WIXLIB

The CapstoneExperienceFrom Students to ProfessionalsCOMPUTER SCIENCE AND ENGINEERING 2019-2020

The Capstone ExperienceDepartment of Computer Science and EngineeringCSE498, Collaborative DesignDr. Wayne DyksenProfessor of Computer Scienceand EngineeringThe Capstone Experience provides the educational capstone for all studentsmajoring in computer science at Michigan State University. Teams of studentsbuild software projects for corporate clients.During the Capstone Experience, students design, develop, debug, document,and deliver a software project for acorporate client, work in a team environment, develop written and oralcommunication skills, become proficient with softwaredevelopment tools and environments, and consider issues of professionalismand ethics.Corporate clients are local, regional, andnational including Accenture, Amazon,AppDynamics, Auto-Owners Insurance,Bosch, Dow Chemical, Evolutio, FordMotor Company, General Motors,Google, Herman Miller, Learning A-Z,Lockheed Martin Space, MaxCogito,Meijer, Michigan State University,Microsoft, Mozilla, MSU Federal CreditUnion, Place Technology, Principal,Proofpoint, Quicken Loans, TechnologyServices Group, TechSmith, UnionPacific Railroad, United Airlines, UrbanScience, Volkswagen and Whirlpool.

2019-2020Michigan State UniversityAt the end of eachsemester, the College ofEngineering sponsorsDesign Day, at whichstudent teams fromthroughout the Collegeshowcase their Capstoneprojects throughout theEngineering Building.Computer science capstone teamsdemonstrate the software projectsthat they have designed, developedand delivered for their corporateclient. Teams compete for fourawards, which are conferred by apanel of corporate judges.THANKS TO AUTO-OWNERS INSURANCEWe thank Auto-Owners Insurance, aFortune 500 company headquartered inLansing, Michigan, for their continuedsupport of Michigan State University and theCapstone Experience, including the printingof The Capstone Experience booklet.Check out the Capstone Experience web site atwww.capstone.cse.msu.edu. For more information about thecapstone experience or becoming a capstone project sponsor,contact Dr. Wayne Dyksen by email (dyksen@msu.edu) orby phone (517-353-5573).PAGE 1

The Capstone ExperienceCapstone Project Sponsors Fall 2019Chicago, Illinois & Washington, D.C.Seattle, Washington & Detroit, Michigan San Jose, California & Southfield, MichiganLansing, MichiganPlymouth, MichiganMidland, MichiganIndianapolis, IndianaDearborn, MichiganDetroit, MichiganCambridge, MassachusettsZeeland, MichiganAnn Arbor, MichiganGrand Rapids, Michigan Grand Rapids, Michigan Redmond, WashingtonEast Lansing, MichiganSunnyvale, CaliforniaOmaha, Nebraska & Okemos, MichiganMountain View, CaliforniaChicago, IllinoisChicago, IllinoisRoyal Oak, Michigan Auburn Hills, MichiganPAGE 2East Lansing, MichiganOkemos, MichiganDetroit, MichiganChicago, Illinois

Computer Science and EngineeringAccentureEmail Classification Using Machine LearningAccenture is a Fortune Global 500 company that solves theirclients’ toughest challenges by providing services in strategy,consulting, digital, technology and operations. Accenture’siDefense provides contextual, timely and actionable security intelligenceto the largest governments and organizations in the world, enablingthem to make smarter decisions to defend against new and evolvingthreats.Spam emails are a growing issue for many companies. Accordingto SpamHaus, 14.5 billion spam emails are sent globally every day,accounting for nearly 45% of all emails sent. Spam emails can rangefrom mild annoyance to exceedingly dangerous, possibly containingpotent computer viruses and malware.Due to the increased sophistication of spam emails, it is becomingmore and more challenging for companies and employees to determinethe legitimacy of their email messages. Any mistake by an employee canlead to a serious security breach.Our Email Classification application utilizes machine learningand natural language processing algorithms to automatically classifyand categorize incoming emails based solely on their content, therebyquickly and easily identifying spam emails.Without the threat of malicious spam emails, employees andcompanies can more safely and securely manage their emails withoutworrying about potential security threats.Administrators and security analysts from Accenture’s clientcompanies also have access to our web dashboard which enables themto easily view metrics and statistics of their email systems.Our Email Classification Using Machine Learning system is hostedon a virtual machine running CentOS. Our web app is built using Flaskand Bootstrap. Our data is stored in a Mongo database.Michigan State UniversityAccentureVarsha OdapallyOkemos, MichiganLisa CawleyChicago, IllinoisKevin WilsonRochester, MichiganAlireza SalimiWashington, D.C.Team Members (left to right)Project SponsorsYuyu SuGuangdong, ChinaGriffin CarrFenton, MichiganSofia ColellaGrosse Ile, MichiganPAGE 3

