & S Sci cience ce Hands ds-On On Certify ify 6 Professi ofessional onal Found ndat ation ion T Certific ificat ates es: (Stan anford ford OHS) E IBM SPSS Statistics Math, Physics, Biology, Chemistry, Enhan ance ce STEAM AMS S Skil ills IBM Modeler DA/DM DM (IBM000129876) JAVA, Stati atisti tics Literature A JMP/Pr JM P/Pro, Python IASSC YB/GB/BB BB (GR764000541MC) Research/Writing M Latex Paper Proceedings JMP Stati atistical tical Thin inki king g (2018 Goal) Oral/Poster Presentations JMP DOE OE (2019 Goal) Fun, Re Real al S Team Building JMP Scrip ipt t Specialist (2019 Goal) Learning “STEAMS” techniques help motivate school learning on project -based and practical way 4
Gl Glob obal l Vi Visio ion Lea eade ders rshi hip: p: 20 2017-2018 2018 Con onfe ference rences s Cult Cu ltur ure-Sho Shocki cking ng IWSM, M, Groning oningen, en, Nether herlands lands IWSM, M, Bristol, stol, UK ASA JSM, , Vancou ouve ver, , CAN JMP , , Prag ague ue, , Czech IEOM/A /ASQ SQ STEM, , Palo o Republi ublic S Alto, o, CA ISF, , Boulde lder, , CO T FSDM, , Hualien alien, , Taiwa wan IEOM/A /ASQ SQ STEM, , E Santa a Clara, CA JMP, Cary, y, NC A IEOM, , Bandu dung ng, Indon onesia esia ASA, SDSS, , M Reston, on, VA S AQI Six Sigma a Nashv shvil ille, le, TN ISF, , Cairns, irns, Australia alia ASA JSM, , Baltim imor ore, e, MD IEOM, , Paris, is, Franc ance FSDM, , Bangkok, gkok, Thail iland nd IBC, Barcelona elona, Spain IEOM OM Rabat at, , Moroc occo ISCB, , Melbourne ourne IEOM OM Bogota, ota, Colom ombia ia Australia alia IEOM, , DC 5
JMP13 13 >> Analy lyze e >> Fit t Y by X > >> Nonpar Den ensi sity ty 1. Chocolate Anti-Oxidant Science Mason C., (2018 July) y) “Multivariate Statist stics of of Antioxid xidan ant Chocolate”, SMS IWSM Bristol tol Proc ocee eedings, gs, Vol 2 37 37-40 40 6
IS EATING CHOCOLATE UNHEALTHY? Chocolate te has not be been n proven en harmful ul. Life Expectancy 8 (2015 Estimate) E JMP13 13 >> Analy lyze e >> Fit t Y by X > >> Median ian: : 74.75 Nonpar ar Density nsity #9: 82.50 N #32: 80.57 #31: 80.68 GI GI #33: 80.54 Anti-Oxi Oxidan ant t Capaci acity ty/gram /gram #20: 81.70 #15: 81.98 N #13: 82.15 #24: 81.23 E #43: 79.68 #19: 81.75 E RI RI N Dark chocolate is a powerful source of G antioxidant. If chocolate’s serving size is equal to that of an apple, it has the highest amount of antioxidant. 7
CHOCOLATE & ATRIAL FIBRILLATION (AF) T E Lower Cardi diovas vascul cular r Heart t Dise sease se (CHD) risk if C taking 2 Chocolate servings per week (1 serving = 30 g) H • Chocolate may be inversely associated with AF N O • Dark chocolate may be a healthy snacking option L • AF = Atrial Fibrillation (a cardiovascular O disease) G • Next, how Chocolate can reduce CHD risk and Y AF associated cardiovascular disease https://heart.bmj.com/content/103/15/1163 https://www.bmj.com/content/343/bmj.d4488 8
FLAV0NOIDS SCIENCE & STRUCTURE • Flavonoids are the most abundant polyphenols in human diet that have antioxidant properties. • Flavonoids have the general structure of a 15- carbon skeleton C6-C3-C6. S ▪ Consists of two phenyl rings (A and B) and a heterocyclic ring (C). CI CI E N C • There are seven different types of flavonoids based on its chemical structure: E ▪ Flavones, flavanol, flavanones, isoflavones, anthocyanidins, chalcones, catechins • Chocolate flavonoids are flavanols which can promote healthy blood flow from head to toe. 9
FREE RADICALS AND ANTIOXIDANTS ▪ Free radicals are atoms with odd number of electrons ▪ Antioxidants reduce free radical formation S CI CI ▪ Reactive free radicals causes cells mal-function E ▪ Excess free radicals damages blood vessel N C ▪ After the oxidation of free radicals, LDL (Low-density E Lipoprotein)can cause CVD (Cardiovascular Disease) ▪ The oxidized components attract macrophages which absorb & deposit Cholesterol 10
DARK CHOCOLATE LITERATURE RESEARCH T • Bene nefits: fits: E – A lot of soluble fiber C – A lot of minerals: iron, magnesium, copper, manganese, potassium, phosphorus, zinc, H selenium – Powerful source of antioxidant N – Improve blood flow and lower blood pressure O – Increases HDL (good cholesterol) and decreases LDL (bad cholesterol) L – Lower risk of cardiovascular disease (CVD) O – Improve brain function 1 G • Conc ncerns: ns: Y – Causes migraines – Increases chance of ki kidney ney stone nes – Side effects from caffeine such as irregular ar heartbe tbeat at 11
(3 (3) JMP 13 >> A (1) JMP 13 >> Analy (1 Analy lyze ze >> Clusteri tering >> lyze e >> Cluste ter Varia riable bles Distribution istribution 2. Clustering Nutritions & Science (2 (2) JMP 13 >> Analyze yze >> (4 (4) JMP 13 >> Analyze yze >> Multivari tivariate ate Multivari tivariate ate Metho thods ds >> Metho thods ds >> Pr Prin incip ciple le Components ents >> Bi-Plo Plot Multivari tivariate ate Mason C., (2018 July), y), “Choose Healt lthy Chocolate”, IEOM Europe ope Pari ris Proc oceed edings, gs, 434-441 441 • 12
(1) CHOCOLATE NUTRITION DISTRIBUTION S JMP 13 >> Analy lyze e >> • 60+ Chocolate nutrition data collected from “Target” store. Distribution istribution T • The quantities of the eight most critical ingredients were analyzed. A T I S T Most Dark Chocolate (Qualitat tative Clustering Criteria) has: I 1 st Cluster: higher Cocoa percent, Dietary Fiber and Iron • 2 nd Cluster: lower Cholesterol, Calcium, and Sugar C • S Chocolate Product Nutrition data has indicated that Dark Chocolate is healthier than the Milk and White Chocolate 13
(2) DARK CHOCOLATE CORRELATION • 1 st Cluster: Sugar and Cocoa_Percent have a negative correlation of -0.9162. SC SC • 2 nd Cluster: Dietary Fiber and Iron have a I positive correlation of 0.7722. EN EN CE CE Any other better way to cluster nutritions? Pair-Wise se Pearson arson Correlat relation on JMP 13 >> Analy lyze e >> Multivariate tivariate Metho thods ds >> Multivari tivariate ate 14
(3) VARIABLE CLUSTERING JMP 13 >> Analy lyze e >> Clusteri tering >> Cl Cluster ster Vari riab able les Signal nal Noise se S-N Ra Ratio tio SC SC I E N CE CE & Clustering Nutritions can interpret the relevant Chocolate Science insight well: Cluster 1: the higher the saturated fat, the higher the total fat, and the higher the calories. AI AI Cluster 2: Calcium/Cholesterol, and Cocoa percent have a negative correlation. Cluster 3: the higher the sugar, the higher the carbohydrates. Comm mmon n Sense se Cluster 4: Iron and dietary fiber are positively correlated. 15
(4) Principle Component Bi-Plot 1 st Cluster: Cocoa Percent, Dietary Fiber, and Iron are near each other (Higher for M Visual isualizati ization on Dark Chocolate) A T 2 nd Cluster: Total Fat, Saturated Fat, and H H Calories & 3 rd Cluster: Calcium, Sugar, and Cholesterol are near each other AI AI (Higher for Milk/White Chocolate) JMP 13 >> Analy lyze e >> Multivariate tivariate Methods thods >> Princip ciple le Componen nents ts >> Bi-Pl Plot ot 16
Comparing Four Clustering Methods E N GI GI N E E RI RI N G • Four different clustering methods show similar clustering patterns • Clustering “ Statistics and Engineering ” results match Chocolate “ Science and Technology ” Literature Research well ( STE AM S). 17
Recommend
More recommend