The Capstone ExperienceAmazonSPARTI: Selling Partner Application Ready to IntegrateFounded in 1994 as an online bookstore, Amazon is the largestonline retailer in the world. Amazon has seen tremendousgrowth and success, making history by becoming the secondU.S. company to be valued at 1 trillion. A key factor in Amazon’srise to the top is their e-commerce platform, which accounted fornearly 50% of all online retail purchases last year.Today, more than half of the items sold on Amazon aremanaged and listed by third-party sellers. Amazon third-partysellers utilize the Amazon Seller Central portal to manuallymanage their listings and inventories on Amazon’s platform. Whilethe Seller Central site works well for small businesses, manualmanagement becomes close to impossible for large and growingbusinesses.Third-party sellers often create custom selling managementapplications. However, the process of creating these customapplications is often too difficult or overly time-consuming.Our SPARTI application (Selling Partner Application Readyto Integrate) enables Amazon’s third-party sellers to quickly andeasily create custom selling management applications.SPARTI provides users with a template application capableof fully connecting with Amazon’s seller services. To deploy theircustom site, a third-party seller merely needs to update the giventemplate code with their own information.Turnkey integration with Amazon Web Services (AWS)is also supported within SPARTI, giving third-party sellers theability to automatically deploy and host their applications in thecloud.Within the course of a day, a third-party seller is ableto utilize the SPARTI project to build a containerized .NETapplication hosted on AWS ECS Fargate. The infrastructure forthe application is instantiated by AWS CloudFormation.Michigan State UniversityAmazonTyler RozwadowskiWaterford, MichiganChristin BurekSeattle, WashingtonJordan MulcahyJackson, MichiganGarret GawDetroit, MichiganRose WangShanghai, Shanghai, ChinaEvan DaikokuSeattle, WashingtonMatt MaplePortage, MichiganSushma GopalakrishnanDetroit, MichiganNoah GirardSouth Lyon, MichiganMadhuri MarriDetroit, MichiganTeam Members (left to right)PAGE 4Project Sponsors

Computer Science and EngineeringAppDynamicsBizIQ Flow Map Using Sequential Analytics DataAcquired by Cisco for 3.7 billion dollars, AppDynamics offersApplication Performance Management (APM) solutions totheir customers. These APM solutions monitor customers’application stacks and give them flawless experiences.Currently, customers have access to linear f low maprepresentations of individual applications. However, customerscannot represent business transactions that branch in multipledirections and across multiple application stacks.BizIQ Flow Map Using Sequential Analytics Data augmentsAppDynamics’ current offerings by allowing customers to representmulti-branch and multi-application business transactions. Itenables users to create custom flow maps representing the varioustransactions and save the flow for viewing and editing purposes.Flows are easily analyzed. The user sees the average time it takesfor a particular business transaction to occur and the flow can befiltered to show specific instances.Consider the manager of a car manufacturer. The manager isassessing the time it takes for a customer to unlock their car doorusing an app on their cell phone. When a user unlocks their car withthe mobile app, events are collected and sent to a central interface.These various events are connected to create a flow map. If thereis an issue with the amount of time elapsed after the user unlockstheir car, the manager sees this in the flow map. For example, ifverification usually takes one second and the flow shows it took fiveseconds, a potential problem may be impacting this user. The flowmap generated by BizIQ Flow Map Using Sequential Analytics Dataalerts the manager to this potential problem.BizIQ Flow Map Using Sequential Analytics Data is createdusing Node.js and utilizes the AppDynamics Analytics API to acquiredata. The visuals of the project are created using d3.js, React and CSS.Michigan State UniversityAppDynamicsQuinton SchwagleHartland, MichiganChirag DesaiSan Jose, CaliforniaNaifu JiBeijing, Beijing, ChinaShawn PenriceSouthfield, MichiganBen ReadSaline, MichiganMichael SicklesSan Jose, CaliforniaCarter LewisSaugatuck, MichiganScott YoungSan Jose, CaliforniaTeam Members (left to right)Project SponsorsTom CurrieBirmingham, MichiganPAGE 5

The Capstone ExperienceAuto-Owners Insurance“Danger Diner” VR TrainingAuto-Owners Insurance is a Fortune 500 companythat provides home, life, automobile, and businessinsurance to over 3 million policy holders. With over47,000 independent agents, Auto-Owners has been serving thecommunity since 1916.Auto-Owners insures businesses throughout the Midwest.Therefore, recognizing good and bad safety practices is an essentialskill for their insurers.The best way to learn the principles of good or badbusiness practice is real-world experience. However, this can beprohibitively expensive and time-consuming.Our “Danger Diner” VR Training is a competitive virtualreality game designed to teach Auto-Owners insurers to identifygood and bad safety practices. Insurers learn in an immersive andinteractive way providing them with a realistic experience.Using an Oculus Rift headset, Touch controllers and sensors,insurers explore a virtual restaurant. A player is tasked withidentifying potential safety and hazard items throughout thescene. Players are educated about business safety with a simulationof a realistic, everyday restaurant.Each round features a unique selection of items. All itemlocations are randomly generated, ensuring that no two gamesessions are the same.To give our game a competitive feel, the scores are recordedand displayed on a leaderboard.“Danger Diner” helps new insurers get hands-on training withno setup or expense and can also be played with large groups fortraining seminars and meetings.“Danger Diner” is built using the Unity Game Engine. Thegame is played using an Oculus Rift headset, Oculus Touchcontrollers, Oculus sensors, and the SteamVR application.Michigan State UniversityAuto-OwnersNick XieTianjin, Tianjin, ChinaRoss HackerLansing, MichiganMax DeDonaNorthville, MichiganScott LakeLansing, MichiganJillian TosoltLivonia, MichiganJim SchumacherLansing, MichiganTeam Members (left to right)Max DudleyMorris, IllinoisPAGE 6Project Sponsors